Information processing system

The integrated information processing system enhances ophthalmological diagnosis by using AI and human interpretation, addressing limitations in existing systems and improving diagnostic flexibility and accuracy.

JP2024169527AActive Publication Date: 2024-12-05NIKON CORP +1
View PDF 8 Cites 0 Cited by

Patent Information

Application Number
JP2024160478
Authority / Receiving Office
JP · JP
Patent Type
Applications
Current Assignee / Owner
Priority Date
2019-07-31
Filing Date
2024-09-17
Publication Date
2024-12-05
Estimated Expiration
2040-07-29

AI Technical Summary

Technical Problem

Existing ophthalmological information processing systems lack flexibility in diagnosis methods, limiting the degree of freedom for requesters.

Method used

An information processing system that integrates an image acquisition device, a first information processing device, a second information processing device, and a third information processing device, utilizing artificial intelligence and human interpretation for comprehensive diagnosis, with data transmission and processing to enhance diagnostic capabilities.

Benefits of technology

The system provides flexible and comprehensive ophthalmological diagnosis by combining AI and human expertise, improving diagnostic accuracy and efficiency.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 2024169527000001_ABST
    Figure 2024169527000001_ABST
Patent Text Reader

Abstract

To increase a degree of diagnostic freedom of a request source.SOLUTION: An information processing system comprises: an image acquisition device for acquiring subject eye image data of a patient; a first information processing device for storing the subject eye image data; a second information processing device for obtaining the subject eye image data as first diagnosis results using artificial intelligence; and a third information processing device for obtaining the subject eye image data as second diagnosis results by a radiologist. The image acquisition device executes processing for generating diagnosis method information indicating a diagnosis by artificial intelligence and / or a radiologist, and first transmission processing for transmitting first transmission data including the subject eye image data and the diagnosis method information to the first information processing device. The first information processing device executes processing for storing the subject eye image data when receiving the first transmission data from the image acquisition device, and second transmission processing for transmitting second transmission data including the subject eye mage data to the second information processing device and / or the third information processing device on the basis of the diagnosis method information.SELECTED DRAWING: Figure 1
Need to check novelty before this filing date? Find Prior Art

Description

Incorporation by Reference

[0001] This application claims priority to U.S. Provisional Patent Application No. 62 / 880,961, 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 image acquisition device, an information processing method, an image acquisition method, and a program. [Background technology]

[0003] An ophthalmologic information processing server capable of performing ophthalmologic image analysis is known (see Patent Document 1). There is a demand for a system that increases the degree of freedom of diagnosis for requesting parties. [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 comprises an image acquisition device that acquires image data of a patient's test eye, a first information processing device capable of communicating with the image acquisition device and storing the test eye image data, a second information processing device capable of communicating with the first information processing device and for obtaining a first diagnostic result by artificial intelligence from the test eye image data, and a third information processing device capable of communicating with the first information processing device and for obtaining a second diagnostic result by an image reading physician from the test eye image data, wherein the image acquisition device executes a first generation process that generates diagnostic method information indicating a diagnosis by artificial intelligence and / or a diagnosis by an image reading physician, and a first transmission process that transmits first transmission data including the test eye image data and the diagnostic method information to the first information processing device, and the first information processing device, upon receiving the first transmission data from the image acquisition device, executes a storage process that stores the test eye image data, and a second transmission process that transmits second transmission data including the test eye image data to the second information processing device and / or the third information processing device based on the diagnostic method information.

[0006] A first information processing device which is one aspect of the invention disclosed in the present application is a first information processing device capable of communicating with an image acquisition device which acquires image data of a patient's test eye, stores the image data of the test eye, and includes a receiving unit which receives first transmission data including the test eye image data and diagnostic method information indicating whether the image diagnosis is by artificial intelligence and / or by a doctor, transmitted from the image acquisition device, a generating unit which generates second transmission data including the test eye image data, a control unit which determines a destination of the second transmission data based on the diagnostic method information from a second information processing device which performs image diagnosis by artificial intelligence and outputs a first diagnostic result, and a transmitting unit which transmits the second transmission data to the destination determined by the control unit.

[0007] An image acquisition device according to one aspect of the invention disclosed in the present application is an image acquisition device having an acquisition unit capable of communicating with a first information processing device that stores image data of a patient's test eye and acquires the image data of the test eye, a generation unit that generates first transmission data including the test eye image data and diagnostic method information indicating whether the image diagnosis is by artificial intelligence and / or by an image interpretation doctor, and the test eye image data, and a transmission unit that transmits the first transmission data to the first information processing device.

[0008] An information processing method which is one aspect of the invention disclosed in the present application is executed by a first information processing device capable of communicating with an image acquisition device which acquires image data of a patient's test eye and stores the image data of the test eye, the first information processing device receiving first transmission data including the test eye image data and diagnostic method information indicating whether the image diagnosis is by artificial intelligence and / or by a doctor, transmitted from the image acquisition device, the first information processing device generating second transmission data including the test eye image data, the first information processing device determining a destination of the second transmission data based on the diagnostic method information from a second information processing device which performs image diagnosis by artificial intelligence and outputs a first diagnostic result, and a third information processing device which performs image diagnosis by a radiologist and outputs a second diagnostic result, and the first information processing device transmitting the second transmission data to the determined destination.

[0009] An information processing method which is one aspect of the invention disclosed in the present application is executed by an image acquisition device capable of communicating with a first information processing device which stores image data of a patient's test eye and which acquires the image data of the test eye, the image acquisition device acquires the image data of the test eye, the image acquisition device generates first transmission data including the image data of the test eye and diagnostic method information indicating whether the image diagnosis is by artificial intelligence and / or by an image interpretation doctor, and the image acquisition device transmits the first transmission data to the first information processing device.

[0010] A program which is one aspect of the invention disclosed in the present application causes a first information processing device, which is capable of communicating with an image acquisition device that acquires image data of a patient's test eye and stores the image data of the test eye, to execute information processing, and causes the first information processing device to execute the following processes: receiving first transmission data including the test eye image data and diagnostic method information indicating whether the image diagnosis is by artificial intelligence and / or by a doctor, transmitted from the image acquisition device; generating second transmission data including the test eye image data; determining a destination of the second transmission data based on the diagnostic method information from a second information processing device that performs image diagnosis by artificial intelligence and outputs a first diagnostic result, and a third information processing device that performs image diagnosis by a radiologist and outputs a second diagnostic result; and transmitting the second transmission data to the determined destination.

[0011] A program which is one aspect of the invention disclosed in the present application is a program which causes an image acquisition device capable of communicating with a first information processing device which stores image data of a patient's test eye and which acquires the image data of the test eye to execute an image acquisition process, a process of acquiring the image data of the test eye, a process of generating first transmission data which includes diagnostic method information indicating whether the image diagnosis is performed by artificial intelligence and / or by an image interpretation physician and the image data of the test eye, and a process of transmitting the first transmission data to the first information processing device. [Brief description of the drawings]

[0012] [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] 2 is a block diagram showing an example of a functional configuration of the image interpretation server according to the first embodiment. FIG. [Figure 8] FIG. 4 is a sequence diagram showing an example of image diagnosis processing in the first embodiment. [Figure 9] 3 is an example of a patient information DB in the first embodiment. [Figure 10] 13 is an example of an input screen for setting an AI / image interpretation flag in the first embodiment. [Figure 11] 11 is a flowchart showing an example of an AI / image interpretation flag setting process in the first embodiment. [Figure 12] 3 is an example of a data structure of anonymized diagnostic target data 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] 13 is another example of a display screen for displaying a diagnosis result in the first embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0013] 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

[0014] 1 is an explanatory diagram showing an example of the configuration of an image diagnostic system according to this embodiment. The image diagnostic system includes a management server 100, a diagnosis server 200, and an image interpretation server 250. The image diagnostic 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.

[0015] 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.

[0016] 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. The fundus image data may be a fundus image data set that is a combination of two or more of the above-mentioned data. The photographing device 500 may capture not only the fundus but also the anterior segment of the subject's eye to generate anterior segment image data. The fundus image data and the anterior segment image data are examples of subject's eye image data.

[0017] The terminal 400 is an example of an image acquisition device, and is a computer such as a PC (Personal Computer) or tablet used by a requesting doctor or an ophthalmic equipment operator. The terminal 400 is connected to the in-hospital server 300. The terminal 400 transmits AI / image interpretation information, patient information, and fundus image data to the in-hospital server 300. The AI / image interpretation information is information indicating a diagnostic method, that is, whether a diagnosis is made by the AI ​​220 installed in the diagnosis server 200 which is the server of the first request destination, a diagnosis is made by an image interpretation doctor in a facility where the image interpretation server 250 which is the server of the second request destination is installed, or a diagnosis is made by both of these.

[0018] The AI / image interpretation information may be stored as an AI / image interpretation flag (01: image diagnosis by AI, 10: image diagnosis by an image interpretation doctor, 11: image diagnosis by both AI and image interpretation). The AI / image interpretation information is also request destination designation information for designating the request destination of image diagnosis, either image diagnosis by AI by the requester, image diagnosis by an image interpretation doctor by the requester, or both image diagnosis by AI and image diagnosis by an image interpretation doctor by the requester. The AI / image interpretation flag can also function as a request destination designation information flag.

[0019] The in-hospital server 300 is an example of an image acquisition device, and has a patient information DB (DataBase) 310 that holds patient information, and stores the acquired patient information 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 creates diagnostic target data, which is an example of first transmission data, by combining the patient information, fundus image data, and AI / image interpretation information received from the terminal 400 into a data set. Then, the in-hospital server 300 transmits the diagnostic target data to the management server 100. Note that a part or all of the patient information and the AI / image interpretation information in the diagnostic target data may be generated by the in-hospital server 300. Also, the fundus image data captured by the photographing device 500 may be stored in the patient information DB 310.

[0020] The management server 100 is an example of a first information processing device, and generates anonymized diagnostic target data (an example of second transmission data) which is diagnostic target data obtained by anonymizing a portion of the diagnostic target data (e.g., patient information) received from the in-hospital server 300. The management server 100 is connected to the diagnostic server 200 and the image interpretation server 250 via a network. Based on the AI / image interpretation information, the management server 100 selects the diagnostic server 200 and / or the image interpretation server 250 as a request destination (transmission destination) of fundus image data, and transmits the anonymized diagnostic target data to the selected server.

[0021] Furthermore, the management server 100 receives image diagnosis results from the diagnosis server 200 and / or image interpretation server 250, and transmits them to the in-hospital server 300 and the terminal 400. The function of storing fundus image data may be stored in an image DB (not shown) of the management server 100, rather than in the in-hospital server 300. Small-scale clinics may not have an in-hospital server, and the function of the in-hospital server 300 may be performed by the management server 100.

[0022] When the AI / image interpretation information is an AI / image interpretation flag generated by the in-hospital server 300 or the terminal 400, the management server 100 determines the destination server of the anonymized diagnosis target data according to the AI / image interpretation flag.

[0023] The diagnostic server 200 is an example of a second information processing device, and is equipped with an AI (Artificial Intelligence) 220 that performs image diagnosis on fundus image data. When the diagnostic server 200 receives the anonymized diagnosis target data, the diagnostic server 200 performs image diagnosis on the fundus image data included in the anonymized diagnosis target data using the AI ​​220, and transmits an encrypted diagnosis result to the management server 100. The AI ​​220 may be capable of determining the symptom level of a predetermined disease such as diabetic retinopathy, or may be capable of determining the occurrence or nonoccurrence of symptoms of one or more types of diseases.

[0024] The image interpretation server 250 is an example of a third information processing device, and is, for example, a server owned by an image interpretation facility where an image interpretation doctor is located. When the image interpretation server 250 receives the anonymized diagnosis target data, it displays the fundus image included in the anonymized diagnosis target data on a display or the like, and accepts input of a diagnosis result for the fundus image data by an image interpretation doctor or the like. The image interpretation server 250 encrypts the input diagnosis result, and transmits the encrypted diagnosis result to the management server 100.

[0025] Any devices included in the image diagnostic system may be connected to each other. In addition, some or all of the functions of each device included in the image diagnostic system may be included in another device, or some or all of the above-mentioned devices may be integrated. Specifically, for example, the terminal 400 and the imaging device 500 may be integrated, or the in-hospital server 300 and the terminal 400 may be integrated.

[0026] 1 illustrates one diagnostic server 200 and one image interpretation server 250 for ease of explanation, the image diagnostic system may include a plurality of diagnostic servers 200 and a plurality of image interpretation servers 250. In other words, in this case, the management server 100 may request image diagnosis from one or more selected diagnostic servers 200 and / or one or more image interpretation servers 250.

[0027] 2 is a block diagram showing an example of the hardware configuration of the computers constituting the management server 100, the diagnosis server 200, the image interpretation server 250, 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 data and programs (e.g., BIOS), etc. The RAM is a high-speed, volatile storage element such as a DRAM (Dynamic Random Access Memory), and temporarily stores the program executed by the processor 601 and data used when the program is 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 a device, 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 execution result of a program in a format that can be visually recognized by an 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 200, interpretation server 250, 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, a server 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 server selection unit 102 selects a server to which the diagnostic target data is to be transmitted (a server to which image diagnosis is to be requested) based on the AI / radiography 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 200, and transmits it 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 server selection unit 102 by operating according to a server 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 server selection information 110. The server selection information 110 is information configured of a lookup table or the like showing the correspondence between the AI / image interpretation information and the server (the diagnosis server 200 and / or the image interpretation server 250) to which the image diagnosis is requested to be performed. Note that, when the terminal 400 or the in-hospital server 300 determines the server to which the anonymized diagnostic data is to be transmitted, the management server 100 does not need to hold the server selection information 110.

[0037] The server 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 regardless of the data structure, for example, a data structure appropriately selected from a table, a list, a database, or a queue may store the information.

[0039] 4 is a block diagram showing an example of a functional configuration of the diagnostic server 200. The diagnostic server 200 includes an image diagnosis unit 201, a learning information management unit 202, a diagnostic screen generation unit 203, and a management unit 204. The diagnostic server 200 also holds a learning DB 210 and an image diagnosis model 211. The learning DB 210 is a DB for constructing the image diagnosis model 211. The image diagnosis model 211 is a model that outputs a diagnosis result when fundus image data is input.

[0040] The AI ​​220 is realized by the image diagnosis unit 201, the learning information management unit 202, the learning DB 210, and the image diagnosis model 211. The image diagnosis unit 201 performs image diagnosis of, for example, diabetic retinopathy using the image diagnosis model 211 on fundus image data included in the anonymized diagnosis target data received from the management server 100, and determines the grade of diabetic retinopathy.

[0041] The learning information management unit 202 stores the fundus 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 202 updates (e.g., optimizes) the image diagnosis model 211 by learning based on the updated learning DB 210.

[0042] The diagnostic screen generating unit 203 generates a diagnosed fundus image by superimposing a mark indicating the position of the lesion and the letters of the disease name on the diagnosed fundus image. The management unit 204 manages the version and updates of the AI ​​220. The management unit 204 also packages the grade of diabetic retinopathy and the diagnosed fundus image (if created by the diagnostic screen generating unit 203) as a diagnostic result. Then, the management unit 204 links the diagnostic result with anonymous patient information to generate AI diagnostic result information. The generated AI diagnostic result information is transmitted to the management server 100.

[0043] The diagnostic server 200 may not have a learning function of the image diagnosis model 211. That is, the diagnostic server 200 may continue to execute image diagnosis while keeping the predetermined image diagnosis model 211 fixed without updating the image diagnosis model 211. In this case, the diagnostic server 200 may not have the learning information management unit 202 and the learning DB 210.

[0044] 5 is a block diagram showing an example of the functional configuration of the in-hospital server 300. The in-hospital server 300 includes 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. The in-hospital server 300 may hold server selection information, and in this case, the in-hospital server 300 may use the server selection information to determine a destination server to which the anonymized diagnostic data is to be transmitted.

[0045] 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, or 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 personal information and diagnostic history information of patients.

[0046] When the in-hospital server 300 has server selection information, the server selection information is, similar to the server selection information 110 possessed by the management server 100, information composed of, for example, a lookup table showing the correspondence between AI / interpretation information and a server (diagnosis server 200 and / or interpretation server 250).

[0047] 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 AI / image interpretation information setting 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 fundus image data. The AI / image interpretation information setting unit 402 acquires information for selecting a server that performs image diagnosis. The display screen generating unit 403 generates screen information to be displayed on an output device 604.

[0048] The terminal 400 may hold server selection information, and in this case, the terminal 400 may use the server selection information to determine the destination server to which the anonymized diagnostic data is to be transmitted. The server selection information held by the terminal 400 indicates, for example, the correspondence between the AI / image interpretation information and the server (the diagnostic server 200 and / or the image interpretation server 250), similar to the server selection information 110. The terminal 400 may hold server selection information, and in this case, the terminal 400 may use the server selection information to determine the destination server to which the anonymized diagnostic data is to be transmitted.

[0049] When the terminal 400 has server selection information, the server selection information is, similar to the server selection information 110 possessed by the management server 100, information composed of, for example, a lookup table showing the correspondence between AI / interpretation information and a server (diagnosis server 200 and / or interpretation server 250).

[0050] 7 is a block diagram showing an example of the functional configuration of the image interpretation server 250. The image interpretation server 250 includes, for example, a diagnostic screen generating unit 251, a diagnostic information management unit 252, and a management unit 253. The image interpretation server 250 also holds, for example, a diagnostic information DB 260 that accumulates a collection of diagnostic cases.

[0051] The diagnostic screen generator 251 generates a diagnostic screen using the fundus image data of the diagnosis target data transmitted from the management server 100 and anonymized patient information (patient information such as gender and age that is necessary for the image interpretation physician to make a diagnosis and does not identify individuals) based on instructions from an image interpretation physician at the image interpretation facility that owns the image interpretation server 250. Then, the generated diagnostic screen data is displayed on a display (not shown). The image interpretation physician interprets the fundus image on the diagnostic screen and determines the grade of diabetic retinopathy (and may also discover other lesions).

[0052] The image interpreting doctor then inputs the grade of diabetic retinopathy in the diagnosis result input field of the diagnostic screen. The image interpreting doctor's findings and findings on other lesions that have been found may be entered as text in the comment entry field of the diagnostic screen. Furthermore, marks and characters may be entered on the displayed fundus image. Furthermore, the diagnostic screen generating unit 251 may display on the display so that data on the diagnostic case collection can be referenced from the diagnostic information DB 260 in response to a request from the image interpreting doctor.

[0053] The diagnostic information management unit 252 packages the grade of diabetic retinopathy via the diagnostic screen, the text input by the image interpretation doctor, and the image data of the fundus image on which the image interpretation doctor has written, as a diagnostic result. The management unit 253 then links the information of the image interpretation doctor who performed the image interpretation (such as the name and a code indicating the image interpretation doctor), the diagnostic result, and the anonymous patient information to generate image interpretation doctor diagnosis result information. The image interpretation doctor diagnosis result information is then transmitted to the management server 100.

[0054] Fig. 8 is a sequence diagram showing an example of image diagnosis processing. In Fig. 8, a server that performs image diagnosis is selected based on AI / image interpretation information.

[0055] First, the diagnostic target data generating unit 401 of the terminal 400 accepts input of patient information via the input device 603 (S801). 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. For a patient whose information is already registered in the patient information DB 310, the diagnostic target data generating unit 401 may, for example, accept input of an ID for identifying a patient and acquire other information from the registered information corresponding to the ID.

[0056] The diagnostic target data generating unit 401 acquires the subject eye image data of both the left and right eyes of the patient transmitted from the photographing device 500 (S802). In this embodiment, the subject eye 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.

[0057] Next, the AI / image interpretation information setting unit 402 sets the AI / image interpretation information (S803). The AI / image interpretation information setting unit 402 may set an AI / image interpretation flag as the AI / image interpretation information, or may collect information required for the management server 100 to determine the destination server as the AI / image interpretation information. Details of step S803 will be described later.

[0058] Next, the diagnostic object data generating unit 401 transmits the diagnostic object data including the patient information, the right / left eye flag, the fundus image data, and the AI / image interpretation information to the management server 100 via the in-hospital server 300 (S804). 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.

[0059] If the patient information received from the terminal 400 is insufficient, the patient information management unit 302 may acquire the patient information by referring to the patient information DB 310 and supplement the diagnostic target data. 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.

[0060] Next, the anonymization processing unit 101 of the management server 100 performs anonymization processing on the patient information and diagnosis history information included in the received diagnostic target data using a predetermined algorithm (S805). As the anonymization processing, the anonymization processing unit 101 performs processing such as 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. Note that the anonymization processing unit 101 may anonymize only a part of the patient information and diagnosis history information (for example, only sensitive information related to privacy). Also, the anonymization processing on the patient information may be performed in advance by the anonymization processing unit 301 of the in-hospital server 300 before the diagnostic target data is transmitted to the management server 100.

[0061] The server selection unit 102 of the management server 100 selects at least one of the diagnostic server 200 and the interpretation server 250 based on the AI / interpretation information (e.g., AI / interpretation flag) included in the received diagnostic target data, and transmits the anonymized diagnostic target data including the anonymized patient information, the image data of the test eye, and the AI / interpretation information to the selected diagnostic server 200 (S806).

[0062] In addition, the server selection unit 102 may encrypt the anonymized diagnostic target data using an encryption key and then transmit it to the selected server. In this case, the diagnostic server 200 and / or the interpretation server 250 have a decryption key corresponding to the encryption key, and first decrypt the anonymized diagnostic target data with the decryption key in step S807 described later.

[0063] Next, the diagnostic server 200 and / or the image interpretation server 250 that have received the anonymized diagnostic target data start a process of performing image diagnosis on the fundus image data included in the received anonymized diagnostic target data (S807). When the diagnostic server 200 receives the anonymized diagnostic target data, the image diagnosis unit 201 performs image diagnosis using the image diagnosis model 211. At this time, the image diagnosis unit 201 may use anonymized patient information and right / left eye flags, etc., in the image diagnosis by AI.

[0064] When the image interpretation server 250 receives the anonymized diagnosis target data, the diagnostic information management unit 252 may transmit diagnostic information including the test eye image data and the input diagnostic result to the diagnostic server 200, for example, via the management server 100. In this case, the learning information management unit 202 of the diagnostic server 200 updates the learning DB 210 by storing the test eye image data in the learning DB 210 as learning data, and updates the image diagnosis model 211 based on the updated learning DB 210. This allows the AI ​​220 of the diagnostic server 200 to perform learning even when the diagnostic server 200 is not requested to perform image diagnosis.

[0065] When the image interpretation server 250 receives the anonymized diagnosis target data, the diagnostic screen generating unit 251 displays the anonymized patient information, the right / left eye flag, and the image data of the subject eye on the output device 604 (display) of the image interpretation server 250. The diagnostic screen generating unit 251 of the image interpretation server 250 accepts input of image diagnosis results from a user of the image interpretation server 250 (e.g., an image interpretation doctor) via the input device 603.

[0066] The diagnostic server 200 and / or the image interpretation server 250 that performed the fundus image diagnosis generate diagnostic result information. Specifically, when the diagnostic server 200 performs the fundus image diagnosis in step S807, the diagnostic screen generating unit 203 generates a diagnosed fundus image (an example of a first diagnostic result) in which a mark indicating a lesion position or letters indicating a disease name are superimposed on the diagnosed fundus image.

[0067] Furthermore, when the image interpretation server 250 starts the process of image diagnosis in step S807, the diagnostic information management unit 252 packages the grade of diabetic retinopathy via the diagnostic screen, the text input by the image interpretation doctor, and the image data of the fundus image on which the image interpretation doctor has written, as a diagnostic result. The management unit 253 links the information of the image interpretation doctor who performed the image interpretation, the diagnostic result, and the anonymous patient information, and generates image interpretation doctor diagnostic result information (an example of a second diagnostic result).

[0068] Next, the diagnostic server 200 and / or the image interpretation server 250 that generated the image diagnosis result encrypts the image diagnosis result (a diagnosed fundus image when the diagnosis is made by the diagnostic server 200, and image interpretation doctor's diagnosis result information (diagnosed disease name, lesion grade, image interpretation doctor's findings, etc.) when the diagnosis is made by the image interpretation server 250) using the encryption key held by the diagnostic server 200 and generates an encrypted image diagnosis result, and transmits it to the management server 100 (S809). Note that in step S809, anonymization may be performed instead of or in addition to encryption.

[0069] Next, the diagnostic result data generating unit 104 of the management server 100 decrypts the received encrypted image diagnosis result using the decryption key held by the management server 100 (S810). If the received image diagnosis result has been anonymized, the diagnostic result data generating unit 104 restores the anonymized image diagnosis result patient information. Then, the decrypted image diagnosis result is linked to the patient information of the patient before anonymization.

[0070] Next, the diagnostic result data generation unit 104 generates a display screen (FIGS. 13 and 14 described below) showing the diagnostic result, which is the grade of diabetic retinopathy, and links this display screen showing the diagnostic result to the patient ID and stores it in a memory not shown.

[0071] In addition, if the management server 100 does not receive the encrypted image diagnosis result from the server that transmitted the data to be anonymized, even after a predetermined time has elapsed, the management server 100 may transmit the data to be anonymized to another server and request image diagnosis.

[0072] Next, the diagnostic result data generating unit 104 links the decrypted diagnostic image result with the patient information of the patient before anonymization and transmits it to the in-hospital server 300 (S811). The display screen generating unit 303 of the in-hospital server 300 displays a display screen based on the received diagnostic image result and patient information on the output device 604 of the in-hospital server 300 (S812). Note that the terminal 400 may acquire the diagnostic image result and the patient information from the in-hospital server 300, and the display screen generating unit 403 of the terminal 400 may display a display screen based on the diagnostic image result and the patient information on the output device 604 of the terminal 400.

[0073] 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.

[0074] Next, the patient information management unit 302 stores the decoded image diagnosis result and diagnosis history information indicating which server executed the image diagnosis in the patient information DB 310 (S813).

[0075] Fig. 9 is an example of the patient information DB 310. The patient information DB 310 includes a patient information column 3101 and a diagnosis history information column 3102. The patient information column 3101 stores, for example, personal information of each patient. The diagnosis history information column 3102 stores a diagnosis history of fundus image data by the diagnosis server 200 and the image interpretation server 250. In the example of Fig. 8, the fundus image data, the diagnosis result, the photographing date of the fundus image, and identification information of the diagnosis server 200 and / or the image interpretation server 250 that performed the image diagnosis are recorded as the diagnosis history.

[0076] The details of the AI / image interpretation information setting process in step S803 will be described below. In the following example, the AI / image interpretation information setting unit 402 of the terminal 400 sets an AI / image interpretation flag as the AI / image interpretation information in step S803. In this case, the management server 100 determines the destination server of the fundus image data according to the AI / image interpretation flag.

[0077] The AI / image interpretation information setting unit 402 directly accepts the setting of the AI / image interpretation flag via the input device 603 or the communication IF 605. Fig. 10 is an example of an input screen for setting the AI / image interpretation flag. The input screen 1000 includes a patient information display area 1001, a left eye image display area 1002, a right eye image display area 1003, a diagnostic method selection area 1004, and a send button 1005.

[0078] The patient information display area 1001 displays information about the patient, such as an ID for identifying the patient, and information about the image of the subject's eye, such as the date and time the image of the subject's eye was captured. The left eye image display area 1002 displays, for example, the image of the left eye of the subject's eye. The right eye image display area 1003 displays the image of the right eye of the subject's eye.

[0079] The diagnostic method selection area 1004 is an area for setting an AI / image interpretation flag. When "AI" is selected in the diagnostic method selection area 1004, the AI / image interpretation flag "01" indicating the diagnostic server 200 is selected, when "image interpretation doctor" is selected, the AI / image interpretation flag "10" indicating the image interpretation server 250 is selected, and when "AI+image interpretation doctor" is selected, the AI / image interpretation flag "11" indicating both the diagnostic server 200 and the image interpretation server 250 is selected.

[0080] 10, "image interpretation doctor" is selected in the diagnostic technique selection area 1004, i.e., the AI / image interpretation flag "10" indicating the image interpretation server 250 is selected. When the send button 1005 is selected, the AI / image interpretation flag selected in the diagnostic technique selection area 1004 is set. This allows the user of the terminal 400 to perform image diagnosis using a desired server.

[0081] Furthermore, when the terminal 400 holds the server selection information, the AI / image interpretation information setting unit 402 may acquire predetermined information in step S803 and set an AI / image interpretation flag indicating a destination server corresponding to the acquired information in the server selection information held by the terminal 400. The diagnosis history information of the patient indicated by the patient information DB 310 of the in-hospital server 300 is an example of the predetermined information.

[0082] 11 is a flowchart showing an example of the AI / image interpretation flag setting process in step S803 in such a case. First, the AI / image interpretation information setting unit 402 acquires the diagnosis history of the patient from the patient information DB 310 of the hospital server 300 as the AI / image interpretation information (S1101).

[0083] The AI / image interpretation information setting unit 402 extracts progress information of the acquired diagnostic history (S1102). Specifically, for example, the AI / image interpretation information setting unit 402 acquires the most recent diagnostic information of the acquired diagnostic history.

[0084] Next, the AI / image interpretation information setting unit 402 determines whether the image diagnosis source in the most recent diagnostic information is the diagnostic server 200 or the image interpretation server 250 (S1103). If the AI / image interpretation information setting unit 402 determines that the image diagnosis source in the most recent diagnostic information is the diagnostic server 200 (S1103: diagnostic server), it sets an AI / image interpretation flag indicating the image interpretation server 250 (S1104) and ends the processing of step S802.

[0085] If the AI / image interpretation information setting unit 402 determines that the image diagnosis source in the most recent diagnostic information is the image interpretation server 250 (S1003: image interpretation server), it sets an AI / image interpretation flag indicating the diagnostic server 200 (S1005) and terminates the processing of step S802.

[0086] 10, the AI / image interpretation flag is determined from the most recent diagnosis history, but for example, the most recent predetermined number of diagnosis histories or all of the diagnosis histories may be referenced. Specifically, for example, if the number of diagnoses by the image interpretation server 250 is equal to or greater than the number of diagnoses by the diagnostic server 200 in the most recent predetermined number of diagnosis histories or all of the diagnosis histories, the AI / image interpretation flag indicating the diagnostic server 200 may be set, and if the number of diagnoses by the image interpretation server 250 is less than the number of diagnoses by the diagnostic server 200, the AI / image interpretation flag indicating the image interpretation server 250 may be set.

[0087] For example, in step S1103, if there is no past diagnostic history for the patient, an AI / image interpretation flag indicating the diagnostic server 200 may be set, or an AI / image interpretation flag indicating the image interpretation server 250 may be set.

[0088] 10, the patient can receive image diagnosis by the diagnostic server 200 and the image interpretation server 250 in a well-balanced manner without being biased toward a specific server. On the other hand, when the doctor or patient using the terminal 400 prefers a specific server, an AI / image interpretation flag may be set to indicate the same server as the image diagnosis source in the most recent diagnosis history. Also, for example, in the first diagnosis of the patient, an AI / image interpretation flag may be set to indicate both the diagnostic server 200 and the image interpretation server 250.

[0089] Furthermore, in step S803, the AI / image interpretation information setting unit 402 may set an AI / image interpretation flag based on the medical department of the doctor who uses the terminal 400. Specifically, for example, the AI / image interpretation information setting unit 402 accepts an input of the medical department, and if the medical department is ophthalmology, sets the AI / image interpretation flag indicating the diagnosis server 200, and if the medical department is other than ophthalmology (e.g., internal medicine), sets the AI / image interpretation flag indicating the image interpretation server 250.

[0090] As a result, a knowledgeable doctor whose medical specialty is ophthalmology can obtain a sufficient diagnostic result even with image diagnosis by the diagnostic server 200 that performs a quick diagnosis by the AI ​​220, and a doctor other than an ophthalmologist can obtain a diagnostic result that includes the knowledge of an image interpretation doctor. Note that, when it is considered that image diagnosis by the AI ​​220 provides more abundant knowledge than image diagnosis by an image interpretation doctor, an AI / image interpretation flag may be set to indicate the diagnostic server 200 when the medical specialty is other than ophthalmology, and an AI / image interpretation flag may be set to indicate the image interpretation server 250 when the medical specialty is ophthalmology.

[0091] In addition, in step S803, the AI / image interpretation information setting unit 402 may set an AI / image interpretation flag based on information on the installation location of the photographing device 500. Specifically, the terminal 400 holds information indicating the correspondence between the identification information of the photographing device 500 and the installation location. The AI / image interpretation information setting unit 402 acquires the identification information of the photographing device 500 that captured the subject's eye image, and identifies the installation location of the photographing device 500. If the installation location is an institution with an ophthalmologist, such as a diabetes center or a hospital with an ophthalmology department, the AI / image interpretation information setting unit 402 sets an AI / image interpretation flag indicating the diagnosis server 200, and if the installation location is an institution without an ophthalmologist, such as an internist, the AI / image interpretation flag indicating the image interpretation server 250.

[0092] As a result, in institutions that have knowledgeable ophthalmologists, such as diabetes centers and hospitals with ophthalmology departments, sufficient diagnostic results can be obtained even with image diagnosis by the diagnostic server 200, which performs rapid diagnosis using AI 220, and doctors other than ophthalmologists, such as internal medicine doctors, can obtain diagnostic results that include the knowledge of image interpreters.

[0093] In addition, when image diagnosis by AI 220 is considered to have more abundant knowledge than image diagnosis by an image interpretation doctor, an AI / image interpretation flag may be set to indicate diagnosis server 200 when the installation location is an institution such as an internist that does not have an ophthalmologist, and an AI / image interpretation flag may be set to indicate image interpretation server 250 when the installation location is an institution such as a diabetes center or a hospital with an ophthalmology department that has an ophthalmologist. Also, in a similar manner to the above, the AI / image interpretation flag may be set based on the installation location of terminal 400 or in-hospital server 300.

[0094] Furthermore, the AI / image interpretation information setting unit 402 may set the AI / image interpretation flag based on fee information of a diagnostic course consisting of one or more diagnoses including image diagnosis of fundus image data in step S803. Specifically, for example, the AI / image interpretation information setting unit 402 accepts input of fee information of a diagnostic course, and sets the AI / image interpretation flag indicating the diagnostic server 200 if the fee is less than a predetermined threshold, and sets the AI / image interpretation flag indicating the image interpretation server 250 if the fee is equal to or more than the predetermined threshold.

[0095] The diagnostic server 200 automatically performs diagnosis using the AI ​​220, but since the diagnostic cost of the image interpretation server 250 is often high due to the labor costs of the image interpretation doctor, an appropriate diagnosis according to the fee can be received by setting the AI / image interpretation flag based on the fee information of the diagnostic course as described above. Note that, for example, if image diagnosis using the AI ​​220 is more expensive, the AI / image interpretation flag may be set to indicate the diagnostic server 200 when the fee is equal to or greater than a predetermined threshold, and the AI / image interpretation flag may be set to indicate the image interpretation server 250 when the fee is less than the predetermined threshold.

[0096] In addition, in step S803, the AI / image interpretation information setting unit 402 may set the AI / image interpretation flag based on, for example, schedule information of an image interpretation doctor who performs image diagnosis by the image interpretation server 250.

[0097] Specifically, the AI / image interpretation information setting unit 402 periodically acquires schedule information of the image interpretation doctor who performs the image diagnosis (for example, information indicating when the image diagnosis can be performed, such as the image interpretation doctor's free time) from the image interpretation server 250. For example, the AI / image interpretation information setting unit 402 refers to the schedule information and sets an AI / image interpretation flag indicating the diagnosis server 200 if the time until the image interpretation doctor can start the image diagnosis is equal to or greater than a predetermined value, and sets an AI / image interpretation flag indicating the image interpretation server 250 if the time is less than the predetermined value.

[0098] As a result, when the image-reading doctor is not available, a quick image diagnosis can be made by the AI ​​220 of the diagnostic server 200, and when the image-reading doctor is available, an image diagnosis based on the image-reading doctor's knowledge can be made.

[0099] In addition, in step S803, the AI / image interpretation information setting unit 402 may set an AI / image interpretation flag based on, for example, symptoms and / or diagnostic classification of a diagnosis target desired by a doctor or the like using the terminal 400.

[0100] Specifically, the AI / image interpretation information setting unit 402 accepts input of symptoms and / or diagnostic classifications to be diagnosed, and sets an AI / image interpretation flag indicating a server capable of performing image diagnosis of the symptoms and / or diagnostic classifications. Note that the terminal 400 is assumed to previously store information indicating symptoms and / or diagnostic classifications that can be diagnosed by the diagnosis server 200 and the image interpretation server 250 (doctors who perform image diagnosis by the image interpretation server 250).

[0101] Furthermore, in step S803, the AI / image interpretation information setting unit 402 may set an AI / image interpretation flag based on the angle of view of the image of the subject's eye captured by the photographing device 500. Specifically, the AI / image interpretation information setting unit 402 acquires the angle of view of the image of the subject's eye captured by the photographing device 500 from the photographing device 500. Note that the AI / image interpretation information setting unit 402 may hold in advance a correspondence between the ID of the photographing device 500 and the angle of view, and acquire the angle of view according to the correspondence.

[0102] If the acquired angle of view is equal to or greater than a predetermined value, the AI / image interpretation information setting unit 402 sets an AI / image interpretation flag indicating the diagnostic server 200, and if the angle of view is less than the predetermined value, sets an AI / image interpretation flag indicating the image interpretation server 250. Note that the AI / image interpretation information setting unit 402 may set an AI / image interpretation flag indicating the diagnostic server 200 if the acquired angle of view is less than a predetermined value, and set an AI / image interpretation flag indicating the image interpretation server 250 if the angle of view is equal to or greater than the predetermined value.

[0103] This allows image diagnosis to be performed using an image of the subject's eye having an angle of view that is suitable for an image interpretation doctor using the AI ​​220 of the diagnosis server 200 and the image interpretation server 250 (eg, capable of performing a highly accurate diagnosis).

[0104] In the above example, an example was described in which the terminal 400 collects the necessary information and sets the AI / interpretation flag, but the in-hospital server 300 or management server 100 may collect the necessary information and set the AI / interpretation flag.

[0105] 10, the AI / image interpretation flag may be selected by the AI / image interpretation information setting unit 402 based on the above-mentioned information. When the AI / image interpretation flag set by the input screen 1000 and the AI / image interpretation flag selected by the AI / image interpretation information setting unit 402 are different, the AI / image interpretation information setting unit 402 may, for example, display the AI / image interpretation flag selected by the AI / image interpretation information setting unit 402 on a display via the display screen generating unit 403 to recommend it to the user, or may set the AI / image interpretation flag selected by the AI / image interpretation information setting unit 402.

[0106] In the above example, the AI / image interpretation flag is determined from one type of information, but the AI / image interpretation flag may be determined from multiple types of information. Specifically, for example, a condition branch based on the values ​​indicated by the multiple types of information is described in the server selection information 110, and the AI / image interpretation flag is determined from the values ​​of the multiple types of information.

[0107] 12 shows an example of the data structure of the anonymized diagnostic target data transmitted from the management server 100 to the diagnostic server 200. 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.

[0108] The header 701 describes, for example, information defining the data format of the diagnostic object data, the source and destination of the diagnostic object data, etc. The DICOM data 702 describes, for example, the format of the medical image (fundus image) data captured by the photographing device 500, information defining the communication protocol between medical devices including the photographing device 500, etc.

[0109] The user data 703 includes, for example, an AI / image interpretation flag, a right / left eye flag, anonymous patient information, and additional information. The right / left eye flag is a flag (for example, any one of the values ​​L, R, or LR) 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.

[0110] The additional information includes, for example, attribute information of the captured image such as device information of the photographing device 500, information about the hospital and doctor using the terminal 400, and the name of the disease to be diagnosed. The angle of view, modality, and resolution of the image (subject's eye image) captured by the photographing device 500, as well as the device ID of the photographing device 500, are all examples of device information.

[0111] The modality is information indicating the type of the photographing device 500 (e.g., a fundus camera, a scanning laser ophthalmoscope, an optical coherence tomograph, etc.) or the type of image (e.g., a fundus image or an angiogram image captured by a red laser or a near-infrared laser) as a medical image captured by the photographing device 500. In addition, the names of the doctors and hospitals using the terminal 400, the locations where the terminals are 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), etc. are examples of the facility information.

[0112] Among the additional information, the contents that can be described in the DICOM data 702 , such as the terminal ID and modality of the imaging device 500 , may be described only in the DICOM data 702 .

[0113] 13 shows a display screen (screen layout) for displaying a diagnosis result. A display screen 1300 includes a patient information display area 1301, a request destination information display area 1302, an additional information display area 1303, a diagnosis result display area 1304, and a second opinion button 1305.

[0114] The patient information display area 1301 displays patient information included in the image diagnosis data. The request destination information display area 1302 displays information on the request destination that performed the image diagnosis. When the image diagnosis is performed by the artificial intelligence of the diagnosis server 200, the request destination information display area 1302 displays the ID or server name of the AI ​​220 that performed the image diagnosis.

[0115] When fundus image data is sent to the image interpretation server 250 and an image diagnosis is performed by an image interpretation physician, the request destination information display area 1302 displays the ID or server name of the image interpretation server, the name of the image interpretation facility that owns the image interpretation server, and the name of the facility and doctor that performed the image diagnosis.

[0116] The additional information display area 1303 displays some or all of the additional information (angle of view, resolution, diagnosis type, etc.) included in the diagnostic target data. The diagnosis result display area 1304 displays information showing the diagnosis result of the fundus image data. In the example of Fig. 13, fundus images of both eyes, bars showing the symptom levels of diabetic retinopathy of both eyes, and findings of both eyes are displayed in the diagnosis result display area 1304.

[0117] 13, a right-pointing arrow (indicator) indicating the fundus 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 fundus 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 grasp the symptom levels of diabetic retinopathy in both eyes and the difference in symptom levels just by glancing at the diagnosis result display area 1304.

[0118] The second opinion button 1305 is a button for requesting a second opinion from another server. When the image diagnosis is performed by the diagnosis server 200, if the second opinion button 1305 is selected, the management server 100 is notified to transmit the anonymized image diagnosis data to the image interpretation server 250.

[0119] In addition, when fundus image data is sent to the image interpretation server 250 and image diagnosis is performed by an image interpretation doctor, if the second opinion button 1305 is selected, the management server 100 is notified to transmit anonymized image diagnosis data to the diagnosis server 200. This allows a doctor or a patient to receive an image diagnosis by another server as a second opinion after viewing the image diagnosis result.

[0120] The second opinion button 1305 may be displayed only when the symptoms in the image diagnosis result are worse than a predetermined level (for example, below Mild in FIG. 13). When the symptoms in the image diagnosis result are worse than a predetermined level, the second opinion button 1305 may not be displayed and an image diagnosis by another server may be automatically received.

[0121] In addition, when image diagnosis is performed by the AI ​​220 of the diagnosis server 200 that can diagnose the presence or absence of the onset of a disease but cannot diagnose the symptom level of the disease, the second opinion button 1305 may be displayed. In addition, the management server 100 may hold correspondence information between a disease and a server that can diagnose the symptom level of the disease.

[0122] In this case, when the second opinion button 1305 is selected, the management server 100 refers to the corresponding information and identifies a server capable of diagnosing the symptom level of the disease. The management server 100 may transmit information indicating the identified server to the in-hospital server 300 to display it, or may transmit the anonymized diagnosis target data again to the identified server and request image diagnosis.

[0123] Also, the diagnostic server 200 and / or the image interpretation server 250 that performed the image diagnosis may include a second opinion instruction in the encrypted image diagnosis result and transmit it. Specifically, when the AI ​​220 of the diagnostic server 200 judges that a second opinion is necessary (for example, when it judges that a disease has occurred), or when the image interpretation server 250 receives an input of a second opinion instruction from a user (for example, an image interpretation doctor), a second opinion instruction is generated.

[0124] The second opinion button 1305 may be displayed only when a second opinion instruction is included in the encrypted image diagnosis result, or, when a second opinion instruction is included in the encrypted image diagnosis result, the second opinion button 1305 may not be displayed and an image diagnosis by another server may be automatically received.

[0125] Fig. 14 is an example of a display screen that displays a diagnosis result when a second opinion is received. Fig. 14 shows an example in which the request destination 1 that made the first diagnosis is an artificial intelligence, and the request destination 2 that made the diagnosis as a second opinion is an image interpretation doctor. The display screen 1400 includes a patient information display area 1401, a request destination information display area 1402, an additional information display area 1403, a diagnosis result display area 1404, and another second opinion button 1406. The contents displayed in the patient information display area 1401 and the additional information display area 1403 are the same as the contents displayed in the patient information display area 1301 and the additional information display area 1303 in Fig. 13, respectively.

[0126] The differences from Fig. 13 will be described. The request destination information display area 1402 displays information on request destination 1 and request destination 2. In the case of Fig. 14, request destination 1 is displayed as "diagnosis server A", and as request destination 2, the name of the image interpretation server, "image interpretation server A", the name of the image interpretation facility that owns the image interpretation server, "XX image interpretation center", and the name of the facility and doctor who performed the image diagnosis are displayed.

[0127] In the diagnosis result display area 1404, images of both the examined eyes, bars indicating the symptom levels of diabetic retinopathy in both the eyes, and findings of both the eyes are displayed for both the initial diagnosis and the diagnosis as a second opinion. When another second opinion button 1406 is operated, a further diagnosis as a second opinion can be received from another request destination 3 different from request destination 1 and request destination 2. In this case, the management server 100 selects a third request destination server different from the diagnosis server A and the image interpretation server A as a candidate for the diagnosis destination.

[0128] By displaying two diagnostic results together as in the display screen 1400 of FIG. 14, the users of the hospital server 300 and the terminal 400 can obtain a more accurate diagnostic result by combining the two.

[0129] 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]

[0130] 100 Management server, 101 Anonymization processing unit, 102 Server selection unit, 103 Display screen generation unit, 104 Diagnostic result data generation unit, 200 Diagnostic server, 201 Image diagnosis unit, 202 Learning information management unit, 203 Diagnostic screen generation unit, 204 Management unit, 210 Learning DB, 211 Image diagnosis model, 250 Reading server, 251 Diagnostic screen generation unit, 252 Diagnostic information management unit, 253 Management unit, 260 Diagnostic information DB, 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 AI / reading information setting unit, 403 Display screen generation unit, 600 Computer, 601 Processor, 602 Storage device, 603 Input device, 604 Output device, 605 communication I / F

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; A second information processing device capable of communicating with the first information processing device and for obtaining a first diagnosis result by artificial intelligence from the subject's eye image data; and a third information processing device capable of communicating with the first information processing device and for obtaining a second diagnosis result by a doctor who interprets the subject's eye image data, The image acquisition device includes: A first generation process for generating diagnostic technique information indicating a diagnosis by an artificial intelligence and / or a diagnosis by a radiologist; a first transmission process for transmitting first transmission data including the test eye image data and the diagnostic technique information 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; An information processing system that executes a second transmission process of transmitting second transmission data including the test eye image data to the second information processing device and / or the third information processing device based on the diagnostic method information.

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