Apparatus and method for constructing biomarkers based on data obtained before and during surgery

The biomarker construction device and method leverage pre- and intra-surgical data to create biomarkers for precise surgical difficulty prediction and outcome evaluation, enhancing surgical planning and prognosis.

WO2026235343A1PCT designated stage Publication Date: 2026-11-12HUTOM CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
PCT/KR2026/005845
Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
Priority Date
2025-05-08
Filing Date
2026-05-06
Publication Date
2026-11-12

AI Technical Summary

Technical Problem

Existing processes fail to effectively utilize data acquired before and during surgery to establish biomarkers for predicting surgical difficulty and evaluating surgical outcomes.

Method used

A biomarker construction device and method that uses medical and surgical image data to create biomarkers, predicting surgical difficulty and evaluating surgical outcomes by analyzing vascular deformation, body fat characteristics, tumor size and location, surgical workflow, and other factors.

Benefits of technology

Enables objective and accurate prediction of surgical difficulty and evaluation of surgical outcomes using biomarkers, improving surgical planning and prognosis prediction.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure KR2026005845_12112026_PF_FP_ABST
    Figure KR2026005845_12112026_PF_FP_ABST
Patent Text Reader

Abstract

Provided are an apparatus and method for constructing biomarkers based on surgery-related data. The apparatus comprises: a communication unit; a memory storing at least one process for constructing biomarkers on the basis of surgery-related data; and a processor performing an operation according to the process, wherein the processor constructs a first biomarker on the basis of medical image data received from a hospital server through the communication unit before surgery, constructs a second biomarker on the basis of surgical image data for a surgery procedure received from the hospital server through the communication unit during or after surgery, and performs surgical difficulty prediction and surgical evaluation / prognosis prediction on the basis of at least one of the first biomarker and the second biomarker.
Need to check novelty before this filing date? Find Prior Art

Description

Device and method for constructing biomarkers based on data acquired before and during surgery

[0001] The present disclosure relates to an apparatus and method for establishing biomarkers based on data acquired before and during surgery.

[0002] When a patient visits a hospital, a series of processes proceed sequentially, such as undergoing various tests, receiving a diagnosis, and undergoing surgery to treat the disease. Various data can be obtained from each of these processes.

[0003] In particular, with the recent advancement of technology, it has become possible to film the entire surgical process.

[0004] However, there is a lack of processes to utilize the various data acquired before and during surgery, either individually or in combination.

[0005] The embodiments disclosed in this disclosure aim to provide an apparatus and method for establishing biomarkers based on data acquired before and during surgery.

[0006] The problems that this disclosure aims to solve are not limited to those mentioned above, and other unmentioned problems will be clearly understood by a person skilled in the art from the description below.

[0007] A biomarker construction device based on data acquired before and during surgery according to one aspect of the present disclosure for achieving the aforementioned technical problem comprises a communication unit, a memory storing at least one process for constructing a biomarker based on data acquired before and during surgery, and a processor that performs an operation according to said process. The processor can construct a first biomarker based on medical image data received from a hospital server via the communication unit before surgery, construct a second biomarker based on surgical image data regarding the surgical process received from the hospital server via the communication unit during or after surgery, and perform surgery difficulty prediction and surgery evaluation / prognosis prediction based on at least one of the first biomarker and the second biomarker.

[0008] In addition, the first biomarker may include vascular deformation, body fat characteristics, the size and arrangement relationship between the target organ and surrounding organs, the size and location of the tumor, and the relationship between the tumor and surrounding lymph nodes.

[0009] In addition, the processor predicts the surgical difficulty through the quantification of each of the vascular deformation, body fat characteristics, the size and arrangement relationship between the target organ and surrounding organs, the size and location of the tumor, and the relationship between the tumor and surrounding lymph nodes, and the surgical difficulty may be predicted differently depending on the characteristics of the patient group including the patient.

[0010] In addition, the above surgery includes a plurality of phases having a sequential order, and each of the plurality of phases may include a plurality of actions.

[0011] Additionally, the second biomarker includes a surgical workflow, errors and events, an organ, a surgical tool, action efficiency, tissue adhesions of the organ, and a camera, and the surgical workflow, errors and events, the organ, the surgical tool, action efficiency, tissue adhesions of the organ, and the camera may each include at least one detailed classification item.

[0012] Additionally, the detailed classification items of the surgical workflow may include the total surgery time and the time for each of the plurality of phases, and the number of interruptions for each of the plurality of phases; the detailed classification items of errors and events may include the number and time of occurrence of errors and events for each of the plurality of phases, the number and time of actions caused by the errors and events for each of the plurality of phases, and the level of the errors and events for each of the plurality of phases; the detailed classification items of action efficiency may include the number and time of specific actions for each of the plurality of phases; and the detailed classification items of adhesion between organ tissues may include the number and time of occurrence of adhesion between organ tissues for each of the plurality of phases, and the level of adhesion between organ tissues for each of the plurality of phases.

[0013] Additionally, the processor performs the surgical evaluation by comparing the surgical plan predicted based on the first biomarker with the surgical tool movement analyzed based on the second biomarker, and the surgical plan may include a tool used in each action of each phase during the actual surgery and the movement path of the tool.

[0014] In addition, the processor can perform the prognosis prediction using medical image data received prior to the surgery, medical image data taken after a preset period has elapsed following the surgery, and surgical results analyzed based on the second biomarker.

[0015] In addition, a method for constructing biomarkers based on data acquired before and during surgery according to another aspect of the present disclosure for achieving the aforementioned technical challenge may include the steps of constructing a first biomarker based on medical image data received from a hospital server before surgery, constructing a second biomarker based on surgical image data regarding the surgical process received from the hospital server during or after surgery, and performing a surgical difficulty prediction and surgical evaluation / prognosis prediction based on at least one of the first biomarker and the second biomarker.

[0016] In addition, a computer program stored on a computer-readable recording medium for executing a method for implementing the present disclosure may be further provided.

[0017] In addition, a computer-readable recording medium for recording a computer program for executing a method for implementing the present disclosure may be further provided.

[0018] According to the aforementioned means for solving the problem of the present disclosure, by using biomarkers extracted from data obtained before surgery or biomarkers obtained from surgical images capturing the surgical process, or by using both together, it is possible to predict the difficulty of surgery in an objective and accurate manner compared to the conventional method in which a physician predicts the difficulty of surgery based on their own clinical knowledge.

[0019] In addition, by using biomarkers extracted from data acquired prior to surgery or biomarkers obtained from surgical images capturing the surgical process, either individually or in combination, surgical evaluation and patient prognosis prediction can be performed, thereby enabling the verification of the basis for such evaluation and prediction using objective indicators.

[0020] The effects of the present disclosure are not limited to those mentioned above, and other unmentioned effects will be clearly understood by a person skilled in the art from the description below.

[0021] FIG. 1 is a drawing for explaining a biomarker construction device based on data acquired before and during surgery according to one embodiment of the present disclosure.

[0022] FIG. 2 is a diagram illustrating the overall flow of a prediction service using biomarkers according to one embodiment of the present disclosure.

[0023] FIG. 3 is a flowchart of a method for constructing biomarkers based on data acquired before and during surgery according to one embodiment of the present disclosure.

[0024] FIG. 4 is a drawing for explaining the steps of surgery according to one embodiment of the present disclosure.

[0025] FIG. 5 is a diagram illustrating a second biomarker extracted through a surgical image according to one embodiment of the present disclosure.

[0026] Throughout this disclosure, the same reference numerals denote the same components. This disclosure does not describe all elements of the embodiments, and general content in the art to which this disclosure pertains or content that overlaps between embodiments is omitted. The terms “part, module, component, block” as used in the specification may be implemented in software or hardware, and depending on the embodiments, a plurality of “parts, modules, components, blocks” may be implemented as a single component, or a single “part, module, component, block” may include a plurality of components. Throughout the specification, when a part is described as being “connected” to another part, this includes not only direct connection but also indirect connection, and indirect connection includes connection via a wireless communication network.

[0027] Furthermore, when it is stated that a part "includes" a certain component, this means that, unless specifically stated otherwise, it does not exclude other components but may include additional components.

[0028] Throughout the specification, when it is stated that a component is located "on" another component, this includes not only cases where a component is in contact with another component, but also cases where another component exists between the two components.

[0029] The terms first, second, etc. are used to distinguish one component from another, and the components are not limited by the aforementioned terms.

[0030] Singular expressions include plural expressions unless there is an obvious exception in the context.

[0031] In each step, identification codes are used for convenience of explanation and do not describe the order of the steps; the steps may be performed differently from the specified order unless a specific order is clearly indicated in the context.

[0032] The operating principles and embodiments of the present disclosure will be described below with reference to the attached drawings.

[0033] Prior to the explanation, the meanings of the terms used in this specification are briefly explained. However, since the explanation of terms is intended to aid in understanding this specification, it should be noted that unless explicitly stated as a limiting factor, they are not used to limit the technical scope of this disclosure.

[0034] In this specification, the term "device" includes all various devices capable of performing computational processing and providing results to a user. For example, a device may include a computer, a server device, and a portable terminal, or be any one of these forms.

[0035] Here, the computer may include, for example, a notebook, desktop, laptop, tablet PC, slate PC, etc. equipped with a web browser.

[0036] The above server device is a server that processes information by communicating with an external device, and may include an application server, a computing server, a database server, a file server, a game server, a mail server, a proxy server, and a web server.

[0037] The above portable terminal may include, for example, all types of handheld-based wireless communication devices such as PCS (Personal Communication System), GSM (Global System for Mobile communications), PDC (Personal Digital Cellular), PHS (Personal Handyphone System), PDA (Personal Digital Assistant), IMT (International Mobile Telecommunication)-2000, CDMA (Code Division Multiple Access)-2000, W-CDMA (W-Code Division Multiple Access), WiBro (Wireless Broadband Internet) terminals, smartphones, etc., as well as wearable devices such as watches, rings, bracelets, anklets, necklaces, glasses, contact lenses, or head-mounted devices (HMDs).

[0038] Functions related to artificial intelligence according to the present disclosure are operated through a processor and memory. The processor may be composed of one or more processors. In this case, the one or more processors may be general-purpose processors such as CPUs, APs, and DSPs (Digital Signal Processors), graphics-dedicated processors such as GPUs and VPUs (Vision Processing Units), or artificial intelligence-dedicated processors such as NPUs. The one or more processors control the processing of input data according to predefined operation rules or artificial intelligence models stored in memory. Alternatively, if the one or more processors are artificial intelligence-dedicated processors, the artificial intelligence-dedicated processors may be designed with a hardware structure specialized for processing a specific artificial intelligence model.

[0039] The predefined rules of operation or artificial intelligence models are characterized by being created through learning. Here, being created through learning means that a predefined rules of operation or artificial intelligence models configured to perform a desired characteristic (or objective) are created by a basic artificial intelligence model being trained using a number of training data by a learning algorithm. Such learning may be performed on the device itself where the artificial intelligence according to the present disclosure is executed, or it may be performed through a separate server and / or system. Examples of learning algorithms include supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning, but are not limited to the examples described above.

[0040] An artificial intelligence model may be composed of multiple neural network layers. Each of the multiple neural network layers has multiple weight values ​​and performs neural network operations through operations between the results of previous layers and the multiple weights. The multiple weights possessed by the multiple neural network layers can be optimized based on the learning results of the artificial intelligence model. For example, the multiple weights may be updated so that the loss value or cost value obtained from the artificial intelligence model during the learning process is reduced or minimized. The artificial neural network may include a Deep Neural Network (DNN), such as a Convolutional Neural Network (CNN), Deep Neural Network (DNN), Recurrent Neural Network (RNN), Restricted Boltzmann Machine (RBM), Deep Belief Network (DBN), Bidirectional Recurrent Deep Neural Network (BRDNN), or Deep Q-Networks, but is not limited to the examples mentioned above.

[0041] The processor can create a neural network, train (or learn) a neural network, perform operations based on received input data, generate an information signal based on the results of the operation, or retrain the neural network.

[0042] Neural networks include CNN (Convolutional Neural Network), RNN (Recurrent Neural Network), perceptron, multilayer perceptron, FF (Feed Forward), RBF (Radial Basis Network), DFF (Deep Feed Forward), LSTM (Long Short Term Memory), GRU (Gated Recurrent Unit), AE (Auto Encoder), VAE (Variational Auto) Encoder), DAE (Denoising Auto Encoder), SAE (Sparse Auto Encoder), MC (Markov Chain), HN (Hopfield Network), BM (Boltzmann Machine), RBM (Restricted Boltzmann Machine), DBN (Depp Belief Network), DCN (Deep Convolutional Network), DN (Deconvolutional Network), DCIGN (Deep Convolutional Inverse Graphics Network), GAN (Generative Adversarial Network), LSM (Liquid State Machine), ELM (Extreme Learning Machine), ESN (Echo It will be understood by a person skilled in the art that any neural network may be included, but is not limited to, State Network, Deep Residual Network, Differential Neural Computer, Neural Turning Machine, Capsule Network, Kohonen Network, and Attention Network.

[0043] According to an exemplary embodiment of the present disclosure, the processor comprises a Convolutional Neural Network (CNN) such as GoogleNet, AlexNet, VGG Network, Region with Convolutional Neural Network (R-CNN), Region Proposal Network (RPN), Recurrent Neural Network (RNN), Stacking-based Deep Neural Network (S-DNN), State-Space Dynamic Neural Network (S-SDNN), Deconvolution Network, Deep Belief Network (DBN), Restructured Boltzmann Machine (RBM), Fully Convolutional Network, Long Short-Term Memory (LSTM) Network, Classification Network, Generative Modeling, eXplainable AI, Continual AI, Representation Learning, AI for Material Design, BERT, SP-BERT, MRC / QA, Text Analysis, Dialog System, GPT-3, GPT-4 for Natural Language Processing, Visual Analytics, Visual Understanding, Video Synthesis for Vision Processing, Anomaly Detection, Prediction, Time-Series Forecasting, Optimization for ResNet Data Intelligence, Various artificial intelligence structures and algorithms, such as recommendation and data creation, may be used, but are not limited thereto.

[0044] Hereinafter, embodiments of the present disclosure will be described in detail with reference to the attached drawings.

[0045] FIG. 1 is a drawing for explaining a biomarker construction device based on data acquired before and during surgery according to one embodiment of the present disclosure.

[0046] A biomarker construction device based on data acquired before and during surgery according to one embodiment of the present disclosure (hereinafter, biomarker construction device) (10) can construct a first biomarker using medical image data taken before surgery and construct a second biomarker using surgical image data taken during surgery.

[0047] The biomarker construction device (10) can predict the difficulty of a patient's surgery and plan and recommend a surgery plan using the first biomarker. At this time, the difficulty of the surgery or the surgery plan can be predicted or recommended by using at least one of the patient's basic information, diagnostic information, medical imaging data, and electronic medical record (EMR) data obtained before surgery together with the first biomarker.

[0048] The biomarker construction device (10) can perform surgery evaluation and patient prognosis prediction using the second biomarker. At this time, the surgery evaluation or patient prognosis prediction can be performed using at least one of the following: basic patient information, diagnostic information, medical imaging data, and electronic medical record (EMR) data obtained before surgery, along with the second biomarker, and basic information, diagnostic information, medical imaging data, and electronic medical record (EMR) data obtained after a preset time has elapsed after surgery.

[0049] The hospital server (20) may store all information or data related to the patient and all information or data related to the surgery. The hospital server (20) may provide necessary information or data to the biomarker building device (10) upon request from the biomarker building device (10).

[0050] The hospital server (20) can receive the difficulty and plan for the patient's surgery from the biomarker construction device (10) before the patient's surgery. Through this, the doctor can check the difficulty of the patient's upcoming surgery through quantitative figures and determine how to proceed with the surgery.

[0051] The hospital server (20) can receive an evaluation of the patient's surgery and the patient's prognosis from the biomarker construction device (10) during or after the patient's surgery. Through this, the doctor can objectively evaluate the surgery they are currently performing or have performed using objective indicators and determine how those indicators affect the patient's prognosis.

[0052] The hospital server (20) may be a computer installed in the hospital, or a laptop, tablet PC, mobile phone, etc. used by a doctor in the hospital.

[0053] Referring to FIG. 1, the biomarker construction device (10) may include a communication unit (11), a memory (12), and a processor (13). The processor (13) may include a first biomarker construction module (131), a second biomarker construction module (132), and a prediction module (133). However, in some embodiments, the biomarker construction device (10) and the processor (13) may include fewer or more components than the components shown in FIG. 1.

[0054] The communication unit (11) may include one or more modules that enable wireless or wired communication between the biomarker construction device (10) and the hospital server (20), and between the biomarker construction device (10) and the communication network. For example, it may include at least one of a wired communication module, a wireless communication module, a short-range communication module, and a location information module.

[0055] Various types of communication networks may be used, for example, wireless communication methods such as WLAN (Wireless LAN), Wi-Fi, Wibro, Wimax, and HSDPA (High Speed ​​Downlink Packet Access), or wired communication methods such as Ethernet, xDSL (ADSL, VDSL), HFC (Hybrid Fiber Coax), FTTC (Fiber to The Curb), and FTTH (Fiber to The Home).

[0056] Meanwhile, the communication network is not limited to the communication method presented above, and may include all forms of communication methods that are widely known or will be developed in the future, in addition to the communication method described above.

[0057] The wired communication module may include various wired communication modules such as a Local Area Network (LAN) module, a Wide Area Network (WAN) module, or a Value Added Network (VAN) module, as well as various cable communication modules such as USB (Universal Serial Bus), HDMI (High Definition Multimedia Interface), DVI (Digital Visual Interface), RS-232 (recommended standard 232), power line communication, or POTS (plain old telephone service).

[0058] In addition to Wi-Fi modules and WiBro (Wireless broadband) modules, the wireless communication module may include wireless communication modules that support various wireless communication methods such as GSM (global System for Mobile Communication), CDMA (Code Division Multiple Access), WCDMA (Wideband Code Division Multiple Access), UMTS (universal mobile telecommunications system), TDMA (Time Division Multiple Access), LTE (Long Term Evolution), 4G, 5G, and 6G.

[0059] The short-range communication module is for short-range communication and can support short-range communication by using at least one of Bluetooth™, RFID (Radio Frequency Identification), Infrared Data Association (IrDA), UWB (Ultra Wideband), ZigBee, NFC (Near Field Communication), Wi-Fi (Wireless-Fidelity), Wi-Fi Direct, and Wireless USB (Wireless Universal Serial Bus) technologies.

[0060] The memory (12) may store at least one process for establishing a biomarker based on data acquired before and during surgery.

[0061] The memory (12) can store data supporting various functions of the biomarker construction device (10) and programs for the operation of the processor (13), and can store input / output data (e.g., music files, still images, videos, etc.), and can store a number of application programs (or applications) running on the biomarker construction device (10), data for the operation of the biomarker construction device (10), and commands. At least some of these application programs can be downloaded from an external server via wireless communication.

[0062] Such memory (12) may include at least one type of storage medium among flash memory type, hard disk type, SSD type (Solid State Disk type), SSD type (Silicon Disk Drive type), multimedia card micro type, card type memory (e.g., SD or XD memory, etc.), RAM (random access memory; RAM), SRAM (static random access memory), ROM (read-only memory; ROM), EEPROM (electrically erasable programmable read-only memory), PROM (programmable read-only memory), magnetic memory, magnetic disk, and optical disk. Additionally, the memory (12) may be a database that is separated from the biomarker construction device (10) but connected via wired or wireless connection.

[0063] The processor (13) may perform the aforementioned operation using data stored in the memory, which stores data for an algorithm or a program that reproduces the algorithm for controlling the operation of components within the biomarker construction device (10). At this time, the memory (12) and the processor (13) may each be implemented as separate chips. Alternatively, the memory (12) and the processor (13) may be implemented as a single chip.

[0064] The virtual body model generation module (131) of the processor (13) can generate a first virtual body model based on the patient's medical imaging data. Here, the first virtual body model is the patient's organ

[0065] Here, medical imaging data may be scan images obtained by scanning a patient's body (e.g., CT (computer tomography) images), but is not limited thereto, and may also be other imaging data such as Magnetic Resonance Imaging (MRI) and Positron Emission Tomography (PET) images in addition to CT images.

[0066] The first biomarker construction module (131) of the processor (13) can construct a first biomarker using medical image data taken before surgery.

[0067] The second biomarker construction module (132) of the processor (13) can construct a second biomarker using surgical image data taken during surgery.

[0068] The prediction module (133) of the processor (13) can predict the difficulty of the surgery and the surgery plan based on at least one of the first biomarker and the second biomarker, and can perform surgery evaluation and predict the patient's prognosis.

[0069] In addition, the processor (13) can control one or a combination of the components described above in order to implement various embodiments according to the present disclosure described in FIGS. 2 to 5 below on the biomarker construction device (10).

[0070] Hereinafter, with reference to FIGS. 2 to 5, a method for constructing first and second biomarkers based on data acquired before and during surgery will be described in detail.

[0071] FIG. 2 is a diagram illustrating the overall flow of a prediction service using biomarkers according to one embodiment of the present disclosure.

[0072] FIG. 3 is a flowchart of a method for constructing biomarkers based on surgery-related data obtained before, during, or after surgery according to one embodiment of the present disclosure.

[0073] FIG. 4 is a drawing for explaining the steps of surgery according to one embodiment of the present disclosure.

[0074] FIG. 5 is a diagram illustrating a second biomarker extracted through a surgical image according to one embodiment of the present disclosure.

[0075] For convenience of explanation, each step is described below as being performed by the processor (13), but each step can be understood as being performed by any one of the first biomarker construction module (131), second biomarker construction module (132), prediction module (133) and modules not shown in FIG. 1 included in the processor (13).

[0076] First, with reference to FIG. 2, the overall flow of the service of the present disclosure will be described.

[0077] Patients visit a hospital to undergo examinations and diagnoses, and the service of the present disclosure can perform patient analysis through basic patient information, diagnostic information, medical imaging data, EMR data, etc. obtained during this pre-operative process (visit, examination, and diagnosis). Through patient analysis, the difficulty of the surgery for the patient can be predicted and a surgical plan can be predicted.

[0078] Here, basic information may include, but is not limited to, the patient's age, gender, weight, height, BMI, smoking status, drinking status, dietary habits, etc.

[0079] Diagnostic information may include, but is not limited to, the patient's diagnosed disease name, date of initial diagnosis, number of treatments, etc.

[0080] Medical imaging data may be scan images obtained by scanning a patient's body (e.g., computer tomography (CT) images, but is not limited thereto), and may also be other imaging data such as magnetic resonance imaging (MRI) and positron emission tomography (PET) images in addition to CT images.

[0081] The physician proceeds with the surgery by referring to the surgical difficulty and surgical plan, and the service of the present disclosure can perform surgical analysis using surgical video data acquired during such surgery. Through surgical analysis, the surgery can be evaluated and the patient's prognosis can be predicted.

[0082] Here, surgical video data may be video data in which the entire process of the surgery, from start to finish, is captured in real time. It may be captured by a device (camera) installed in the operating room, or by a device (camera) worn or carried by a doctor in the operating room.

[0083] However, although Figure 2 describes the prediction of surgical difficulty as being performed before surgery through patient analysis, it is not limited to this, and the prediction of surgical difficulty can be performed during or after surgery using surgical image data.

[0084] Referring to FIG. 3, the processor (13) of the biomarker construction device (10) can construct a first biomarker based on the patient's medical image data received from the hospital server (20) before surgery (S310).

[0085] Here, the first biomarker is information extracted from data acquired prior to surgery and can be used to provide a pre-operative prediction service to the physician.

[0086] The first biomarker may include, but is not limited to, vascular deformation, body fat characteristics, the size and arrangement relationship between the target organ and surrounding organs, the size and location of the tumor, and the relationship between the tumor and surrounding lymph nodes, and various items may be used as the first biomarker.

[0087] Vascular variation can be an indicator of the arrangement of blood vessels according to the patient's body structure. Vascular variation is a feature obtainable through a patient's virtual body model generated using the patient's medical imaging data.

[0088] Here, the virtual body model can be generated based on 3D modeling data generated for each of the organ to be operated on (target organ) and adjacent or connected surrounding organs and blood vessels using an artificial intelligence-based 3D model.

[0089] Body fat characteristics can serve as indicators of a patient's visceral fat, subcutaneous fat, and muscle. Body fat characteristics are features that allow identification of the boundaries and respective volumes of the patient's visceral fat, subcutaneous fat, and muscle.

[0090] Specifically, the processor (13) can extract the volume of subcutaneous fat, the volume ratio of subcutaneous fat, and the volume perimeter of subcutaneous fat using an artificial intelligence-based extraction model, extract the volume of visceral fat, the volume ratio of visceral fat, and the volume perimeter of visceral fat, and extract the volume of muscle, the volume ratio of muscle, and the volume perimeter of muscle.

[0091] The size and arrangement relationship between the target organ and surrounding organs is a feature that can determine the size of the target organ containing cancer cells (tumor), the size of the surrounding organ adjacent to the target organ, the location of the surrounding organ relative to the target organ, and the distance between them.

[0092] Tumor size and location are features that allow one to determine the size of the cancer cells (tumor) and where they are located within the target organ.

[0093] The relationship between the tumor and surrounding lymph nodes is a feature that allows verification of the distance between cancer cells (tumor) and surrounding lymph nodes.

[0094] Referring to FIG. 3, the processor (13) of the biomarker construction device (10) can construct a second biomarker based on surgical video data of the surgical process received from the hospital server during or after surgery (S320).

[0095] Here, the second biomarker is information extracted from data acquired during or after surgery (surgical video capturing the surgical process) and can be used to provide post-operative prediction services to the doctor.

[0096] As illustrated in FIG. 5, the second biomarker may include surgical workflow, surgical error / event, organ, surgical instrument, optimal action, adhesion between organ tissues, and camera.

[0097] The above surgical workflow, the above errors and events, the above organ, the above surgical tool, the above action efficiency, the adhesion between tissues of the organ, and the above camera may each include at least one detailed classification item.

[0098] Detailed classification items of the surgical workflow may include the total surgery time, the time for each of the plurality of phases, and the number of interruptions for each of the plurality of phases.

[0099] The surgical workflow is a characteristic used to determine the total time from the start to the end of the surgery, the time spent in each phase, and the number of interruptions; the number of interruptions per phase refers to cases where the current action among the multiple actions included in each phase was stopped and the process returned to the previous action.

[0100] Detailed classification items for errors and events may include the number and duration of occurrence of errors and events by the plurality of phases, the number and duration of operations caused by the errors and events by the plurality of phases, and the level of the errors and events by the plurality of phases.

[0101] Errors and events are features for identifying the number and time of occurrence of errors and events (e.g., bleeding) per phase, for identifying the number and time of actions performed to stop bleeding per phase, and for identifying the location, cause, characteristics, and recovery status of bleeding per phase.

[0102] The detailed classification items for organs may include the appearance of organs in each of the aforementioned multiple phases, the number of organ contacts, and the time.

[0103] Organs are features used to determine whether a specific organ appears in each phase, and to determine the number of times and the time a specific tool contacts that organ in each phase.

[0104] The detailed classification items of the surgical tool may include the use of the tool in each of the above multiple phases, the number of times and time the tool is used, the trajectory of the tool's movement, the cumulative path length, the partial path length, the speed, and the center.

[0105] The surgical tool is a feature for determining which tool was used in each phase, a feature for determining the number of times and time the tool was used in each phase, and a feature for determining the trajectory, cumulative path length, partial path length, speed, and center of the tool in each phase.

[0106] The detailed classification items of action efficiency may include the number of operations and time of specific actions for each of the aforementioned multiple phases.

[0107] Action efficiency is a feature for determining the number of times and time a pre-set action (e.g., the action in the 8th sequence) is performed for each phase.

[0108] The detailed classification items for inter-tissue adhesions of organs may include the level of inter-tissue adhesions of organs by the plurality of phases mentioned above, and the frequency and time of appearance for each level of inter-tissue adhesions of organs.

[0109] Inter-tissue adhesion of organs is a feature intended to determine the degree of inter-tissue adhesion of organs for each phase, and to determine the frequency and duration of appearance of adhered tissues according to the level of inter-tissue adhesion of organs.

[0110] Detailed classification items of the camera may include the cumulative path length and partial path length of the camera trajectory, the number of camera movements, and the center focus.

[0111] The camera is a feature for determining the cumulative path length and partial path length according to the trajectory of the camera capturing surgical images for each phase, and a feature for determining the number of times the camera moved (number of times position and angle changed) for each phase.

[0112] Referring again to FIG. 3, the processor (13) of the biomarker construction device (10) can predict the difficulty of surgery based on at least one of the first biomarker and the second biomarker, and perform surgery evaluation and prognosis prediction (S330).

[0113] That is, the processor (13) can predict the difficulty of surgery and perform surgery evaluation / prognosis prediction by utilizing each of the first biomarker and the second biomarker, or by utilizing both the first biomarker and the second biomarker.

[0114] First, I will explain the prediction of surgical difficulty.

[0115] According to the embodiment, the processor (13) can predict the difficulty of the surgery before surgery by utilizing only the first biomarker.

[0116] According to the embodiment, the processor (13) may predict the difficulty of surgery during surgery or after surgery by utilizing only the second biomarker.

[0117] According to an embodiment, the processor (13) can predict the difficulty of the surgery before the surgery using a first biomarker, and then correct the difficulty predicted before the surgery using a second biomarker during the surgery.

[0118] The processor (13) can predict the difficulty of surgery through the quantification of each of the above vascular deformation, above body fat characteristics, above size and arrangement relationship between the target organ and surrounding organs, above size and location of the tumor, and above relationship between the tumor and surrounding lymph nodes.

[0119] For example, regarding vascular deformation characteristics, higher complexity in the arrangement of blood vessels is quantified as a higher value, which can increase the difficulty of the surgery. In the case of characteristics regarding the size and arrangement relationship between the target organ and surrounding organs, if the surrounding organs are larger than the target organ and the arrangement of the two organs is complex, it is quantified as a higher value, which can increase the difficulty of the surgery. Regarding tumor size and location characteristics, if the tumor is small and located deep inside where it is not visible, it is quantified as a higher value, which can increase the difficulty of the surgery.

[0120] According to an embodiment, the difficulty of the surgery may be predicted differently depending on the characteristics of the patient group to which the patient belongs. Here, the patient group may be classified based on at least one of the patient's basic information, diagnostic information, medical imaging data, and EMR data obtained prior to surgery.

[0121] For example, regarding the surgical difficulty predicted through the analysis of the first biomarker, the surgical difficulty may be determined to be higher if the patient belongs to the elderly patient group.

[0122] As another example, regarding the surgical difficulty predicted through the analysis of the first biomarker, the difficulty may be determined to be higher if the patient belongs to a group with a history of past surgery.

[0123] The processor (13) can predict the difficulty of the surgery from the surgical image through the level of adhesion between organ tissues and the number and time of appearance of the adhesion tissues according to the level of adhesion.

[0124] For example, in the case of the characteristics of adhesion between organ tissues, the greater the frequency and duration of tissues with a high level of adhesion, the higher the numerical value, which can increase the difficulty of the surgery.

[0125] In addition, the processor (13) of the biomarker construction device (10) can predict a surgery plan based on the first biomarker.

[0126] The surgery includes multiple phases having a sequential order, and each of the multiple phases may include multiple actions.

[0127] Referring to Fig. 4, the entire surgical process can be divided into four phases. Here, Phase 1 may be a stage related to opening the abdomen, Phase 2 may be a stage related to relocating surrounding organs, Phase 3 may be a stage related to removing a tumor from the target organ, and Phase 4 may be a stage related to closing the abdomen.

[0128] Additionally, Phases 1 to 4 may each include three actions. A1-1 to A1-3 are actions to be performed sequentially in Phase 1, A2-1 to A2-3 are actions to be performed sequentially in Phase 2, A3-1 to A3-3 are actions to be performed sequentially in Phase 3, and A4-1 to A4-3 are actions to be performed sequentially in Phase 4.

[0129] Actions in the same sequence across phases may correspond to the same operation or different operations. That is, A1-1, A2-1, A3-1, and A4-1 may be the same operation or different operations. Alternatively, only parts of A1-1, A2-1, A3-1, and A4-1 may be the same operation, while the rest are different operations.

[0130] Although the surgery is described in Figure 4 as being divided into four phases, it is not limited to this and may be divided into fewer or more phases. Additionally, although it is described that each phase includes three actions, it is not limited to this and the number of actions included in each phase may vary.

[0131] The above surgical plan may be for a surgical tool and the movement path of the tool. That is, the processor (13) can analyze the first biomarker to plan a surgical plan regarding which tool to use and which path to move along.

[0132] Specifically, the processor (13) can predict the surgical plan for each action of the phase. That is, it can plan which tool to use and which path to take for which action of a certain phase.

[0133] Next, I will explain the surgical evaluation and prognosis prediction.

[0134] According to the embodiment, the processor (13) can perform surgery evaluation and prognosis prediction using only the first biomarker.

[0135] According to the embodiment, the processor (13) can perform surgery evaluation and prognosis prediction using only the second biomarker.

[0136] According to the embodiment, the processor (13) can perform surgery evaluation and prognosis prediction by utilizing both the first biomarker and the second biomarker.

[0137] The processor (13) can perform a surgical evaluation by comparing the surgical plan predicted based on the first biomarker with the surgical tool movement analyzed based on the second biomarker.

[0138] As described above, the surgical plan may include the tools used in each action of each phase during the actual surgery and the movement paths of the tools.

[0139] For example, the processor (13) can evaluate whether the surgery proceeded according to the planned surgery plan based on the ID of the tool used in each action for each phase identified through the analysis of the second biomarker and the movement of the tool in each action for each phase.

[0140] The processor (13) can predict the postoperative prognosis of the patient using the patient's medical image data received before the surgery, the patient's medical image data taken after a predetermined period has elapsed after the surgery, and the surgical results analyzed based on the second biomarker.

[0141] Specifically, by comparing medical imaging data received before surgery with medical imaging data taken after surgery, changes in the patient's condition before and after surgery are identified. If the patient's condition change differs from the average condition change of other patients who have undergone the same surgery in the past, prognosis prediction can be performed by identifying the biomarker that may be the cause of the difference through surgical results analyzed based on a second biomarker.

[0142] For example, if the total surgery time was longer than usual, prognosis prediction can be performed by reflecting this difference in surgery time.

[0143] As another example, in cases where bleeding occurred during surgery, prognosis prediction can be performed by reflecting the timing, frequency, location, and cause of the bleeding.

[0144] Although FIG. 3 describes the steps being executed sequentially, this is merely an illustrative explanation of the technical concept of the present embodiment. A person skilled in the art to which the present embodiment belongs can modify and adapt the steps described in FIG. 3 in various ways, such as changing the order or executing them in parallel, without departing from the essential characteristics of the present embodiment. Therefore, FIG. 3 is not limited to a chronological order.

[0145] Meanwhile, in the above description, the steps described in FIG. 3 may be further divided into additional steps or combined into fewer steps according to an embodiment of the present disclosure. Additionally, some steps may be omitted as necessary, and the order of the steps may be changed.

[0146] Meanwhile, the disclosed embodiments may be implemented in the form of a recording medium that stores instructions executable by a computer. The instructions may be stored in the form of program code and, when executed by a processor, may generate a program module to perform the operation of the disclosed embodiments. The recording medium may be implemented as a computer-readable recording medium.

[0147] Computer-readable recording media include all types of recording media that store instructions that can be decoded by a computer. Examples include ROM (Read Only Memory), RAM (Random Access Memory), magnetic tape, magnetic disk, flash memory, optical data storage devices, etc.

[0148] As described above, the disclosed embodiments have been explained with reference to the attached drawings. Those skilled in the art will understand that the present disclosure may be practiced in forms different from the disclosed embodiments without changing the technical spirit or essential features of the present disclosure. The disclosed embodiments are illustrative and should not be interpreted restrictively.

Claims

1. Communications Department; A memory storing at least one process for establishing a biomarker based on data acquired before and during surgery; and A processor that performs an operation according to the above process; including The above processor is, A first biomarker is established based on medical image data received from a hospital server via the communication unit before the surgery, a second biomarker is established based on surgical image data regarding the surgical process received from the hospital server via the communication unit during or after the surgery, and surgical difficulty prediction and surgical evaluation / prognosis prediction are performed based on at least one of the first biomarker and the second biomarker. Device for establishing biomarkers based on surgery-related data.

2. In Paragraph 1, The first biomarker above includes vascular deformation, body fat characteristics, the size and arrangement relationship between the target organ and surrounding organs, the size and location of the tumor, and the relationship between the tumor and surrounding lymph nodes. Device for establishing biomarkers based on data acquired before and during surgery.

3. In Paragraph 2, The above processor is, Predicting the difficulty of the surgery through the quantification of each of the above vascular deformation, above body fat characteristics, above size and arrangement relationship between the target organ and surrounding organs, above size and location of the tumor, and above relationship between the tumor and surrounding lymph nodes, and The above surgical difficulty is predicted to vary depending on the characteristics of the patient group to which the patient belongs, Device for establishing biomarkers based on data acquired before and during surgery.

4. In Paragraph 1, The above surgery includes a plurality of phases having a sequential order, and Each of the above plurality of phases includes a plurality of actions. Device for establishing biomarkers based on data acquired before and during surgery.

5. In Paragraph 4, The second biomarker includes surgical workflow, errors and events, organs, surgical tools, action efficiency, tissue adhesions of organs, and cameras, and The above surgical workflow, the above errors and events, the above organ, the above surgical tool, the above action efficiency, the tissue adhesions of the above organ, and the above camera each include at least one detailed classification item, Device for establishing biomarkers based on data acquired before and during surgery.

6. In Paragraph 5, The detailed classification items of the above surgical workflow include the total surgery time, the time for each of the plurality of phases, and the number of interruptions for each of the plurality of phases. The detailed classification items of the above errors and events include the number and duration of occurrence of the plurality of phase-specific errors and events, the number and duration of operations caused by the plurality of phase-specific errors and events, and the level of the plurality of phase-specific errors and events. The detailed classification items of the above action efficiency include the number of operations and time of specific actions for each of the plurality of phases, and The detailed classification items for inter-tissue adhesions of the above organ include the number and time of occurrence of inter-tissue adhesions of the organ by the plurality of phases, and the level of inter-tissue adhesions of the organ by the plurality of phases. Device for establishing biomarkers based on data acquired before and during surgery.

7. In Paragraph 6, The above processor is, The surgical evaluation is performed by comparing the surgical plan predicted based on the first biomarker and the surgical tool movement analyzed based on the second biomarker, and The above surgical plan includes tools used in each action of each phase during actual surgery and the movement paths of said tools. Device for establishing biomarkers based on data acquired before and during surgery.

8. In Paragraph 6, The above processor is, Performing the prognosis prediction using medical imaging data received prior to the surgery, medical imaging data taken after a preset period has elapsed following the surgery, and surgical results analyzed based on the second biomarker. Device for establishing biomarkers based on data acquired before and during surgery.

9. In a method performed by a device, A step of establishing a first biomarker based on medical imaging data received from a hospital server prior to surgery; A step of establishing a second biomarker based on surgical video data regarding the surgical process received from the hospital server during or after the surgery; and A step of performing a surgical difficulty prediction and a surgical evaluation / prognosis prediction based on at least one of the first biomarker and the second biomarker; comprising Method for establishing biomarkers based on data acquired before and during surgery.

10. A computer-readable recording medium that is combined with a computer, which is hardware, and stores a computer program that executes the method of claim 9.