Information processing system
The system addresses the issue of inappropriate server selection in ophthalmological image analysis by using a management server to choose the right AI models for image diagnosis based on device and clinical context, enhancing diagnostic accuracy and efficiency.
Patent Information
- Application Number
- JP2024160469
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2019-07-31
- Filing Date
- 2024-09-17
- Publication Date
- 2024-11-21
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
Existing ophthalmological information processing systems fail to consider the appropriate selection of servers based on the device that took the image and the source of the request for image analysis.
An information processing system that includes an image acquisition device, a first information processing device, and a management server that selects and transmits data to appropriate image diagnostic devices based on additional information such as device specifications and clinical context, using artificial intelligence to perform tailored image diagnoses.
Enables accurate and efficient image diagnosis by selecting the most suitable AI models for different types of ophthalmological images, improving diagnostic accuracy and reducing user confusion in server selection.
Smart Images

Figure 2024163350000001_ABST
Abstract
Description
Incorporation by Reference
[0001] This application claims priority to U.S. Provisional Patent Application No. 62 / 880,980, filed July 31, 2019, the contents of which are incorporated herein by reference. [Technical field]
[0002] The present invention relates to an information processing system, an information processing device, an information processing method, and a program. [Background technology]
[0003] An ophthalmological information processing server capable of performing ophthalmological image analysis is known (see Patent Document 1). However, selection of an appropriate ophthalmological information processing server according to the device that captured the image, the source of the request for image analysis, etc. has not been considered in the past. [Prior art documents] [Patent documents]
[0004] [Patent Document 1] Patent No. 5951086 Summary of the Invention
[0005] An information processing system according to one aspect of the invention disclosed in the present application includes an image acquisition device that acquires image data of a patient's test eye, and a first information processing device that is capable of communicating with the image acquisition device and stores the test eye image data. The image acquisition device executes a first transmission process to transmit first transmission data, including the test eye image data and additional information used to identify an image diagnostic device that performs an image diagnosis on the test eye image data, to the first information processing device. Upon receiving the first transmission data from the image acquisition device, the first information processing device executes a storage process to store the test eye image data, an identification process to identify, based on the additional information, at least one of a first image diagnostic device that performs a first image diagnosis on the test eye image data and a second image diagnostic device that performs a second image diagnosis different from the first image diagnosis on the test eye image data, and a second transmission process to transmit second transmission data including the test eye image data to the identified image diagnostic device.
[0006] An information processing system which is one aspect of the invention disclosed in the present application comprises an image acquisition device which acquires image data of a patient's test eye, and a first information processing device which is capable of communicating with the image acquisition device and stores the test eye image data, wherein the image acquisition device executes a first transmission process which transmits first transmission data including the test eye image data and additional information used to identify an artificial intelligence which performs image diagnosis of the test eye image data to the first information processing device, and upon receiving the first transmission data from the image acquisition device, the first information processing device executes a storage process which stores the test eye image data, an identification process which identifies at least one of a first artificial intelligence for performing a first image diagnosis of the test eye image data and a second artificial intelligence which performs a second image diagnosis different from the first image diagnosis of the test eye image data based on the additional information, and a second transmission process which transmits second transmission data including the test eye image data and identification information which identifies the artificial intelligence to an image diagnostic device including the identified artificial intelligence.
[0007] An information processing device which is one aspect of the invention disclosed in the present application comprises a processor and a storage device, wherein the storage device holds image data of a patient's test eye, additional information of the test eye image data, and correspondence information between the additional information and an imaging diagnostic device which performs an imaging diagnosis of the test eye image data, and the processor identifies at least one of a first imaging diagnostic device which performs a first imaging diagnosis on the test eye image data and a second imaging diagnostic device which performs a second imaging diagnosis on the test eye image data which is different from the first imaging diagnosis based on the correspondence information and the additional information of the test eye image data, and transmits transmission data including the test eye image data to the identified imaging diagnostic device.
[0008] An information processing device which is one aspect of the invention disclosed in the present application comprises a processor and a storage device, wherein the storage device holds image data of a patient's test eye, additional information of the test eye image data, and correspondence information between the additional information and an artificial intelligence that performs image diagnosis of the test eye image data, and the processor identifies at least one of a first artificial intelligence for performing a first image diagnosis of the test eye image data and a second artificial intelligence for performing a second image diagnosis different from the first image diagnosis of the test eye image data based on the correspondence information and the additional information of the test eye image data, and transmits second transmission data including identification information identifying the test eye image data and the artificial intelligence to an image diagnostic device including the identified artificial intelligence.
[0009] An information processing method which is one aspect of the invention disclosed in the present application is executed by an information processing device, the information processing device having a processor and a storage device, the storage device holding image data of a patient's test eye, additional information of the test eye image data, and correspondence information between the additional information and an imaging diagnostic device which performs an image diagnosis of the test eye image data, and the information processing method includes the processor identifying at least one of a first imaging diagnostic device which performs a first imaging diagnosis on the test eye image data and a second imaging diagnostic device which performs a second imaging diagnosis on the test eye image data which is different from the first imaging diagnosis based on the correspondence information and the additional information of the test eye image data, and the processor transmitting transmission data including the test eye image data to the identified imaging diagnostic device.
[0010] An information processing method which is one aspect of the invention disclosed in the present application is executed by an information processing device, wherein the information processing device has a processor and a storage device, and the storage device holds image data of a patient's test eye, additional information of the test eye image data, and correspondence information between the additional information and an artificial intelligence that performs image diagnosis of the test eye image data, and in the information processing method, the processor identifies at least one of a first artificial intelligence for performing a first image diagnosis of the test eye image data and a second artificial intelligence for performing a second image diagnosis different from the first image diagnosis of the test eye image data based on the correspondence information and the additional information of the test eye image data, and the processor transmits second transmission data including identification information identifying the test eye image data and the artificial intelligence to an image diagnostic device including the identified artificial intelligence.
[0011] A program which is one aspect of the invention disclosed in the present application is a program for causing an information processing device to execute information processing, the information processing device having a processor and a storage device, the storage device holding image data of a patient's test eye, additional information of the test eye image data, and correspondence information between the additional information and an imaging diagnostic device that performs an imaging diagnosis of the test eye image data, the program causing the processor to execute a process of identifying at least one of a first imaging diagnostic device that performs a first imaging diagnosis on the test eye image data and a second imaging diagnostic device that performs a second imaging diagnosis on the test eye image data, which is different from the first imaging diagnosis, based on the correspondence information and the additional information of the test eye image data, and a process of transmitting transmission data including the test eye image data to the identified imaging diagnostic device.
[0012] A program which is one aspect of the invention disclosed in the present application is a program for causing an information processing device to execute information processing, the information processing device having a processor and a storage device, the storage device holding image data of a patient's test eye, additional information of the test eye image data, and correspondence information between the additional information and an artificial intelligence that performs image diagnosis of the test eye image data, and the program causes the processor to execute a process of identifying at least one of a first artificial intelligence for performing a first image diagnosis of the test eye image data and a second artificial intelligence for performing a second image diagnosis different from the first image diagnosis of the test eye image data based on the correspondence information and the additional information of the test eye image data, and a process of transmitting second transmission data including identification information that identifies the test eye image data and the artificial intelligence to an image diagnostic device including the identified artificial intelligence. [Brief description of the drawings]
[0013] [Figure 1] FIG. 1 is an explanatory diagram illustrating an example of the configuration of an image diagnostic system according to a first embodiment. [Diagram 2] 2 is a block diagram illustrating an example of a hardware configuration of a computer according to the first embodiment. [Diagram 3] 2 is a block diagram illustrating an example of a functional configuration of a management server according to the first embodiment. FIG. [Figure 4] 4 is a block diagram showing an example of a functional configuration of a diagnostic server according to the first embodiment. FIG. [Diagram 5] 3 is a block diagram showing an example of a functional configuration of an in-hospital server according to the first embodiment. FIG. [Figure 6] 3 is a block diagram showing an example of a functional configuration of a terminal according to the first embodiment; FIG. [Figure 7] FIG. 2 is a sequence diagram showing an image diagnosis process of the image diagnosis system in the first embodiment. [Figure 8] 13 is a flowchart illustrating an example of a diagnosis server determination process in the first embodiment. [Figure 9] 13 is a flowchart illustrating an example of a diagnosis server determination process in the first embodiment. [Figure 10] 4 is an example of AI selection information according to the first embodiment. [Figure 11] 3 is an example of a data structure of anonymized diagnostic target data in the first embodiment. [Figure 12] 4 is an example of a display screen that displays a diagnosis result in the first embodiment. [Figure 13] 4 is an example of a display screen that displays a diagnosis result in the first embodiment. [Figure 14] 4 is an example of a display screen that displays a diagnosis result in the first embodiment. [Figure 15] 13 is an example of a display screen displaying a diagnosis result when image diagnosis is performed by a plurality of diagnosis servers in the first embodiment. [Figure 16] FIG. 11 is an explanatory diagram illustrating a configuration example of an image diagnostic system according to a second embodiment. [Figure 17] FIG. 11 is a sequence diagram showing an example of an image diagnosis process of the image diagnosis system in the second embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS
[0014] Hereinafter, an embodiment of the present invention will be described with reference to the accompanying drawings. It should be noted that the embodiment is merely an example for realizing the present invention and does not limit the technical scope of the present invention. The same reference numerals are used to refer to the same components in each drawing. EXAMPLES
[0015] 1 is an explanatory diagram showing a configuration example of an image diagnosis system according to a first embodiment. The image diagnosis system includes a management server 100, a diagnostic server 201, a diagnostic server 202, and a diagnostic server 203. The image diagnosis system also includes an in-hospital server 300, a terminal 400, and an imaging device 500, which are installed in, for example, a hospital, a clinic, or a medical examination facility. The in-hospital server 300, the terminal 400, and the imaging device 500 are each connected via a network.
[0016] The photographing device 500 is an ophthalmic device that photographs the fundus, and examples of such devices include a fundus camera, a scanning laser ophthalmoscope, and an optical coherence tomography. The photographing device 500 is connected to the terminal 400. The photographing device 500 photographs the patient's subject eye and generates fundus image data of the right eye and the left eye of the subject eye. The generated fundus image data is transmitted to the terminal 400.
[0017] The fundus image data may be any one of fundus image data captured by a fundus camera, fundus image data of the fundus captured by a scanning laser ophthalmoscope, and tomographic data of the fundus captured by an optical coherence tomography. Alternatively, the fundus image data set may be a combination of two or more of them. The fundus image data is an example of the subject's eye image data.
[0018] The terminal 400, which is an example of an image acquisition device, is a computer such as a PC (Personal Computer) or a tablet used by a doctor, an operator of an ophthalmologic device, etc. The terminal 400 is connected to the in-hospital server 300. The terminal 400 transmits data, which is an example of first transmission data including fundus image data and additional information, to the in-hospital server 300.
[0019] The additional information includes any one or a combination of device information related to the performance and specifications of the photographing device 500, facility information including the medical department (ophthalmology, internal medicine, diabetes internal medicine, etc.) of the hospital or clinic using the terminal 400, the fee for the diagnostic course, the name of the doctor, etc., and diagnosis type information including the diagnostic mode and the name of the disease to be diagnosed. The field angle, modality, and resolution of the photographed image (subject's eye image) of the photographing device 500, as well as image attribute information including the model number and terminal ID of the photographing device 500, are examples of the device information. The modality is information indicating the type of the photographing device 500 (e.g., fundus camera, scanning laser ophthalmoscope, optical coherence tomograph, etc.) or the type of image as a medical image photographed by the photographing device 500 (e.g., fundus image photographed by a red laser or near-infrared laser, angiography image, etc.). Further, the names of doctors and hospitals that use terminal 400, the locations where the terminals are installed (information on medical departments such as ophthalmology, internal medicine, and diabetic medicine, and information on facilities such as eyeglass stores and health checkup facilities), etc. are examples of facility information.
[0020] The in-hospital server 300, which is an example of an image acquisition device, has a patient information DB (DataBase) 310 that holds patient information, and stores the patient information received from the terminal 400 in the patient information DB 310. The in-hospital server 300 is connected to the management server 100 via a network. The in-hospital server 300 includes the patient information, fundus image data, and additional information received from the terminal 400 in the diagnostic target data, and transmits the diagnostic target data, which is an example of first transmission data, to the management server 100. Note that part or all of the patient information and part or all of the additional information in the diagnostic target data may be generated by the in-hospital server 300.
[0021] The management server 100, which is an example of a first information processing device, generates anonymized diagnostic target data, which is an example of second transmission data, and is diagnostic target data in which part of information (e.g., patient information) of the diagnostic target data received from the in-hospital server 300 has been anonymized. The management server 100 is connected to the diagnostic server 201, the diagnostic server 202, and the diagnostic server 203 via a network. Based on the additional information, the management server 100 selects one of the diagnostic servers 201, 202, and 203 as a diagnostic server that performs image diagnosis of the fundus image data included in the anonymized diagnostic target data, and transmits the anonymized diagnostic target data to the selected diagnostic server.
[0022] The diagnostic servers 201-203, which are all examples of image diagnostic devices, are equipped with AI (Artificial Intelligence) that performs image diagnosis on fundus image data. AI1, AI2, and AI3 installed in the diagnostic servers 201-203 each have different functions (algorithms) (described later). The diagnostic server that receives the anonymized diagnostic target data performs image diagnosis on the fundus image data included in the anonymized diagnostic target data using the installed AI. The diagnosis result is encrypted and transmitted to the in-hospital server 300 and the terminal 400 via the management server 100.
[0023] The following describes an example of each of the diagnostic servers 201 to 203. Here, the fundus images and disease names to be diagnosed by each AI are just examples, and various combinations of fundus images and disease names to be diagnosed are possible.
[0024] The diagnostic server 201, which is an example of an image diagnostic device, is equipped with an AI 221 that performs a diagnosis of diabetic retinopathy on a fundus image captured by an imaging device 500 with a narrow angle of view (angle of view of 30 to less than 100 degrees starting from the center of the eyeball), which is an example of a first angle of view. If the device information in the additional information indicates a narrow angle of view, the management server 100 transmits anonymized diagnostic target data to the diagnostic server 201.
[0025] The diagnostic server 202 is a diagnostic server equipped with an AI 222 that performs a diagnosis of diabetic retinopathy on fundus images captured by an imaging device 500 with a wide angle of view (angle of view of 100 degrees or more and less than 200 degrees starting from the center of the eyeball), either of which is an example of the second angle of view, or a super wide angle of view (angle of view of 200 degrees or more starting from the center of the eyeball). When the device information in the additional information indicates a wide angle of view and the diagnostic mode indicates diabetic retinopathy, the management server 100 transmits anonymized diagnostic target data to the diagnostic server 202.
[0026] The diagnostic server 203 is a diagnostic server equipped with an AI 223 capable of diagnosing not only diabetic retinopathy but also various other fundus diseases, targeting fundus images captured by an ultra-wide-angle (angle of view of 200 degrees or more starting from the center of the eyeball) photographing device 500. When the device information of the additional information indicates an ultra-wide-angle and the facility information indicates an ophthalmologist, the management server 100 transmits anonymized diagnostic target data to the diagnostic server 203.
[0027] 2 is a block diagram showing an example of the hardware configuration of the computers constituting the management server 100, the diagnostic server, the in-hospital server 300, and the terminal 400. The computer 600 has, for example, a processor (CPU) 601, a storage device 602, an input device 603, an output device 604, and a communication I / F (InterFace) 605, which are connected to each other by an internal signal line 606.
[0028] The processor 601 executes a program stored in the storage device 602. The storage device 602 includes a memory. The memory includes a ROM, which is a non-volatile storage element, and a RAM, which is a volatile storage element. The ROM stores immutable programs (e.g., BIOS) and the like. The RAM is a high-speed, volatile storage element such as a DRAM (Dynamic Random Access Memory), and temporarily stores the programs executed by the processor 601 and data used when the programs are executed.
[0029] The storage device 602 also includes an auxiliary storage device. The auxiliary storage device is, for example, a large-capacity non-volatile storage device such as a magnetic storage device (HDD) or a flash memory (SSD), and stores the programs executed by the processor 601 and data used when the programs are executed. In other words, the programs are read from the auxiliary storage device, loaded into the memory, and executed by the processor 601.
[0030] The input device 603 is an interface, such as a keyboard or a mouse, that receives input from an operator. The output device 604 is a device, such as a display or a printer, that outputs the results of program execution in a format that can be viewed by the operator. The input device 603 and the output device 604 may be integrated together, such as a touch panel device. The communication I / F 605 is a network interface device that controls communication with other devices according to a predetermined protocol.
[0031] The programs executed by the processor 601 are provided to the computer 600 via a removable medium (such as a CD-ROM or a flash memory) or a network, and are stored in a non-volatile auxiliary storage device that is a non-transitory storage medium. For this reason, the computer 600 should have an interface for reading data from the removable medium.
[0032] The management server 100, diagnostic server, in-hospital server 300, and terminal 400 are each a computer system configured on a single physical computer 600, or on multiple logically or physically configured computers 600, and may operate in separate threads on the same computer 600, or may operate on virtual computers constructed on multiple physical computer resources.
[0033] 3 is a block diagram showing an example of the functional configuration of the management server 100. The management server 100 includes an anonymization processing unit 101, an AI selection unit 102, a display screen generation unit 103, and a diagnosis result data generation unit 104. The anonymization processing unit 101 anonymizes patient information included in the diagnostic target data transmitted from the in-hospital server 300. The AI selection unit 102 selects an AI that performs image diagnosis on the fundus image data included in the diagnostic target data, based on additional information included in the diagnostic target data.
[0034] The display screen generating unit 103 generates screen information to be displayed on the output device 604. The diagnostic result data generating unit 104 decrypts the encrypted diagnostic result received from the diagnostic server, generates a display screen (FIGS. 12, 13, and 14) showing the diagnostic result, and transmits the information of this display screen to the in-hospital server 300.
[0035] The functional units included in the management server 100 are realized by a processor 601 of a computer 600 that realizes the management server 100. Specifically, the processor 601 functions as the anonymization processing unit 101 by operating according to an anonymization processing program loaded into a memory included in the storage device 602, and functions as the AI selection unit 102 by operating according to an AI selection program loaded into a memory included in the storage device 602. Similarly, other functional units included in the management server 100 and functional units included in other devices are realized by the processor 601 operating according to programs loaded into the memory.
[0036] The management server 100 holds the AI selection information 110. The AI selection information 110 holds correspondence information between the additional information and the diagnostic server 201, the diagnostic server 202, and the diagnostic server 203. As described later, since AI221, AI222, and AI223 each include a different image diagnosis model, the AI selection information 110 can also be said to include correspondence information between the additional information and the image diagnosis model. In the AI selection information 110, a conditional branch based on the value of one or more types of additional information is described, thereby determining an AI corresponding to the additional information. In addition, in the AI selection information 110, the correspondence between the value (or value range) of one or more types of additional information and the AI220 may be described in a table format.
[0037] The AI selection information 110 is stored in an auxiliary storage device included in the storage device 602 of the computer 600 that realizes the management server 100. Similarly, information and DBs held by other devices are stored in an auxiliary storage device included in the storage device 602 of the computer 600 that realizes the other devices.
[0038] In this embodiment, the information used by each device included in the image diagnostic system may be expressed in any data structure without depending on the data structure. For example, the information may be stored in a data structure appropriately selected from a table, a list, a database, or a queue. Various types of information are stored and held in a non-volatile memory or the like.
[0039] Fig. 4 is a block diagram showing an example of the functional configuration of the diagnostic server 201. The functional configurations of the diagnostic servers 201, 202, and 203 differ only in the AI function, and other configurations (such as the display screen generation unit and management unit) have similar functions. Therefore, the functional configuration of the diagnostic server 201 will be described.
[0040] The diagnostic server 201 includes, for example, an image diagnosis unit 2011, a learning information management unit 2021, a diagnostic image generation unit 2031, and a management unit 2041. The diagnostic server 201 also holds a learning DB 2101 and an image diagnosis model 2111. The learning DB 2101 is a DB for constructing the image diagnosis model 2111. The image diagnosis model 2111 is a model that outputs a diagnosis result when image data is input, and targets a fundus image captured by a photographing device 500 with a narrow angle of view (angle of view of 30 to less than 100 degrees starting from the center of the eyeball) and outputs the grade of the diabetic retinopathy symptom as a diagnosis result. In this embodiment, the grade of the diabetic retinopathy symptom is based on the five-stage International Classification of Severity.
[0041] The AI 221 is realized by the image diagnosis unit 2011, the learning information management unit 2021, the learning DB 2101, and the image diagnosis model 2111. The image diagnosis unit 2011 executes image diagnosis using the image diagnosis model 2111 on fundus image data included in the anonymized diagnosis target data received from the management server 100.
[0042] The learning information management unit 2021 stores the subject eye image data and the image diagnosis results included in the anonymized diagnosis target data in the learning DB 210 as learning data for AI, and updates the learning DB 210. The learning information management unit 2021 updates (e.g., optimizes) the image diagnosis model 2111 by learning based on the updated learning DB 2101.
[0043] The diagnostic image generating unit 2031 generates a diagnosed fundus image by superimposing a mark indicating the position of a lesion or letters of the disease name on the diagnosed fundus image. The management unit 2041 manages the AI 221. The diagnosed fundus image is transmitted to the management server 100 together with the diagnosis result.
[0044] The diagnostic server 201 may not have a learning function of the image diagnosis model 2111. That is, the diagnostic server 201 may continue to execute image diagnosis while keeping the predetermined image diagnosis model 2111 fixed without updating the image diagnosis model 2111. In this case, the diagnostic server 201 may not have the learning information management unit 2021 and the learning DB 2101.
[0045] Both diagnostic server 202 and diagnostic server 203 have the same configuration as diagnostic server 201, except that they have an image diagnosis model different from diagnostic server 201.
[0046] The image diagnosis model held by the diagnostic server 202 is a model that outputs a diagnostic result when image data is input, and targets fundus images captured with a wide-angle (angle of view of 100 degrees or more but less than 200 degrees starting from the center of the eyeball) or ultra-wide-angle (angle of view of 200 degrees or more starting from the center of the eyeball) imaging device 500, and outputs the grade of diabetic retinopathy symptoms as the diagnostic result.
[0047] The image diagnosis model held by the diagnostic server 203 is a model that outputs diagnostic results when image data is input, and targets fundus images captured with an ultra-wide-angle (angle of view of 200 degrees or more starting from the center of the eyeball) photographing device 500, and outputs diagnostic results for not only diabetic retinopathy but also various other fundus diseases.
[0048] The image diagnosis units, learning information management units, and learning DBs of the diagnostic servers 202 and 203 are compatible with the image diagnosis models held by them.
[0049] 5 is a block diagram showing an example of the functional configuration of the in-hospital server 300. The in-hospital server 300 includes, for example, an anonymization processing unit 301, a patient information management unit 302, and a display screen generation unit 303. The in-hospital server 300 also holds a patient information DB 310.
[0050] The anonymization processing unit 301 anonymizes patient information included in the diagnostic target data. The patient information management unit 302 stores the patient information included in the diagnostic target data in the patient information DB 310, and acquires patient information from the patient information DB 310 and adds it to the diagnostic target data. The display screen generation unit 303 generates screen information to be displayed on the output device 604. The patient information DB 310 holds patient information.
[0051] 6 is a block diagram showing an example of a functional configuration of the terminal 400. The terminal 400 includes a diagnostic object data generating unit 401, an additional information acquiring unit 402, and a display screen generating unit 403. The diagnostic object data generating unit 401 generates diagnostic object data including patient information, additional information, and image data of the subject's eye. The additional information acquiring unit 402 acquires additional information for selecting an AI (or a diagnostic server having an AI appropriate for diagnosis). The display screen generating unit 403 generates screen information to be displayed on an output device 604.
[0052] Fig. 7 is a sequence diagram showing the image diagnosis process of the image diagnosis system of Example 1. In the example of Fig. 7, a diagnosis server that performs image diagnosis of a fundus image is selected based on the device information of the photographing device 500 and the like.
[0053] First, the diagnostic target data generating unit 401 of the terminal 400 accepts input of patient information via the input device 603 (S701). An ID for identifying a patient, as well as the patient's age, sex, address, medical history, medication history, and interview results, are all examples of patient information. Note that, for patients whose information is already registered in the patient information DB 310, if the input of an ID for identifying the patient is accepted, the input of other patient information can be omitted.
[0054] The diagnostic target data generating unit 401 acquires fundus image data of both eyes of the patient transmitted from the photographing device 500 (S702). In this embodiment, fundus image data of both eyes may be acquired, or fundus image data of only one eye, the left eye or the right eye, may be acquired. The diagnostic target data generating unit 401 generates a right / left eye flag indicating whether the fundus image data is data of both eyes, data of only the right eye, or data of only the left eye. The diagnostic target data generating unit 401 may acquire fundus image data from a device other than the photographing device 500.
[0055] Next, the additional information acquisition unit 402 acquires the additional information (S703). Specifically, for example, the additional information acquisition unit 402 acquires device information from the photographing device 500, or receives input of the hospital or doctor's department that uses the terminal 400, as the additional information.
[0056] The additional information may be stored in advance in the storage device 602 of the terminal 400. Also, for example, the photographing device 500 may embed device information in the fundus image data as metadata, and the additional information acquiring unit 402 may acquire the device information from the fundus image data.
[0057] Next, the diagnostic object data generating unit 401 transmits the diagnostic object data including the patient information, the fundus image data, the right / left eye flag, and the additional information to the management server 100 via the in-hospital server 300 (S704). The patient information managing unit 302 of the in-hospital server 300 stores the patient information received from the terminal 400 in the patient information DB 310.
[0058] If the patient information received from the terminal 400 is insufficient, the patient information management unit 302 may acquire and supplement the patient information by referring to the patient information DB 310. Specifically, for example, if the patient information received from the terminal 400 is only an ID for identifying the patient, the patient information management unit 302 acquires the patient information corresponding to the ID from the patient information DB 310, and transmits the diagnostic target data including the acquired patient information to the management server 100.
[0059] Next, the anonymization processing unit 101 of the management server 100 performs anonymization processing on the patient information included in the received diagnostic target data using a predetermined algorithm (S705). The anonymization processing includes anonymizing the patient ID (replacing it with an ID unique to the fundus image data) and deleting the patient's personal information such as the name and disease name. The anonymization processing unit 101 may anonymize only a part of the patient information (for example, only sensitive information related to privacy). The anonymization processing on the patient information may be performed in advance, for example, by the anonymization processing unit 301 of the in-hospital server 300, before the diagnostic target data is transmitted to the management server 100.
[0060] The AI selection unit 102 of the management server 100 selects at least one of the diagnostic servers 201, 202, and 203 based on the AI selection information 110 and the additional information included in the received diagnostic target data, and transmits the anonymized diagnostic target data (see FIG. 11 described later) including the anonymized patient information, fundus image data, right / left eye flag, and additional information to the selected diagnostic server (here, it is assumed that the diagnostic server 201 is selected) (S706). Details of step S706 will be described later.
[0061] In addition, the AI selection unit 102 may encrypt the anonymized diagnosis target data using an encryption key and then transmit it to the selected diagnostic server 201. In this case, the diagnostic server 201 has a decryption key corresponding to the encryption key, and first decrypts the anonymized diagnosis target data with the decryption key in step S707 described below.
[0062] Next, the image diagnosis unit 2011 of the diagnostic server 201 that has received the anonymized diagnostic target data performs image diagnosis on the fundus image data included in the received anonymized diagnostic target data using an image diagnosis model 2111 that diagnoses diabetic retinopathy using narrow-angle fundus images (S707).
[0063] The learning information management unit 2021 of the diagnosis server 201 updates the learning DB 2101 by storing the fundus image data in the learning DB 2101 as learning data, and updates the image diagnosis model 2111 based on the updated learning DB 2101 (S708). Note that the learning information management unit 2021 may also store the anonymized patient information and additional information in the learning DB 2101 as learning data.
[0064] Next, the management unit 2041 generates image diagnosis result data including at least the anonymized patient information and the image diagnosis result. The image diagnosis result is encrypted using an encryption key held by the diagnosis server 201 to generate an encrypted image diagnosis result, and is transmitted to the management server 100 (S709). The image diagnosis result data may include a diagnosed fundus image in which a mark indicating the position of a lesion or letters indicating the name of a disease are superimposed on the diagnosed fundus image.
[0065] Next, the diagnostic result data generating unit 104 of the management server 100 decrypts the received encrypted image diagnostic result using the decryption key held by the management server 100 (S710). The diagnostic result data generating unit 104 also restores the anonymized patient information. Then, the decrypted image diagnostic result is linked to the patient information of the patient before anonymization.
[0066] Next, the diagnostic result data generating unit 104 generates a display screen (FIG. 12) showing the diagnostic result including the grade of diabetic retinopathy, which is the diagnostic result, assigns a patient ID to it, and stores it in a memory (not shown).
[0067] When the management server 100 receives an encrypted image diagnosis result from the diagnostic server 202, the diagnostic result data generation unit 104 generates a display screen (FIG. 13) showing the diagnosis result. When the management server 100 receives an encrypted image diagnosis result from the diagnostic server 203, the diagnostic result data generation unit 104 generates a display screen (FIG. 14) showing the diagnosis result.
[0068] Next, the diagnostic result data generating unit 104 links the display screen showing the diagnostic result with the patient information and transmits them to the in-hospital server 300 (S711). The display screen generating unit 303 of the in-hospital server 300 displays a display screen based on the received display screen showing the diagnostic result and the patient information on the output device 604 of the in-hospital server 300 (S712). Note that the terminal 400 may acquire the image diagnostic result and the patient information from the in-hospital server 300, and the display screen generating unit 403 of the terminal 400 may display the display screen showing the diagnostic result and the display screen based on the patient information on the output device 604 of the terminal 400.
[0069] In addition, the display screen generation unit 103 of the management server 100 may generate information for the display screen based on the image diagnosis results and patient information and transmit it to the in-hospital server 300, and the in-hospital server 300 and the terminal 400 may display the display screen according to the generated information.
[0070] Fig. 8 is a flowchart showing an example of the diagnostic server determination process in step S706. In the example of Fig. 8, the diagnostic server to which the anonymized diagnostic target data is transmitted is determined based on the angle of view information included in the additional information. First, the AI selection unit 102 of the management server 100 acquires the additional information including the angle of view information from the diagnostic target data (S801).
[0071] The AI selection unit 102 determines whether the angle of view indicated by the angle of view information is a wide angle of view (S802). Specifically, when the angle of view information indicates a specific angle, if the angle is equal to or greater than a predetermined value (e.g., 100 degrees), it is determined to be a wide angle of view, and if the angle is less than the predetermined value, it is determined to be not a wide angle of view (a narrow angle of view).
[0072] Also, for example, the management server 100 may hold device information of each photographing device 500. Specifically, the device information is a lookup table that defines the model number or terminal ID of each photographing device 500 in association with the angle of view, resolution, etc. In this case, the AI selection unit 102 may acquire the model number or terminal ID of the photographing device 500 from the additional information, and refer to the device information to determine whether the angle of view of the photographing device 500 indicated by the model number or terminal ID is a wide angle.
[0073] If the AI selection unit 102 determines that the angle of view indicated by the angle of view information is a wide angle of view (S802: Yes), it transmits the anonymized diagnosis target data to the diagnostic server 202 (S803), and if it determines that the angle of view is not a wide angle of view (S802: No), it transmits the anonymized diagnosis target data to the diagnostic server 201 (S804) and terminates the processing of step S705.
[0074] 8, the AI installed in the diagnostic server 202 can perform highly accurate image diagnosis on a fundus image captured at a wide angle of view, and the AI installed in the diagnostic server 201 can perform highly accurate image diagnosis on an image of the subject's eye captured at a narrow angle of view. This allows the AI selection unit 102 to select an appropriate diagnostic server depending on the angle of view used to capture the image of the subject's eye.
[0075] 8, the AI selection unit 102 determines whether the angle of view indicated by the angle of view information is a wide angle of view, and selects a destination diagnostic server from the two diagnostic servers 201 and 202. The AI selection unit 102 may also determine which of three or more angle of view categories the angle of view indicated by the angle of view information corresponds to, and refer to the AI selection information 110 to select a diagnostic server corresponding to that category.
[0076] 8, the diagnostic server is selected according to the angle of view, but the diagnostic server may be selected using other elements included in the additional information. For example, the AI selection unit 102 may determine the diagnostic server using facility information included in the additional information (the name of the doctor and hospital who uses the terminal 400, the location where the terminal 400 is installed (information on medical departments such as ophthalmology, internal medicine, and diabetic internal medicine, and information on facilities such as eyeglass stores and health checkup facilities), and the fee for the diagnostic course at the hospital or clinic where the terminal 400 is installed).
[0077] At this time, the AI selection unit 102 selects, for example, the diagnostic server 203 if the medical department information is ophthalmology, and selects the diagnostic server 201 if the medical department information is internal medicine. Also, the AI selection unit 102 selects, for example, the diagnostic server 202 or 203 if the fee for the diagnostic course is a predetermined value or more, and selects the diagnostic server 201 if the fee for the diagnostic course is less than the predetermined value.
[0078] Also, assume that there exists a diagnostic server 201 equipped with an AI that diagnoses the onset of a specific disease (e.g., diabetic retinopathy) with high accuracy, and a diagnostic server 203 that comprehensively diagnoses the onset of multiple types of diseases. The additional information includes information indicating the disease to be diagnosed. In this case, the AI selection unit 102 selects, for example, the diagnostic server 201 if the disease to be diagnosed indicated by the additional information is the specific disease, and selects the diagnostic server 203 if the disease to be diagnosed indicated by the additional information is not a specific disease name but a comprehensive diagnosis.
[0079] Also, for example, the diagnostic server 201 is equipped with an AI that performs highly accurate image diagnosis on an image of the subject's eye captured by a fundus camera, and the diagnostic server 202 is equipped with an AI that performs highly accurate image diagnosis on an image of the subject's eye captured by a scanning laser ophthalmoscope. The additional information includes information indicating a modality. In this case, the AI selection unit 102 selects the diagnostic server 201 if the modality indicated by the additional information is a fundus camera, and selects the diagnostic server 202 if the modality indicated by the additional information is a scanning laser ophthalmoscope.
[0080] In this way, the AI selection unit 102 can select a diagnostic server equipped with the most suitable AI from among multiple diagnostic servers based on the additional information. This eliminates the user's confusion and / or worries over which diagnostic server to select, and allows the fundus image data to be sent to an appropriate diagnostic server.
[0081] Fig. 9 is a flow chart showing another example of the diagnostic server determination process in step S706. In Fig. 9, the diagnostic server to which the anonymized diagnostic target data is transmitted is determined based on multiple types of information (field of view information and medical department information) included in the additional information. In other words, it is assumed that the field of view information and medical department information are included in the additional information. The differences from Fig. 8 will be described.
[0082] When the AI selection unit 102 determines that the angle of view indicated by the angle of view information is a wide angle of view (S802: Yes), it determines whether the medical department indicated by the medical department information is ophthalmology or internal medicine (S901). When the AI selection unit 102 determines that the medical department indicated by the medical department information is ophthalmology (S901: ophthalmology), it transmits the anonymized diagnosis target data to the diagnostic server 203 (S803), and when it determines that the medical department is internal medicine (S901: internal medicine), it transmits the anonymized diagnosis target data to the diagnostic server 202 (S902), and ends the processing of step S705.
[0083] 9, the AI installed in the diagnostic server 202 is capable of performing a detailed diagnosis of the symptom level of a specific disease (e.g., diabetic retinopathy) with high accuracy for fundus image data captured with a wide angle of view. The AI installed in the diagnostic server 201 is capable of performing image diagnosis with high accuracy for fundus image data captured with a narrow angle of view. The AI installed in the diagnostic server 203 is capable of diagnosing the onset of multiple types of diseases with high accuracy for fundus image data captured with a wide angle of view.
[0084] This allows the AI selection unit 102 to select an appropriate diagnostic server depending on the photographing angle of view of the subject's eye image and the hospital where the terminal 400 is installed or the medical department of the doctor who uses the terminal 400. In other words, the fundus image data can be sent to an appropriate diagnostic server based on multiple types of information (angle of view information and medical department information) included in the additional information.
[0085] In FIG. 9, all fundus image data captured at a narrow angle of view is transmitted to the diagnostic server 201. However, for image data of the subject's eye captured at a narrow angle of view, conditional branching based on further additional information may also be added to select a destination diagnostic server from among multiple different diagnostic servers.
[0086] In addition, in Fig. 9, one specific diagnostic server is selected from multiple diagnostic servers using two types of additional information, but the correspondence between the additional information and the diagnostic server can be arbitrarily designed according to the characteristics of each AI installed in the diagnostic server. For example, three or more types of additional information may be used, and the diagnostic server can be determined by arbitrary conditional branching using multiple types of additional information.
[0087] FIG. 10 is an example of the AI selection information 110. In the example of FIG. 10, the correspondence between additional information and diagnostic servers is described in a table format. The AI selection information 110 includes, for example, a record number column 1101, an additional information column 1102, and a diagnostic server ID column 1103. The record number column 1101 holds a number for identifying a record of the AI selection information 110. The additional information column 1102 holds one or more types of additional information elements (such as field of view information, modality information, medical department information, and resolution information). The diagnostic server ID column 1103 holds an ID for identifying a diagnostic server that is a destination of anonymized diagnostic target data corresponding to a combination of additional information.
[0088] For example, the AI selection unit 102 acquires additional information in step S706, and transmits the anonymized diagnostic target data to a diagnostic server having a diagnostic server ID corresponding to the acquired additional information in the table of Fig. 10. Note that the conditional branches as shown in Figs. 8 and 9 may be described in a table format as shown in Fig. 10.
[0089] 11 shows an example of the data structure of the anonymized diagnostic target data transmitted from the management server 100 to the diagnostic server. The anonymized diagnostic target data includes, for example, a header 701, DICOM (Digital Imaging and Communications in Medicine) data 702, user data 703, and fundus image data 704.
[0090] The header 701 describes information such as the source and destination of data, and the type of data (medical image, document, e-mail, etc.). The DICOM data 702 describes, for example, the format of a medical image captured by the imaging device 500, information defining a communication protocol between medical devices including the imaging device 500, etc.
[0091] The user data 703 includes, for example, a diagnosis type flag, a right / left eye flag, anonymous patient information, and additional information. The diagnosis type flag is a flag indicating the name of a disease diagnosed by the diagnostic server selected by the AI selection unit 102 (a value that identifies diabetic retinopathy, age-related macular degeneration, and all fundus diseases, etc.). The right / left eye flag is a flag indicating whether the fundus image data 704 is image data of the right eye, image data of the left eye, or image data of both eyes (for example, any value of L, R, or LR). Note that, among the additional information, the contents that may also be described in the DICOM data 702, such as the terminal ID and modality of the photographing device 500, may be described only in the DICOM data 702.
[0092] Fig. 12 is an example of a display screen displaying a diagnosis result by the diagnosis server 201. Fig. 12 shows a display screen (screen layout) when a diagnosis of the symptom level of diabetic retinopathy is performed on the image data of a subject's eye (fundus image) captured at a narrow angle of view.
[0093] The display screen includes a patient information display area 1201, an AI information display area 1202, an additional information display area 1203, and a diagnosis result display area 1204. The patient information display area 1201 displays, for example, patient information included in the image diagnosis data. The AI information display area 1202 displays, for example, the ID of the diagnostic server that performed the image diagnosis and the ID (or version number) of the AI that performed the image diagnosis. The additional information display area 1203 displays, for example, a part or all of the additional information included in the diagnosis target data (angle of view, resolution, diagnosis type, etc.).
[0094] The diagnostic result display area 1204 displays information showing the diagnosis result of the fundus image data by the diagnostic server. In the example of Fig. 12, the diagnostic result display area 1204 displays fundus images of both eyes, bars showing the five-stage symptom level of diabetic retinopathy of both eyes, and findings of both eyes.
[0095] In the example of Fig. 12, a right-pointing arrow (indicator) indicating the image of the right eye and the symptom level of diabetic retinopathy in the right eye is displayed on the right side of the bar, and a left-pointing arrow indicating the image of the left eye and the symptom level of diabetic retinopathy in the left eye is displayed on the left side of the bar. This allows the user to understand the symptom level of diabetic retinopathy in both eyes and the difference in the symptom level just by glancing at the diagnosis result display area 1204. Furthermore, the findings in the diagnosis result display area 1204 are generated by the AI of the diagnosis server. The findings may be input and edited by the user of the terminal 400.
[0096] FIG. 13 is an example of a display screen that displays the diagnosis result by the diagnosis server 202. FIG. 13 is a display screen when a diagnosis of the symptom level of diabetic retinopathy is performed on wide-angle fundus image data captured at a wide angle of view. When a patient suffers from diabetic retinopathy, an abnormality occurs in the peripheral part of the fundus as an early symptom, and then the abnormality spreads to the center. By capturing the fundus at a wide angle of view, wide-angle fundus image data including not only the central part of the fundus but also the peripheral part can be obtained. Therefore, an AI that performs image diagnosis on wide-angle fundus images captured at a wide angle of view can not only estimate the current symptom level of diabetic retinopathy, but also predict the future symptom level taking into account the condition of the peripheral part of the fundus.
[0097] Therefore, in the example of Fig. 13, in addition to the bars showing the current diabetic retinopathy symptom levels of both eyes in five stages, a bar showing the future diabetic retinopathy symptom levels of both eyes is displayed in the diagnosis result display area 1204. Also, the findings in the diagnosis result display area 1204 include predicted conditions in the future (one year later in Fig. 13, but three months later, six months later, etc. may also be used).
[0098] In the example of Figure 13, the current symptom level and the future symptom level are displayed in the diagnosis result display area 1204, but the current symptom level in the central part of the fundus and the current symptom level in the peripheral part may also be displayed in the diagnosis result display area 1204.
[0099] FIG. 14 is an example of a display screen displaying the diagnosis results by the diagnostic server 203. FIG. 14 is a display screen in the case where multiple diseases are diagnosed for wide-angle fundus image data captured with a wide angle of view. One of the multiple diseases is diabetic retinopathy. This is similar to the display of the diagnosis result for diabetic retinopathy in FIG. 13. FIG. 14 further displays bars and arrows (indicators) indicating the symptom categories and progression levels for diseases 2 and 3. Diseases 2 and 3 are fundus diseases that can be identified by the AI 223 of the diagnostic server 203, such as age-related macular degeneration and retinal detachment.
[0100] Below, a modified example of the display screen for displaying the diagnosis result will be described.
[0101] When an imaging diagnosis is performed that can diagnose whether or not a disease has developed, but cannot determine the symptom level of the disease, the diagnosis result display area 1204 may be configured to display information indicating the disease that is suspected to have developed.
[0102] In such a case, the diagnosis result display area 1204 may further display a message recommending image diagnosis by a diagnosis server having an AI capable of diagnosing the specific symptom level of the disease suspected to develop.
[0103] The management server 100 may also store correspondence information between a disease and a diagnostic server equipped with an AI capable of diagnosing the symptom level of the disease. In this case, when the management server 100 receives an instruction to perform image diagnosis according to the message from the in-hospital server 300, it refers to the correspondence information and identifies one of the diagnostic servers that can transmit the diagnostic server equipped with an AI capable of diagnosing the symptom level of the disease. Then, the management server 100 may transmit information indicating the diagnostic server to the in-hospital server 300 to display it, or may transmit the anonymized diagnosis target data to the diagnostic server again and request image diagnosis.
[0104] The image diagnostic system includes a diagnostic server equipped with two AIs: an AI (referred to as AI A) that performs image diagnosis on an image with a low resolution (e.g., a first resolution less than a predetermined value), and an AI (referred to as AI B) that performs image diagnosis on an image with a high resolution (e.g., a second resolution equal to or higher than the predetermined value). In this case, if the diagnosis result by AI A indicates that there is an abnormality in the fundus, a message recommending image diagnosis by AI B using fundus image data with higher resolution may be displayed in the diagnosis result display area 1204. Alternatively, a message recommending photographing with fundus image data with higher resolution may be displayed.
[0105] In addition, anonymized diagnosis target data may be transmitted to multiple diagnostic servers, that is, image diagnosis of fundus image data may be performed by AI with different image diagnosis models. FIG. 15 is an example of a display screen displaying diagnostic results when image diagnosis is performed by multiple diagnostic servers. FIG. 15 is an example of a display screen when a diagnosis of the symptom level of diabetic retinopathy for wide-angle fundus image data taken with a wide angle is performed by two diagnostic servers. In addition, the classification and number of classifications of symptom levels indicating the diagnostic results by these two diagnostic servers are different.
[0106] In this case, for example, as shown in Fig. 15, the diagnostic result display area 1204 displays a first diagnostic result by a diagnostic server equipped with an AI that performs image diagnosis of diabetic retinopathy according to Classification 1 (International Classification of Severity, which classifies diabetic retinopathy into 5 grades) and a second diagnostic result by a diagnostic server equipped with an AI that performs image diagnosis of diabetic retinopathy according to Classification 2 (Modified Davis Classification, which classifies diabetic retinopathy into 3 grades). That is, the symptom levels of diabetic retinopathy according to two different classifications are displayed.
[0107] Also, for example, the display screen generating unit 103 of the management server 100 may generate a symptom level that takes into account symptom levels according to different classifications, and display it as a comprehensive result.
[0108] Specifically, a score corresponding to the symptom level of each classification is determined in advance (for example, in classification 1, No DR is 1 point, Mild is 3 points, ..., in classification 2, A1 is 1 point, A2 is 7 points, ..., etc.), and the display screen generation unit 103 calculates the average of the scores corresponding to the symptom levels for the left and right eyes.
[0109] In addition, in the overall result, a symptom level corresponding to each category of average score (symptom level 1 if 1 point or more and less than 2.5 points, symptom level 2 if 2.5 points or more and less than 5 points, ... etc.) is predefined. The display screen generating unit 103 specifies the symptom level corresponding to the calculated average for each of the left and right eyes, and displays the specified symptom level as the overall result in the diagnosis result display area 1204. This makes it possible to integrate the diagnosis results of the AI that diagnoses diabetic retinopathy using multiple different classifications and present a new index. Note that classification 2 is not limited to the modified Davis classification, and may be the Fukuda classification, etc.
[0110] In this embodiment, the management server 100 determines the diagnostic server that performs image diagnosis of the fundus image data included in the anonymized diagnostic target data, but another device (e.g., the in-hospital server 300, the terminal 400, or the photographing device 500) may determine the diagnostic server. In this case, the other device holds the AI selection information 110. The other device also includes information (e.g., a flag) indicating the determined diagnostic server in the user data 703. EXAMPLES
[0111] A diagnostic server 900 in the image diagnostic system of the second embodiment is equipped with a plurality of AIs 901 to 902. Differences from the first embodiment will be described.
[0112] FIG. 16 is an explanatory diagram showing a configuration example of an image diagnostic system according to a second embodiment. The image diagnostic system is different from the image diagnostic system shown in FIG. 1 in that the diagnostic server 900 is equipped with multiple AIs. For ease of explanation, the image diagnostic system shown in FIG. 16 has one diagnostic server 900, but the image diagnostic system may have multiple diagnostic servers, and some or all of the multiple diagnostic servers may be equipped with multiple AIs. The multiple AIs (two or more AIs including AI901 and AI902) each have a different image diagnostic model.
[0113] The AI selection information 110 of the second embodiment includes information for identifying an AI using additional information transmitted from the in-hospital server 300 or the terminal 400. That is, for example, in Fig. 10, the AI selection information 110 may further include an AI ID field. The AI ID is an ID for identifying an AI that performs image diagnosis of anonymized diagnostic target data corresponding to the value of the additional information.
[0114] Fig. 17 is a sequence diagram showing the image diagnosis processing of the image diagnosis system in the second embodiment. The differences from Fig. 7 will be described. Step S1601 is executed instead of step S702. In step S1601, the AI selection unit 102 of the management server 100 selects at least one AI from multiple AIs (two or three or more AIs including AI901 and AI902) based on the AI selection information 110 and additional information included in the received diagnostic target data.
[0115] Further, in step S1601, the AI selection unit 102 includes AI information (e.g., the AI ID) indicating the selected AI 220 in the user data 703, and transmits the anonymized diagnostic target data including the user data 703 to a diagnostic server equipped with the selected AI 220.
[0116] Next, the management unit of the diagnostic server that has received the anonymized diagnostic target data selects the AI 220 indicated by the AI information included in the anonymized diagnostic target data, and inputs the fundus image data included in the anonymized diagnostic target data to the selected AI 220 (S1602). Next, the process proceeds to step S707.
[0117] In the second embodiment, the management server 100 determines the AI to perform image diagnosis of the fundus image data included in the anonymized diagnosis target data, but another device (e.g., the diagnosis server 900, the in-hospital server 300, the terminal 400, or the photographing device 500) may determine the AI. In this case, the other device holds the AI selection information 110. In addition, the other device includes information (e.g., a flag) indicating the determined AI in the user data 703.
[0118] However, when the diagnostic server 900 decides on an AI, it is desirable to transmit the anonymized diagnostic target data to all diagnostic servers, since the management server 100 cannot determine which diagnostic server 900 has the appropriate AI. Then, the diagnostic server 900 that has received the anonymized diagnostic target data refers to the AI selection information 110 and determines whether or not the AI installed in the diagnostic server can perform image diagnosis of the fundus image data. Then, if the diagnostic server is equipped with an AI that can perform image diagnosis, it returns the diagnosis result by the AI to the management server 100.
[0119] The present invention is not limited to the above, and may be implemented in any combination thereof. In addition, other embodiments that are conceivable within the scope of the technical concept of the present invention are also included in the scope of the present invention. [Explanation of symbols]
[0120] 100 Management server, 101 Anonymization processing unit, 102 AI selection unit, 103 Display screen generation unit, 104 Diagnostic result data generation unit, 110 AI selection information, 201 Diagnostic server, 2011 Image diagnosis unit, 300 In-hospital server, 301 Anonymization processing unit, 302 Patient information management unit, 303 Display screen generation unit, 310 Patient information DB, 400 Terminal, 401 Diagnostic target data generation unit, 402 Additional information acquisition unit, 403 Display screen generation unit, 600 Computer, 601 Processor, 602 Storage device, 603 Input device, 604 Output device, 605 Communication I / F, 900 Diagnostic server, 2021 Learning information management unit, 2031 Diagnostic image generation unit, 2041 Management unit, 2101 Learning DB, 2111 Image diagnosis model
Claims
[Claim 1] An image acquisition device for acquiring image data of a patient's eye to be examined; a first information processing device capable of communicating with the image acquisition device and storing the subject's eye image data, The image acquisition device includes: execute a first transmission process of transmitting first transmission data, which includes the test eye image data and additional information used to specify an image diagnostic apparatus that performs image diagnosis on the test eye image data, to the first information processing device; The first information processing device is a storage process for storing the subject's eye image data when the first transmission data is received from the image acquisition device; a process of identifying at least one of a first diagnostic imaging apparatus that performs a first image diagnosis on the subject's eye image data and a second diagnostic imaging apparatus that performs a second image diagnosis different from the first image diagnosis on the subject's eye image data, based on the additional information; and a second transmission process of transmitting second transmission data including the test eye image data to the specified imaging diagnostic apparatus.
Citation Information
Patent Citations
Remote image reading system, its method, method for storing and managing medical image, and medical image server
JP2002329190A
Coordinated diagnosis system
JP2003323496A
Remote diagnostic reading system and remote diagnostic reading method
JP2014048824A
Information processing system and method for controlling the same, information processing apparatus, and program
JP2018139139A
Ophthalmic information processing system, ophthalmic information processing server, and ophthalmic information processing method
JP5951086B2
