System

Abstract

A system is provided.SOLUTION: A system comprising: means for electronically collecting medical image data and health data of a patient from a medical facility; means comprising an artificial intelligence model for pre-processing and analyzing the medical image data and the health data; means for generating a 3D model based on analysis results; and means for visualizing and presenting the 3D model to medical staff.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The technology of the present disclosure relates to a system. [Background technology]

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Interpreting medical images and making diagnoses is extremely difficult, and accuracy and speed are always required. The complexity of diagnosis is particularly challenging in specialized fields such as dentistry and surgery. Poor communication between patients and medical staff also hinders accurate diagnosis and the development of effective treatment plans. This can lead to delayed or misdiagnosis, potentially increasing the patient's health risk. There is a need for the development of tools and systems to effectively solve this problem. [Means for solving the problem]

[0005] To solve this problem, we provide a system that includes a means for electronically collecting medical image data and patient health data from medical institutions and an artificial intelligence model for preprocessing and analyzing the medical image data and health data. We also provide a system that includes a means for generating a 3D model based on the analysis results and visualizes and presents the 3D model to medical staff. We also provide a system that uses the 3D model for communication between patients and medical staff and includes a means for creating and confirming treatment plans, thereby improving the speed and accuracy of diagnoses. This allows medical staff to quickly and accurately handle difficult diagnoses and deepen mutual understanding with patients.

[0006] "Medical image data" refers to digital images obtained at medical institutions that visually capture the internal state of a patient's body.

[0007] "Health data" refers to information about a patient's health status, such as their medical history, medication information, diagnostic results, and test data.

[0008] "Preprocessing" is the process of applying noise removal, conversion to a standard format, and other processing to acquired medical image data and health data to make it suitable for analysis.

[0009] "Analysis" is the process of extracting diagnostic information, such as anomaly detection and disease classification, from preprocessed medical image data and health data using artificial intelligence models.

[0010] An "artificial intelligence model" is a collection of algorithms that use technologies such as machine learning and deep learning to analyze data and make predictions or classifications.

[0011] A "3D model" is a digital model that visualizes a patient's body parts in three dimensions, generated based on the analysis results.

[0012] "Visualization" refers to the interactive display of data or models, transforming them into a form that can be intuitively understood by users.

[0013] "Medical staff" refers to medical professionals involved in diagnosing and treating patients, such as doctors, nurses, and technicians.

[0014] "Communication" is the process of dialogue and explanation that allows medical staff and patients to share information and deepen understanding.

[0015] A "treatment plan" refers to a detailed plan for determining and implementing the most appropriate treatment based on a patient's symptoms and medical condition. [Brief explanation of the drawings]

[0016] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0017] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0018] First, the terms used in the following description will be explained.

[0019] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0020] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0021] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0022] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0023] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0024] [First embodiment]

[0025] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0026] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0027] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0028] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0029] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0030] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0031] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0032] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0034] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0035] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0036] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0037] The present invention, "3D Health Analyzer," is a system for improving the accuracy and speed of diagnoses in medical institutions and streamlining communication between medical staff and patients. This system consists of a series of processes that collect and analyze medical image data and patient health data, and visualize the results as a 3D model. Below, the processing of the system's program is explained in natural language and detailed with concrete examples.

[0038] overview

[0039] "3D Health Analyzer" is a system consisting of three parties: a server, a terminal, and a user. The server is responsible for data collection, preprocessing, analysis, and generation of 3D models. The terminal provides an interface for medical staff to view and manipulate the 3D models. Users are medical staff and patients, and are responsible for sharing and understanding diagnostic information and treatment plans through the system.

[0040] Program processing flow

[0041] Collection Phase

[0042] The server collects medical image data and patient health data from the medical institution's electronic medical record system and imaging diagnostic equipment (e.g., X-ray, MRI, CT scan) via API.

[0043] Example: A server obtains image data of a patient's teeth from a dental X-ray machine in a dental clinic, and simultaneously collects data about the patient's medical history and current symptoms.

[0044] Preprocessing Phase

[0045] The server performs noise removal and interpolation on the collected medical image data.

[0046] Example: The server removes noise from acquired dental X-ray images and complements degraded parts of the images.

[0047] The server converts the health data into a standard format and makes it suitable for AI models.

[0048] Example: Converting a patient's past medical records and current health status data into a standardized format.

[0049] Analysis Phase

[0050] The server inputs the preprocessed data into the AI ​​model and performs the analysis.

[0051] Example: The server uses an AI model to analyze the patient's dental condition and identify areas of decay and possible periodontitis.

[0052] The server extracts the analysis results as numerical and text data and uses them as the basic data for generating a 3D model.

[0053] Example: Based on AI analysis, the location and size of cavities are extracted as numerical data.

[0054] 3D model generation phase

[0055] The server uses a 3D CG engine to generate a realistic 3D model based on the analysis results.

[0056] Example: A server generates a 3D dental model and visually highlights identified areas of caries.

[0057] Visualization Phase

[0058] The server visualizes the generated 3D model using a web viewer or dedicated application and delivers it to medical staff.

[0059] Example: The server uploads the generated 3D tooth model to a dashboard on the cloud, where it can be displayed in a viewer for medical staff.

[0060] Review and communication phase

[0061] Using the terminal, medical staff can access a dashboard and conduct examinations while viewing the 3D model.

[0062] Example: A dentist uses a tablet to view a 3D model of a patient's teeth, highlighting any cavities and providing explanations.

[0063] Based on the generated 3D model, users (medical staff and patients) discuss and reach a consensus on detailed diagnoses and treatment plans.

[0064] Example: Dentists and patients can view 3D models to discuss in detail treatment plans and preventative measures for cavities.

[0065] The "3D Health Analyzer" of this invention allows medical staff to significantly reduce the time and effort required to analyze medical images, thereby improving diagnostic accuracy. Furthermore, the use of 3D models facilitates communication with patients, increasing their understanding and acceptance of treatment. This improves the overall quality of medical care and reduces patient health risks.

[0066] The processing flow will be explained below.

[0067] Step 1: Data collection

[0068] server

[0069] Medical imaging data and patient health data are collected via APIs from medical institutions' electronic medical record systems and imaging diagnostic devices (e.g., X-ray machines, MRIs, CT scans).

[0070] Example: A server obtains dental image data of a particular patient from a dental x-ray machine in a dental clinic, and simultaneously collects the patient's medical history and current health data.

[0071] Step 2: Data Storage

[0072] server

[0073] Collected medical image data and health data are stored in temporary cloud storage.

[0074] Example: The server stores the acquired data in secure cloud storage and manages it in a database.

[0075] Step 3: Data cleaning

[0076] server

[0077] A pre-processing algorithm is used to remove noise from medical image data.

[0078] Example: Image filtering is used to remove noise from X-ray images and adjust image brightness and contrast.

[0079] Detect missing data and outliers in health data and impute or remove them appropriately.

[0080] Example: The server uses an imputation algorithm to fill in missing values ​​in health data and remove outliers.

[0081] Step 4: Data Standardization

[0082] server

[0083] Standardize the units and notations of health data (e.g., blood pressure, blood sugar levels, etc.) and convert them into a standard format.

[0084] Example: Convert blood pressure data into a unified unit (mmHg) and standardize the range of values.

[0085] Medical image data is also converted into a format suitable for AI models (e.g., DICOM format).

[0086] Example: Converting an X-ray image in JPG format to DICOM format.

[0087] Step 5: AI model analysis

[0088] server

[0089] Preprocessed medical image data and standardized health data are input into the AI ​​model and analysis is performed.

[0090] Example: The server uses an AI model to analyze images of teeth and automatically detect the location and depth of cavities.

[0091] As a diagnostic result, abnormalities and important findings are extracted as numerical or text data.

[0092] Example: As a result of AI analysis, the coordinates of the location and depth of cavities are obtained as numerical data.

[0093] Step 6: 3D model generation

[0094] server

[0095] Based on the analysis results, a 3D model of the medical image is generated using a 3D CG engine.

[0096] Example: The server generates a 3D model of the teeth from the analysis results, highlighting areas of decay.

[0097] The completed 3D model is visualized and delivered to a web viewer or dedicated application.

[0098] Example: The generated 3D model can be uploaded to a cloud-based dashboard and accessed by medical staff via a dedicated app.

[0099] Step 7: View on the dashboard

[0100] Terminal

[0101] Medical staff access the dashboard hosted on the server through a browser on their PC or tablet.

[0102] Example: A doctor uses a tablet to access a dashboard in the cloud and open a 3D model of a patient.

[0103] On the dashboard, select a 3D model of a specific patient and zoom in / out, rotate, and more to view details.

[0104] Example: The doctor rotates the 3D model to see the precise location and size of the cavities.

[0105] If necessary, screen captures and report output are performed to share diagnostic information with other medical staff and patients.

[0106] Example: A doctor generates a diagnostic report with a captured image of the 3D model and shares it with other medical staff.

[0107] Step 8: Promote communication with patients

[0108] Users (medical staff, patients)

[0109] When medical staff meet with patients, they explain things to them while displaying 3D models on a PC or tablet.

[0110] Example: A dentist shows a patient a 3D model of a tooth and explains the condition and treatment of the tooth.

[0111] Patients can understand diagnostic information by visually viewing the 3D model.

[0112] Example: A patient looks at a model of their own teeth and understands what the dentist is explaining.

[0113] Medical staff and patients create and review treatment plans based on the generated 3D model.

[0114] Example: Dentists and patients can review treatment schedules and procedures by referring to the 3D model.

[0115] Example 1

[0116] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0117] With conventional medical data analysis systems, medical staff spent a lot of time and effort analyzing diagnostic results and communicating with patients. This resulted in inconsistent diagnostic accuracy and low patient understanding and treatment acceptance. Furthermore, the lack of integrated analysis of medical images and health data made it difficult to develop comprehensive diagnoses and treatment plans. Furthermore, there were limited means of presenting analysis results in a visually understandable manner.

[0118] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0119] In this invention, the server includes: means for electronically collecting medical image data and patient health data from medical institutions; means for performing noise reduction and interpolation on the medical image data; means for converting the health data into a standard format and arranging it in a format suitable for analysis; means including an artificial intelligence model for preprocessing and analyzing the medical image data and the health data; means for instructing the artificial intelligence model to perform analysis using prompts; means for extracting the analysis results as numerical data and text data and using them as basic data for generating a 3D model; means for using a computer graphics engine to generate a realistic 3D model based on the analysis results; and means for visualizing the 3D model and presenting it to medical staff. This improves the accuracy and speed of diagnosis and enables efficient communication with patients.

[0120] "Medical image data" refers to image information such as X-rays, MRIs, and CT scans obtained at medical institutions.

[0121] "Patient Health Data" means information about a patient's health, such as the patient's medical history, current symptoms, and vital signs.

[0122] "Noise removal" is a process that removes unnecessary high-frequency components and errors from medical image data.

[0123] "Complement" is a process of filling in missing parts of medical image data to improve image quality.

[0124] A "standard format" is a common structure or format established to maintain data consistency and compatibility.

[0125] An "artificial intelligence model" is a computational algorithm used to analyze large amounts of data and find patterns and regularities.

[0126] A "prompt sentence" is a short piece of text that instructs an artificial intelligence model to perform a specific analysis.

[0127] "Numerical data" is information in a numerical format that quantitatively expresses the analysis results.

[0128] "Text data" is information that expresses analysis results and explanations in text format.

[0129] A "3D model" is a visual representation generated as a three-dimensional shape based on the analysis results.

[0130] A "computer graphics engine" is software for generating and displaying three-dimensional computer graphics.

[0131] The present invention, "3D Health Analyzer," is a system for improving the accuracy and speed of diagnoses in medical institutions and streamlining communication between medical staff and patients. This system consists of a series of processes that collect, preprocess, and analyze medical image data and patient health data, and visualize the results as a 3D model.

[0132] Hardware and Software Configuration

[0133] This system is mainly composed of three components: a server, a terminal, and a user. The specific hardware and software configuration is as follows:

[0134] Server: A computer system responsible for collecting, preprocessing, and analyzing data, and generating 3D models. Software used here includes APIs, Python's OpenCV library, generative AI models such as TensorFlow or PyTorch, and computer graphics engines such as Unity or Unreal Engine.

[0135] Terminal: A device used by medical staff to view and manipulate 3D models. This can be a display device such as a tablet or PC.

[0136] Users: Medical staff and patients who share and understand diagnostic information and treatment plans through the system.

[0137] Data collection and preprocessing

[0138] The server collects medical image data and patient health data from medical institutions' electronic medical record systems and imaging diagnostic devices (e.g., X-rays, MRIs, CT scans) via APIs. The collected data is stored in a database and backed up. For example, the server collects image data of patients' teeth from dental X-ray machines at a dental clinic, and simultaneously obtains data about the patient's medical history and current symptoms.

[0139] As part of preprocessing, the server performs noise removal and interpolation on medical image data and converts the health data into a standard format. For example, the server removes noise from collected dental X-ray images and interpolates image degradation. It also converts patients' past medical records and current health status data into a standard format (e.g., HL7 format).

[0140] Data analysis and 3D model generation

[0141] The server inputs the preprocessed medical image data and health data into the generative AI model. It uses prompts to provide specific instructions to the AI ​​model. Specific examples of prompts include, "Please identify the location of cavities in this patient's dental X-rays" and "Please convert the collected health data into a standard format and analyze the risk of periodontitis."

[0142] The analysis results from the generative AI model are extracted as numerical and text data, and the server uses this data to generate a 3D model. Specifically, the server uses a 3D CG engine such as Unity or Unreal Engine to generate a realistic 3D model based on the analysis results. The generated 3D model is presented to medical staff in a visually easy-to-understand format.

[0143] Visualization and Communication

[0144] The generated 3D model is visualized by the server through a web viewer or dedicated application. Medical staff can access the dashboard using a terminal and examine the patient while viewing the 3D model. For example, a dentist can view the 3D model of a patient's teeth on a tablet and explain the procedure, highlighting any cavities.

[0145] Furthermore, users (medical staff and patients) can discuss and reach consensus on detailed diagnoses and treatment plans based on the generated 3D models. For example, dentists and patients can discuss in detail treatment plans and preventive measures for cavities while looking at the 3D models.

[0146] In this way, the "3D Health Analyzer" of the present invention enables medical staff to improve the accuracy and speed of diagnosis, and also facilitates smooth communication with patients.

[0147] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0148] Step 1:

[0149] Data collection

[0150] The server collects medical image data and patient health data from the medical institution's electronic medical record system and imaging diagnostic equipment (e.g., X-ray, MRI, CT scan).

[0151] Input: Medical imaging data and patient health data from the medical institution's database.

[0152] Output: The collected medical image data and patient health data are stored in a database on the server.

[0153] What it does: Every day at 2 AM, the server runs an automated script to collect new patient data from the dental x-ray machine in the dental clinic.

[0154] Step 2:

[0155] Data Loss Prevention

[0156] The server backs up the collected data and stores it in a database, which prevents data loss and ensures safety.

[0157] Input: Collected data (medical imaging data and health data).

[0158] Output: Data stored in the database and backup data.

[0159] How it works: The server backs up collected dental X-ray images and health data to two different data centers.

[0160] Step 3:

[0161] Image data preprocessing

[0162] The server performs noise removal and interpolation on the collected medical image data.

[0163] Input: Collected medical image data.

[0164] Output: Denoised and imputed medical image data.

[0165] Specific operation: The server uses Python's OpenCV library to analyze the pixel values ​​of the acquired image and apply a filter to suppress high-frequency noise.

[0166] Step 4:

[0167] Health data format conversion

[0168] The server converts the health data into a standard format and makes it suitable for analysis.

[0169] Input: Collected health data.

[0170] Output: Health data converted into a standard format.

[0171] Specific operation: The server converts the patient's blood pressure, heart rate, and past medical records into HL7 format.

[0172] Step 5:

[0173] Input to AI model and prompt generation

[0174] The server inputs the preprocessed data into the generative AI model and uses prompt statements to direct the analysis.

[0175] Input: Denoised medical image data and health data in standard formats.

[0176] Output: The analysis results of the generative AI model.

[0177] Specific operation: The server generates a prompt statement such as, "Please identify the cavities in this patient's dental X-ray image," and instructs the AI ​​model.

[0178] Step 6:

[0179] Obtaining analysis results and extracting data

[0180] The server receives the analysis results from the AI ​​model and extracts them as numerical and text data.

[0181] Input: Analysis results of the generative AI model.

[0182] Output: Numerical and textual data.

[0183] Specific operation: The server stores the analysis results received from the AI ​​model, such as the location and size of cavities, as numerical data in a database.

[0184] Step 7:

[0185] 3D model generation

[0186] The server uses a 3D CG engine to generate a realistic 3D model based on the analysis results.

[0187] Input: Numeric and text data.

[0188] Output: Realistic 3D models.

[0189] Specific operation: The server uses Unity or Unreal Engine to generate a 3D model based on the analysis results and highlights visually important parts.

[0190] Step 8:

[0191] 3D model visualization and distribution

[0192] The server uploads the generated 3D model to a web viewer or dedicated application.

[0193] Input: A generated 3D model.

[0194] Output: 3D model that can be viewed in a web viewer or dedicated application.

[0195] Specific operation: The server uploads the generated 3D model to a dashboard on the cloud and notifies medical staff of an access URL or QR code.

[0196] Step 9:

[0197] Checked by medical staff

[0198] Using the terminal, medical staff can access the dashboard and conduct examinations while viewing the 3D model.

[0199] Input: 3D models uploaded to a web viewer or dedicated application.

[0200] Output: Medical staff examination results.

[0201] Specific operation: The dentist zooms in and rotates the 3D model of the patient on the tablet, checking the areas of tooth decay while explaining to the patient.

[0202] Step 10:

[0203] Sharing Diagnoses and Treatment Plans

[0204] Based on the generated 3D model, users (medical staff and patients) discuss and reach a consensus on detailed diagnoses and treatment plans.

[0205] Input: Medical staff review results and 3D model.

[0206] Output: Diagnosis and treatment plan.

[0207] How it works: Dentists and patients discuss treatment options while looking at the 3D model and select the best treatment plan.

[0208] (Application example 1)

[0209] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0210] It is important for medical institutions to analyze medical image data and health data more effectively and improve the accuracy and speed of diagnoses. Visual support is also required to facilitate communication between patients and medical staff and provide easy-to-understand diagnoses and treatment plans. Furthermore, there is a need to provide a virtual health checkup experience that allows patients to check their health status from home, enabling more people to efficiently manage their health.

[0211] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0212] In this invention, the server includes: means for electronically collecting medical image data and patient health data from medical institutions; means including an artificial intelligence model for preprocessing and analyzing the medical image data and the health data; means for generating a 3D model based on the analysis results; means for visualizing the 3D model and presenting it to medical staff; means for allowing users to view the 3D model via an interface on a smartphone or head-mounted display; and means for providing a virtual health checkup experience. This allows users to easily check their health status from home and to better understand diagnoses and treatment plans through communication with medical staff.

[0213] "Medical image data" refers to image data obtained at a medical institution, including images taken using equipment such as X-rays, MRIs, and CT scans.

[0214] "Patient health data" refers to information such as a patient's medical history, current health status, medical records, and symptoms.

[0215] "Preprocessing" refers to the process of removing noise and standardizing collected medical image data and health data to prepare them in a format suitable for analysis.

[0216] "Artificial intelligence model" refers to a program that uses machine learning and deep learning to analyze medical image data and health data.

[0217] "3D model" refers to a three-dimensional visual model generated based on medical image data and analysis results.

[0218] "Visualization" refers to displaying 3D models in a way that makes them easy for medical staff to understand.

[0219] "Interface" refers to the connection method and display device that allows users to view 3D models through a smartphone or head-mounted display.

[0220] The "virtual health checkup experience" refers to an experience that allows users to check and diagnose their health status from the comfort of their own home.

[0221] A "smartphone" refers to a portable information terminal that can use communication functions and applications.

[0222] A "head-mounted display" refers to a display device that is worn on the head and provides visual information.

[0223] The present invention is a system that improves the accuracy and speed of diagnoses by utilizing medical image data and patient health data collected from medical institutions. This system is composed of three entities: a server, a terminal, and a user, as described below.

[0224] The server has the function of collecting medical image data and patient health data from medical institutions' electronic medical record systems and imaging diagnostic devices (e.g., X-ray devices, MRI devices, CT scan devices) via APIs. The server also performs preprocessing on the collected data, such as noise removal and conversion to a standard format. This preprocessing prepares the data in a format suitable for the artificial intelligence model. The preprocessed data is then input into the artificial intelligence model for analysis. Based on the results of this analysis, the server generates a 3D model. This 3D model is generated in real time using a 3D CG engine.

[0225] The device provides an interface for visualizing the generated 3D model. Medical staff can use this device to check the 3D model and operate the interface. The visualized 3D model is uploaded to a dashboard on the cloud and displayed in a viewer for medical staff. In addition, the device has a function that allows the user (patient) to check the 3D model using a smartphone or head-mounted display.

[0226] Users are medical staff and patients, who use the generated 3D models to discuss and reach consensus on detailed diagnoses and treatment plans. Patients can experience virtual medical checkups from home using a smartphone or head-mounted display. For example, when a patient uploads MRI scan data from home, the system analyzes the data and generates a 3D model. The generated 3D model is displayed on a smartphone or head-mounted display so that the patient can view it at home.

[0227] The main hardware and software used include Python, Numpy, Scikit-learn, Nibabel, and Vedo, which are used to handle the steps of data collection, preprocessing, analysis, 3D model generation, and visualization.

[0228] As a concrete example, the following prompt sentence can be used:

[0229] Example prompt sentence:

[0230] "I've been having frequent headaches lately. I'd like you to check the state of my brain based on my MRI scan data and visualize it as a 3D model."

[0231] In this way, the system of the present invention improves diagnostic accuracy at medical institutions and facilitates smooth communication between patients and medical staff. Furthermore, by providing a virtual health checkup experience, patients can easily check their health status and use medical services from the comfort of their own homes.

[0232] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0233] Step 1:

[0234] The server collects medical image data and patient health data from medical institutions' electronic medical record systems and diagnostic imaging devices via APIs. During this collection process, data is obtained from various devices using API calls and stored in a database. The input is the medical image data and health data sent from the devices, and the output is the raw data stored in the server's database.

[0235] Step 2:

[0236] The server performs preprocessing on the collected medical image data to remove noise and correct image quality. Specifically, it performs noise removal filtering and image correction using libraries such as Python's Nibabel and OpenCV. The input is the medical image data collected in step 1, and the output is clean medical image data that has been corrected and denoised.

[0237] Step 3:

[0238] The server performs preprocessing to convert the patient's health data into a standard format and prepare it for analysis. Specifically, it uses Python's Pandas library to clean the data, extract necessary items, and format it. The input is the health data collected in step 1, and the output is the standardized health data.

[0239] Step 4:

[0240] The server inputs the preprocessed medical image data and health data into an artificial intelligence model for analysis. This analysis uses libraries such as Scikit-learn and TensorFlow to apply machine learning and deep learning models to extract meaningful results from the data. The input is the data preprocessed in steps 2 and 3, and the output is the numerical and text data of the analysis results.

[0241] Step 5:

[0242] The server generates a 3D model based on the analysis results. Specifically, it uses a 3D CG engine such as the Vedo library to generate a three-dimensional model that visually represents the analysis results. The input is the analysis result data obtained in step 4, and the output is the generated 3D model.

[0243] Step 6:

[0244] The server visualizes the generated 3D model using a web viewer or a dedicated application so that users can check it through an interface. For example, a web page for displaying the 3D model is built using a web framework such as Flask or Django. The input is the 3D model generated in step 5, and the output is the visualized 3D model displayed in a web viewer that users can access.

[0245] Step 7:

[0246] The user checks the generated 3D model using a smartphone or a head-mounted display. Specifically, the user can launch a dedicated viewer app and interactively view the 3D model. The input is access to the 3D model display page visualized in Step 6, and the output is the user experience of checking the 3D model and understanding the health condition.

[0247] Step 8:

[0248] Users (medical staff and patients) discuss detailed diagnoses and treatment plans based on the generated 3D model and reach a consensus. For example, a patient can view the 3D model together with medical staff and discuss diagnostic results and specific treatment options. The inputs are the 3D model confirmed in step 7 and feedback from the users, and the output is the agreed-upon diagnostic information and treatment plan.

[0249] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0250] The present invention, "3D Health Analyzer," is a system that improves the accuracy and speed of diagnoses in medical institutions and streamlines communication between medical staff and patients. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it provides interactive functions that correspond to the user's emotional state. Below, the processing of the system's program is explained in natural language and detailed with specific examples.

[0251] overview

[0252] "3D Health Analyzer" is a system consisting of four components: a server, a terminal, a user, and an emotion engine. The server is responsible for data collection, preprocessing, analysis, 3D model generation, and emotion engine management. The terminal provides an interface for medical staff to view and manipulate the 3D models. Users are medical staff and patients, and their role is to share and understand diagnostic information and treatment plans through the system. The emotion engine recognizes the user's emotional state and provides feedback accordingly.

[0253] Program processing flow

[0254] Collection Phase

[0255] The server collects medical image data and patient health data from the medical institution's electronic medical record system and imaging diagnostic equipment (e.g., X-ray, MRI, CT scan) via API.

[0256] Example: A server retrieves image data for a particular patient from an MRI machine in a surgeon's office, while also collecting the patient's medical history and current health data.

[0257] Preprocessing Phase

[0258] The server performs noise removal and interpolation on the collected medical image data.

[0259] Example: The server removes noise from acquired MRI images and complements degraded parts of the images.

[0260] The server converts the health data into a standard format and makes it suitable for AI models.

[0261] Example: Converting a patient's past medical records and current health status data into a standardized format.

[0262] Analysis Phase

[0263] The server inputs the preprocessed data into the AI ​​model and performs the analysis.

[0264] Example: The server uses an AI model to analyze a patient's MRI images and identify the location and size of a tumor.

[0265] The server extracts the analysis results as numerical and text data and uses them as the basic data for generating a 3D model.

[0266] Example: As a result of AI analysis, the location coordinates and size of a tumor are obtained as numerical data.

[0267] 3D model generation phase

[0268] The server uses a 3D CG engine to generate a realistic 3D model based on the analysis results.

[0269] Example: The server generates a 3D model of the tumor from the analysis results and visually highlights the tumor location.

[0270] Visualization Phase

[0271] The server visualizes the generated 3D model using a web viewer or dedicated application and delivers it to medical staff.

[0272] Example: The generated 3D model can be uploaded to a cloud-based dashboard and accessed by medical staff via a dedicated app.

[0273] Emotion Engine

[0274] The server uses an emotion engine to recognize the emotions of users (mainly patients) in real time.

[0275] For example, based on input from the camera and microphone, the emotion engine analyzes the patient's facial expressions and tone of voice to understand their emotional state.

[0276] The server adjusts the display and feedback of the 3D model based on the recognized emotion.

[0277] For example, if a patient is feeling anxious, the system will change the display of the 3D model to something simpler and easier to explain.

[0278] Confirmation and communication promotion

[0279] Using the terminal, medical staff can access a dashboard and conduct examinations while viewing the 3D model.

[0280] Example: A surgeon uses a tablet to view a 3D model of a patient's tumor and explain it in detail.

[0281] Users (medical staff and patients) discuss and reach a consensus on detailed diagnoses and treatment plans based on the generated 3D models and feedback from the emotion engine.

[0282] Example: A surgeon and a patient discuss in detail the tumor treatment plan and the risks of surgery while looking at a 3D model. The emotion engine provides appropriate feedback to reduce the patient's anxiety and facilitate communication.

[0283] By combining the "3D Health Analyzer" of this invention with an emotion engine, medical staff can make diagnoses and explanations that take into account the patient's emotional state, thereby improving patient understanding and satisfaction. This system offers a new approach to improving both diagnostic accuracy and the quality of medical services.

[0284] The processing flow will be explained below.

[0285] Step 1: Data collection

[0286] server

[0287] Medical imaging data and patient health data are collected via APIs from medical institutions' electronic medical record systems and imaging diagnostic devices (e.g., X-ray machines, MRIs, CT scans).

[0288] Example: A server retrieves image data for a particular patient from an MRI machine in a surgeon's office, while also collecting the patient's medical history and current health data.

[0289] Step 2: Data Storage

[0290] server

[0291] Collected medical image data and health data are stored in temporary cloud storage.

[0292] Example: The server stores the acquired data in secure cloud storage and manages it in a database.

[0293] Step 3: Data cleaning

[0294] server

[0295] A pre-processing algorithm is used to remove noise from medical image data.

[0296] Example: Image filtering is used to remove noise from MRI images and adjust image brightness and contrast.

[0297] Detect missing data and outliers in health data and impute or remove them appropriately.

[0298] Example: The server uses an imputation algorithm to fill in missing values ​​in health data and remove outliers.

[0299] Step 4: Data Standardization

[0300] server

[0301] Standardize the units and notations of health data (e.g., blood pressure, blood sugar levels, etc.) and convert them into a standard format.

[0302] Example: Convert blood pressure data into a unified unit (mmHg) and standardize the range of values.

[0303] Medical image data is also converted into a format suitable for AI models (e.g., DICOM format).

[0304] Example: Converting a JPG format MRI image to DICOM format.

[0305] Step 5: AI model analysis

[0306] server

[0307] Preprocessed medical image data and standardized health data are input into the AI ​​model and analysis is performed.

[0308] Example: The server uses an AI model to analyze a patient's MRI images and identify the location and size of a tumor.

[0309] As a diagnostic result, abnormalities and important findings are extracted as numerical or text data.

[0310] Example: As a result of AI analysis, the location coordinates and size of a tumor are obtained as numerical data.

[0311] Step 6: 3D model generation

[0312] server

[0313] Based on the analysis results, a 3D model of the medical image is generated using a 3D CG engine.

[0314] Example: The server generates a 3D model of the tumor from the analysis results and visually highlights the tumor location.

[0315] The completed 3D model is visualized and delivered to a web viewer or dedicated application.

[0316] Example: The generated 3D model can be uploaded to a cloud-based dashboard and accessed by medical staff via a dedicated app.

[0317] Step 7: Sentiment Analysis

[0318] server

[0319] An emotion engine is used to recognize the user's (patient's) emotional state in real time.

[0320] Example: Based on input from the camera and microphone, the emotion engine analyzes the patient's facial expressions and tone of voice to understand their emotional state.

[0321] Step 8: Emotion-Based Display Adjustment

[0322] server

[0323] The display of a 3D model is adjusted based on the recognized emotion.

[0324] For example, if a patient is feeling anxious, the system will change the display of the 3D model to something simpler and easier to explain.

[0325] Step 9: View on the Dashboard

[0326] Terminal

[0327] Medical staff access the dashboard hosted on the server through a browser on their PC or tablet.

[0328] Example: A doctor uses a tablet to access a dashboard in the cloud and open a 3D model of a patient.

[0329] On the dashboard, select a 3D model of a specific patient and zoom in / out, rotate, and more to view details.

[0330] Example: A doctor rotates the 3D model to see the precise location and size of a tumor.

[0331] If necessary, screen captures and report output are performed to share diagnostic information with other medical staff and patients.

[0332] Example: A doctor generates a diagnostic report with a captured image of the 3D model and shares it with other medical staff.

[0333] Step 10: Promote communication with patients

[0334] Users (medical staff, patients)

[0335] When medical staff meet with patients, they explain things to them while displaying 3D models on a PC or tablet.

[0336] Example: A surgeon shows a patient a 3D model of the tumor and explains the surgical procedure.

[0337] Patients can understand diagnostic information by visually viewing the 3D model.

[0338] Example: A patient looks at a model of their tumor and understands what the surgeon is explaining.

[0339] Medical staff and patients create and review treatment plans based on the generated 3D model and feedback from the emotion engine.

[0340] For example, a surgeon and a patient can review the treatment schedule and procedures while referring to a 3D model. The emotion engine provides appropriate feedback to reduce patient anxiety and facilitate communication.

[0341] Example 2

[0342] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0343] The current medical system not only lacks diagnostic accuracy and speed, but also lacks interactive functions for smooth communication between medical staff and patients. In particular, it is difficult to diagnose and explain things taking into account the patient's emotional state, which leads to problems such as a decrease in patient understanding and satisfaction. There is a need to efficiently solve these issues.

[0344] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0345] In this invention, the server includes a means for electronically collecting medical image data and patient health data from medical institutions, a means including an artificial intelligence model for preprocessing and analyzing the medical image data and health data, a means for generating a 3D model based on the analysis results, a means for visualizing the 3D model and presenting it to medical staff, a means for recognizing the user's emotional state and adjusting the display content of the 3D model based on that feedback, and a means for the patient and medical staff to discuss and reach a consensus on detailed diagnoses and treatment plans based on the generated 3D model and feedback from the emotion engine, thereby improving the accuracy and speed of diagnoses and enabling interactive communication that reflects the patient's emotional state.

[0346] "Medical image data" refers to image information obtained from imaging diagnostic equipment (e.g., X-ray, MRI, CT scan) used in medical institutions.

[0347] "Patient health data" refers to digital information such as a patient's medical history, current physical condition, and test results obtained from an electronic medical record system.

[0348] "Preprocessing" refers to a series of processes that remove noise and complement collected raw data, converting it into a form suitable for analysis.

[0349] An "artificial intelligence model" is a program that uses machine learning algorithms to analyze data and make diagnoses and predictions.

[0350] "Analysis results" refers to conclusions or insights derived from data processed using artificial intelligence models.

[0351] A "3D model" refers to a three-dimensional visual display created based on the analysis results, specifically a three-dimensional display of the affected area and internal structure.

[0352] "Visualization" refers to the display of data or information in a visual form, specifically on a screen or in a VR space.

[0353] "User's emotional state" refers to the results obtained by analyzing the emotions and feelings the user is currently experiencing based on information obtained from a camera, microphone, etc.

[0354] "Feedback" refers to the adjustment of displayed content, specific advice, or explanations that the system provides based on the user's emotional state or other information.

[0355] "Discussion" refers to a discussion in which medical staff and patients share information and exchange opinions to determine treatment plans and diagnostic procedures.

[0356] "Consensus building" refers to medical staff and patients reaching a mutually acceptable treatment plan and diagnostic policy through discussion.

[0357] MODE FOR CARRYING OUT THE INVENTION

[0358] This invention is a system called "3D Health Analyzer" that improves the accuracy and speed of diagnoses in medical institutions and streamlines communication between medical staff and patients. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it provides interactive functions that respond to the user's emotional state.

[0359] System Configuration

[0360] "3D Health Analyzer" is a system that includes a server, a terminal, a user, and an emotion engine.

[0361] 1. Server: Responsible for data collection, preprocessing, analysis, 3D model generation, and emotion engine management.

[0362] 2. Terminal: Provides an interface for medical staff to view and manipulate the 3D model.

[0363] 3. Users: Medical staff and patients who share and understand diagnostic information and treatment plans through the system.

[0364] 4. Emotion Engine: Recognizes the user's emotional state and provides feedback accordingly.

[0365] Hardware and software used

[0366] Specific hardware and software examples include:

[0367] Imaging equipment: MRI, CT scan, X-ray, etc.

[0368] Electronic medical record system: A system that manages patient health data

[0369] Server software: Software on the server that manages data collection, preprocessing, and analysis

[0370] AI model: Machine learning algorithms used for data analysis

[0371] 3D CG engine: 3D model generation software such as Unity or Unreal Engine

[0372] Emotion Engine: Software that analyzes the user's emotional state

[0373] Program processing example

[0374] Example 1:

[0375] "We input the MRI images and the patient's medical history into the 3D Health Analyzer to generate a 3D model of the tumor. If the patient is concerned, we adjust the display to simplify it."

[0376] Example 2:

[0377] "Collect patient health data from electronic medical records, analyze it with an AI model, and generate a 3D model based on the results. Use an emotion engine to recognize patient emotions and provide feedback."

[0378] An example of an operation sequence

[0379] 1. Data collection: The server collects the necessary medical data from the medical institution's electronic medical record system and imaging diagnostic equipment via the API.

[0380] 2. Data preprocessing: The collected data will be preprocessed by the server to remove noise and perform imputation. The patient's health data will be converted into a standard format.

[0381] 3. Data analysis: The preprocessed data is input into the AI ​​model for analysis, and the analysis results are extracted as numerical data or text data.

[0382] 4. 3D model generation: Based on the analysis results, the server generates a 3D model using a 3D CG engine.

[0383] 5. Visualization: The generated 3D model is visualized in a web viewer or dedicated application and delivered to medical staff.

[0384] 6. Utilizing an Emotion Engine: The server recognizes the user's emotional state and adjusts the display content and feedback of the 3D model accordingly.

[0385] By introducing this "3D Health Analyzer," medical facilities can significantly improve the accuracy and speed of diagnosis, as well as patient understanding and satisfaction. By combining it with an emotion engine, it can provide interactive feedback that takes into account the patient's emotional state, resulting in more efficient medical services.

[0386] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0387] Step 1:

[0388] The server collects medical image data and patient health data from medical institutions' electronic medical record systems and diagnostic imaging devices via APIs.

[0389] As a specific example of operation, the server calls the API of the MRI device, obtains image data of a specific patient, and obtains the patient's medical history and current physical condition data from the electronic medical record.

[0390] Input: Image data from MRI scanner, patient health data from electronic medical records

[0391] Output: Medical imaging data and patient health data

[0392] Step 2:

[0393] The server performs preprocessing by removing noise and complementing the medical image data collected.

[0394] Specifically, the server applies a noise reduction algorithm to remove noise from the acquired MRI images, complement the degraded parts, and convert the patient's health data into a standard format.

[0395] Input: Medical image data, patient health data

[0396] Output: Denoised and imputed medical image data, standardized health data

[0397] Step 3:

[0398] The server inputs the preprocessed medical data into the AI ​​model and performs data analysis.

[0399] As a specific example of how it works, preprocessed MRI image data and standardized health data are input into the AI ​​model, and an analysis is performed to identify the location and size of the tumor, with numerical and text data being obtained as the analysis results.

[0400] Input: Preprocessed medical image data, standardized health data

[0401] Output: Analysis results (tumor location, size)

[0402] Step 4:

[0403] The server generates a 3D model based on the analysis results.

[0404] As a specific example of how it works, the server uses a 3D CG engine (e.g., Unity or Unreal Engine) to generate a 3D model of the tumor based on the analysis results and combines it with other parts of the human body to create a complete picture.

[0405] Input: Analysis results (tumor location, size)

[0406] Output: Generated 3D model

[0407] Step 5:

[0408] The server visualizes the generated 3D model through a web viewer or dedicated application and delivers it to medical staff.

[0409] As a specific example of how it works, the server uploads the generated 3D model to a cloud dashboard and displays it in a dedicated application for medical staff.

[0410] Input: Generated 3D model

[0411] Output: Web viewer, 3D model displayed in dedicated application

[0412] Step 6:

[0413] The server uses an emotion engine to recognize the emotional state of the user (mainly the patient) in real time.

[0414] As a specific example of how it works, the emotion engine analyzes the patient's facial expressions and tone of voice based on input from the camera and microphone, and grasps the patient's emotional state.

[0415] Input: Video and audio data from cameras and microphones

[0416] Output: Perceived patient emotional state

[0417] Step 7:

[0418] The server adjusts the display content and feedback of the 3D model based on the emotional state it recognizes.

[0419] As a specific example of how this works, if a patient is feeling anxious, the display content of the 3D model is adjusted to be simple and easy to explain.

[0420] Input: Recognized patient emotional state, generated 3D model

[0421] Output: Visualization and feedback of the adjusted 3D model

[0422] Step 8:

[0423] Using the terminal, medical staff can access the dashboard and conduct examinations while viewing the 3D model.

[0424] As a specific example of how it works, medical staff use a tablet device to display a 3D model of the patient's tumor and perform an examination and explanation.

[0425] Input: Adjusted 3D model, feedback

[0426] Output: Examination and explanation by medical staff

[0427] Step 9:

[0428] Users (medical staff and patients) discuss and reach a consensus on detailed diagnoses and treatment plans based on the generated 3D models and feedback from the emotion engine.

[0429] As a specific example of how it works, medical staff and patients can discuss treatment plans and surgical risks while looking at the 3D model, and the emotion engine provides feedback to reduce the patient's anxiety.

[0430] Input: Adjusted 3D model, feedback

[0431] Output: Consensus diagnosis and treatment plan

[0432] (Application example 2)

[0433] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0434] In modern factory environments, it is difficult to monitor workers' health and mental stress in real time and respond appropriately. This can lead to reduced work efficiency and safety risks. Furthermore, communication with workers tends to be lacking, and health problems are often only addressed after they occur. Therefore, there is a need for a system that can monitor workers' health and emotions in real time and provide efficient feedback.

[0435] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for electronically collecting medical image data and patient health data from medical institutions, means including an artificial intelligence model for preprocessing and analyzing the medical image data and the health data, means for generating a 3D model based on the analysis results, means for visualizing the 3D model and presenting it to a user, means for recognizing the user's emotions and providing feedback according to their emotional state, and means for adjusting the display content of the 3D model based on the emotion recognition means. This makes it possible to monitor the health status and emotions of workers in real time and provide appropriate feedback, thereby improving work efficiency and ensuring safety.

[0436] A "medical institution" is an organization or facility that provides medical services to patients.

[0437] "Electronically collected" refers to obtaining information as digital data using networks or sensors.

[0438] "Medical image data" refers to image information of a patient's inside the body obtained from imaging diagnostic devices such as CT scans and MRIs.

[0439] "Patient health data" refers to digital data relating to a patient's medical history and current health status.

[0440] "Preprocessing" refers to the process of processing collected data, such as by removing noise and standardizing it, to prepare it in a format suitable for analysis.

[0441] An "artificial intelligence model" refers to a system that uses algorithms such as machine learning and deep learning to analyze data and detect patterns and anomalies.

[0442] "Generating a 3D model" refers to creating a three-dimensional image using computer graphics based on the analysis results.

[0443] "Visualizing" refers to the process of displaying digital data in a graphical form that makes it easier for humans to understand.

[0444] "Users" refers to factory workers and managers who use this system.

[0445] "Emotion recognition" means analyzing the user's psychological state from facial expressions, tone of voice, etc., and inferring specific emotions.

[0446] "Providing feedback" refers to providing users with advice, instructions, alerts, etc. in real time based on their emotions and health data.

[0447] "Adjusting the displayed content" refers to changing the visual information and feedback content based on the results of emotion recognition and presenting it in a form appropriate for the user.

[0448] The present invention, "Factory 3D Health Analyzer," is a system aimed at improving the health management and safety of workers in a factory environment. This system is composed of four components: a server, a terminal, a user, and an emotion engine.

[0449] server

[0450] The server is responsible for data collection, pre-processing, analysis, 3D model generation and emotion engine management.

[0451] Collection Method

[0452] The server electronically collects medical image data and patient health data from medical institutions through APIs.

[0453] Pretreatment means

[0454] The server first performs preprocessing on the collected data, such as noise removal and conversion to a standard format, so that the health data is in a format suitable for AI models.

[0455] Analysis means

[0456] The pre-processed data is then input into an artificial intelligence model on the server, which then performs an analysis, such as identifying the location and size of a tumor from collected medical image data.

[0457] 3D model generation method

[0458] Based on the analysis results, the server uses a 3D model generation engine to generate a realistic 3D model, which is then used to display the factory's work lines and equipment in 3D.

[0459] Feedback methods

[0460] The emotion engine recognizes the user's emotional state and provides feedback based on that emotion. For example, if the user is feeling stressed, the system will issue an appropriate alert and adjust the work environment accordingly.

[0461] Terminal

[0462] The terminal provides an interface for workers to view and manipulate the 3D model.

[0463] Visualization tools

[0464] The generated 3D model is visualized and displayed on devices such as smart glasses or tablets, allowing workers to check their own health status and working environment in real time.

[0465] For example, sensors built into smart glasses collect vital data (heart rate, body temperature, oxygen concentration) from workers and send it to a server. The server analyzes the data and sends the results to the device as a 3D model. If the worker's heart rate is high, the smart glasses will display an alert saying, "Please take a break."

[0466] User

[0467] The users are the workers and administrators who operate and check the system.

[0468] emotion recognition means

[0469] The system analyzes the worker's facial expressions and tone of voice via cameras and microphones to detect stress and anxiety, and the server then generates appropriate feedback and sends it to the device.

[0470] Feedback Adjustment Means

[0471] Based on the emotion recognition results, the display content of the 3D model and the feedback content are adjusted, which can reduce stress and anxiety for workers.

[0472] Examples of prompts include, "Generate appropriate feedback to be displayed when a worker wearing smart glasses feels stressed" and "Monitor the worker's health status based on sensor data and suggest how to automatically adjust the work plan based on that status."

[0473] As described above, the "Factory 3D Health Analyzer" of this invention makes it possible to monitor and adjust the health status and emotions of workers in real time, thereby improving work efficiency and ensuring safety in factories.

[0474] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0475] Step 1:

[0476] The server collects medical image data and patient health data from the medical institution's electronic medical record system and imaging diagnostic equipment via API. The input is data from the electronic medical record system and imaging diagnostic equipment, and the output is the collected medical image data and health data. This collected data is input into the next pre-processing phase.

[0477] Step 2:

[0478] The server performs pre-processing on the collected medical image data, such as noise removal and interpolation. The input is the medical image data collected in step 1, and the output is clear medical image data that has been subjected to noise removal and interpolation. This processing is intended to improve the accuracy of medical image analysis.

[0479] Step 3:

[0480] The server inputs preprocessed medical image data and standardized health data into the AI ​​model and performs the analysis. The input is preprocessed medical image data and health data, and the output is numerical and text data as the analysis results. For example, diagnostic information such as the location and size of a tumor is output.

[0481] Step 4:

[0482] The server generates a 3D model using a 3D model generation engine based on the analysis results. The input is the numerical and text data of the analysis results obtained in Step 3, and the output is the 3D model data. The generated 3D model is useful for detailed visualization of specific parts.

[0483] Step 5:

[0484] The server uploads the generated 3D model to a cloud database or web dashboard and distributes it so that it can be accessed by medical staff and workers. The input is the 3D model data, and the output is accessible via a web viewer or dedicated application. This allows the user, or worker, to view the 3D model on their device.

[0485] Step 6:

[0486] The server uses an emotion engine to analyze and recognize the user's emotional state in real time. The input is video and audio data from a camera and microphone, and the output is the type of emotion recognized. For example, it determines whether the user is feeling stressed.

[0487] Step 7:

[0488] The server adjusts the display content and feedback of the 3D model based on the emotion recognition results. The input is the emotion data recognized in step 6, and the output is the adjusted display content and feedback message of the 3D model. For example, for a user who is feeling stressed, the display will be simpler and easier to understand.

[0489] Step 8:

[0490] The terminal presents the adjusted 3D model and feedback to the user (worker). The input is the adjusted 3D model and feedback data sent from the server in step 7, and the output is the information displayed on the terminal screen. This allows the worker to deepen their understanding of their own health condition and work environment and respond appropriately.

[0491] Step 9:

[0492] The user (worker) uses the terminal to check the displayed 3D model and feedback, and respond or take action as necessary. The input is the information displayed on the terminal, and the output is the worker's actions or responses. For example, this includes actions such as taking a break or reporting to a manager.

[0493] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0494] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0495] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0496] [Second embodiment]

[0497] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0498] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0499] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0500] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0501] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0502] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0503] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0504] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0505] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0506] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0507] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0508] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0509] The present invention, "3D Health Analyzer," is a system for improving the accuracy and speed of diagnoses in medical institutions and streamlining communication between medical staff and patients. This system consists of a series of processes that collect and analyze medical image data and patient health data, and visualize the results as a 3D model. Below, the processing of the system's program is explained in natural language and detailed with concrete examples.

[0510] overview

[0511] "3D Health Analyzer" is a system consisting of three parties: a server, a terminal, and a user. The server is responsible for data collection, preprocessing, analysis, and generation of 3D models. The terminal provides an interface for medical staff to view and manipulate the 3D models. Users are medical staff and patients, and are responsible for sharing and understanding diagnostic information and treatment plans through the system.

[0512] Program processing flow

[0513] Collection Phase

[0514] The server collects medical image data and patient health data from the medical institution's electronic medical record system and imaging diagnostic equipment (e.g., X-ray, MRI, CT scan) via API.

[0515] Example: A server obtains image data of a patient's teeth from a dental X-ray machine in a dental clinic, and simultaneously collects data about the patient's medical history and current symptoms.

[0516] Preprocessing Phase

[0517] The server performs noise removal and interpolation on the collected medical image data.

[0518] Example: The server removes noise from acquired dental X-ray images and complements degraded parts of the images.

[0519] The server converts the health data into a standard format and makes it suitable for AI models.

[0520] Example: Converting a patient's past medical records and current health status data into a standardized format.

[0521] Analysis Phase

[0522] The server inputs the preprocessed data into the AI ​​model and performs the analysis.

[0523] Example: The server uses an AI model to analyze the patient's dental condition and identify areas of decay and possible periodontitis.

[0524] The server extracts the analysis results as numerical and text data and uses them as the basic data for generating a 3D model.

[0525] Example: Based on AI analysis, the location and size of cavities are extracted as numerical data.

[0526] 3D model generation phase

[0527] The server uses a 3D CG engine to generate a realistic 3D model based on the analysis results.

[0528] Example: A server generates a 3D dental model and visually highlights identified areas of caries.

[0529] Visualization Phase

[0530] The server visualizes the generated 3D model using a web viewer or dedicated application and delivers it to medical staff.

[0531] Example: The server uploads the generated 3D tooth model to a dashboard on the cloud, where it can be displayed in a viewer for medical staff.

[0532] Review and communication phase

[0533] Using the terminal, medical staff can access a dashboard and conduct examinations while viewing the 3D model.

[0534] Example: A dentist uses a tablet to view a 3D model of a patient's teeth, highlighting any cavities and providing explanations.

[0535] Based on the generated 3D model, users (medical staff and patients) discuss and reach a consensus on detailed diagnoses and treatment plans.

[0536] Example: Dentists and patients can view 3D models to discuss in detail treatment plans and preventative measures for cavities.

[0537] The "3D Health Analyzer" of this invention allows medical staff to significantly reduce the time and effort required to analyze medical images, thereby improving diagnostic accuracy. Furthermore, the use of 3D models facilitates communication with patients, increasing their understanding and acceptance of treatment. This improves the overall quality of medical care and reduces patient health risks.

[0538] The processing flow will be explained below.

[0539] Step 1: Data collection

[0540] server

[0541] Medical imaging data and patient health data are collected via APIs from medical institutions' electronic medical record systems and imaging diagnostic devices (e.g., X-ray machines, MRIs, CT scans).

[0542] Example: A server obtains dental image data of a particular patient from a dental x-ray machine in a dental clinic, and simultaneously collects the patient's medical history and current health data.

[0543] Step 2: Data Storage

[0544] server

[0545] Collected medical image data and health data are stored in temporary cloud storage.

[0546] Example: The server stores the acquired data in secure cloud storage and manages it in a database.

[0547] Step 3: Data cleaning

[0548] server

[0549] A pre-processing algorithm is used to remove noise from medical image data.

[0550] Example: Image filtering is used to remove noise from X-ray images and adjust image brightness and contrast.

[0551] Detect missing data and outliers in health data and impute or remove them appropriately.

[0552] Example: The server uses an imputation algorithm to fill in missing values ​​in health data and remove outliers.

[0553] Step 4: Data Standardization

[0554] server

[0555] Standardize the units and notations of health data (e.g., blood pressure, blood sugar levels, etc.) and convert them into a standard format.

[0556] Example: Convert blood pressure data into a unified unit (mmHg) and standardize the range of values.

[0557] Medical image data is also converted into a format suitable for AI models (e.g., DICOM format).

[0558] Example: Converting an X-ray image in JPG format to DICOM format.

[0559] Step 5: AI model analysis

[0560] server

[0561] Preprocessed medical image data and standardized health data are input into the AI ​​model and analysis is performed.

[0562] Example: The server uses an AI model to analyze images of teeth and automatically detect the location and depth of cavities.

[0563] As a diagnostic result, abnormalities and important findings are extracted as numerical or text data.

[0564] Example: As a result of AI analysis, the coordinates of the location and depth of cavities are obtained as numerical data.

[0565] Step 6: 3D model generation

[0566] server

[0567] Based on the analysis results, a 3D model of the medical image is generated using a 3D CG engine.

[0568] Example: The server generates a 3D model of the teeth from the analysis results, highlighting areas of decay.

[0569] The completed 3D model is visualized and delivered to a web viewer or dedicated application.

[0570] Example: The generated 3D model can be uploaded to a cloud-based dashboard and accessed by medical staff via a dedicated app.

[0571] Step 7: View on the dashboard

[0572] Terminal

[0573] Medical staff access the dashboard hosted on the server through a browser on their PC or tablet.

[0574] Example: A doctor uses a tablet to access a dashboard in the cloud and open a 3D model of a patient.

[0575] On the dashboard, select a 3D model of a specific patient and zoom in / out, rotate, and more to view details.

[0576] Example: The doctor rotates the 3D model to see the precise location and size of the cavities.

[0577] If necessary, screen captures and report output are performed to share diagnostic information with other medical staff and patients.

[0578] Example: A doctor generates a diagnostic report with a captured image of the 3D model and shares it with other medical staff.

[0579] Step 8: Promote communication with patients

[0580] Users (medical staff, patients)

[0581] When medical staff meet with patients, they explain things to them while displaying 3D models on a PC or tablet.

[0582] Example: A dentist shows a patient a 3D model of a tooth and explains the condition and treatment of the tooth.

[0583] Patients can understand diagnostic information by visually viewing the 3D model.

[0584] Example: A patient looks at a model of their own teeth and understands what the dentist is explaining.

[0585] Medical staff and patients create and review treatment plans based on the generated 3D model.

[0586] Example: Dentists and patients can review treatment schedules and procedures by referring to the 3D model.

[0587] Example 1

[0588] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0589] With conventional medical data analysis systems, medical staff spent a lot of time and effort analyzing diagnostic results and communicating with patients. This resulted in inconsistent diagnostic accuracy and low patient understanding and treatment acceptance. Furthermore, the lack of integrated analysis of medical images and health data made it difficult to develop comprehensive diagnoses and treatment plans. Furthermore, there were limited means of presenting analysis results in a visually understandable manner.

[0590] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0591] In this invention, the server includes: means for electronically collecting medical image data and patient health data from medical institutions; means for performing noise reduction and interpolation on the medical image data; means for converting the health data into a standard format and arranging it in a format suitable for analysis; means including an artificial intelligence model for preprocessing and analyzing the medical image data and the health data; means for instructing the artificial intelligence model to perform analysis using prompts; means for extracting the analysis results as numerical data and text data and using them as basic data for generating a 3D model; means for using a computer graphics engine to generate a realistic 3D model based on the analysis results; and means for visualizing the 3D model and presenting it to medical staff. This improves the accuracy and speed of diagnosis and enables efficient communication with patients.

[0592] "Medical image data" refers to image information such as X-rays, MRIs, and CT scans obtained at medical institutions.

[0593] "Patient Health Data" means information about a patient's health, such as the patient's medical history, current symptoms, and vital signs.

[0594] "Noise removal" is a process that removes unnecessary high-frequency components and errors from medical image data.

[0595] "Complement" is a process of filling in missing parts of medical image data to improve image quality.

[0596] A "standard format" is a common structure or format established to maintain data consistency and compatibility.

[0597] An "artificial intelligence model" is a computational algorithm used to analyze large amounts of data and find patterns and regularities.

[0598] A "prompt sentence" is a short piece of text that instructs an artificial intelligence model to perform a specific analysis.

[0599] "Numerical data" is information in a numerical format that quantitatively expresses the analysis results.

[0600] "Text data" is information that expresses analysis results and explanations in text format.

[0601] A "3D model" is a visual representation generated as a three-dimensional shape based on the analysis results.

[0602] A "computer graphics engine" is software for generating and displaying three-dimensional computer graphics.

[0603] The present invention, "3D Health Analyzer," is a system for improving the accuracy and speed of diagnoses in medical institutions and streamlining communication between medical staff and patients. This system consists of a series of processes that collect, preprocess, and analyze medical image data and patient health data, and visualize the results as a 3D model.

[0604] Hardware and Software Configuration

[0605] This system is mainly composed of three components: a server, a terminal, and a user. The specific hardware and software configuration is as follows:

[0606] Server: A computer system responsible for collecting, preprocessing, and analyzing data, and generating 3D models. Software used here includes APIs, Python's OpenCV library, generative AI models such as TensorFlow or PyTorch, and computer graphics engines such as Unity or Unreal Engine.

[0607] Terminal: A device used by medical staff to view and manipulate 3D models. This can be a display device such as a tablet or PC.

[0608] Users: Medical staff and patients who share and understand diagnostic information and treatment plans through the system.

[0609] Data collection and preprocessing

[0610] The server collects medical image data and patient health data from medical institutions' electronic medical record systems and imaging diagnostic devices (e.g., X-rays, MRIs, CT scans) via APIs. The collected data is stored in a database and backed up. For example, the server collects image data of patients' teeth from dental X-ray machines at a dental clinic, and simultaneously obtains data about the patient's medical history and current symptoms.

[0611] As part of preprocessing, the server performs noise removal and interpolation on medical image data and converts the health data into a standard format. For example, the server removes noise from collected dental X-ray images and interpolates image degradation. It also converts patients' past medical records and current health status data into a standard format (e.g., HL7 format).

[0612] Data analysis and 3D model generation

[0613] The server inputs the preprocessed medical image data and health data into the generative AI model. It uses prompts to provide specific instructions to the AI ​​model. Specific examples of prompts include, "Please identify the location of cavities in this patient's dental X-rays" and "Please convert the collected health data into a standard format and analyze the risk of periodontitis."

[0614] The analysis results from the generative AI model are extracted as numerical and text data, and the server uses this data to generate a 3D model. Specifically, the server uses a 3D CG engine such as Unity or Unreal Engine to generate a realistic 3D model based on the analysis results. The generated 3D model is presented to medical staff in a visually easy-to-understand format.

[0615] Visualization and Communication

[0616] The generated 3D model is visualized by the server through a web viewer or dedicated application. Medical staff can access the dashboard using a terminal and examine the patient while viewing the 3D model. For example, a dentist can view the 3D model of a patient's teeth on a tablet and explain the procedure, highlighting any cavities.

[0617] Furthermore, users (medical staff and patients) can discuss and reach consensus on detailed diagnoses and treatment plans based on the generated 3D models. For example, dentists and patients can discuss in detail treatment plans and preventive measures for cavities while looking at the 3D models.

[0618] In this way, the "3D Health Analyzer" of the present invention enables medical staff to improve the accuracy and speed of diagnosis, and also facilitates smooth communication with patients.

[0619] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0620] Step 1:

[0621] Data collection

[0622] The server collects medical image data and patient health data from the medical institution's electronic medical record system and imaging diagnostic equipment (e.g., X-ray, MRI, CT scan).

[0623] Input: Medical imaging data and patient health data from the medical institution's database.

[0624] Output: The collected medical image data and patient health data are stored in a database on the server.

[0625] What it does: Every day at 2 AM, the server runs an automated script to collect new patient data from the dental x-ray machine in the dental clinic.

[0626] Step 2:

[0627] Data Loss Prevention

[0628] The server backs up the collected data and stores it in a database, which prevents data loss and ensures safety.

[0629] Input: Collected data (medical imaging data and health data).

[0630] Output: Data stored in the database and backup data.

[0631] How it works: The server backs up collected dental X-ray images and health data to two different data centers.

[0632] Step 3:

[0633] Image data preprocessing

[0634] The server performs noise removal and interpolation on the collected medical image data.

[0635] Input: Collected medical image data.

[0636] Output: Denoised and imputed medical image data.

[0637] Specific operation: The server uses Python's OpenCV library to analyze the pixel values ​​of the acquired image and apply a filter to suppress high-frequency noise.

[0638] Step 4:

[0639] Health data format conversion

[0640] The server converts the health data into a standard format and makes it suitable for analysis.

[0641] Input: Collected health data.

[0642] Output: Health data converted into a standard format.

[0643] Specific operation: The server converts the patient's blood pressure, heart rate, and past medical records into HL7 format.

[0644] Step 5:

[0645] Input to AI model and prompt generation

[0646] The server inputs the preprocessed data into the generative AI model and uses prompt statements to direct the analysis.

[0647] Input: Denoised medical image data and health data in standard formats.

[0648] Output: The analysis results of the generative AI model.

[0649] Specific operation: The server generates a prompt statement such as, "Please identify the cavities in this patient's dental X-ray image," and instructs the AI ​​model.

[0650] Step 6:

[0651] Obtaining analysis results and extracting data

[0652] The server receives the analysis results from the AI ​​model and extracts them as numerical and text data.

[0653] Input: Analysis results of the generative AI model.

[0654] Output: Numerical and textual data.

[0655] Specific operation: The server stores the analysis results received from the AI ​​model, such as the location and size of cavities, as numerical data in a database.

[0656] Step 7:

[0657] 3D model generation

[0658] The server uses a 3D CG engine to generate a realistic 3D model based on the analysis results.

[0659] Input: Numeric and text data.

[0660] Output: Realistic 3D models.

[0661] Specific operation: The server uses Unity or Unreal Engine to generate a 3D model based on the analysis results and highlights visually important parts.

[0662] Step 8:

[0663] 3D model visualization and distribution

[0664] The server uploads the generated 3D model to a web viewer or dedicated application.

[0665] Input: A generated 3D model.

[0666] Output: 3D model that can be viewed in a web viewer or dedicated application.

[0667] Specific operation: The server uploads the generated 3D model to a dashboard on the cloud and notifies medical staff of an access URL or QR code.

[0668] Step 9:

[0669] Checked by medical staff

[0670] Using the terminal, medical staff can access the dashboard and conduct examinations while viewing the 3D model.

[0671] Input: 3D models uploaded to a web viewer or dedicated application.

[0672] Output: Medical staff examination results.

[0673] Specific operation: The dentist zooms in and rotates the 3D model of the patient on the tablet, checking the areas of tooth decay while explaining to the patient.

[0674] Step 10:

[0675] Sharing Diagnoses and Treatment Plans

[0676] Based on the generated 3D model, users (medical staff and patients) discuss and reach a consensus on detailed diagnoses and treatment plans.

[0677] Input: Medical staff review results and 3D model.

[0678] Output: Diagnosis and treatment plan.

[0679] How it works: Dentists and patients discuss treatment options while looking at the 3D model and select the best treatment plan.

[0680] (Application example 1)

[0681] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0682] It is important for medical institutions to analyze medical image data and health data more effectively and improve the accuracy and speed of diagnoses. Visual support is also required to facilitate communication between patients and medical staff and provide easy-to-understand diagnoses and treatment plans. Furthermore, there is a need to provide a virtual health checkup experience that allows patients to check their health status from home, enabling more people to efficiently manage their health.

[0683] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0684] In this invention, the server includes: means for electronically collecting medical image data and patient health data from medical institutions; means including an artificial intelligence model for preprocessing and analyzing the medical image data and the health data; means for generating a 3D model based on the analysis results; means for visualizing the 3D model and presenting it to medical staff; means for allowing users to view the 3D model via an interface on a smartphone or head-mounted display; and means for providing a virtual health checkup experience. This allows users to easily check their health status from home and to better understand diagnoses and treatment plans through communication with medical staff.

[0685] "Medical image data" refers to image data obtained at a medical institution, including images taken using equipment such as X-rays, MRIs, and CT scans.

[0686] "Patient health data" refers to information such as a patient's medical history, current health status, medical records, and symptoms.

[0687] "Preprocessing" refers to the process of removing noise and standardizing collected medical image data and health data to prepare them in a format suitable for analysis.

[0688] "Artificial intelligence model" refers to a program that uses machine learning and deep learning to analyze medical image data and health data.

[0689] "3D model" refers to a three-dimensional visual model generated based on medical image data and analysis results.

[0690] "Visualization" refers to displaying 3D models in a way that makes them easy for medical staff to understand.

[0691] "Interface" refers to the connection method and display device that allows users to view 3D models through a smartphone or head-mounted display.

[0692] The "virtual health checkup experience" refers to an experience that allows users to check and diagnose their health status from the comfort of their own home.

[0693] A "smartphone" refers to a portable information terminal that can use communication functions and applications.

[0694] A "head-mounted display" refers to a display device that is worn on the head and provides visual information.

[0695] The present invention is a system that improves the accuracy and speed of diagnoses by utilizing medical image data and patient health data collected from medical institutions. This system is composed of three entities: a server, a terminal, and a user, as described below.

[0696] The server has the function of collecting medical image data and patient health data from medical institutions' electronic medical record systems and imaging diagnostic devices (e.g., X-ray devices, MRI devices, CT scan devices) via APIs. The server also performs preprocessing on the collected data, such as noise removal and conversion to a standard format. This preprocessing prepares the data in a format suitable for the artificial intelligence model. The preprocessed data is then input into the artificial intelligence model for analysis. Based on the results of this analysis, the server generates a 3D model. This 3D model is generated in real time using a 3D CG engine.

[0697] The device provides an interface for visualizing the generated 3D model. Medical staff can use this device to check the 3D model and operate the interface. The visualized 3D model is uploaded to a dashboard on the cloud and displayed in a viewer for medical staff. In addition, the device has a function that allows the user (patient) to check the 3D model using a smartphone or head-mounted display.

[0698] Users are medical staff and patients, who use the generated 3D models to discuss and reach consensus on detailed diagnoses and treatment plans. Patients can experience virtual medical checkups from home using a smartphone or head-mounted display. For example, when a patient uploads MRI scan data from home, the system analyzes the data and generates a 3D model. The generated 3D model is displayed on a smartphone or head-mounted display so that the patient can view it at home.

[0699] The main hardware and software used include Python, Numpy, Scikit-learn, Nibabel, and Vedo, which are used to handle the steps of data collection, preprocessing, analysis, 3D model generation, and visualization.

[0700] As a concrete example, the following prompt sentence can be used:

[0701] Example prompt sentence:

[0702] "I've been having frequent headaches lately. I'd like you to check the state of my brain based on my MRI scan data and visualize it as a 3D model."

[0703] In this way, the system of the present invention improves diagnostic accuracy at medical institutions and facilitates smooth communication between patients and medical staff. Furthermore, by providing a virtual health checkup experience, patients can easily check their health status and use medical services from the comfort of their own homes.

[0704] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0705] Step 1:

[0706] The server collects medical image data and patient health data from medical institutions' electronic medical record systems and diagnostic imaging devices via APIs. During this collection process, data is obtained from various devices using API calls and stored in a database. The input is the medical image data and health data sent from the devices, and the output is the raw data stored in the server's database.

[0707] Step 2:

[0708] The server performs preprocessing on the collected medical image data to remove noise and correct image quality. Specifically, it performs noise removal filtering and image correction using libraries such as Python's Nibabel and OpenCV. The input is the medical image data collected in step 1, and the output is clean medical image data that has been corrected and denoised.

[0709] Step 3:

[0710] The server performs preprocessing to convert the patient's health data into a standard format and prepare it for analysis. Specifically, it uses Python's Pandas library to clean the data, extract necessary items, and format it. The input is the health data collected in step 1, and the output is the standardized health data.

[0711] Step 4:

[0712] The server inputs the preprocessed medical image data and health data into an artificial intelligence model for analysis. This analysis uses libraries such as Scikit-learn and TensorFlow to apply machine learning and deep learning models to extract meaningful results from the data. The input is the data preprocessed in steps 2 and 3, and the output is the numerical and text data of the analysis results.

[0713] Step 5:

[0714] The server generates a 3D model based on the analysis results. Specifically, it uses a 3D CG engine such as the Vedo library to generate a three-dimensional model that visually represents the analysis results. The input is the analysis result data obtained in step 4, and the output is the generated 3D model.

[0715] Step 6:

[0716] The server visualizes the generated 3D model using a web viewer or a dedicated application so that users can check it through an interface. For example, a web page for displaying the 3D model is built using a web framework such as Flask or Django. The input is the 3D model generated in step 5, and the output is the visualized 3D model displayed in a web viewer that users can access.

[0717] Step 7:

[0718] The user checks the generated 3D model using a smartphone or a head-mounted display. Specifically, the user can launch a dedicated viewer app and interactively view the 3D model. The input is access to the 3D model display page visualized in Step 6, and the output is the user experience of checking the 3D model and understanding the health condition.

[0719] Step 8:

[0720] Users (medical staff and patients) discuss detailed diagnoses and treatment plans based on the generated 3D model and reach a consensus. For example, a patient can view the 3D model together with medical staff and discuss diagnostic results and specific treatment options. The inputs are the 3D model confirmed in step 7 and feedback from the users, and the output is the agreed-upon diagnostic information and treatment plan.

[0721] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0722] The present invention, "3D Health Analyzer," is a system that improves the accuracy and speed of diagnoses in medical institutions and streamlines communication between medical staff and patients. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it provides interactive functions that correspond to the user's emotional state. Below, the processing of the system's program is explained in natural language and detailed with specific examples.

[0723] overview

[0724] "3D Health Analyzer" is a system consisting of four components: a server, a terminal, a user, and an emotion engine. The server is responsible for data collection, preprocessing, analysis, 3D model generation, and emotion engine management. The terminal provides an interface for medical staff to view and manipulate the 3D models. Users are medical staff and patients, and their role is to share and understand diagnostic information and treatment plans through the system. The emotion engine recognizes the user's emotional state and provides feedback accordingly.

[0725] Program processing flow

[0726] Collection Phase

[0727] The server collects medical image data and patient health data from the medical institution's electronic medical record system and imaging diagnostic equipment (e.g., X-ray, MRI, CT scan) via API.

[0728] Example: A server retrieves image data for a particular patient from an MRI machine in a surgeon's office, while also collecting the patient's medical history and current health data.

[0729] Preprocessing Phase

[0730] The server performs noise removal and interpolation on the collected medical image data.

[0731] Example: The server removes noise from acquired MRI images and complements degraded parts of the images.

[0732] The server converts the health data into a standard format and makes it suitable for AI models.

[0733] Example: Converting a patient's past medical records and current health status data into a standardized format.

[0734] Analysis Phase

[0735] The server inputs the preprocessed data into the AI ​​model and performs the analysis.

[0736] Example: The server uses an AI model to analyze a patient's MRI images and identify the location and size of a tumor.

[0737] The server extracts the analysis results as numerical and text data and uses them as the basic data for generating a 3D model.

[0738] Example: As a result of AI analysis, the location coordinates and size of a tumor are obtained as numerical data.

[0739] 3D model generation phase

[0740] The server uses a 3D CG engine to generate a realistic 3D model based on the analysis results.

[0741] Example: The server generates a 3D model of the tumor from the analysis results and visually highlights the tumor location.

[0742] Visualization Phase

[0743] The server visualizes the generated 3D model using a web viewer or dedicated application and delivers it to medical staff.

[0744] Example: The generated 3D model can be uploaded to a cloud-based dashboard and accessed by medical staff via a dedicated app.

[0745] Emotion Engine

[0746] The server uses an emotion engine to recognize the emotions of users (mainly patients) in real time.

[0747] For example, based on input from the camera and microphone, the emotion engine analyzes the patient's facial expressions and tone of voice to understand their emotional state.

[0748] The server adjusts the display and feedback of the 3D model based on the recognized emotion.

[0749] For example, if a patient is feeling anxious, the system will change the display of the 3D model to something simpler and easier to explain.

[0750] Confirmation and communication promotion

[0751] Using the terminal, medical staff can access a dashboard and conduct examinations while viewing the 3D model.

[0752] Example: A surgeon uses a tablet to view a 3D model of a patient's tumor and explain it in detail.

[0753] Users (medical staff and patients) discuss and reach a consensus on detailed diagnoses and treatment plans based on the generated 3D models and feedback from the emotion engine.

[0754] Example: A surgeon and a patient discuss in detail the tumor treatment plan and the risks of surgery while looking at a 3D model. The emotion engine provides appropriate feedback to reduce the patient's anxiety and facilitate communication.

[0755] By combining the "3D Health Analyzer" of this invention with an emotion engine, medical staff can make diagnoses and explanations that take into account the patient's emotional state, thereby improving patient understanding and satisfaction. This system offers a new approach to improving both diagnostic accuracy and the quality of medical services.

[0756] The processing flow will be explained below.

[0757] Step 1: Data collection

[0758] server

[0759] Medical imaging data and patient health data are collected via APIs from medical institutions' electronic medical record systems and imaging diagnostic devices (e.g., X-ray machines, MRIs, CT scans).

[0760] Example: A server retrieves image data for a particular patient from an MRI machine in a surgeon's office, while also collecting the patient's medical history and current health data.

[0761] Step 2: Data Storage

[0762] server

[0763] Collected medical image data and health data are stored in temporary cloud storage.

[0764] Example: The server stores the acquired data in secure cloud storage and manages it in a database.

[0765] Step 3: Data cleaning

[0766] server

[0767] A pre-processing algorithm is used to remove noise from medical image data.

[0768] Example: Image filtering is used to remove noise from MRI images and adjust image brightness and contrast.

[0769] Detect missing data and outliers in health data and impute or remove them appropriately.

[0770] Example: The server uses an imputation algorithm to fill in missing values ​​in health data and remove outliers.

[0771] Step 4: Data Standardization

[0772] server

[0773] Standardize the units and notations of health data (e.g., blood pressure, blood sugar levels, etc.) and convert them into a standard format.

[0774] Example: Convert blood pressure data into a unified unit (mmHg) and standardize the range of values.

[0775] Medical image data is also converted into a format suitable for AI models (e.g., DICOM format).

[0776] Example: Converting a JPG format MRI image to DICOM format.

[0777] Step 5: AI model analysis

[0778] server

[0779] Preprocessed medical image data and standardized health data are input into the AI ​​model and analysis is performed.

[0780] Example: The server uses an AI model to analyze a patient's MRI images and identify the location and size of a tumor.

[0781] As a diagnostic result, abnormalities and important findings are extracted as numerical or text data.

[0782] Example: As a result of AI analysis, the location coordinates and size of a tumor are obtained as numerical data.

[0783] Step 6: 3D model generation

[0784] server

[0785] Based on the analysis results, a 3D model of the medical image is generated using a 3D CG engine.

[0786] Example: The server generates a 3D model of the tumor from the analysis results and visually highlights the tumor location.

[0787] The completed 3D model is visualized and delivered to a web viewer or dedicated application.

[0788] Example: The generated 3D model can be uploaded to a cloud-based dashboard and accessed by medical staff via a dedicated app.

[0789] Step 7: Sentiment Analysis

[0790] server

[0791] An emotion engine is used to recognize the user's (patient's) emotional state in real time.

[0792] Example: Based on input from the camera and microphone, the emotion engine analyzes the patient's facial expressions and tone of voice to understand their emotional state.

[0793] Step 8: Emotion-Based Display Adjustment

[0794] server

[0795] The display of a 3D model is adjusted based on the recognized emotion.

[0796] For example, if a patient is feeling anxious, the system will change the display of the 3D model to something simpler and easier to explain.

[0797] Step 9: View on the Dashboard

[0798] Terminal

[0799] Medical staff access the dashboard hosted on the server through a browser on their PC or tablet.

[0800] Example: A doctor uses a tablet to access a dashboard in the cloud and open a 3D model of a patient.

[0801] On the dashboard, select a 3D model of a specific patient and zoom in / out, rotate, and more to view details.

[0802] Example: A doctor rotates the 3D model to see the precise location and size of a tumor.

[0803] If necessary, screen captures and report output are performed to share diagnostic information with other medical staff and patients.

[0804] Example: A doctor generates a diagnostic report with a captured image of the 3D model and shares it with other medical staff.

[0805] Step 10: Promote communication with patients

[0806] Users (medical staff, patients)

[0807] When medical staff meet with patients, they explain things to them while displaying 3D models on a PC or tablet.

[0808] Example: A surgeon shows a patient a 3D model of the tumor and explains the surgical procedure.

[0809] Patients can understand diagnostic information by visually viewing the 3D model.

[0810] Example: A patient looks at a model of their tumor and understands what the surgeon is explaining.

[0811] Medical staff and patients create and review treatment plans based on the generated 3D model and feedback from the emotion engine.

[0812] For example, a surgeon and a patient can review the treatment schedule and procedures while referring to a 3D model. The emotion engine provides appropriate feedback to reduce patient anxiety and facilitate communication.

[0813] Example 2

[0814] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0815] The current medical system not only lacks diagnostic accuracy and speed, but also lacks interactive functions for smooth communication between medical staff and patients. In particular, it is difficult to diagnose and explain things taking into account the patient's emotional state, which leads to problems such as a decrease in patient understanding and satisfaction. There is a need to efficiently solve these issues.

[0816] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0817] In this invention, the server includes a means for electronically collecting medical image data and patient health data from medical institutions, a means including an artificial intelligence model for preprocessing and analyzing the medical image data and health data, a means for generating a 3D model based on the analysis results, a means for visualizing the 3D model and presenting it to medical staff, a means for recognizing the user's emotional state and adjusting the display content of the 3D model based on that feedback, and a means for the patient and medical staff to discuss and reach a consensus on detailed diagnoses and treatment plans based on the generated 3D model and feedback from the emotion engine, thereby improving the accuracy and speed of diagnoses and enabling interactive communication that reflects the patient's emotional state.

[0818] "Medical image data" refers to image information obtained from imaging diagnostic equipment (e.g., X-ray, MRI, CT scan) used in medical institutions.

[0819] "Patient health data" refers to digital information such as a patient's medical history, current physical condition, and test results obtained from an electronic medical record system.

[0820] "Preprocessing" refers to a series of processes that remove noise and complement collected raw data, converting it into a form suitable for analysis.

[0821] An "artificial intelligence model" is a program that uses machine learning algorithms to analyze data and make diagnoses and predictions.

[0822] "Analysis results" refers to conclusions or insights derived from data processed using artificial intelligence models.

[0823] A "3D model" refers to a three-dimensional visual display created based on the analysis results, specifically a three-dimensional display of the affected area and internal structure.

[0824] "Visualization" refers to the display of data or information in a visual form, specifically on a screen or in a VR space.

[0825] "User's emotional state" refers to the results obtained by analyzing the emotions and feelings the user is currently experiencing based on information obtained from a camera, microphone, etc.

[0826] "Feedback" refers to the adjustment of displayed content, specific advice, or explanations that the system provides based on the user's emotional state or other information.

[0827] "Discussion" refers to a discussion in which medical staff and patients share information and exchange opinions to determine treatment plans and diagnostic procedures.

[0828] "Consensus building" refers to medical staff and patients reaching a mutually acceptable treatment plan and diagnostic policy through discussion.

[0829] MODE FOR CARRYING OUT THE INVENTION

[0830] This invention is a system called "3D Health Analyzer" that improves the accuracy and speed of diagnoses in medical institutions and streamlines communication between medical staff and patients. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it provides interactive functions that respond to the user's emotional state.

[0831] System Configuration

[0832] "3D Health Analyzer" is a system that includes a server, a terminal, a user, and an emotion engine.

[0833] 1. Server: Responsible for data collection, preprocessing, analysis, 3D model generation, and emotion engine management.

[0834] 2. Terminal: Provides an interface for medical staff to view and manipulate the 3D model.

[0835] 3. Users: Medical staff and patients who share and understand diagnostic information and treatment plans through the system.

[0836] 4. Emotion Engine: Recognizes the user's emotional state and provides feedback accordingly.

[0837] Hardware and software used

[0838] Specific hardware and software examples include:

[0839] Imaging equipment: MRI, CT scan, X-ray, etc.

[0840] Electronic medical record system: A system that manages patient health data

[0841] Server software: Software on the server that manages data collection, preprocessing, and analysis

[0842] AI model: Machine learning algorithms used for data analysis

[0843] 3D CG engine: 3D model generation software such as Unity or Unreal Engine

[0844] Emotion Engine: Software that analyzes the user's emotional state

[0845] Program processing example

[0846] Example 1:

[0847] "We input the MRI images and the patient's medical history into the 3D Health Analyzer to generate a 3D model of the tumor. If the patient is concerned, we adjust the display to simplify it."

[0848] Example 2:

[0849] "Collect patient health data from electronic medical records, analyze it with an AI model, and generate a 3D model based on the results. Use an emotion engine to recognize patient emotions and provide feedback."

[0850] An example of an operation sequence

[0851] 1. Data collection: The server collects the necessary medical data from the medical institution's electronic medical record system and imaging diagnostic equipment via the API.

[0852] 2. Data preprocessing: The collected data will be preprocessed by the server to remove noise and perform imputation. The patient's health data will be converted into a standard format.

[0853] 3. Data analysis: The preprocessed data is input into the AI ​​model for analysis, and the analysis results are extracted as numerical data or text data.

[0854] 4. 3D model generation: Based on the analysis results, the server generates a 3D model using a 3D CG engine.

[0855] 5. Visualization: The generated 3D model is visualized in a web viewer or dedicated application and delivered to medical staff.

[0856] 6. Utilizing an Emotion Engine: The server recognizes the user's emotional state and adjusts the display content and feedback of the 3D model accordingly.

[0857] By introducing this "3D Health Analyzer," medical facilities can significantly improve the accuracy and speed of diagnosis, as well as patient understanding and satisfaction. By combining it with an emotion engine, it can provide interactive feedback that takes into account the patient's emotional state, resulting in more efficient medical services.

[0858] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0859] Step 1:

[0860] The server collects medical image data and patient health data from medical institutions' electronic medical record systems and diagnostic imaging devices via APIs.

[0861] As a specific example of operation, the server calls the API of the MRI device, obtains image data of a specific patient, and obtains the patient's medical history and current physical condition data from the electronic medical record.

[0862] Input: Image data from MRI scanner, patient health data from electronic medical records

[0863] Output: Medical imaging data and patient health data

[0864] Step 2:

[0865] The server performs preprocessing by removing noise and complementing the medical image data collected.

[0866] Specifically, the server applies a noise reduction algorithm to remove noise from the acquired MRI images, complement the degraded parts, and convert the patient's health data into a standard format.

[0867] Input: Medical image data, patient health data

[0868] Output: Denoised and imputed medical image data, standardized health data

[0869] Step 3:

[0870] The server inputs the preprocessed medical data into the AI ​​model and performs data analysis.

[0871] As a specific example of how it works, preprocessed MRI image data and standardized health data are input into the AI ​​model, and an analysis is performed to identify the location and size of the tumor, with numerical and text data being obtained as the analysis results.

[0872] Input: Preprocessed medical image data, standardized health data

[0873] Output: Analysis results (tumor location, size)

[0874] Step 4:

[0875] The server generates a 3D model based on the analysis results.

[0876] As a specific example of how it works, the server uses a 3D CG engine (e.g., Unity or Unreal Engine) to generate a 3D model of the tumor based on the analysis results and combines it with other parts of the human body to create a complete picture.

[0877] Input: Analysis results (tumor location, size)

[0878] Output: Generated 3D model

[0879] Step 5:

[0880] The server visualizes the generated 3D model through a web viewer or dedicated application and delivers it to medical staff.

[0881] As a specific example of how it works, the server uploads the generated 3D model to a cloud dashboard and displays it in a dedicated application for medical staff.

[0882] Input: Generated 3D model

[0883] Output: Web viewer, 3D model displayed in dedicated application

[0884] Step 6:

[0885] The server uses an emotion engine to recognize the emotional state of the user (mainly the patient) in real time.

[0886] As a specific example of how it works, the emotion engine analyzes the patient's facial expressions and tone of voice based on input from the camera and microphone, and grasps the patient's emotional state.

[0887] Input: Video and audio data from cameras and microphones

[0888] Output: Perceived patient emotional state

[0889] Step 7:

[0890] The server adjusts the display content and feedback of the 3D model based on the emotional state it recognizes.

[0891] As a specific example of how this works, if a patient is feeling anxious, the display content of the 3D model is adjusted to be simple and easy to explain.

[0892] Input: Recognized patient emotional state, generated 3D model

[0893] Output: Visualization and feedback of the adjusted 3D model

[0894] Step 8:

[0895] Using the terminal, medical staff can access the dashboard and conduct examinations while viewing the 3D model.

[0896] As a specific example of how it works, medical staff use a tablet device to display a 3D model of the patient's tumor and perform an examination and explanation.

[0897] Input: Adjusted 3D model, feedback

[0898] Output: Examination and explanation by medical staff

[0899] Step 9:

[0900] Users (medical staff and patients) discuss and reach a consensus on detailed diagnoses and treatment plans based on the generated 3D models and feedback from the emotion engine.

[0901] As a specific example of how it works, medical staff and patients can discuss treatment plans and surgical risks while looking at the 3D model, and the emotion engine provides feedback to reduce the patient's anxiety.

[0902] Input: Adjusted 3D model, feedback

[0903] Output: Consensus diagnosis and treatment plan

[0904] (Application example 2)

[0905] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0906] In modern factory environments, it is difficult to monitor workers' health and mental stress in real time and respond appropriately. This can lead to reduced work efficiency and safety risks. Furthermore, communication with workers tends to be lacking, and health problems are often only addressed after they occur. Therefore, there is a need for a system that can monitor workers' health and emotions in real time and provide efficient feedback.

[0907] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for electronically collecting medical image data and patient health data from medical institutions, means including an artificial intelligence model for preprocessing and analyzing the medical image data and the health data, means for generating a 3D model based on the analysis results, means for visualizing the 3D model and presenting it to a user, means for recognizing the user's emotions and providing feedback according to their emotional state, and means for adjusting the display content of the 3D model based on the emotion recognition means. This makes it possible to monitor the health status and emotions of workers in real time and provide appropriate feedback, thereby improving work efficiency and ensuring safety.

[0908] A "medical institution" is an organization or facility that provides medical services to patients.

[0909] "Electronically collected" refers to obtaining information as digital data using networks or sensors.

[0910] "Medical image data" refers to image information of a patient's inside the body obtained from imaging diagnostic devices such as CT scans and MRIs.

[0911] "Patient health data" refers to digital data relating to a patient's medical history and current health status.

[0912] "Preprocessing" refers to the process of processing collected data, such as by removing noise and standardizing it, to prepare it in a format suitable for analysis.

[0913] An "artificial intelligence model" refers to a system that uses algorithms such as machine learning and deep learning to analyze data and detect patterns and anomalies.

[0914] "Generating a 3D model" refers to creating a three-dimensional image using computer graphics based on the analysis results.

[0915] "Visualizing" refers to the process of displaying digital data in a graphical form that makes it easier for humans to understand.

[0916] "Users" refers to factory workers and managers who use this system.

[0917] "Emotion recognition" means analyzing the user's psychological state from facial expressions, tone of voice, etc., and inferring specific emotions.

[0918] "Providing feedback" refers to providing users with advice, instructions, alerts, etc. in real time based on their emotions and health data.

[0919] "Adjusting the displayed content" refers to changing the visual information and feedback content based on the results of emotion recognition and presenting it in a form appropriate for the user.

[0920] The present invention, "Factory 3D Health Analyzer," is a system aimed at improving the health management and safety of workers in a factory environment. This system is composed of four components: a server, a terminal, a user, and an emotion engine.

[0921] server

[0922] The server is responsible for data collection, pre-processing, analysis, 3D model generation and emotion engine management.

[0923] Collection Method

[0924] The server electronically collects medical image data and patient health data from medical institutions through APIs.

[0925] Pretreatment means

[0926] The server first performs preprocessing on the collected data, such as noise removal and conversion to a standard format, so that the health data is in a format suitable for AI models.

[0927] Analysis means

[0928] The pre-processed data is then input into an artificial intelligence model on the server, which then performs an analysis, such as identifying the location and size of a tumor from collected medical image data.

[0929] 3D model generation method

[0930] Based on the analysis results, the server uses a 3D model generation engine to generate a realistic 3D model, which is then used to display the factory's work lines and equipment in 3D.

[0931] Feedback methods

[0932] The emotion engine recognizes the user's emotional state and provides feedback based on that emotion. For example, if the user is feeling stressed, the system will issue an appropriate alert and adjust the work environment accordingly.

[0933] Terminal

[0934] The terminal provides an interface for workers to view and manipulate the 3D model.

[0935] Visualization tools

[0936] The generated 3D model is visualized and displayed on devices such as smart glasses or tablets, allowing workers to check their own health status and working environment in real time.

[0937] For example, sensors built into smart glasses collect vital data (heart rate, body temperature, oxygen concentration) from workers and send it to a server. The server analyzes the data and sends the results to the device as a 3D model. If the worker's heart rate is high, the smart glasses will display an alert saying, "Please take a break."

[0938] User

[0939] The users are the workers and administrators who operate and check the system.

[0940] emotion recognition means

[0941] The system analyzes the worker's facial expressions and tone of voice via cameras and microphones to detect stress and anxiety, and the server then generates appropriate feedback and sends it to the device.

[0942] Feedback Adjustment Means

[0943] Based on the emotion recognition results, the display content of the 3D model and the feedback content are adjusted, which can reduce stress and anxiety for workers.

[0944] Examples of prompts include, "Generate appropriate feedback to be displayed when a worker wearing smart glasses feels stressed" and "Monitor the worker's health status based on sensor data and suggest how to automatically adjust the work plan based on that status."

[0945] As described above, the "Factory 3D Health Analyzer" of this invention makes it possible to monitor and adjust the health status and emotions of workers in real time, thereby improving work efficiency and ensuring safety in factories.

[0946] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0947] Step 1:

[0948] The server collects medical image data and patient health data from the medical institution's electronic medical record system and imaging diagnostic equipment via API. The input is data from the electronic medical record system and imaging diagnostic equipment, and the output is the collected medical image data and health data. This collected data is input into the next pre-processing phase.

[0949] Step 2:

[0950] The server performs pre-processing on the collected medical image data, such as noise removal and interpolation. The input is the medical image data collected in step 1, and the output is clear medical image data that has been subjected to noise removal and interpolation. This processing is intended to improve the accuracy of medical image analysis.

[0951] Step 3:

[0952] The server inputs preprocessed medical image data and standardized health data into the AI ​​model and performs the analysis. The input is preprocessed medical image data and health data, and the output is numerical and text data as the analysis results. For example, diagnostic information such as the location and size of a tumor is output.

[0953] Step 4:

[0954] The server generates a 3D model using a 3D model generation engine based on the analysis results. The input is the numerical and text data of the analysis results obtained in Step 3, and the output is the 3D model data. The generated 3D model is useful for detailed visualization of specific parts.

[0955] Step 5:

[0956] The server uploads the generated 3D model to a cloud database or web dashboard and distributes it so that it can be accessed by medical staff and workers. The input is the 3D model data, and the output is accessible via a web viewer or dedicated application. This allows the user, or worker, to view the 3D model on their device.

[0957] Step 6:

[0958] The server uses an emotion engine to analyze and recognize the user's emotional state in real time. The input is video and audio data from a camera and microphone, and the output is the type of emotion recognized. For example, it determines whether the user is feeling stressed.

[0959] Step 7:

[0960] The server adjusts the display content and feedback of the 3D model based on the emotion recognition results. The input is the emotion data recognized in step 6, and the output is the adjusted display content and feedback message of the 3D model. For example, for a user who is feeling stressed, the display will be simpler and easier to understand.

[0961] Step 8:

[0962] The terminal presents the adjusted 3D model and feedback to the user (worker). The input is the adjusted 3D model and feedback data sent from the server in step 7, and the output is the information displayed on the terminal screen. This allows the worker to deepen their understanding of their own health condition and work environment and respond appropriately.

[0963] Step 9:

[0964] The user (worker) uses the terminal to check the displayed 3D model and feedback, and respond or take action as necessary. The input is the information displayed on the terminal, and the output is the worker's actions or responses. For example, this includes actions such as taking a break or reporting to a manager.

[0965] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0966] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0967] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0968] [Third embodiment]

[0969] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0970] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0971] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0972] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0973] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0974] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0975] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0976] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0977] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0978] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0979] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0980] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0981] The present invention, "3D Health Analyzer," is a system for improving the accuracy and speed of diagnoses in medical institutions and streamlining communication between medical staff and patients. This system consists of a series of processes that collect and analyze medical image data and patient health data, and visualize the results as a 3D model. Below, the processing of the system's program is explained in natural language and detailed with concrete examples.

[0982] overview

[0983] "3D Health Analyzer" is a system consisting of three parties: a server, a terminal, and a user. The server is responsible for data collection, preprocessing, analysis, and generation of 3D models. The terminal provides an interface for medical staff to view and manipulate the 3D models. Users are medical staff and patients, and are responsible for sharing and understanding diagnostic information and treatment plans through the system.

[0984] Program processing flow

[0985] Collection Phase

[0986] The server collects medical image data and patient health data from the medical institution's electronic medical record system and imaging diagnostic equipment (e.g., X-ray, MRI, CT scan) via API.

[0987] Example: A server obtains image data of a patient's teeth from a dental X-ray machine in a dental clinic, and simultaneously collects data about the patient's medical history and current symptoms.

[0988] Preprocessing Phase

[0989] The server performs noise removal and interpolation on the collected medical image data.

[0990] Example: The server removes noise from acquired dental X-ray images and complements degraded parts of the images.

[0991] The server converts the health data into a standard format and makes it suitable for AI models.

[0992] Example: Converting a patient's past medical records and current health status data into a standardized format.

[0993] Analysis Phase

[0994] The server inputs the preprocessed data into the AI ​​model and performs the analysis.

[0995] Example: The server uses an AI model to analyze the patient's dental condition and identify areas of decay and possible periodontitis.

[0996] The server extracts the analysis results as numerical and text data and uses them as the basic data for generating a 3D model.

[0997] Example: Based on AI analysis, the location and size of cavities are extracted as numerical data.

[0998] 3D model generation phase

[0999] The server uses a 3D CG engine to generate a realistic 3D model based on the analysis results.

[1000] Example: A server generates a 3D dental model and visually highlights identified areas of caries.

[1001] Visualization Phase

[1002] The server visualizes the generated 3D model using a web viewer or dedicated application and delivers it to medical staff.

[1003] Example: The server uploads the generated 3D tooth model to a dashboard on the cloud, where it can be displayed in a viewer for medical staff.

[1004] Review and communication phase

[1005] Using the terminal, medical staff can access a dashboard and conduct examinations while viewing the 3D model.

[1006] Example: A dentist uses a tablet to view a 3D model of a patient's teeth, highlighting any cavities and providing explanations.

[1007] Based on the generated 3D model, users (medical staff and patients) discuss and reach a consensus on detailed diagnoses and treatment plans.

[1008] Example: Dentists and patients can view 3D models to discuss in detail treatment plans and preventative measures for cavities.

[1009] The "3D Health Analyzer" of this invention allows medical staff to significantly reduce the time and effort required to analyze medical images, thereby improving diagnostic accuracy. Furthermore, the use of 3D models facilitates communication with patients, increasing their understanding and acceptance of treatment. This improves the overall quality of medical care and reduces patient health risks.

[1010] The processing flow will be explained below.

[1011] Step 1: Data collection

[1012] server

[1013] Medical imaging data and patient health data are collected via APIs from medical institutions' electronic medical record systems and imaging diagnostic devices (e.g., X-ray machines, MRIs, CT scans).

[1014] Example: A server obtains dental image data of a particular patient from a dental x-ray machine in a dental clinic, and simultaneously collects the patient's medical history and current health data.

[1015] Step 2: Data Storage

[1016] server

[1017] Collected medical image data and health data are stored in temporary cloud storage.

[1018] Example: The server stores the acquired data in secure cloud storage and manages it in a database.

[1019] Step 3: Data cleaning

[1020] server

[1021] A pre-processing algorithm is used to remove noise from medical image data.

[1022] Example: Image filtering is used to remove noise from X-ray images and adjust image brightness and contrast.

[1023] Detect missing data and outliers in health data and impute or remove them appropriately.

[1024] Example: The server uses an imputation algorithm to fill in missing values ​​in health data and remove outliers.

[1025] Step 4: Data Standardization

[1026] server

[1027] Standardize the units and notations of health data (e.g., blood pressure, blood sugar levels, etc.) and convert them into a standard format.

[1028] Example: Convert blood pressure data into a unified unit (mmHg) and standardize the range of values.

[1029] Medical image data is also converted into a format suitable for AI models (e.g., DICOM format).

[1030] Example: Converting an X-ray image in JPG format to DICOM format.

[1031] Step 5: AI model analysis

[1032] server

[1033] Preprocessed medical image data and standardized health data are input into the AI ​​model and analysis is performed.

[1034] Example: The server uses an AI model to analyze images of teeth and automatically detect the location and depth of cavities.

[1035] As a diagnostic result, abnormalities and important findings are extracted as numerical or text data.

[1036] Example: As a result of AI analysis, the coordinates of the location and depth of cavities are obtained as numerical data.

[1037] Step 6: 3D model generation

[1038] server

[1039] Based on the analysis results, a 3D model of the medical image is generated using a 3D CG engine.

[1040] Example: The server generates a 3D model of the teeth from the analysis results, highlighting areas of decay.

[1041] The completed 3D model is visualized and delivered to a web viewer or dedicated application.

[1042] Example: The generated 3D model can be uploaded to a cloud-based dashboard and accessed by medical staff via a dedicated app.

[1043] Step 7: View on the dashboard

[1044] Terminal

[1045] Medical staff access the dashboard hosted on the server through a browser on their PC or tablet.

[1046] Example: A doctor uses a tablet to access a dashboard in the cloud and open a 3D model of a patient.

[1047] On the dashboard, select a 3D model of a specific patient and zoom in / out, rotate, and more to view details.

[1048] Example: The doctor rotates the 3D model to see the precise location and size of the cavities.

[1049] If necessary, screen captures and report output are performed to share diagnostic information with other medical staff and patients.

[1050] Example: A doctor generates a diagnostic report with a captured image of the 3D model and shares it with other medical staff.

[1051] Step 8: Promote communication with patients

[1052] Users (medical staff, patients)

[1053] When medical staff meet with patients, they explain things to them while displaying 3D models on a PC or tablet.

[1054] Example: A dentist shows a patient a 3D model of a tooth and explains the condition and treatment of the tooth.

[1055] Patients can understand diagnostic information by visually viewing the 3D model.

[1056] Example: A patient looks at a model of their own teeth and understands what the dentist is explaining.

[1057] Medical staff and patients create and review treatment plans based on the generated 3D model.

[1058] Example: Dentists and patients can review treatment schedules and procedures by referring to the 3D model.

[1059] Example 1

[1060] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1061] With conventional medical data analysis systems, medical staff spent a lot of time and effort analyzing diagnostic results and communicating with patients. This resulted in inconsistent diagnostic accuracy and low patient understanding and treatment acceptance. Furthermore, the lack of integrated analysis of medical images and health data made it difficult to develop comprehensive diagnoses and treatment plans. Furthermore, there were limited means of presenting analysis results in a visually understandable manner.

[1062] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1063] In this invention, the server includes: means for electronically collecting medical image data and patient health data from medical institutions; means for performing noise reduction and interpolation on the medical image data; means for converting the health data into a standard format and arranging it in a format suitable for analysis; means including an artificial intelligence model for preprocessing and analyzing the medical image data and the health data; means for instructing the artificial intelligence model to perform analysis using prompts; means for extracting the analysis results as numerical data and text data and using them as basic data for generating a 3D model; means for using a computer graphics engine to generate a realistic 3D model based on the analysis results; and means for visualizing the 3D model and presenting it to medical staff. This improves the accuracy and speed of diagnosis and enables efficient communication with patients.

[1064] "Medical image data" refers to image information such as X-rays, MRIs, and CT scans obtained at medical institutions.

[1065] "Patient Health Data" means information about a patient's health, such as the patient's medical history, current symptoms, and vital signs.

[1066] "Noise removal" is a process that removes unnecessary high-frequency components and errors from medical image data.

[1067] "Complement" is a process of filling in missing parts of medical image data to improve image quality.

[1068] A "standard format" is a common structure or format established to maintain data consistency and compatibility.

[1069] An "artificial intelligence model" is a computational algorithm used to analyze large amounts of data and find patterns and regularities.

[1070] A "prompt sentence" is a short piece of text that instructs an artificial intelligence model to perform a specific analysis.

[1071] "Numerical data" is information in a numerical format that quantitatively expresses the analysis results.

[1072] "Text data" is information that expresses analysis results and explanations in text format.

[1073] A "3D model" is a visual representation generated as a three-dimensional shape based on the analysis results.

[1074] A "computer graphics engine" is software for generating and displaying three-dimensional computer graphics.

[1075] The present invention, "3D Health Analyzer," is a system for improving the accuracy and speed of diagnoses in medical institutions and streamlining communication between medical staff and patients. This system consists of a series of processes that collect, preprocess, and analyze medical image data and patient health data, and visualize the results as a 3D model.

[1076] Hardware and Software Configuration

[1077] This system is mainly composed of three components: a server, a terminal, and a user. The specific hardware and software configuration is as follows:

[1078] Server: A computer system responsible for collecting, preprocessing, and analyzing data, and generating 3D models. Software used here includes APIs, Python's OpenCV library, generative AI models such as TensorFlow or PyTorch, and computer graphics engines such as Unity or Unreal Engine.

[1079] Terminal: A device used by medical staff to view and manipulate 3D models. This can be a display device such as a tablet or PC.

[1080] Users: Medical staff and patients who share and understand diagnostic information and treatment plans through the system.

[1081] Data collection and preprocessing

[1082] The server collects medical image data and patient health data from medical institutions' electronic medical record systems and imaging diagnostic devices (e.g., X-rays, MRIs, CT scans) via APIs. The collected data is stored in a database and backed up. For example, the server collects image data of patients' teeth from dental X-ray machines at a dental clinic, and simultaneously obtains data about the patient's medical history and current symptoms.

[1083] As part of preprocessing, the server performs noise removal and interpolation on medical image data and converts the health data into a standard format. For example, the server removes noise from collected dental X-ray images and interpolates image degradation. It also converts patients' past medical records and current health status data into a standard format (e.g., HL7 format).

[1084] Data analysis and 3D model generation

[1085] The server inputs the preprocessed medical image data and health data into the generative AI model. It uses prompts to provide specific instructions to the AI ​​model. Specific examples of prompts include, "Please identify the location of cavities in this patient's dental X-rays" and "Please convert the collected health data into a standard format and analyze the risk of periodontitis."

[1086] The analysis results from the generative AI model are extracted as numerical and text data, and the server uses this data to generate a 3D model. Specifically, the server uses a 3D CG engine such as Unity or Unreal Engine to generate a realistic 3D model based on the analysis results. The generated 3D model is presented to medical staff in a visually easy-to-understand format.

[1087] Visualization and Communication

[1088] The generated 3D model is visualized by the server through a web viewer or dedicated application. Medical staff can access the dashboard using a terminal and examine the patient while viewing the 3D model. For example, a dentist can view the 3D model of a patient's teeth on a tablet and explain the procedure, highlighting any cavities.

[1089] Furthermore, users (medical staff and patients) can discuss and reach consensus on detailed diagnoses and treatment plans based on the generated 3D models. For example, dentists and patients can discuss in detail treatment plans and preventive measures for cavities while looking at the 3D models.

[1090] In this way, the "3D Health Analyzer" of the present invention enables medical staff to improve the accuracy and speed of diagnosis, and also facilitates smooth communication with patients.

[1091] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1092] Step 1:

[1093] Data collection

[1094] The server collects medical image data and patient health data from the medical institution's electronic medical record system and imaging diagnostic equipment (e.g., X-ray, MRI, CT scan).

[1095] Input: Medical imaging data and patient health data from the medical institution's database.

[1096] Output: The collected medical image data and patient health data are stored in a database on the server.

[1097] What it does: Every day at 2 AM, the server runs an automated script to collect new patient data from the dental x-ray machine in the dental clinic.

[1098] Step 2:

[1099] Data Loss Prevention

[1100] The server backs up the collected data and stores it in a database, which prevents data loss and ensures safety.

[1101] Input: Collected data (medical imaging data and health data).

[1102] Output: Data stored in the database and backup data.

[1103] How it works: The server backs up collected dental X-ray images and health data to two different data centers.

[1104] Step 3:

[1105] Image data preprocessing

[1106] The server performs noise removal and interpolation on the collected medical image data.

[1107] Input: Collected medical image data.

[1108] Output: Denoised and imputed medical image data.

[1109] Specific operation: The server uses Python's OpenCV library to analyze the pixel values ​​of the acquired image and apply a filter to suppress high-frequency noise.

[1110] Step 4:

[1111] Health data format conversion

[1112] The server converts the health data into a standard format and makes it suitable for analysis.

[1113] Input: Collected health data.

[1114] Output: Health data converted into a standard format.

[1115] Specific operation: The server converts the patient's blood pressure, heart rate, and past medical records into HL7 format.

[1116] Step 5:

[1117] Input to AI model and prompt generation

[1118] The server inputs the preprocessed data into the generative AI model and uses prompt statements to direct the analysis.

[1119] Input: Denoised medical image data and health data in standard formats.

[1120] Output: The analysis results of the generative AI model.

[1121] Specific operation: The server generates a prompt statement such as, "Please identify the cavities in this patient's dental X-ray image," and instructs the AI ​​model.

[1122] Step 6:

[1123] Obtaining analysis results and extracting data

[1124] The server receives the analysis results from the AI ​​model and extracts them as numerical and text data.

[1125] Input: Analysis results of the generative AI model.

[1126] Output: Numerical and textual data.

[1127] Specific operation: The server stores the analysis results received from the AI ​​model, such as the location and size of cavities, as numerical data in a database.

[1128] Step 7:

[1129] 3D model generation

[1130] The server uses a 3D CG engine to generate a realistic 3D model based on the analysis results.

[1131] Input: Numeric and text data.

[1132] Output: Realistic 3D models.

[1133] Specific operation: The server uses Unity or Unreal Engine to generate a 3D model based on the analysis results and highlights visually important parts.

[1134] Step 8:

[1135] 3D model visualization and distribution

[1136] The server uploads the generated 3D model to a web viewer or dedicated application.

[1137] Input: A generated 3D model.

[1138] Output: 3D model that can be viewed in a web viewer or dedicated application.

[1139] Specific operation: The server uploads the generated 3D model to a dashboard on the cloud and notifies medical staff of an access URL or QR code.

[1140] Step 9:

[1141] Checked by medical staff

[1142] Using the terminal, medical staff can access the dashboard and conduct examinations while viewing the 3D model.

[1143] Input: 3D models uploaded to a web viewer or dedicated application.

[1144] Output: Medical staff examination results.

[1145] Specific operation: The dentist zooms in and rotates the 3D model of the patient on the tablet, checking the areas of tooth decay while explaining to the patient.

[1146] Step 10:

[1147] Sharing Diagnoses and Treatment Plans

[1148] Based on the generated 3D model, users (medical staff and patients) discuss and reach a consensus on detailed diagnoses and treatment plans.

[1149] Input: Medical staff review results and 3D model.

[1150] Output: Diagnosis and treatment plan.

[1151] How it works: Dentists and patients discuss treatment options while looking at the 3D model and select the best treatment plan.

[1152] (Application example 1)

[1153] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1154] It is important for medical institutions to analyze medical image data and health data more effectively and improve the accuracy and speed of diagnoses. Visual support is also required to facilitate communication between patients and medical staff and provide easy-to-understand diagnoses and treatment plans. Furthermore, there is a need to provide a virtual health checkup experience that allows patients to check their health status from home, enabling more people to efficiently manage their health.

[1155] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1156] In this invention, the server includes: means for electronically collecting medical image data and patient health data from medical institutions; means including an artificial intelligence model for preprocessing and analyzing the medical image data and the health data; means for generating a 3D model based on the analysis results; means for visualizing the 3D model and presenting it to medical staff; means for allowing users to view the 3D model via an interface on a smartphone or head-mounted display; and means for providing a virtual health checkup experience. This allows users to easily check their health status from home and to better understand diagnoses and treatment plans through communication with medical staff.

[1157] "Medical image data" refers to image data obtained at a medical institution, including images taken using equipment such as X-rays, MRIs, and CT scans.

[1158] "Patient health data" refers to information such as a patient's medical history, current health status, medical records, and symptoms.

[1159] "Preprocessing" refers to the process of removing noise and standardizing collected medical image data and health data to prepare them in a format suitable for analysis.

[1160] "Artificial intelligence model" refers to a program that uses machine learning and deep learning to analyze medical image data and health data.

[1161] "3D model" refers to a three-dimensional visual model generated based on medical image data and analysis results.

[1162] "Visualization" refers to displaying 3D models in a way that makes them easy for medical staff to understand.

[1163] "Interface" refers to the connection method and display device that allows users to view 3D models through a smartphone or head-mounted display.

[1164] The "virtual health checkup experience" refers to an experience that allows users to check and diagnose their health status from the comfort of their own home.

[1165] A "smartphone" refers to a portable information terminal that can use communication functions and applications.

[1166] A "head-mounted display" refers to a display device that is worn on the head and provides visual information.

[1167] The present invention is a system that improves the accuracy and speed of diagnoses by utilizing medical image data and patient health data collected from medical institutions. This system is composed of three entities: a server, a terminal, and a user, as described below.

[1168] The server has the function of collecting medical image data and patient health data from medical institutions' electronic medical record systems and imaging diagnostic devices (e.g., X-ray devices, MRI devices, CT scan devices) via APIs. The server also performs preprocessing on the collected data, such as noise removal and conversion to a standard format. This preprocessing prepares the data in a format suitable for the artificial intelligence model. The preprocessed data is then input into the artificial intelligence model for analysis. Based on the results of this analysis, the server generates a 3D model. This 3D model is generated in real time using a 3D CG engine.

[1169] The device provides an interface for visualizing the generated 3D model. Medical staff can use this device to check the 3D model and operate the interface. The visualized 3D model is uploaded to a dashboard on the cloud and displayed in a viewer for medical staff. In addition, the device has a function that allows the user (patient) to check the 3D model using a smartphone or head-mounted display.

[1170] Users are medical staff and patients, who use the generated 3D models to discuss and reach consensus on detailed diagnoses and treatment plans. Patients can experience virtual medical checkups from home using a smartphone or head-mounted display. For example, when a patient uploads MRI scan data from home, the system analyzes the data and generates a 3D model. The generated 3D model is displayed on a smartphone or head-mounted display so that the patient can view it at home.

[1171] The main hardware and software used include Python, Numpy, Scikit-learn, Nibabel, and Vedo, which are used to handle the steps of data collection, preprocessing, analysis, 3D model generation, and visualization.

[1172] As a concrete example, the following prompt sentence can be used:

[1173] Example prompt sentence:

[1174] "I've been having frequent headaches lately. I'd like you to check the state of my brain based on my MRI scan data and visualize it as a 3D model."

[1175] In this way, the system of the present invention improves diagnostic accuracy at medical institutions and facilitates smooth communication between patients and medical staff. Furthermore, by providing a virtual health checkup experience, patients can easily check their health status and use medical services from the comfort of their own homes.

[1176] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1177] Step 1:

[1178] The server collects medical image data and patient health data from medical institutions' electronic medical record systems and diagnostic imaging devices via APIs. During this collection process, data is obtained from various devices using API calls and stored in a database. The input is the medical image data and health data sent from the devices, and the output is the raw data stored in the server's database.

[1179] Step 2:

[1180] The server performs preprocessing on the collected medical image data to remove noise and correct image quality. Specifically, it performs noise removal filtering and image correction using libraries such as Python's Nibabel and OpenCV. The input is the medical image data collected in step 1, and the output is clean medical image data that has been corrected and denoised.

[1181] Step 3:

[1182] The server performs preprocessing to convert the patient's health data into a standard format and prepare it for analysis. Specifically, it uses Python's Pandas library to clean the data, extract necessary items, and format it. The input is the health data collected in step 1, and the output is the standardized health data.

[1183] Step 4:

[1184] The server inputs the preprocessed medical image data and health data into an artificial intelligence model for analysis. This analysis uses libraries such as Scikit-learn and TensorFlow to apply machine learning and deep learning models to extract meaningful results from the data. The input is the data preprocessed in steps 2 and 3, and the output is the numerical and text data of the analysis results.

[1185] Step 5:

[1186] The server generates a 3D model based on the analysis results. Specifically, it uses a 3D CG engine such as the Vedo library to generate a three-dimensional model that visually represents the analysis results. The input is the analysis result data obtained in step 4, and the output is the generated 3D model.

[1187] Step 6:

[1188] The server visualizes the generated 3D model using a web viewer or a dedicated application so that users can check it through an interface. For example, a web page for displaying the 3D model is built using a web framework such as Flask or Django. The input is the 3D model generated in step 5, and the output is the visualized 3D model displayed in a web viewer that users can access.

[1189] Step 7:

[1190] The user checks the generated 3D model using a smartphone or a head-mounted display. Specifically, the user can launch a dedicated viewer app and interactively view the 3D model. The input is access to the 3D model display page visualized in Step 6, and the output is the user experience of checking the 3D model and understanding the health condition.

[1191] Step 8:

[1192] Users (medical staff and patients) discuss detailed diagnoses and treatment plans based on the generated 3D model and reach a consensus. For example, a patient can view the 3D model together with medical staff and discuss diagnostic results and specific treatment options. The inputs are the 3D model confirmed in step 7 and feedback from the users, and the output is the agreed-upon diagnostic information and treatment plan.

[1193] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1194] The present invention, "3D Health Analyzer," is a system that improves the accuracy and speed of diagnoses in medical institutions and streamlines communication between medical staff and patients. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it provides interactive functions that correspond to the user's emotional state. Below, the processing of the system's program is explained in natural language and detailed with specific examples.

[1195] overview

[1196] "3D Health Analyzer" is a system consisting of four components: a server, a terminal, a user, and an emotion engine. The server is responsible for data collection, preprocessing, analysis, 3D model generation, and emotion engine management. The terminal provides an interface for medical staff to view and manipulate the 3D models. Users are medical staff and patients, and their role is to share and understand diagnostic information and treatment plans through the system. The emotion engine recognizes the user's emotional state and provides feedback accordingly.

[1197] Program processing flow

[1198] Collection Phase

[1199] The server collects medical image data and patient health data from the medical institution's electronic medical record system and imaging diagnostic equipment (e.g., X-ray, MRI, CT scan) via API.

[1200] Example: A server retrieves image data for a particular patient from an MRI machine in a surgeon's office, while also collecting the patient's medical history and current health data.

[1201] Preprocessing Phase

[1202] The server performs noise removal and interpolation on the collected medical image data.

[1203] Example: The server removes noise from acquired MRI images and complements degraded parts of the images.

[1204] The server converts the health data into a standard format and makes it suitable for AI models.

[1205] Example: Converting a patient's past medical records and current health status data into a standardized format.

[1206] Analysis Phase

[1207] The server inputs the preprocessed data into the AI ​​model and performs the analysis.

[1208] Example: The server uses an AI model to analyze a patient's MRI images and identify the location and size of a tumor.

[1209] The server extracts the analysis results as numerical and text data and uses them as the basic data for generating a 3D model.

[1210] Example: As a result of AI analysis, the location coordinates and size of a tumor are obtained as numerical data.

[1211] 3D model generation phase

[1212] The server uses a 3D CG engine to generate a realistic 3D model based on the analysis results.

[1213] Example: The server generates a 3D model of the tumor from the analysis results and visually highlights the tumor location.

[1214] Visualization Phase

[1215] The server visualizes the generated 3D model using a web viewer or dedicated application and delivers it to medical staff.

[1216] Example: The generated 3D model can be uploaded to a cloud-based dashboard and accessed by medical staff via a dedicated app.

[1217] Emotion Engine

[1218] The server uses an emotion engine to recognize the emotions of users (mainly patients) in real time.

[1219] For example, based on input from the camera and microphone, the emotion engine analyzes the patient's facial expressions and tone of voice to understand their emotional state.

[1220] The server adjusts the display and feedback of the 3D model based on the recognized emotion.

[1221] For example, if a patient is feeling anxious, the system will change the display of the 3D model to something simpler and easier to explain.

[1222] Confirmation and communication promotion

[1223] Using the terminal, medical staff can access a dashboard and conduct examinations while viewing the 3D model.

[1224] Example: A surgeon uses a tablet to view a 3D model of a patient's tumor and explain it in detail.

[1225] Users (medical staff and patients) discuss and reach a consensus on detailed diagnoses and treatment plans based on the generated 3D models and feedback from the emotion engine.

[1226] Example: A surgeon and a patient discuss in detail the tumor treatment plan and the risks of surgery while looking at a 3D model. The emotion engine provides appropriate feedback to reduce the patient's anxiety and facilitate communication.

[1227] By combining the "3D Health Analyzer" of this invention with an emotion engine, medical staff can make diagnoses and explanations that take into account the patient's emotional state, thereby improving patient understanding and satisfaction. This system offers a new approach to improving both diagnostic accuracy and the quality of medical services.

[1228] The processing flow will be explained below.

[1229] Step 1: Data collection

[1230] server

[1231] Medical imaging data and patient health data are collected via APIs from medical institutions' electronic medical record systems and imaging diagnostic devices (e.g., X-ray machines, MRIs, CT scans).

[1232] Example: A server retrieves image data for a particular patient from an MRI machine in a surgeon's office, while also collecting the patient's medical history and current health data.

[1233] Step 2: Data Storage

[1234] server

[1235] Collected medical image data and health data are stored in temporary cloud storage.

[1236] Example: The server stores the acquired data in secure cloud storage and manages it in a database.

[1237] Step 3: Data cleaning

[1238] server

[1239] A pre-processing algorithm is used to remove noise from medical image data.

[1240] Example: Image filtering is used to remove noise from MRI images and adjust image brightness and contrast.

[1241] Detect missing data and outliers in health data and impute or remove them appropriately.

[1242] Example: The server uses an imputation algorithm to fill in missing values ​​in health data and remove outliers.

[1243] Step 4: Data Standardization

[1244] server

[1245] Standardize the units and notations of health data (e.g., blood pressure, blood sugar levels, etc.) and convert them into a standard format.

[1246] Example: Convert blood pressure data into a unified unit (mmHg) and standardize the range of values.

[1247] Medical image data is also converted into a format suitable for AI models (e.g., DICOM format).

[1248] Example: Converting a JPG format MRI image to DICOM format.

[1249] Step 5: AI model analysis

[1250] server

[1251] Preprocessed medical image data and standardized health data are input into the AI ​​model and analysis is performed.

[1252] Example: The server uses an AI model to analyze a patient's MRI images and identify the location and size of a tumor.

[1253] As a diagnostic result, abnormalities and important findings are extracted as numerical or text data.

[1254] Example: As a result of AI analysis, the location coordinates and size of a tumor are obtained as numerical data.

[1255] Step 6: 3D model generation

[1256] server

[1257] Based on the analysis results, a 3D model of the medical image is generated using a 3D CG engine.

[1258] Example: The server generates a 3D model of the tumor from the analysis results and visually highlights the tumor location.

[1259] The completed 3D model is visualized and delivered to a web viewer or dedicated application.

[1260] Example: The generated 3D model can be uploaded to a cloud-based dashboard and accessed by medical staff via a dedicated app.

[1261] Step 7: Sentiment Analysis

[1262] server

[1263] An emotion engine is used to recognize the user's (patient's) emotional state in real time.

[1264] Example: Based on input from the camera and microphone, the emotion engine analyzes the patient's facial expressions and tone of voice to understand their emotional state.

[1265] Step 8: Emotion-Based Display Adjustment

[1266] server

[1267] The display of a 3D model is adjusted based on the recognized emotion.

[1268] For example, if a patient is feeling anxious, the system will change the display of the 3D model to something simpler and easier to explain.

[1269] Step 9: View on the Dashboard

[1270] Terminal

[1271] Medical staff access the dashboard hosted on the server through a browser on their PC or tablet.

[1272] Example: A doctor uses a tablet to access a dashboard in the cloud and open a 3D model of a patient.

[1273] On the dashboard, select a 3D model of a specific patient and zoom in / out, rotate, and more to view details.

[1274] Example: A doctor rotates the 3D model to see the precise location and size of a tumor.

[1275] If necessary, screen captures and report output are performed to share diagnostic information with other medical staff and patients.

[1276] Example: A doctor generates a diagnostic report with a captured image of the 3D model and shares it with other medical staff.

[1277] Step 10: Promote communication with patients

[1278] Users (medical staff, patients)

[1279] When medical staff meet with patients, they explain things to them while displaying 3D models on a PC or tablet.

[1280] Example: A surgeon shows a patient a 3D model of the tumor and explains the surgical procedure.

[1281] Patients can understand diagnostic information by visually viewing the 3D model.

[1282] Example: A patient looks at a model of their tumor and understands what the surgeon is explaining.

[1283] Medical staff and patients create and review treatment plans based on the generated 3D model and feedback from the emotion engine.

[1284] For example, a surgeon and a patient can review the treatment schedule and procedures while referring to a 3D model. The emotion engine provides appropriate feedback to reduce patient anxiety and facilitate communication.

[1285] Example 2

[1286] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1287] The current medical system not only lacks diagnostic accuracy and speed, but also lacks interactive functions for smooth communication between medical staff and patients. In particular, it is difficult to diagnose and explain things taking into account the patient's emotional state, which leads to problems such as a decrease in patient understanding and satisfaction. There is a need to efficiently solve these issues.

[1288] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1289] In this invention, the server includes a means for electronically collecting medical image data and patient health data from medical institutions, a means including an artificial intelligence model for preprocessing and analyzing the medical image data and health data, a means for generating a 3D model based on the analysis results, a means for visualizing the 3D model and presenting it to medical staff, a means for recognizing the user's emotional state and adjusting the display content of the 3D model based on that feedback, and a means for the patient and medical staff to discuss and reach a consensus on detailed diagnoses and treatment plans based on the generated 3D model and feedback from the emotion engine, thereby improving the accuracy and speed of diagnoses and enabling interactive communication that reflects the patient's emotional state.

[1290] "Medical image data" refers to image information obtained from imaging diagnostic equipment (e.g., X-ray, MRI, CT scan) used in medical institutions.

[1291] "Patient health data" refers to digital information such as a patient's medical history, current physical condition, and test results obtained from an electronic medical record system.

[1292] "Preprocessing" refers to a series of processes that remove noise and complement collected raw data, converting it into a form suitable for analysis.

[1293] An "artificial intelligence model" is a program that uses machine learning algorithms to analyze data and make diagnoses and predictions.

[1294] "Analysis results" refers to conclusions or insights derived from data processed using artificial intelligence models.

[1295] A "3D model" refers to a three-dimensional visual display created based on the analysis results, specifically a three-dimensional display of the affected area and internal structure.

[1296] "Visualization" refers to the display of data or information in a visual form, specifically on a screen or in a VR space.

[1297] "User's emotional state" refers to the results obtained by analyzing the emotions and feelings the user is currently experiencing based on information obtained from a camera, microphone, etc.

[1298] "Feedback" refers to the adjustment of displayed content, specific advice, or explanations that the system provides based on the user's emotional state or other information.

[1299] "Discussion" refers to a discussion in which medical staff and patients share information and exchange opinions to determine treatment plans and diagnostic procedures.

[1300] "Consensus building" refers to medical staff and patients reaching a mutually acceptable treatment plan and diagnostic policy through discussion.

[1301] MODE FOR CARRYING OUT THE INVENTION

[1302] This invention is a system called "3D Health Analyzer" that improves the accuracy and speed of diagnoses in medical institutions and streamlines communication between medical staff and patients. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it provides interactive functions that respond to the user's emotional state.

[1303] System Configuration

[1304] "3D Health Analyzer" is a system that includes a server, a terminal, a user, and an emotion engine.

[1305] 1. Server: Responsible for data collection, preprocessing, analysis, 3D model generation, and emotion engine management.

[1306] 2. Terminal: Provides an interface for medical staff to view and manipulate the 3D model.

[1307] 3. Users: Medical staff and patients who share and understand diagnostic information and treatment plans through the system.

[1308] 4. Emotion Engine: Recognizes the user's emotional state and provides feedback accordingly.

[1309] Hardware and software used

[1310] Specific hardware and software examples include:

[1311] Imaging equipment: MRI, CT scan, X-ray, etc.

[1312] Electronic medical record system: A system that manages patient health data

[1313] Server software: Software on the server that manages data collection, preprocessing, and analysis

[1314] AI model: Machine learning algorithms used for data analysis

[1315] 3D CG engine: 3D model generation software such as Unity or Unreal Engine

[1316] Emotion Engine: Software that analyzes the user's emotional state

[1317] Program processing example

[1318] Example 1:

[1319] "We input the MRI images and the patient's medical history into the 3D Health Analyzer to generate a 3D model of the tumor. If the patient is concerned, we adjust the display to simplify it."

[1320] Example 2:

[1321] "Collect patient health data from electronic medical records, analyze it with an AI model, and generate a 3D model based on the results. Use an emotion engine to recognize patient emotions and provide feedback."

[1322] An example of an operation sequence

[1323] 1. Data collection: The server collects the necessary medical data from the medical institution's electronic medical record system and imaging diagnostic equipment via the API.

[1324] 2. Data preprocessing: The collected data will be preprocessed by the server to remove noise and perform imputation. The patient's health data will be converted into a standard format.

[1325] 3. Data analysis: The preprocessed data is input into the AI ​​model for analysis, and the analysis results are extracted as numerical data or text data.

[1326] 4. 3D model generation: Based on the analysis results, the server generates a 3D model using a 3D CG engine.

[1327] 5. Visualization: The generated 3D model is visualized in a web viewer or dedicated application and delivered to medical staff.

[1328] 6. Utilizing an Emotion Engine: The server recognizes the user's emotional state and adjusts the display content and feedback of the 3D model accordingly.

[1329] By introducing this "3D Health Analyzer," medical facilities can significantly improve the accuracy and speed of diagnosis, as well as patient understanding and satisfaction. By combining it with an emotion engine, it can provide interactive feedback that takes into account the patient's emotional state, resulting in more efficient medical services.

[1330] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1331] Step 1:

[1332] The server collects medical image data and patient health data from medical institutions' electronic medical record systems and diagnostic imaging devices via APIs.

[1333] As a specific example of operation, the server calls the API of the MRI device, obtains image data of a specific patient, and obtains the patient's medical history and current physical condition data from the electronic medical record.

[1334] Input: Image data from MRI scanner, patient health data from electronic medical records

[1335] Output: Medical imaging data and patient health data

[1336] Step 2:

[1337] The server performs preprocessing by removing noise and complementing the medical image data collected.

[1338] Specifically, the server applies a noise reduction algorithm to remove noise from the acquired MRI images, complement the degraded parts, and convert the patient's health data into a standard format.

[1339] Input: Medical image data, patient health data

[1340] Output: Denoised and imputed medical image data, standardized health data

[1341] Step 3:

[1342] The server inputs the preprocessed medical data into the AI ​​model and performs data analysis.

[1343] As a specific example of how it works, preprocessed MRI image data and standardized health data are input into the AI ​​model, and an analysis is performed to identify the location and size of the tumor, with numerical and text data being obtained as the analysis results.

[1344] Input: Preprocessed medical image data, standardized health data

[1345] Output: Analysis results (tumor location, size)

[1346] Step 4:

[1347] The server generates a 3D model based on the analysis results.

[1348] As a specific example of how it works, the server uses a 3D CG engine (e.g., Unity or Unreal Engine) to generate a 3D model of the tumor based on the analysis results and combines it with other parts of the human body to create a complete picture.

[1349] Input: Analysis results (tumor location, size)

[1350] Output: Generated 3D model

[1351] Step 5:

[1352] The server visualizes the generated 3D model through a web viewer or dedicated application and delivers it to medical staff.

[1353] As a specific example of how it works, the server uploads the generated 3D model to a cloud dashboard and displays it in a dedicated application for medical staff.

[1354] Input: Generated 3D model

[1355] Output: Web viewer, 3D model displayed in dedicated application

[1356] Step 6:

[1357] The server uses an emotion engine to recognize the emotional state of the user (mainly the patient) in real time.

[1358] As a specific example of how it works, the emotion engine analyzes the patient's facial expressions and tone of voice based on input from the camera and microphone, and grasps the patient's emotional state.

[1359] Input: Video and audio data from cameras and microphones

[1360] Output: Perceived patient emotional state

[1361] Step 7:

[1362] The server adjusts the display content and feedback of the 3D model based on the emotional state it recognizes.

[1363] As a specific example of how this works, if a patient is feeling anxious, the display content of the 3D model is adjusted to be simple and easy to explain.

[1364] Input: Recognized patient emotional state, generated 3D model

[1365] Output: Visualization and feedback of the adjusted 3D model

[1366] Step 8:

[1367] Using the terminal, medical staff can access the dashboard and conduct examinations while viewing the 3D model.

[1368] As a specific example of how it works, medical staff use a tablet device to display a 3D model of the patient's tumor and perform an examination and explanation.

[1369] Input: Adjusted 3D model, feedback

[1370] Output: Examination and explanation by medical staff

[1371] Step 9:

[1372] Users (medical staff and patients) discuss and reach a consensus on detailed diagnoses and treatment plans based on the generated 3D models and feedback from the emotion engine.

[1373] As a specific example of how it works, medical staff and patients can discuss treatment plans and surgical risks while looking at the 3D model, and the emotion engine provides feedback to reduce the patient's anxiety.

[1374] Input: Adjusted 3D model, feedback

[1375] Output: Consensus diagnosis and treatment plan

[1376] (Application example 2)

[1377] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1378] In modern factory environments, it is difficult to monitor workers' health and mental stress in real time and respond appropriately. This can lead to reduced work efficiency and safety risks. Furthermore, communication with workers tends to be lacking, and health problems are often only addressed after they occur. Therefore, there is a need for a system that can monitor workers' health and emotions in real time and provide efficient feedback.

[1379] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for electronically collecting medical image data and patient health data from medical institutions, means including an artificial intelligence model for preprocessing and analyzing the medical image data and the health data, means for generating a 3D model based on the analysis results, means for visualizing the 3D model and presenting it to a user, means for recognizing the user's emotions and providing feedback according to their emotional state, and means for adjusting the display content of the 3D model based on the emotion recognition means. This makes it possible to monitor the health status and emotions of workers in real time and provide appropriate feedback, thereby improving work efficiency and ensuring safety.

[1380] A "medical institution" is an organization or facility that provides medical services to patients.

[1381] "Electronically collected" refers to obtaining information as digital data using networks or sensors.

[1382] "Medical image data" refers to image information of a patient's inside the body obtained from imaging diagnostic devices such as CT scans and MRIs.

[1383] "Patient health data" refers to digital data relating to a patient's medical history and current health status.

[1384] "Preprocessing" refers to the process of processing collected data, such as by removing noise and standardizing it, to prepare it in a format suitable for analysis.

[1385] An "artificial intelligence model" refers to a system that uses algorithms such as machine learning and deep learning to analyze data and detect patterns and anomalies.

[1386] "Generating a 3D model" refers to creating a three-dimensional image using computer graphics based on the analysis results.

[1387] "Visualizing" refers to the process of displaying digital data in a graphical form that makes it easier for humans to understand.

[1388] "Users" refers to factory workers and managers who use this system.

[1389] "Emotion recognition" means analyzing the user's psychological state from facial expressions, tone of voice, etc., and inferring specific emotions.

[1390] "Providing feedback" refers to providing users with advice, instructions, alerts, etc. in real time based on their emotions and health data.

[1391] "Adjusting the displayed content" refers to changing the visual information and feedback content based on the results of emotion recognition and presenting it in a form appropriate for the user.

[1392] The present invention, "Factory 3D Health Analyzer," is a system aimed at improving the health management and safety of workers in a factory environment. This system is composed of four components: a server, a terminal, a user, and an emotion engine.

[1393] server

[1394] The server is responsible for data collection, pre-processing, analysis, 3D model generation and emotion engine management.

[1395] Collection Method

[1396] The server electronically collects medical image data and patient health data from medical institutions through APIs.

[1397] Pretreatment means

[1398] The server first performs preprocessing on the collected data, such as noise removal and conversion to a standard format, so that the health data is in a format suitable for AI models.

[1399] Analysis means

[1400] The pre-processed data is then input into an artificial intelligence model on the server, which then performs an analysis, such as identifying the location and size of a tumor from collected medical image data.

[1401] 3D model generation method

[1402] Based on the analysis results, the server uses a 3D model generation engine to generate a realistic 3D model, which is then used to display the factory's work lines and equipment in 3D.

[1403] Feedback methods

[1404] The emotion engine recognizes the user's emotional state and provides feedback based on that emotion. For example, if the user is feeling stressed, the system will issue an appropriate alert and adjust the work environment accordingly.

[1405] Terminal

[1406] The terminal provides an interface for workers to view and manipulate the 3D model.

[1407] Visualization tools

[1408] The generated 3D model is visualized and displayed on devices such as smart glasses or tablets, allowing workers to check their own health status and working environment in real time.

[1409] For example, sensors built into smart glasses collect vital data (heart rate, body temperature, oxygen concentration) from workers and send it to a server. The server analyzes the data and sends the results to the device as a 3D model. If the worker's heart rate is high, the smart glasses will display an alert saying, "Please take a break."

[1410] User

[1411] The users are the workers and administrators who operate and check the system.

[1412] emotion recognition means

[1413] The system analyzes the worker's facial expressions and tone of voice via cameras and microphones to detect stress and anxiety, and the server then generates appropriate feedback and sends it to the device.

[1414] Feedback Adjustment Means

[1415] Based on the emotion recognition results, the display content of the 3D model and the feedback content are adjusted, which can reduce stress and anxiety for workers.

[1416] Examples of prompts include, "Generate appropriate feedback to be displayed when a worker wearing smart glasses feels stressed" and "Monitor the worker's health status based on sensor data and suggest how to automatically adjust the work plan based on that status."

[1417] As described above, the "Factory 3D Health Analyzer" of this invention makes it possible to monitor and adjust the health status and emotions of workers in real time, thereby improving work efficiency and ensuring safety in factories.

[1418] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1419] Step 1:

[1420] The server collects medical image data and patient health data from the medical institution's electronic medical record system and imaging diagnostic equipment via API. The input is data from the electronic medical record system and imaging diagnostic equipment, and the output is the collected medical image data and health data. This collected data is input into the next pre-processing phase.

[1421] Step 2:

[1422] The server performs pre-processing on the collected medical image data, such as noise removal and interpolation. The input is the medical image data collected in step 1, and the output is clear medical image data that has been subjected to noise removal and interpolation. This processing is intended to improve the accuracy of medical image analysis.

[1423] Step 3:

[1424] The server inputs preprocessed medical image data and standardized health data into the AI ​​model and performs the analysis. The input is preprocessed medical image data and health data, and the output is numerical and text data as the analysis results. For example, diagnostic information such as the location and size of a tumor is output.

[1425] Step 4:

[1426] The server generates a 3D model using a 3D model generation engine based on the analysis results. The input is the numerical and text data of the analysis results obtained in Step 3, and the output is the 3D model data. The generated 3D model is useful for detailed visualization of specific parts.

[1427] Step 5:

[1428] The server uploads the generated 3D model to a cloud database or web dashboard and distributes it so that it can be accessed by medical staff and workers. The input is the 3D model data, and the output is accessible via a web viewer or dedicated application. This allows the user, or worker, to view the 3D model on their device.

[1429] Step 6:

[1430] The server uses an emotion engine to analyze and recognize the user's emotional state in real time. The input is video and audio data from a camera and microphone, and the output is the type of emotion recognized. For example, it determines whether the user is feeling stressed.

[1431] Step 7:

[1432] The server adjusts the display content and feedback of the 3D model based on the emotion recognition results. The input is the emotion data recognized in step 6, and the output is the adjusted display content and feedback message of the 3D model. For example, for a user who is feeling stressed, the display will be simpler and easier to understand.

[1433] Step 8:

[1434] The terminal presents the adjusted 3D model and feedback to the user (worker). The input is the adjusted 3D model and feedback data sent from the server in step 7, and the output is the information displayed on the terminal screen. This allows the worker to deepen their understanding of their own health condition and work environment and respond appropriately.

[1435] Step 9:

[1436] The user (worker) uses the terminal to check the displayed 3D model and feedback, and respond or take action as necessary. The input is the information displayed on the terminal, and the output is the worker's actions or responses. For example, this includes actions such as taking a break or reporting to a manager.

[1437] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1438] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1439] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1440] [Fourth embodiment]

[1441] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1442] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1443] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1444] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1445] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1446] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1447] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1448] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1449] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1450] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1451] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1452] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1453] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1454] The present invention, "3D Health Analyzer," is a system for improving the accuracy and speed of diagnoses in medical institutions and streamlining communication between medical staff and patients. This system consists of a series of processes that collect and analyze medical image data and patient health data, and visualize the results as a 3D model. Below, the processing of the system's program is explained in natural language and detailed with concrete examples.

[1455] overview

[1456] "3D Health Analyzer" is a system consisting of three parties: a server, a terminal, and a user. The server is responsible for data collection, preprocessing, analysis, and generation of 3D models. The terminal provides an interface for medical staff to view and manipulate the 3D models. Users are medical staff and patients, and are responsible for sharing and understanding diagnostic information and treatment plans through the system.

[1457] Program processing flow

[1458] Collection Phase

[1459] The server collects medical image data and patient health data from the medical institution's electronic medical record system and imaging diagnostic equipment (e.g., X-ray, MRI, CT scan) via API.

[1460] Example: A server obtains image data of a patient's teeth from a dental X-ray machine in a dental clinic, and simultaneously collects data about the patient's medical history and current symptoms.

[1461] Preprocessing Phase

[1462] The server performs noise removal and interpolation on the collected medical image data.

[1463] Example: The server removes noise from acquired dental X-ray images and complements degraded parts of the images.

[1464] The server converts the health data into a standard format and makes it suitable for AI models.

[1465] Example: Converting a patient's past medical records and current health status data into a standardized format.

[1466] Analysis Phase

[1467] The server inputs the preprocessed data into the AI ​​model and performs the analysis.

[1468] Example: The server uses an AI model to analyze the patient's dental condition and identify areas of decay and possible periodontitis.

[1469] The server extracts the analysis results as numerical and text data and uses them as the basic data for generating a 3D model.

[1470] Example: Based on AI analysis, the location and size of cavities are extracted as numerical data.

[1471] 3D model generation phase

[1472] The server uses a 3D CG engine to generate a realistic 3D model based on the analysis results.

[1473] Example: A server generates a 3D dental model and visually highlights identified areas of caries.

[1474] Visualization Phase

[1475] The server visualizes the generated 3D model using a web viewer or dedicated application and delivers it to medical staff.

[1476] Example: The server uploads the generated 3D tooth model to a dashboard on the cloud, where it can be displayed in a viewer for medical staff.

[1477] Review and communication phase

[1478] Using the terminal, medical staff can access a dashboard and conduct examinations while viewing the 3D model.

[1479] Example: A dentist uses a tablet to view a 3D model of a patient's teeth, highlighting any cavities and providing explanations.

[1480] Based on the generated 3D model, users (medical staff and patients) discuss and reach a consensus on detailed diagnoses and treatment plans.

[1481] Example: Dentists and patients can view 3D models to discuss in detail treatment plans and preventative measures for cavities.

[1482] The "3D Health Analyzer" of this invention allows medical staff to significantly reduce the time and effort required to analyze medical images, thereby improving diagnostic accuracy. Furthermore, the use of 3D models facilitates communication with patients, increasing their understanding and acceptance of treatment. This improves the overall quality of medical care and reduces patient health risks.

[1483] The processing flow will be explained below.

[1484] Step 1: Data collection

[1485] server

[1486] Medical imaging data and patient health data are collected via APIs from medical institutions' electronic medical record systems and imaging diagnostic devices (e.g., X-ray machines, MRIs, CT scans).

[1487] Example: A server obtains dental image data of a particular patient from a dental x-ray machine in a dental clinic, and simultaneously collects the patient's medical history and current health data.

[1488] Step 2: Data Storage

[1489] server

[1490] Collected medical image data and health data are stored in temporary cloud storage.

[1491] Example: The server stores the acquired data in secure cloud storage and manages it in a database.

[1492] Step 3: Data cleaning

[1493] server

[1494] A pre-processing algorithm is used to remove noise from medical image data.

[1495] Example: Image filtering is used to remove noise from X-ray images and adjust image brightness and contrast.

[1496] Detect missing data and outliers in health data and impute or remove them appropriately.

[1497] Example: The server uses an imputation algorithm to fill in missing values ​​in health data and remove outliers.

[1498] Step 4: Data Standardization

[1499] server

[1500] Standardize the units and notations of health data (e.g., blood pressure, blood sugar levels, etc.) and convert them into a standard format.

[1501] Example: Convert blood pressure data into a unified unit (mmHg) and standardize the range of values.

[1502] Medical image data is also converted into a format suitable for AI models (e.g., DICOM format).

[1503] Example: Converting an X-ray image in JPG format to DICOM format.

[1504] Step 5: AI model analysis

[1505] server

[1506] Preprocessed medical image data and standardized health data are input into the AI ​​model and analysis is performed.

[1507] Example: The server uses an AI model to analyze images of teeth and automatically detect the location and depth of cavities.

[1508] As a diagnostic result, abnormalities and important findings are extracted as numerical or text data.

[1509] Example: As a result of AI analysis, the coordinates of the location and depth of cavities are obtained as numerical data.

[1510] Step 6: 3D model generation

[1511] server

[1512] Based on the analysis results, a 3D model of the medical image is generated using a 3D CG engine.

[1513] Example: The server generates a 3D model of the teeth from the analysis results, highlighting areas of decay.

[1514] The completed 3D model is visualized and delivered to a web viewer or dedicated application.

[1515] Example: The generated 3D model can be uploaded to a cloud-based dashboard and accessed by medical staff via a dedicated app.

[1516] Step 7: View on the dashboard

[1517] Terminal

[1518] Medical staff access the dashboard hosted on the server through a browser on their PC or tablet.

[1519] Example: A doctor uses a tablet to access a dashboard in the cloud and open a 3D model of a patient.

[1520] On the dashboard, select a 3D model of a specific patient and zoom in / out, rotate, and more to view details.

[1521] Example: The doctor rotates the 3D model to see the precise location and size of the cavities.

[1522] If necessary, screen captures and report output are performed to share diagnostic information with other medical staff and patients.

[1523] Example: A doctor generates a diagnostic report with a captured image of the 3D model and shares it with other medical staff.

[1524] Step 8: Promote communication with patients

[1525] Users (medical staff, patients)

[1526] When medical staff meet with patients, they explain things to them while displaying 3D models on a PC or tablet.

[1527] Example: A dentist shows a patient a 3D model of a tooth and explains the condition and treatment of the tooth.

[1528] Patients can understand diagnostic information by visually viewing the 3D model.

[1529] Example: A patient looks at a model of their own teeth and understands what the dentist is explaining.

[1530] Medical staff and patients create and review treatment plans based on the generated 3D model.

[1531] Example: Dentists and patients can review treatment schedules and procedures by referring to the 3D model.

[1532] Example 1

[1533] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1534] With conventional medical data analysis systems, medical staff spent a lot of time and effort analyzing diagnostic results and communicating with patients. This resulted in inconsistent diagnostic accuracy and low patient understanding and treatment acceptance. Furthermore, the lack of integrated analysis of medical images and health data made it difficult to develop comprehensive diagnoses and treatment plans. Furthermore, there were limited means of presenting analysis results in a visually understandable manner.

[1535] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1536] In this invention, the server includes: means for electronically collecting medical image data and patient health data from medical institutions; means for performing noise reduction and interpolation on the medical image data; means for converting the health data into a standard format and arranging it in a format suitable for analysis; means including an artificial intelligence model for preprocessing and analyzing the medical image data and the health data; means for instructing the artificial intelligence model to perform analysis using prompts; means for extracting the analysis results as numerical data and text data and using them as basic data for generating a 3D model; means for using a computer graphics engine to generate a realistic 3D model based on the analysis results; and means for visualizing the 3D model and presenting it to medical staff. This improves the accuracy and speed of diagnosis and enables efficient communication with patients.

[1537] "Medical image data" refers to image information such as X-rays, MRIs, and CT scans obtained at medical institutions.

[1538] "Patient Health Data" means information about a patient's health, such as the patient's medical history, current symptoms, and vital signs.

[1539] "Noise removal" is a process that removes unnecessary high-frequency components and errors from medical image data.

[1540] "Complement" is a process of filling in missing parts of medical image data to improve image quality.

[1541] A "standard format" is a common structure or format established to maintain data consistency and compatibility.

[1542] An "artificial intelligence model" is a computational algorithm used to analyze large amounts of data and find patterns and regularities.

[1543] A "prompt sentence" is a short piece of text that instructs an artificial intelligence model to perform a specific analysis.

[1544] "Numerical data" is information in a numerical format that quantitatively expresses the analysis results.

[1545] "Text data" is information that expresses analysis results and explanations in text format.

[1546] A "3D model" is a visual representation generated as a three-dimensional shape based on the analysis results.

[1547] A "computer graphics engine" is software for generating and displaying three-dimensional computer graphics.

[1548] The present invention, "3D Health Analyzer," is a system for improving the accuracy and speed of diagnoses in medical institutions and streamlining communication between medical staff and patients. This system consists of a series of processes that collect, preprocess, and analyze medical image data and patient health data, and visualize the results as a 3D model.

[1549] Hardware and Software Configuration

[1550] This system is mainly composed of three components: a server, a terminal, and a user. The specific hardware and software configuration is as follows:

[1551] Server: A computer system responsible for collecting, preprocessing, and analyzing data, and generating 3D models. Software used here includes APIs, Python's OpenCV library, generative AI models such as TensorFlow or PyTorch, and computer graphics engines such as Unity or Unreal Engine.

[1552] Terminal: A device used by medical staff to view and manipulate 3D models. This can be a display device such as a tablet or PC.

[1553] Users: Medical staff and patients who share and understand diagnostic information and treatment plans through the system.

[1554] Data collection and preprocessing

[1555] The server collects medical image data and patient health data from medical institutions' electronic medical record systems and imaging diagnostic devices (e.g., X-rays, MRIs, CT scans) via APIs. The collected data is stored in a database and backed up. For example, the server collects image data of patients' teeth from dental X-ray machines at a dental clinic, and simultaneously obtains data about the patient's medical history and current symptoms.

[1556] As part of preprocessing, the server performs noise removal and interpolation on medical image data and converts the health data into a standard format. For example, the server removes noise from collected dental X-ray images and interpolates image degradation. It also converts patients' past medical records and current health status data into a standard format (e.g., HL7 format).

[1557] Data analysis and 3D model generation

[1558] The server inputs the preprocessed medical image data and health data into the generative AI model. It uses prompts to provide specific instructions to the AI ​​model. Specific examples of prompts include, "Please identify the location of cavities in this patient's dental X-rays" and "Please convert the collected health data into a standard format and analyze the risk of periodontitis."

[1559] The analysis results from the generative AI model are extracted as numerical and text data, and the server uses this data to generate a 3D model. Specifically, the server uses a 3D CG engine such as Unity or Unreal Engine to generate a realistic 3D model based on the analysis results. The generated 3D model is presented to medical staff in a visually easy-to-understand format.

[1560] Visualization and Communication

[1561] The generated 3D model is visualized by the server through a web viewer or dedicated application. Medical staff can access the dashboard using a terminal and examine the patient while viewing the 3D model. For example, a dentist can view the 3D model of a patient's teeth on a tablet and explain the procedure, highlighting any cavities.

[1562] Furthermore, users (medical staff and patients) can discuss and reach consensus on detailed diagnoses and treatment plans based on the generated 3D models. For example, dentists and patients can discuss in detail treatment plans and preventive measures for cavities while looking at the 3D models.

[1563] In this way, the "3D Health Analyzer" of the present invention enables medical staff to improve the accuracy and speed of diagnosis, and also facilitates smooth communication with patients.

[1564] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1565] Step 1:

[1566] Data collection

[1567] The server collects medical image data and patient health data from the medical institution's electronic medical record system and imaging diagnostic equipment (e.g., X-ray, MRI, CT scan).

[1568] Input: Medical imaging data and patient health data from the medical institution's database.

[1569] Output: The collected medical image data and patient health data are stored in a database on the server.

[1570] What it does: Every day at 2 AM, the server runs an automated script to collect new patient data from the dental x-ray machine in the dental clinic.

[1571] Step 2:

[1572] Data Loss Prevention

[1573] The server backs up the collected data and stores it in a database, which prevents data loss and ensures safety.

[1574] Input: Collected data (medical imaging data and health data).

[1575] Output: Data stored in the database and backup data.

[1576] How it works: The server backs up collected dental X-ray images and health data to two different data centers.

[1577] Step 3:

[1578] Image data preprocessing

[1579] The server performs noise removal and interpolation on the collected medical image data.

[1580] Input: Collected medical image data.

[1581] Output: Denoised and imputed medical image data.

[1582] Specific operation: The server uses Python's OpenCV library to analyze the pixel values ​​of the acquired image and apply a filter to suppress high-frequency noise.

[1583] Step 4:

[1584] Health data format conversion

[1585] The server converts the health data into a standard format and makes it suitable for analysis.

[1586] Input: Collected health data.

[1587] Output: Health data converted into a standard format.

[1588] Specific operation: The server converts the patient's blood pressure, heart rate, and past medical records into HL7 format.

[1589] Step 5:

[1590] Input to AI model and prompt generation

[1591] The server inputs the preprocessed data into the generative AI model and uses prompt statements to direct the analysis.

[1592] Input: Denoised medical image data and health data in standard formats.

[1593] Output: The analysis results of the generative AI model.

[1594] Specific operation: The server generates a prompt statement such as, "Please identify the cavities in this patient's dental X-ray image," and instructs the AI ​​model.

[1595] Step 6:

[1596] Obtaining analysis results and extracting data

[1597] The server receives the analysis results from the AI ​​model and extracts them as numerical and text data.

[1598] Input: Analysis results of the generative AI model.

[1599] Output: Numerical and textual data.

[1600] Specific operation: The server stores the analysis results received from the AI ​​model, such as the location and size of cavities, as numerical data in a database.

[1601] Step 7:

[1602] 3D model generation

[1603] The server uses a 3D CG engine to generate a realistic 3D model based on the analysis results.

[1604] Input: Numeric and text data.

[1605] Output: Realistic 3D models.

[1606] Specific operation: The server uses Unity or Unreal Engine to generate a 3D model based on the analysis results and highlights visually important parts.

[1607] Step 8:

[1608] 3D model visualization and distribution

[1609] The server uploads the generated 3D model to a web viewer or dedicated application.

[1610] Input: A generated 3D model.

[1611] Output: 3D model that can be viewed in a web viewer or dedicated application.

[1612] Specific operation: The server uploads the generated 3D model to a dashboard on the cloud and notifies medical staff of an access URL or QR code.

[1613] Step 9:

[1614] Checked by medical staff

[1615] Using the terminal, medical staff can access the dashboard and conduct examinations while viewing the 3D model.

[1616] Input: 3D models uploaded to a web viewer or dedicated application.

[1617] Output: Medical staff examination results.

[1618] Specific operation: The dentist zooms in and rotates the 3D model of the patient on the tablet, checking the areas of tooth decay while explaining to the patient.

[1619] Step 10:

[1620] Sharing Diagnoses and Treatment Plans

[1621] Based on the generated 3D model, users (medical staff and patients) discuss and reach a consensus on detailed diagnoses and treatment plans.

[1622] Input: Medical staff review results and 3D model.

[1623] Output: Diagnosis and treatment plan.

[1624] How it works: Dentists and patients discuss treatment options while looking at the 3D model and select the best treatment plan.

[1625] (Application example 1)

[1626] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1627] It is important for medical institutions to analyze medical image data and health data more effectively and improve the accuracy and speed of diagnoses. Visual support is also required to facilitate communication between patients and medical staff and provide easy-to-understand diagnoses and treatment plans. Furthermore, there is a need to provide a virtual health checkup experience that allows patients to check their health status from home, enabling more people to efficiently manage their health.

[1628] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1629] In this invention, the server includes: means for electronically collecting medical image data and patient health data from medical institutions; means including an artificial intelligence model for preprocessing and analyzing the medical image data and the health data; means for generating a 3D model based on the analysis results; means for visualizing the 3D model and presenting it to medical staff; means for allowing users to view the 3D model via an interface on a smartphone or head-mounted display; and means for providing a virtual health checkup experience. This allows users to easily check their health status from home and to better understand diagnoses and treatment plans through communication with medical staff.

[1630] "Medical image data" refers to image data obtained at a medical institution, including images taken using equipment such as X-rays, MRIs, and CT scans.

[1631] "Patient health data" refers to information such as a patient's medical history, current health status, medical records, and symptoms.

[1632] "Preprocessing" refers to the process of removing noise and standardizing collected medical image data and health data to prepare them in a format suitable for analysis.

[1633] "Artificial intelligence model" refers to a program that uses machine learning and deep learning to analyze medical image data and health data.

[1634] "3D model" refers to a three-dimensional visual model generated based on medical image data and analysis results.

[1635] "Visualization" refers to displaying 3D models in a way that makes them easy for medical staff to understand.

[1636] "Interface" refers to the connection method and display device that allows users to view 3D models through a smartphone or head-mounted display.

[1637] The "virtual health checkup experience" refers to an experience that allows users to check and diagnose their health status from the comfort of their own home.

[1638] A "smartphone" refers to a portable information terminal that can use communication functions and applications.

[1639] A "head-mounted display" refers to a display device that is worn on the head and provides visual information.

[1640] The present invention is a system that improves the accuracy and speed of diagnoses by utilizing medical image data and patient health data collected from medical institutions. This system is composed of three entities: a server, a terminal, and a user, as described below.

[1641] The server has the function of collecting medical image data and patient health data from medical institutions' electronic medical record systems and imaging diagnostic devices (e.g., X-ray devices, MRI devices, CT scan devices) via APIs. The server also performs preprocessing on the collected data, such as noise removal and conversion to a standard format. This preprocessing prepares the data in a format suitable for the artificial intelligence model. The preprocessed data is then input into the artificial intelligence model for analysis. Based on the results of this analysis, the server generates a 3D model. This 3D model is generated in real time using a 3D CG engine.

[1642] The device provides an interface for visualizing the generated 3D model. Medical staff can use this device to check the 3D model and operate the interface. The visualized 3D model is uploaded to a dashboard on the cloud and displayed in a viewer for medical staff. In addition, the device has a function that allows the user (patient) to check the 3D model using a smartphone or head-mounted display.

[1643] Users are medical staff and patients, who use the generated 3D models to discuss and reach consensus on detailed diagnoses and treatment plans. Patients can experience virtual medical checkups from home using a smartphone or head-mounted display. For example, when a patient uploads MRI scan data from home, the system analyzes the data and generates a 3D model. The generated 3D model is displayed on a smartphone or head-mounted display so that the patient can view it at home.

[1644] The main hardware and software used include Python, Numpy, Scikit-learn, Nibabel, and Vedo, which are used to handle the steps of data collection, preprocessing, analysis, 3D model generation, and visualization.

[1645] As a concrete example, the following prompt sentence can be used:

[1646] Example prompt sentence:

[1647] "I've been having frequent headaches lately. I'd like you to check the state of my brain based on my MRI scan data and visualize it as a 3D model."

[1648] In this way, the system of the present invention improves diagnostic accuracy at medical institutions and facilitates smooth communication between patients and medical staff. Furthermore, by providing a virtual health checkup experience, patients can easily check their health status and use medical services from the comfort of their own homes.

[1649] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1650] Step 1:

[1651] The server collects medical image data and patient health data from medical institutions' electronic medical record systems and diagnostic imaging devices via APIs. During this collection process, data is obtained from various devices using API calls and stored in a database. The input is the medical image data and health data sent from the devices, and the output is the raw data stored in the server's database.

[1652] Step 2:

[1653] The server performs preprocessing on the collected medical image data to remove noise and correct image quality. Specifically, it performs noise removal filtering and image correction using libraries such as Python's Nibabel and OpenCV. The input is the medical image data collected in step 1, and the output is clean medical image data that has been corrected and denoised.

[1654] Step 3:

[1655] The server performs preprocessing to convert the patient's health data into a standard format and prepare it for analysis. Specifically, it uses Python's Pandas library to clean the data, extract necessary items, and format it. The input is the health data collected in step 1, and the output is the standardized health data.

[1656] Step 4:

[1657] The server inputs the preprocessed medical image data and health data into an artificial intelligence model for analysis. This analysis uses libraries such as Scikit-learn and TensorFlow to apply machine learning and deep learning models to extract meaningful results from the data. The input is the data preprocessed in steps 2 and 3, and the output is the numerical and text data of the analysis results.

[1658] Step 5:

[1659] The server generates a 3D model based on the analysis results. Specifically, it uses a 3D CG engine such as the Vedo library to generate a three-dimensional model that visually represents the analysis results. The input is the analysis result data obtained in step 4, and the output is the generated 3D model.

[1660] Step 6:

[1661] The server visualizes the generated 3D model using a web viewer or a dedicated application so that users can check it through an interface. For example, a web page for displaying the 3D model is built using a web framework such as Flask or Django. The input is the 3D model generated in step 5, and the output is the visualized 3D model displayed in a web viewer that users can access.

[1662] Step 7:

[1663] The user checks the generated 3D model using a smartphone or a head-mounted display. Specifically, the user can launch a dedicated viewer app and interactively view the 3D model. The input is access to the 3D model display page visualized in Step 6, and the output is the user experience of checking the 3D model and understanding the health condition.

[1664] Step 8:

[1665] Users (medical staff and patients) discuss detailed diagnoses and treatment plans based on the generated 3D model and reach a consensus. For example, a patient can view the 3D model together with medical staff and discuss diagnostic results and specific treatment options. The inputs are the 3D model confirmed in step 7 and feedback from the users, and the output is the agreed-upon diagnostic information and treatment plan.

[1666] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1667] The present invention, "3D Health Analyzer," is a system that improves the accuracy and speed of diagnoses in medical institutions and streamlines communication between medical staff and patients. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it provides interactive functions that correspond to the user's emotional state. Below, the processing of the system's program is explained in natural language and detailed with specific examples.

[1668] overview

[1669] "3D Health Analyzer" is a system consisting of four components: a server, a terminal, a user, and an emotion engine. The server is responsible for data collection, preprocessing, analysis, 3D model generation, and emotion engine management. The terminal provides an interface for medical staff to view and manipulate the 3D models. Users are medical staff and patients, and their role is to share and understand diagnostic information and treatment plans through the system. The emotion engine recognizes the user's emotional state and provides feedback accordingly.

[1670] Program processing flow

[1671] Collection Phase

[1672] The server collects medical image data and patient health data from the medical institution's electronic medical record system and imaging diagnostic equipment (e.g., X-ray, MRI, CT scan) via API.

[1673] Example: A server retrieves image data for a particular patient from an MRI machine in a surgeon's office, while also collecting the patient's medical history and current health data.

[1674] Preprocessing Phase

[1675] The server performs noise removal and interpolation on the collected medical image data.

[1676] Example: The server removes noise from acquired MRI images and complements degraded parts of the images.

[1677] The server converts the health data into a standard format and makes it suitable for AI models.

[1678] Example: Converting a patient's past medical records and current health status data into a standardized format.

[1679] Analysis Phase

[1680] The server inputs the preprocessed data into the AI ​​model and performs the analysis.

[1681] Example: The server uses an AI model to analyze a patient's MRI images and identify the location and size of a tumor.

[1682] The server extracts the analysis results as numerical and text data and uses them as the basic data for generating a 3D model.

[1683] Example: As a result of AI analysis, the location coordinates and size of a tumor are obtained as numerical data.

[1684] 3D model generation phase

[1685] The server uses a 3D CG engine to generate a realistic 3D model based on the analysis results.

[1686] Example: The server generates a 3D model of the tumor from the analysis results and visually highlights the tumor location.

[1687] Visualization Phase

[1688] The server visualizes the generated 3D model using a web viewer or dedicated application and delivers it to medical staff.

[1689] Example: The generated 3D model can be uploaded to a cloud-based dashboard and accessed by medical staff via a dedicated app.

[1690] Emotion Engine

[1691] The server uses an emotion engine to recognize the emotions of users (mainly patients) in real time.

[1692] For example, based on input from the camera and microphone, the emotion engine analyzes the patient's facial expressions and tone of voice to understand their emotional state.

[1693] The server adjusts the display and feedback of the 3D model based on the recognized emotion.

[1694] For example, if a patient is feeling anxious, the system will change the display of the 3D model to something simpler and easier to explain.

[1695] Confirmation and communication promotion

[1696] Using the terminal, medical staff can access a dashboard and conduct examinations while viewing the 3D model.

[1697] Example: A surgeon uses a tablet to view a 3D model of a patient's tumor and explain it in detail.

[1698] Users (medical staff and patients) discuss and reach a consensus on detailed diagnoses and treatment plans based on the generated 3D models and feedback from the emotion engine.

[1699] Example: A surgeon and a patient discuss in detail the tumor treatment plan and the risks of surgery while looking at a 3D model. The emotion engine provides appropriate feedback to reduce the patient's anxiety and facilitate communication.

[1700] By combining the "3D Health Analyzer" of this invention with an emotion engine, medical staff can make diagnoses and explanations that take into account the patient's emotional state, thereby improving patient understanding and satisfaction. This system offers a new approach to improving both diagnostic accuracy and the quality of medical services.

[1701] The processing flow will be explained below.

[1702] Step 1: Data collection

[1703] server

[1704] Medical imaging data and patient health data are collected via APIs from medical institutions' electronic medical record systems and imaging diagnostic devices (e.g., X-ray machines, MRIs, CT scans).

[1705] Example: A server retrieves image data for a particular patient from an MRI machine in a surgeon's office, while also collecting the patient's medical history and current health data.

[1706] Step 2: Data Storage

[1707] server

[1708] Collected medical image data and health data are stored in temporary cloud storage.

[1709] Example: The server stores the acquired data in secure cloud storage and manages it in a database.

[1710] Step 3: Data cleaning

[1711] server

[1712] A pre-processing algorithm is used to remove noise from medical image data.

[1713] Example: Image filtering is used to remove noise from MRI images and adjust image brightness and contrast.

[1714] Detect missing data and outliers in health data and impute or remove them appropriately.

[1715] Example: The server uses an imputation algorithm to fill in missing values ​​in health data and remove outliers.

[1716] Step 4: Data Standardization

[1717] server

[1718] Standardize the units and notations of health data (e.g., blood pressure, blood sugar levels, etc.) and convert them into a standard format.

[1719] Example: Convert blood pressure data into a unified unit (mmHg) and standardize the range of values.

[1720] Medical image data is also converted into a format suitable for AI models (e.g., DICOM format).

[1721] Example: Converting a JPG format MRI image to DICOM format.

[1722] Step 5: AI model analysis

[1723] server

[1724] Preprocessed medical image data and standardized health data are input into the AI ​​model and analysis is performed.

[1725] Example: The server uses an AI model to analyze a patient's MRI images and identify the location and size of a tumor.

[1726] As a diagnostic result, abnormalities and important findings are extracted as numerical or text data.

[1727] Example: As a result of AI analysis, the location coordinates and size of a tumor are obtained as numerical data.

[1728] Step 6: 3D model generation

[1729] server

[1730] Based on the analysis results, a 3D model of the medical image is generated using a 3D CG engine.

[1731] Example: The server generates a 3D model of the tumor from the analysis results and visually highlights the tumor location.

[1732] The completed 3D model is visualized and delivered to a web viewer or dedicated application.

[1733] Example: The generated 3D model can be uploaded to a cloud-based dashboard and accessed by medical staff via a dedicated app.

[1734] Step 7: Sentiment Analysis

[1735] server

[1736] An emotion engine is used to recognize the user's (patient's) emotional state in real time.

[1737] Example: Based on input from the camera and microphone, the emotion engine analyzes the patient's facial expressions and tone of voice to understand their emotional state.

[1738] Step 8: Emotion-Based Display Adjustment

[1739] server

[1740] The display of a 3D model is adjusted based on the recognized emotion.

[1741] For example, if a patient is feeling anxious, the system will change the display of the 3D model to something simpler and easier to explain.

[1742] Step 9: View on the Dashboard

[1743] Terminal

[1744] Medical staff access the dashboard hosted on the server through a browser on their PC or tablet.

[1745] Example: A doctor uses a tablet to access a dashboard in the cloud and open a 3D model of a patient.

[1746] On the dashboard, select a 3D model of a specific patient and zoom in / out, rotate, and more to view details.

[1747] Example: A doctor rotates the 3D model to see the precise location and size of a tumor.

[1748] If necessary, screen captures and report output are performed to share diagnostic information with other medical staff and patients.

[1749] Example: A doctor generates a diagnostic report with a captured image of the 3D model and shares it with other medical staff.

[1750] Step 10: Promote communication with patients

[1751] Users (medical staff, patients)

[1752] When medical staff meet with patients, they explain things to them while displaying 3D models on a PC or tablet.

[1753] Example: A surgeon shows a patient a 3D model of the tumor and explains the surgical procedure.

[1754] Patients can understand diagnostic information by visually viewing the 3D model.

[1755] Example: A patient looks at a model of their tumor and understands what the surgeon is explaining.

[1756] Medical staff and patients create and review treatment plans based on the generated 3D model and feedback from the emotion engine.

[1757] For example, a surgeon and a patient can review the treatment schedule and procedures while referring to a 3D model. The emotion engine provides appropriate feedback to reduce patient anxiety and facilitate communication.

[1758] Example 2

[1759] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1760] The current medical system not only lacks diagnostic accuracy and speed, but also lacks interactive functions for smooth communication between medical staff and patients. In particular, it is difficult to diagnose and explain things taking into account the patient's emotional state, which leads to problems such as a decrease in patient understanding and satisfaction. There is a need to efficiently solve these issues.

[1761] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1762] In this invention, the server includes a means for electronically collecting medical image data and patient health data from medical institutions, a means including an artificial intelligence model for preprocessing and analyzing the medical image data and health data, a means for generating a 3D model based on the analysis results, a means for visualizing the 3D model and presenting it to medical staff, a means for recognizing the user's emotional state and adjusting the display content of the 3D model based on that feedback, and a means for the patient and medical staff to discuss and reach a consensus on detailed diagnoses and treatment plans based on the generated 3D model and feedback from the emotion engine, thereby improving the accuracy and speed of diagnoses and enabling interactive communication that reflects the patient's emotional state.

[1763] "Medical image data" refers to image information obtained from imaging diagnostic equipment (e.g., X-ray, MRI, CT scan) used in medical institutions.

[1764] "Patient health data" refers to digital information such as a patient's medical history, current physical condition, and test results obtained from an electronic medical record system.

[1765] "Preprocessing" refers to a series of processes that remove noise and complement collected raw data, converting it into a form suitable for analysis.

[1766] An "artificial intelligence model" is a program that uses machine learning algorithms to analyze data and make diagnoses and predictions.

[1767] "Analysis results" refers to conclusions or insights derived from data processed using artificial intelligence models.

[1768] A "3D model" refers to a three-dimensional visual display created based on the analysis results, specifically a three-dimensional display of the affected area and internal structure.

[1769] "Visualization" refers to the display of data or information in a visual form, specifically on a screen or in a VR space.

[1770] "User's emotional state" refers to the results obtained by analyzing the emotions and feelings the user is currently experiencing based on information obtained from a camera, microphone, etc.

[1771] "Feedback" refers to the adjustment of displayed content, specific advice, or explanations that the system provides based on the user's emotional state or other information.

[1772] "Discussion" refers to a discussion in which medical staff and patients share information and exchange opinions to determine treatment plans and diagnostic procedures.

[1773] "Consensus building" refers to medical staff and patients reaching a mutually acceptable treatment plan and diagnostic policy through discussion.

[1774] MODE FOR CARRYING OUT THE INVENTION

[1775] This invention is a system called "3D Health Analyzer" that improves the accuracy and speed of diagnoses in medical institutions and streamlines communication between medical staff and patients. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it provides interactive functions that respond to the user's emotional state.

[1776] System Configuration

[1777] "3D Health Analyzer" is a system that includes a server, a terminal, a user, and an emotion engine.

[1778] 1. Server: Responsible for data collection, preprocessing, analysis, 3D model generation, and emotion engine management.

[1779] 2. Terminal: Provides an interface for medical staff to view and manipulate the 3D model.

[1780] 3. Users: Medical staff and patients who share and understand diagnostic information and treatment plans through the system.

[1781] 4. Emotion Engine: Recognizes the user's emotional state and provides feedback accordingly.

[1782] Hardware and software used

[1783] Specific hardware and software examples include:

[1784] Imaging equipment: MRI, CT scan, X-ray, etc.

[1785] Electronic medical record system: A system that manages patient health data

[1786] Server software: Software on the server that manages data collection, preprocessing, and analysis

[1787] AI model: Machine learning algorithms used for data analysis

[1788] 3D CG engine: 3D model generation software such as Unity or Unreal Engine

[1789] Emotion Engine: Software that analyzes the user's emotional state

[1790] Program processing example

[1791] Example 1:

[1792] "We input the MRI images and the patient's medical history into the 3D Health Analyzer to generate a 3D model of the tumor. If the patient is concerned, we adjust the display to simplify it."

[1793] Example 2:

[1794] "Collect patient health data from electronic medical records, analyze it with an AI model, and generate a 3D model based on the results. Use an emotion engine to recognize patient emotions and provide feedback."

[1795] An example of an operation sequence

[1796] 1. Data collection: The server collects the necessary medical data from the medical institution's electronic medical record system and imaging diagnostic equipment via the API.

[1797] 2. Data preprocessing: The collected data will be preprocessed by the server to remove noise and perform imputation. The patient's health data will be converted into a standard format.

[1798] 3. Data analysis: The preprocessed data is input into the AI ​​model for analysis, and the analysis results are extracted as numerical data or text data.

[1799] 4. 3D model generation: Based on the analysis results, the server generates a 3D model using a 3D CG engine.

[1800] 5. Visualization: The generated 3D model is visualized in a web viewer or dedicated application and delivered to medical staff.

[1801] 6. Utilizing an Emotion Engine: The server recognizes the user's emotional state and adjusts the display content and feedback of the 3D model accordingly.

[1802] By introducing this "3D Health Analyzer," medical facilities can significantly improve the accuracy and speed of diagnosis, as well as patient understanding and satisfaction. By combining it with an emotion engine, it can provide interactive feedback that takes into account the patient's emotional state, resulting in more efficient medical services.

[1803] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1804] Step 1:

[1805] The server collects medical image data and patient health data from medical institutions' electronic medical record systems and diagnostic imaging devices via APIs.

[1806] As a specific example of operation, the server calls the API of the MRI device, obtains image data of a specific patient, and obtains the patient's medical history and current physical condition data from the electronic medical record.

[1807] Input: Image data from MRI scanner, patient health data from electronic medical records

[1808] Output: Medical imaging data and patient health data

[1809] Step 2:

[1810] The server performs preprocessing by removing noise and complementing the medical image data collected.

[1811] Specifically, the server applies a noise reduction algorithm to remove noise from the acquired MRI images, complement the degraded parts, and convert the patient's health data into a standard format.

[1812] Input: Medical image data, patient health data

[1813] Output: Denoised and imputed medical image data, standardized health data

[1814] Step 3:

[1815] The server inputs the preprocessed medical data into the AI ​​model and performs data analysis.

[1816] As a specific example of how it works, preprocessed MRI image data and standardized health data are input into the AI ​​model, and an analysis is performed to identify the location and size of the tumor, with numerical and text data being obtained as the analysis results.

[1817] Input: Preprocessed medical image data, standardized health data

[1818] Output: Analysis results (tumor location, size)

[1819] Step 4:

[1820] The server generates a 3D model based on the analysis results.

[1821] As a specific example of how it works, the server uses a 3D CG engine (e.g., Unity or Unreal Engine) to generate a 3D model of the tumor based on the analysis results and combines it with other parts of the human body to create a complete picture.

[1822] Input: Analysis results (tumor location, size)

[1823] Output: Generated 3D model

[1824] Step 5:

[1825] The server visualizes the generated 3D model through a web viewer or dedicated application and delivers it to medical staff.

[1826] As a specific example of how it works, the server uploads the generated 3D model to a cloud dashboard and displays it in a dedicated application for medical staff.

[1827] Input: Generated 3D model

[1828] Output: Web viewer, 3D model displayed in dedicated application

[1829] Step 6:

[1830] The server uses an emotion engine to recognize the emotional state of the user (mainly the patient) in real time.

[1831] As a specific example of how it works, the emotion engine analyzes the patient's facial expressions and tone of voice based on input from the camera and microphone, and grasps the patient's emotional state.

[1832] Input: Video and audio data from cameras and microphones

[1833] Output: Perceived patient emotional state

[1834] Step 7:

[1835] The server adjusts the display content and feedback of the 3D model based on the emotional state it recognizes.

[1836] As a specific example of how this works, if a patient is feeling anxious, the display content of the 3D model is adjusted to be simple and easy to explain.

[1837] Input: Recognized patient emotional state, generated 3D model

[1838] Output: Visualization and feedback of the adjusted 3D model

[1839] Step 8:

[1840] Using the terminal, medical staff can access the dashboard and conduct examinations while viewing the 3D model.

[1841] As a specific example of how it works, medical staff use a tablet device to display a 3D model of the patient's tumor and perform an examination and explanation.

[1842] Input: Adjusted 3D model, feedback

[1843] Output: Examination and explanation by medical staff

[1844] Step 9:

[1845] Users (medical staff and patients) discuss and reach a consensus on detailed diagnoses and treatment plans based on the generated 3D models and feedback from the emotion engine.

[1846] As a specific example of how it works, medical staff and patients can discuss treatment plans and surgical risks while looking at the 3D model, and the emotion engine provides feedback to reduce the patient's anxiety.

[1847] Input: Adjusted 3D model, feedback

[1848] Output: Consensus diagnosis and treatment plan

[1849] (Application example 2)

[1850] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1851] In modern factory environments, it is difficult to monitor workers' health and mental stress in real time and respond appropriately. This can lead to reduced work efficiency and safety risks. Furthermore, communication with workers tends to be lacking, and health problems are often only addressed after they occur. Therefore, there is a need for a system that can monitor workers' health and emotions in real time and provide efficient feedback.

[1852] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for electronically collecting medical image data and patient health data from medical institutions, means including an artificial intelligence model for preprocessing and analyzing the medical image data and the health data, means for generating a 3D model based on the analysis results, means for visualizing the 3D model and presenting it to a user, means for recognizing the user's emotions and providing feedback according to their emotional state, and means for adjusting the display content of the 3D model based on the emotion recognition means. This makes it possible to monitor the health status and emotions of workers in real time and provide appropriate feedback, thereby improving work efficiency and ensuring safety.

[1853] A "medical institution" is an organization or facility that provides medical services to patients.

[1854] "Electronically collected" refers to obtaining information as digital data using networks or sensors.

[1855] "Medical image data" refers to image information of a patient's inside the body obtained from imaging diagnostic devices such as CT scans and MRIs.

[1856] "Patient health data" refers to digital data relating to a patient's medical history and current health status.

[1857] "Preprocessing" refers to the process of processing collected data, such as by removing noise and standardizing it, to prepare it in a format suitable for analysis.

[1858] An "artificial intelligence model" refers to a system that uses algorithms such as machine learning and deep learning to analyze data and detect patterns and anomalies.

[1859] "Generating a 3D model" refers to creating a three-dimensional image using computer graphics based on the analysis results.

[1860] "Visualizing" refers to the process of displaying digital data in a graphical form that makes it easier for humans to understand.

[1861] "Users" refers to factory workers and managers who use this system.

[1862] "Emotion recognition" means analyzing the user's psychological state from facial expressions, tone of voice, etc., and inferring specific emotions.

[1863] "Providing feedback" refers to providing users with advice, instructions, alerts, etc. in real time based on their emotions and health data.

[1864] "Adjusting the displayed content" refers to changing the visual information and feedback content based on the results of emotion recognition and presenting it in a form appropriate for the user.

[1865] The present invention, "Factory 3D Health Analyzer," is a system aimed at improving the health management and safety of workers in a factory environment. This system is composed of four components: a server, a terminal, a user, and an emotion engine.

[1866] server

[1867] The server is responsible for data collection, pre-processing, analysis, 3D model generation and emotion engine management.

[1868] Collection Method

[1869] The server electronically collects medical image data and patient health data from medical institutions through APIs.

[1870] Pretreatment means

[1871] The server first performs preprocessing on the collected data, such as noise removal and conversion to a standard format, so that the health data is in a format suitable for AI models.

[1872] Analysis means

[1873] The pre-processed data is then input into an artificial intelligence model on the server, which then performs an analysis, such as identifying the location and size of a tumor from collected medical image data.

[1874] 3D model generation method

[1875] Based on the analysis results, the server uses a 3D model generation engine to generate a realistic 3D model, which is then used to display the factory's work lines and equipment in 3D.

[1876] Feedback methods

[1877] The emotion engine recognizes the user's emotional state and provides feedback based on that emotion. For example, if the user is feeling stressed, the system will issue an appropriate alert and adjust the work environment accordingly.

[1878] Terminal

[1879] The terminal provides an interface for workers to view and manipulate the 3D model.

[1880] Visualization tools

[1881] The generated 3D model is visualized and displayed on devices such as smart glasses or tablets, allowing workers to check their own health status and working environment in real time.

[1882] For example, sensors built into smart glasses collect vital data (heart rate, body temperature, oxygen concentration) from workers and send it to a server. The server analyzes the data and sends the results to the device as a 3D model. If the worker's heart rate is high, the smart glasses will display an alert saying, "Please take a break."

[1883] User

[1884] The users are the workers and administrators who operate and check the system.

[1885] emotion recognition means

[1886] The system analyzes the worker's facial expressions and tone of voice via cameras and microphones to detect stress and anxiety, and the server then generates appropriate feedback and sends it to the device.

[1887] Feedback Adjustment Means

[1888] Based on the emotion recognition results, the display content of the 3D model and the feedback content are adjusted, which can reduce stress and anxiety for workers.

[1889] Examples of prompts include, "Generate appropriate feedback to be displayed when a worker wearing smart glasses feels stressed" and "Monitor the worker's health status based on sensor data and suggest how to automatically adjust the work plan based on that status."

[1890] As described above, the "Factory 3D Health Analyzer" of this invention makes it possible to monitor and adjust the health status and emotions of workers in real time, thereby improving work efficiency and ensuring safety in factories.

[1891] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1892] Step 1:

[1893] The server collects medical image data and patient health data from the medical institution's electronic medical record system and imaging diagnostic equipment via API. The input is data from the electronic medical record system and imaging diagnostic equipment, and the output is the collected medical image data and health data. This collected data is input into the next pre-processing phase.

[1894] Step 2:

[1895] The server performs pre-processing on the collected medical image data, such as noise removal and interpolation. The input is the medical image data collected in step 1, and the output is clear medical image data that has been subjected to noise removal and interpolation. This processing is intended to improve the accuracy of medical image analysis.

[1896] Step 3:

[1897] The server inputs preprocessed medical image data and standardized health data into the AI ​​model and performs the analysis. The input is preprocessed medical image data and health data, and the output is numerical and text data as the analysis results. For example, diagnostic information such as the location and size of a tumor is output.

[1898] Step 4:

[1899] The server generates a 3D model using a 3D model generation engine based on the analysis results. The input is the numerical and text data of the analysis results obtained in Step 3, and the output is the 3D model data. The generated 3D model is useful for detailed visualization of specific parts.

[1900] Step 5:

[1901] The server uploads the generated 3D model to a cloud database or web dashboard and distributes it so that it can be accessed by medical staff and workers. The input is the 3D model data, and the output is accessible via a web viewer or dedicated application. This allows the user, or worker, to view the 3D model on their device.

[1902] Step 6:

[1903] The server uses an emotion engine to analyze and recognize the user's emotional state in real time. The input is video and audio data from a camera and microphone, and the output is the type of emotion recognized. For example, it determines whether the user is feeling stressed.

[1904] Step 7:

[1905] The server adjusts the display content and feedback of the 3D model based on the emotion recognition results. The input is the emotion data recognized in step 6, and the output is the adjusted display content and feedback message of the 3D model. For example, for a user who is feeling stressed, the display will be simpler and easier to understand.

[1906] Step 8:

[1907] The terminal presents the adjusted 3D model and feedback to the user (worker). The input is the adjusted 3D model and feedback data sent from the server in step 7, and the output is the information displayed on the terminal screen. This allows the worker to deepen their understanding of their own health condition and work environment and respond appropriately.

[1908] Step 9:

[1909] The user (worker) uses the terminal to check the displayed 3D model and feedback, and respond or take action as necessary. The input is the information displayed on the terminal, and the output is the worker's actions or responses. For example, this includes actions such as taking a break or reporting to a manager.

[1910] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1911] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1912] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1913] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1914] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1915] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1916] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1917] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1918] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1919] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1920] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1921] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1922] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1923] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1924] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1925] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1926] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1927] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1928] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1929] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1930] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1931] The following is further disclosed regarding the above embodiment.

[1932] (Claim 1)

[1933] a means for electronically collecting medical image data and patient health data from a medical institution;

[1934] means including an artificial intelligence model for pre-processing and analyzing the medical image data and the health data;

[1935] A means for generating a 3D model based on the analysis results;

[1936] and a means for visualizing and presenting said 3D model to medical staff.

[1937] (Claim 2)

[1938] 10. The system of claim 1, further comprising means for utilizing the 3D model in communication between patients and medical staff.

[1939] (Claim 3)

[1940] 10. The system of claim 1, further comprising means for creating and verifying a treatment plan using the 3D model.

[1941] "Example 1"

[1942] (Claim 1)

[1943] a means for electronically collecting medical image data and patient health data from a medical institution;

[1944] means for performing noise removal and interpolation on the medical image data;

[1945] means for converting the health data into a standard format and arranging it in a form suitable for analysis;

[1946] means including an artificial intelligence model for pre-processing and analyzing the medical image data and the health data;

[1947] means for instructing the artificial intelligence model to perform analysis using a prompt sentence;

[1948] A means for extracting the analysis results as numerical data and text data and using them as basic data for generating a 3D model;

[1949] A computer graphics engine is used to generate realistic 3D models based on the analysis results.

[1950] and a means for visualizing and presenting said 3D model to medical staff.

[1951] (Claim 2)

[1952] 10. The system of claim 1, further comprising means for utilizing the 3D model in communication between patients and medical staff.

[1953] (Claim 3)

[1954] 10. The system of claim 1, further comprising means for creating and verifying a treatment plan using the 3D model.

[1955] "Application Example 1"

[1956] (Claim 1)

[1957] a means for electronically collecting medical image data and patient health data from a medical institution;

[1958] means including an artificial intelligence model for pre-processing and analyzing the medical image data and the health data;

[1959] A means for generating a 3D model based on the analysis results;

[1960] means for visualizing and presenting said 3D model to medical staff;

[1961] A means for allowing a user to view the 3D model through an interface on a smartphone or a head-mounted display;

[1962] A system including a means for providing a virtual health checkup experience.

[1963] (Claim 2)

[1964] 10. The system of claim 1, further comprising means for utilizing the 3D model for communication between patients and medical staff to provide diagnostic information and health status to users through a virtual medical examination experience.

[1965] (Claim 3)

[1966] 10. The system of claim 1, further comprising means for creating and reviewing a treatment plan using the 3D model and presenting the treatment plan in a form that is easy for a user to understand through a virtual medical examination experience.

[1967] "Example 2: Combining Emotion Engines"

[1968] (Claim 1)

[1969] a means for electronically collecting medical image data and patient health data from a medical institution;

[1970] means including an artificial intelligence model for pre-processing and analyzing the medical image data and the health data;

[1971] A means for generating a 3D model based on the analysis results;

[1972] means for visualizing and presenting said 3D model to medical staff;

[1973] A means for recogn...

Claims

1. a means for electronically collecting medical image data and patient health data from a medical institution; means including an artificial intelligence model for pre-processing and analyzing the medical image data and the health data; A means for generating a 3D model based on the analysis results; and a means for visualizing and presenting said 3D model to medical staff.

2. The system of claim 1 , further comprising means for utilizing the 3D model in communication between patients and medical staff.

3. The system of claim 1 , further comprising means for creating and verifying a treatment plan using the 3D model.

Images