Information processing system
The system addresses the lack of consent handling in ophthalmology information processing by integrating consent management, anonymization, and secure data transmission to respect patient privacy and maintain diagnostic integrity.
Patent Information
- Application Number
- JP2024160480
- 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
Ophthalmology information processing systems do not adequately handle patient consent information, leading to potential violations of privacy and misuse of patient data.
An information processing system that includes mechanisms for acquiring, storing, and managing patient consent information, anonymizing data, and performing image diagnosis while respecting patient consent, ensuring secure transmission and storage of eye image data.
Ensures compliance with patient consent, protects personal information, and maintains the integrity of diagnostic results, while allowing secure secondary use of data for learning purposes.
Smart Images

Figure 2024169528000001_ABST
Abstract
Description
Incorporation by Reference
[0001] This application claims priority to U.S. Provisional Application No. 62 / 880,975, filed July 31, 2019, the contents of which are incorporated herein by reference. [Technical field]
[0002] The present invention relates to an information processing system, an information processing device, an information processing method, and an information processing program. [Background technology]
[0003] There are known ophthalmological information processing servers capable of performing a wide variety of ophthalmological image analyses. However, the handling of patient consent information is not taken into consideration. [Prior art documents] [Patent documents]
[0004] [Patent Document 1] JP 2015-221276 A Summary of the Invention
[0005] The information processing system of the first disclosed technique is an information processing system having an image acquisition device that acquires image data of a patient's test eye, a first information processing device that is capable of communicating with the image acquisition device and that stores the image data of the test eye, and a second information processing device that is capable of communicating with the first information processing device and that performs image diagnosis using the image data of the test eye, wherein the image acquisition device executes a first generation process that generates first consent information indicating permission or not to transmit the image data of the test eye to the first information processing device and second consent information indicating permission or not to reuse the image data of the test eye in the second information processing device after image diagnosis in the second information processing device, and a first transmission process that transmits first transmission data including patient information of the patient, the image data of the test eye, and the second consent information to the first information processing device when the first consent information indicates permission to transmit, and the first information processing device receives the first transmission data from the image acquisition device. When the first information processing device receives the first transmission data, it executes a storage process to store the test eye image data, a second generation process to generate identification information unique to the test eye image data, and a second transmission process to transmit second transmission data including the identification information, the test eye image data, and the second consent information to the second information processing device, and when the second information processing device receives the second transmission data from the first information processing device, it executes an image diagnosis process to perform image diagnosis based on the test eye image data, and if the second consent information indicates that reuse of the test eye image data is not permitted, it erases the test eye image data after the image diagnosis process, and if the second consent information indicates that reuse of the test eye image data is permitted, it executes a data process to store the test eye image data and the image diagnosis result by the image diagnosis process in a database, and a third transmission process to transmit third transmission data including the identification information and the image diagnosis result to the first information processing device.
[0006] The information processing system of the second disclosed technology is an information processing system capable of communicating between a first information processing device that stores image data of a patient's test eye and a second information processing device that is capable of communicating with the first information processing device, wherein the first information processing device performs a first transmission process that transmits image data of the patient's test eye to the second information processing device based on consent information regarding consent to the use of the image data of the patient's test eye in the second information processing device, and the second information processing device performs an image diagnosis process that performs image diagnosis based on the image data of the test eye transmitted by the first transmission process, and a second transmission process that transmits the image diagnosis result from the image diagnosis process to the first information processing device.
[0007] The information processing device of the third disclosed technology is an information processing device capable of communicating with other information processing devices, and has a processor that executes a program and a storage device that stores the program, and the processor executes an acquisition process to acquire consent information regarding consent for the use of a patient's test eye image data in the other information processing device, and a transmission process to transmit the test eye image data to the other information processing device based on the consent information acquired by the acquisition process.
[0008] The information processing device of the fourth disclosed technology is an information processing device capable of communicating with other information processing devices that store image data of a patient's test eye, and has a processor that executes a program and a storage device that stores the program, and is capable of accessing a database that stores learning data, and the processor executes a receiving process to receive the test eye image data and consent information indicating whether or not reuse of the test eye image data in the information processing device is permitted from the other information processing device, an image diagnosis process to perform an image diagnosis based on the test eye image data received by the receiving process, a transmission process to transmit the image diagnosis result of the image diagnosis process to the other information processing device, and data processing related to erasing the test eye image data or storing it in the database based on the consent information received by the receiving process.
[0009] The information processing device of the fifth disclosed technology is an information processing device capable of communicating with another first information processing device that stores image data of a patient's test eye and another second information processing device having a database that stores learning data, and has a processor that executes a program and a storage device that stores the program, and the processor executes a receiving process that receives the test eye image data and consent information indicating permission or not permission to reuse the test eye image data in the information processing device from the other first information processing device, an image diagnosis process that performs image diagnosis based on the test eye image data received by the receiving process, a transmission process that transmits the image diagnosis result by the image diagnosis process to the other first information processing device, and data processing that erases the test eye image data or transmits it to the other second information processing device based on the consent information received by the receiving process.
[0010] The information processing program of the sixth disclosed technology causes a processor of an information processing device capable of communicating with other information processing devices to execute an acquisition process to acquire consent information regarding consent for the use of the patient's test eye image data in the other information processing device, and a transmission process to transmit the test eye image data to the other information processing device based on the consent information acquired by the acquisition process.
[0011] The information processing program of the seventh disclosed technology causes a processor of an information processing device that is capable of communicating with other information processing devices that store image data of a patient's test eye and that can access a database that stores learning data to execute a receiving process for receiving the test eye image data and consent information indicating permission or not permission to reuse the test eye image data in the information processing device from the other information processing device, an image diagnosis process for performing an image diagnosis based on the test eye image data received by the receiving process, a transmission process for transmitting the image diagnosis result of the image diagnosis process to the other information processing device, and data processing related to erasing the test eye image data or storing it in the database based on the consent information received by the receiving process.
[0012] The information processing program of the eighth disclosed technology causes a processor of an information processing device capable of communicating with another first information processing device that stores image data of a patient's test eye and another second information processing device having a database that stores learning data to execute a receiving process for receiving the test eye image data and consent information indicating permission or not permission to reuse the test eye image data in the information processing device from the other first information processing device, an image diagnosis process for performing image diagnosis based on the test eye image data received by the receiving process, a transmission process for transmitting the image diagnosis result of the image diagnosis process to the other information processing device, and data processing related to erasing the test eye image data or transmitting it to the other second information processing device based on the consent information received by the receiving process.
[0013] The information processing method of the 9th disclosed technology is an information processing method executed by an information processing device capable of communicating with other information processing devices, and includes an acquisition process for acquiring consent information regarding consent for the use of a patient's test eye image data in the other information processing device, and a transmission process for transmitting the test eye image data to the other information processing device based on the consent information acquired by the acquisition process.
[0014] The information processing method of the 10th disclosed technology is an information processing method executed by an information processing device that is capable of communicating with other information processing devices that store image data of a patient's test eye and can access a database that stores learning data, and includes a receiving process that receives the test eye image data and consent information indicating whether or not reuse of the test eye image data in the information processing device is permitted or not permitted from the other information processing device, an image diagnosis process that performs image diagnosis based on the test eye image data received by the receiving process, a transmission process that transmits the image diagnosis result of the image diagnosis process to the other information processing device, and a data control process that controls the erasure of the test eye image data or the storage of it in the database based on the consent information received by the receiving process.
[0015] The information processing method of the 11th disclosed technology is an information processing method executed by an information processing device capable of communicating with another first information processing device that stores image data of a patient's test eye and another second information processing device having a database that stores learning data, and includes a receiving process that receives the test eye image data and consent information indicating permission or not permission to reuse the test eye image data in the information processing device from the other first information processing device, an image diagnosis process that performs image diagnosis based on the test eye image data received by the receiving process, a transmission process that transmits the image diagnosis result of the image diagnosis process to the other information processing device, and a data control process that controls the erasure of the test eye image data or the transmission to the other second information processing device based on the consent information received by the receiving process. [Brief description of the drawings]
[0016] [Figure 1] FIG. 1 is an explanatory diagram showing an example of image diagnosis using consent information. [Diagram 2] FIG. 2 is a block diagram showing an example of the hardware configuration of a computer. [Diagram 3] FIG. 3 is an explanatory diagram showing an example of the contents stored in the patient information DB. [Figure 4] FIG. 4 is an explanatory diagram of an example of an operation sequence of the information processing system according to the first embodiment. [Diagram 5] FIG. 5 is a flowchart illustrating a detailed example of the procedure of the diagnosis data transmission determination process (step S414) illustrated in FIG. [Figure 6] FIG. 6 is a flowchart showing a detailed processing procedure example 1 of the fundus image data handling process (step S433) shown in FIG. [Figure 7] FIG. 7 is a flowchart showing a detailed processing procedure example 2 of the fundus image data handling process (step S433) shown in FIG. [Figure 8] FIG. 8 is an explanatory diagram showing Example 1 of the correction process (step S702) of the fundus image data. [Figure 9]FIG. 9 is an explanatory diagram showing Example 2 of the correction process (step S702) of the fundus image data. [Figure 10] FIG. 10 is a flowchart showing a detailed processing procedure example 3 of the fundus image data handling process (step S433) shown in FIG. [Figure 11] FIG. 11 is a flowchart showing another detailed processing procedure example of the fundus image data correction processing (step S702) shown in FIG. 7 and FIG. [Figure 12] FIG. 12 is an explanatory diagram showing examples of the severity of diabetic retinopathy. [Figure 13] FIG. 13 is a block diagram of an example of a functional configuration of the information processing system according to the first embodiment. As illustrated in FIG. [Figure 14] FIG. 14 is an explanatory diagram of an example of an operation sequence of the information processing system according to the second embodiment. [Figure 15] FIG. 15 is a flowchart showing a detailed example of the processing procedure of the fundus image data handling process (step S432) shown in FIG. [Figure 16] FIG. 16 is a block diagram of an example of a functional configuration of the information processing system according to the second embodiment. As illustrated in FIG. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS EXAMPLES
[0017] <Example of imaging diagnosis using consent information> FIG. 1 is an explanatory diagram showing an example of fundus image diagnosis using consent information. Fundus image diagnosis using consent information is executed by an information processing system 100. The information processing system 100 includes an in-hospital system 101, a management server 120, and an AI (Artificial Intelligence) server 130. The in-hospital system 101 and the management server 120 are connected to be able to communicate with each other. The management server 120 and the AI server 130 are connected to be able to communicate with each other.
[0018] The in-hospital system 101 is installed in, for example, a hospital or a clinic (ophthalmologist, internist, diabetic internist, etc.). The in-hospital system 101 includes an ophthalmic device 111, a terminal 112, and an in-hospital server 113. The ophthalmic device 111 is communicably connected to the terminal 112. The ophthalmic device 111 is a fundus camera, a scanning laser ophthalmoscope that scans a subject's eye with laser light and generates an image based on reflected light from the fundus, an optical coherence tomography, or the like, and generates fundus image data 102R, 102L of the subject's eye. When there is no need to distinguish between the fundus image data 102R of the right eye and the fundus image data 102L of the left eye, they are referred to as fundus image data 102. The same applies to other symbols that end with "R" or "L". The ophthalmologic apparatus 111 transmits the generated fundus image data 102 to the terminal 112. The fundus image data 102 includes the photographing date. 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, or may be a fundus image data set that is a combination of two or more of them.
[0019] The ophthalmic device 111 is configured with at least one of a fundus camera, a scanning laser ophthalmoscope, and an optical coherence tomograph, for example. Therefore, the fundus image data 102 is any one or a combination of two or more of fundus image data by a fundus camera, fundus image data by a scanning laser ophthalmoscope, and tomographic data by an optical coherence tomograph.
[0020] The terminal 112 is a computer capable of communicating with the ophthalmic device 111 and the in-hospital server 113. The terminal 112 may be capable of directly communicating with the management server 120. The terminal 112 is used by, for example, a doctor. The terminal 112 is, for example, a personal computer or a tablet. The terminal 112 transfers the fundus image data 102 from the ophthalmic device 111 to the in-hospital server 113.
[0021] Moreover, the terminal 112 transmits consent information 103 to the in-hospital server 113. The consent information 103 is information indicating whether or not the patient i consents to the use of the fundus image data 102 of his / her subject eye outside the in-hospital system 101. Specifically, for example, the consent information 103 includes first consent information 103a and second consent information 103b.
[0022] The first consent information 103a is, for example, an external storage flag indicating permission or non-permission of transmission of the fundus image data 102 to the management server 120 outside the in-hospital system 101. When the external storage flag is "1", it indicates permission (OK) of transmission of the fundus image data 102 to the management server 120 outside the in-hospital system 101, and when it is "0", it indicates non-permission (NG).
[0023] The second consent information 103b is, for example, a secondary use flag indicating whether or not reuse of the fundus image data 102 in the AI server 130 outside the in-hospital system 101 is permitted after image diagnosis in the AI server 130. When the secondary use flag is "1", it indicates that secondary use of the fundus image data 102 in the AI server 130 is permitted (OK), and when it is "0", it indicates that it is not permitted (NG). The consent information 103 exists for each patient i. In addition, an expiration date may be set for the consent information 103. In addition, the consent information 103 may exist for each shooting session for each patient i. The data format of the consent information 103 may be any data format as long as it can be recognized by the in-hospital server 113, the management server 120, and the AI server 130.
[0024] The terminal 112 also receives patient information and diagnosis result data 105 from the in-hospital server 113 and displays them on the display screen. The fundus image data 102 from the ophthalmologic apparatus 111, the patient information from the in-hospital server 113, the diagnosis result included in the diagnosis result data 105, and the consent information 103 are associated by the terminal 112 or the in-hospital server 113 with the same ID (for example, a patient ID).
[0025] The in-hospital server 113 is a computer capable of communicating with the terminal 112 and the management server 120. The in-hospital server 113 has a patient information DB 114. The patient information DB 114 is a database that stores patient information. The in-hospital server 113 receives a patient ID and fundus image data 102 from the terminal 112. The in-hospital server 113 stores the fundus image data 102, the diagnosis result included in the diagnosis result data, and the consent information 103 in the patient information DB 114 in association with the patient information identified by the patient ID.
[0026] If the first consent information 103a indicates permission to transmit the fundus image data 102 to the management server 120 outside the hospital system 101, the hospital server 113 transmits the diagnostic data 104 to the management server 120, and if the first consent information 103a indicates non-permission, the hospital server 113 does not transmit the diagnostic data. This enables the hospital server 113 to comply with the first consent information 103a of the patient i. The diagnostic data 104 includes the patient information of the patient i, the fundus image data 102, and the second consent information 103b. The hospital server 113 receives the diagnostic result data 105 from the management server 120. The hospital server 113 stores the diagnostic result included in the received diagnostic result data 105 in the patient information DB 114.
[0027] The management server 120 is a computer capable of communicating with the in-hospital server 113 and the AI server 130. The management server 120 receives the diagnostic data 104 from the in-hospital server 113. The management server 120 anonymizes the received diagnostic data 104. Specifically, for example, the management server 120 issues a new ID (hereinafter, anonymized ID) and associates it with the patient information in the received diagnostic data 104. Then, the management server 120 sets a combination of the anonymized ID and the fundus image data 102 as anonymized diagnostic data 106.
[0028] The patient ID in the patient information may be used as the anonymized ID. In this case, the anonymized diagnostic data 106 is composed of the patient ID, which is the anonymized ID, the fundus image data 102, and the second consent information 103b. This makes the patient information anonymous. The management server 120 may include any information in the patient information that does not uniquely identify the patient i in the anonymized diagnostic data 106. Examples of information that does not uniquely identify the patient i include the eyesight, sex, age, and nationality of the patient i.
[0029] Furthermore, the management server 120 may encrypt the patient information. In this case, the management server 120 transmits a combination of the encrypted patient information and the fundus image data 102 to the AI server 130 as anonymous diagnostic data.
[0030] The management server 120 receives anonymized diagnostic result data 107 from the AI server 130. The anonymized diagnostic result data 107 includes an anonymized ID included in the anonymized diagnostic data 106 and a diagnostic result that is the severity (also called the progression) of the symptoms of the subject's eye. The management server 120 converts the received anonymized diagnostic result data 107 into diagnostic result data 105.
[0031] Specifically, for example, the management server 120 acquires patient information associated with the anonymized ID included in the received anonymized diagnostic result data 107, and replaces the anonymized ID with the acquired patient information, thereby generating diagnostic result data 105 including the patient information and the diagnostic result.
[0032] When the management server 120 transmits anonymized diagnostic data 106, which is a combination of encrypted patient information, fundus image data 102, and second consent information 103b, to the AI server 130, the management server 120 receives anonymized diagnostic result data 107, which includes the encrypted patient information and the diagnostic result, from the AI server 130.
[0033] In this case, the management server 120 decrypts the encrypted patient information to convert the anonymized diagnostic result data 107 into diagnostic result data 105. In this way, the management server 120 can conceal the patient information by anonymization or encryption, and can protect personal information. After that, the management server 120 transmits the generated diagnostic result data 105 to the hospital server 113.
[0034] The AI server 130 is a computer that performs fundus image diagnosis by AI using learning parameters obtained by machine learning or deep learning. The AI server 130 learns combinations of past fundus image data 103 and the progression level as training data, and generates learning parameters. The training data set and learning parameters are stored in a learning DB 1131. The learning DB 1131 also stores findings 105 corresponding to the progression level. Using the learning parameters, the feature amount of the fundus image is extracted using a convolution neural network (CNN). Then, the symptom of the input fundus image is estimated based on the feature amount.
[0035] The AI server 130 receives the anonymized diagnostic data 106. The AI server 130 inputs the fundus image data 102 included in the anonymized diagnostic data 106 into a learning model in which learning parameters are applied to CNN, and outputs the severity.
[0036] The AI server 130 generates anonymized diagnostic result data 107 including the anonymized ID included in the anonymized diagnostic data 106 and the severity output from the learning model. The AI server 130 transmits the generated anonymized diagnostic result data 107 to the management server 120.
[0037] If the second consent information 103 indicates permission to reuse the fundus image data in the AI server 130 after image diagnosis in the AI server 130 outside the in-hospital system 101, the AI server 130 adds the combination of the severity and the fundus image data 102 from which the severity was output as learning data to the learning data set in the learning DB, and if the second consent information 103 indicates disapproval, it does not add it. This allows the AI server 130 to comply with the second consent information 103 of patient i. In this way, the information processing system 100 can protect the personal information of patient i.
[0038] <Example of computer hardware configuration> 2 is a block diagram showing an example of the hardware configuration of a computer (terminal 112, in-hospital server 113, management server 120, AI server 130, DB server 1400). The computer 200 has a processor 201, a storage device 202, an input device 203, an output device 204, and a communication interface (communication IF) 205. The processor 201, the storage device 202, the input device 203, the output device 204, and the communication IF 205 are connected by a bus 206. The processor 201 controls the computer 200.
[0039] The storage device 202 serves as a working area for the processor 201. The storage device 202 is a non-transient or temporary recording medium for storing various programs and data. Examples of the storage device 202 include a read only memory (ROM), a random access memory (RAM), a hard disk drive (HDD), and a flash memory.
[0040] The input device 203 inputs data. Examples of the input device 203 include a keyboard, a mouse, an input pen, a touch panel, a numeric keypad, and a scanner. The output device 204 outputs data. Examples of the output device 204 include a display and a printer. The communication IF 205 connects to a network and transmits and receives data.
[0041] <Patient information DB114> 3 is an explanatory diagram showing an example of the contents stored in the patient information DB 114. The patient information DB 114 has a patient information field 301 and a diagnosis information field 302. The patient information field 301 has, as subfields, a patient ID field 311, a name field 312, a gender field 313, a date of birth field 314, and a contact information field 315. Subfields 311 to 315 in the same row are patient information for patient i (i is, for example, an integer equal to or greater than 1).
[0042] The patient ID field 311 is a storage area for storing a patient ID. The patient ID Pi is identification information that uniquely identifies the patient i. The name field 312 is a storage area for storing the name FNi of the patient i. The gender field 313 is a storage area for storing the gender Si of the patient i. The date of birth field 314 is a storage area for storing the date of birth DOBi of the patient i. The contact field 315 is a storage area for storing the contact information ADi of the patient i.
[0043] The diagnostic information field 302 is a storage area for storing diagnostic information Di1 to Dij up to the jth time (j is an integer equal to or greater than 1) of patient i. The diagnostic information Dij includes fundus image data 102, a diagnostic result Rij, a photographing date Tij, and consent information 103. The diagnostic result Rij includes the severity from the AI server 130. The photographing date Tij is the date on which the fundus image data 102 was generated by photographing the subject's eye with the ophthalmologic apparatus 111. The consent information 103 includes the above-mentioned first consent information 103a (external storage flag) and second consent information 103b (secondary use flag).
[0044] <Example of Operation Sequence of Information Processing System 100> 4 is an explanatory diagram showing an example of an operation sequence of the information processing system 100 according to the first embodiment. When the terminal 112 and the in-hospital server 113 are not distinguished from each other, they are referred to as the image acquisition device 400. The image acquisition device 400 acquires the patient information of the patient i who is to be the subject from the patient information DB 114 (step S411). The image acquisition device 400 acquires the fundus image data 102 of the patient i via the terminal 112 (step S412). Moreover, the in-hospital server 113 acquires the consent information 103 of the patient i via the terminal 112 (step S413).
[0045] Then, the image acquisition device 400 executes a transmission decision process for the diagnostic data 104 including the patient information acquired in step S411, the fundus image data 102 acquired in step S412, and the second consent information 103b acquired in step S413 (step S414). The transmission decision process for the diagnostic data 104 (step S414) is a process for deciding whether or not to transmit the diagnostic data 104 according to the contents of the first consent information 103a.
[0046] If the first consent information 103a indicates permission to transmit, the image acquisition device 400 decides to transmit the diagnostic data 104, and if the first consent information 103a indicates non-permission to transmit, the image acquisition device 400 decides not to transmit the diagnostic data 104. The details of the process of deciding to transmit the diagnostic data 104 (step S414) will be described later. As a result, the image acquisition device 400 transmits the diagnostic data 104 to the management server 120 (step S415) only when it has decided to transmit the diagnostic data 104 in step S414.
[0047] When the diagnostic data 104 is transmitted from the image acquisition device 400, the management server 120 receives the diagnostic data 104 (step S421). Next, the management server 120 anonymizes the patient information included in the diagnostic data 104 (step S422). Then, the management server 120 transmits the anonymized diagnostic data 106 including the anonymized ID associated with the patient information, the fundus image data 102, and the second consent information 103b (secondary use flag) to the AI server 130 (step S423).
[0048] When the anonymized diagnostic data 106 is transmitted from the management server 120, the AI server 130 receives the anonymized diagnostic data 106 (step S431). Next, the AI server 130 executes fundus image diagnosis by inputting the fundus image data 102 included in the anonymized diagnostic data 106 into a learning model (step S432).
[0049] After the fundus image diagnosis (step S432), the AI server 130 executes a handling process for the fundus image data 102 (step S433). The handling process for the fundus image data 102 (step S433) is a process for determining how to handle the fundus image data 102 after the fundus image diagnosis (step S432), such as whether to use the fundus image data 102 as learning data, based on the contents of the second consent information 103b. The details of the handling process for the fundus image data 102 (step S433) will be described later.
[0050] Then, the AI server 130 transmits the anonymized diagnosis result data 107, which includes the anonymized ID and the diagnosis result Rij, which is the severity output by the fundus image diagnosis, to the management server 120 (step S434).
[0051] After that, the AI server 130 executes a learning process (step S435). Specifically, for example, in the fundus image data 102 handling process (step S433), the AI server 130 adds the combination of the fundus image data 102 included in the anonymized diagnostic data received in step S431 and the severity, which is the diagnostic result Rij output in step S432, to the learning data set of the learning DB 131 only if it is permitted to handle the combination as learning data (if the second consent information 103b (secondary use flag) indicates secondary use OK), and updates the learning model with the added learning data set.
[0052] Furthermore, when the anonymized diagnostic result data 107 is transmitted from the AI server 130, the management server 120 receives the anonymized diagnostic result data 107 (step S424). At this time, the management server 120 may transmit completion information indicating that reception of the anonymized diagnostic result data 107 has been completed to the image acquisition device 400. Next, the management server 120 restores the patient information based on the anonymization ID included in the anonymized diagnostic result data 107 (step S425).
[0053] For example, the management server 120 reads out the patient information including the patient ID associated with the anonymized ID stored in step S422. Then, the management server 120 generates the diagnosis result data 105 including the acquired patient information and the diagnosis result Rij (step S426), and transmits the diagnosis result data 105 to the image acquisition device 400 (step S427).
[0054] When the image acquisition device 400 receives the completion information from the management server 120, the image acquisition device 400 may transmit an acquisition request for the diagnosis result data 105 to the management server 120. As a result, when the management server 120 receives the acquisition request, the management server 120 transmits the diagnosis result data 105 to the image acquisition device 400. After that, the management server 120 stores the diagnosis result data 105 (step S428). Then, the processing of the management server 120 is terminated.
[0055] When the diagnosis result data 105 is transmitted from the management server 120, the image acquisition device 400 receives the diagnosis result data 105 (step S416). This allows the terminal 112 to display the fundus image data 102, severity, and patient information on the display screen using the diagnosis result data 105 and the fundus image data 102 from the hospital server 113. Then, the display process ends when an end button (not shown) is operated according to a user instruction.
[0056] FIG. 5 is a flowchart showing a detailed example of the process of determining whether or not to transmit the diagnostic data 104 (step S414) shown in FIG. 4. When the external storage flag, which is the first consent information 103a, is "1" indicating that external storage is permitted (OK) (step S501: Yes), the image acquisition device 400 determines the diagnostic data 104 to be transmitted and ends the process of determining whether or not to transmit the diagnostic data 104 (step S414). On the other hand, when the external storage flag, which is the first consent information 103a, is "0" indicating that external storage is not permitted (NG) (step S501: No), the in-hospital server 113 determines the diagnostic data 104 not to be transmitted and ends the process of determining whether or not to transmit the diagnostic data 104 (step S414). In other words, when the external storage flag, which is the first consent information 103a, is indicating that external storage is not permitted (NG), the captured fundus image is stored only in the in-hospital server, and image diagnosis by AI is not performed.
[0057] Fig. 6 is a flowchart showing a detailed processing procedure example 1 of the handling process (step S433) of the fundus image data 102 shown in Fig. 4. When the secondary use flag, which is the second consent information 103b, is "1" indicating that secondary use is permitted (OK) (step S601: Yes), the AI server 130 stores the combination of the fundus image data 102 and the diagnosis result Rij as learning data in the learning DB 131 and ends the handling process of the fundus image data 102 (step S433). On the other hand, when the secondary use flag, which is the second consent information 103b, is "0" indicating that secondary use is not permitted (NG) (step S601: No), the AI server 130 deletes the fundus image data 102 and ends the handling process of the fundus image data 102 (step S433).
[0058] Fig. 7 is a flowchart showing a detailed processing procedure example 2 of the handling process (step S433) of the fundus image data 102 shown in Fig. 4. In Fig. 6, if the secondary use flag is OK, the fundus image data 102 and the diagnosis result Rij are stored as they are in the learning DB 131 as learning data, but in Fig. 7, even if the secondary use flag is OK, the AI server 130 modifies the fundus image data 102 and then stores it in the learning DB 131 as learning data, taking into consideration personal information protection. The same steps as in Fig. 6 are assigned the same step numbers, and their explanations are omitted.
[0059] If the secondary use flag, which is the second consent information 103b, is "1" indicating that secondary use is permitted (OK) (step S601: Yes), the AI server 130 executes a correction process for the fundus image data 102 (step S702). Here, an example of the correction process (step S702) for the fundus image data 102 will be described. The correction process (step S702) is image processing for preventing unauthorized use of the fundus image data in the event that the fundus image data is leaked to the outside. For example, this processing is intended to prevent unauthorized use of the fundus image data in a retinal authentication system using the fundus image data, and unauthorized registration in a fundus image database.
[0060] Fig. 8 is an explanatory diagram showing Example 1 of the correction process (step S702) of the fundus image data 102. In Fig. 8, the AI server 130 horizontally inverts the right eye fundus image data 102R and converts it into new left eye fundus image data 802L, and horizontally inverts the left eye fundus image data 102L and converts it into new right eye fundus image data 802R. In this case, the AI server 130 changes the diagnosis result RijR to diagnosis result RijL, and also changes the diagnosis result RijL to diagnosis result RijR.
[0061] Fig. 9 is an explanatory diagram showing Example 2 of the correction process (step S702) of the fundus image data 102. Fig. 9 shows an example of correction of the fundus image data 102 of the left eye, but a similar correction is possible for the right eye. The AI server 130 can correct the fundus image data 102L to fundus image data 102L1 by adding blood vessel shape data to the fundus image data 102L.
[0062] The AI server 130 can also modify the fundus image data 102L to fundus image data 102L2 by changing the path of the vascular shape data in the fundus image data 102L. The AI server 130 can also modify the fundus image data 102L to fundus image data 102L3 by deleting the vascular shape data in the fundus image data 102L. When adding, changing, or deleting vascular data, unlike left-right reversal, the diagnosis result Rij is not switched.
[0063] In the addition, modification, and deletion shown in FIG. 9, the AI server 130 preferably modifies image data in a healthy area not related to an abnormal area in the fundus image data 102L by referring to the diagnosis result Rij. A healthy area is, for example, an area where no microaneurysm exists if the diagnosis result Rij is mild non-proliferative retinopathy (hereinafter, first retinopathy), an area that is not an avascular area if the diagnosis result Rij is moderate or severe non-proliferative retinopathy (hereinafter, second retinopathy), and an area where no neovascularization occurs if the diagnosis result Rij is proliferative retinopathy (hereinafter, third retinopathy). Modification of a healthy area does not affect the diagnosis result Rij. This allows the diagnosis result before modification to be maintained even after the fundus image data 102 is modified.
[0064] 9 and 10, even if the corrected fundus image data 802 is leaked to the outside, it will not be authenticated even if it is misused in retinal authentication. In this way, the authentication can be invalidated by the correction, and security can be improved. In addition to correcting the fundus image data 102, the fundus image may be encrypted to further improve security.
[0065] 7, the AI server 130 stores the combination of the fundus image data 802 corrected in step S702 and the diagnosis result Rij as learning data in the learning DB 131 (step S704), and ends the handling process (step S433) of the fundus image data 102. This allows the corrected fundus image data 802 to be used secondary, taking into consideration the privacy of the patient i.
[0066] Fig. 10 is a flowchart showing a detailed processing procedure example 3 of the processing (step S433) of the fundus image data 102 shown in Fig. 4. Although Fig. 7 to Fig. 9 show an example in which the fundus image data 102 is corrected, depending on the degree of the correction, the resulting diagnosis result Rij may differ from the diagnosis result Rij before the correction.
[0067] Therefore, in Figure 10, the AI server 130 performs fundus image diagnosis again on the corrected fundus image data 802, and if the diagnosis result Rij is the same as the pre-correction fundus image data 102, it stores it in the learning DB 131 for secondary use as learning data, thereby achieving both personal information protection and the consistency of the diagnosis results before and after correction.
[0068] 6 and 7 are given the same step numbers, and their explanations are omitted. After the correction process (step S702) of the fundus image data 102 shown in Fig. 7, the AI server 130 re-executes fundus image diagnosis on the corrected fundus image data 802 (step S1001).
[0069] Then, the AI server 130 judges whether or not the re-diagnosis result Rij in step S1001 matches the diagnosis result Rij before the change (step S1002). Specifically, for example, when the fundus image data 102 is flipped horizontally in step S702 as shown in Fig. 8, the AI server 130 judges whether or not the re-diagnosis result RijR of the right eye matches the diagnosis result RijL of the left eye before the correction, and whether or not the re-diagnosis result RijL of the left eye matches the diagnosis result RijR of the right eye before the correction.
[0070] In addition, in step S702, if the fundus image data 102 is not flipped left to right, but rather vascular shape data is added, changed, or deleted as shown in Figure 9, the AI server 130 determines whether the re-diagnosis result RijR for the right eye matches the diagnosis result RijR for the right eye before correction, and whether the re-diagnosis result RijL for the left eye matches the diagnosis result RijL for the left eye before correction.
[0071] If both eyes do not match (step S1002: No), the process returns to step S702, and the AI server 130 re-executes the correction process (step S702) of the fundus image data 102. In this case, the AI server 130 executes a correction different from the corrections that have already been executed, such as adding, changing, or deleting vascular shape data. However, if the vascular shape data to be added, changed, or deleted is different from the target of the already executed addition, change, or deletion, it will be a different correction.
[0072] On the other hand, if there is a match for both eyes (step S1002: Yes), the AI server 130 stores the combination of the latest fundus image data 802 corrected in step S702 and the diagnosis result Rij as learning data in the learning DB 131 (step S704), and terminates the handling process of the fundus image data 102 (step S433).
[0073] This prevents unauthorized use of the fundus image data of patient i and protects the privacy of patient i, while ensuring the identity of the diagnosis result Rij before and after the correction, allowing secondary use of the corrected fundus image data 802 with no change in the diagnosis result Rij. This also makes it possible to suppress a decrease in prediction accuracy by the learning model used for fundus image diagnosis by the AI server 130 when a combination of the corrected fundus image data 802 and its diagnosis result Rij is used as learning data.
[0074] Fig. 11 is a flowchart showing another detailed processing procedure example of the fundus image data correction process (step S702) shown in Fig. 7 and Fig. 9. Fig. 11 shows a processing procedure example in which the AI server 130 corrects the shape data of blood vessels in the retina according to the severity of the diagnosis result Rij. Fig. 12 is an explanatory diagram showing an example of the severity of diabetic retinopathy.
[0075] In Fig. 11, the AI server 130 judges whether the diagnosis result Rij is normal (No DR) or not (step S1101). If the diagnosis result Rij is normal (No DR) (step S1101: Yes), the AI server 130 corrects the shape data of blood vessels in the fundus image data 102 as shown in Fig. 8 or 9 (step S1102). Then, the fundus image data correction process (step S702) ends and proceeds to the next process.
[0076] On the other hand, if the diagnosis result Rij is not abnormal (No DR) (step S1101: No), the AI server 130 judges whether the diagnosis result Rij is first retinopathy (Mild) or third retinopathy (Proliferative) (step S1103). If the diagnosis result Rij is first retinopathy (Mild) or third retinopathy (Proliferative) (step S1103: Yes), the AI server 130 corrects the shape data of blood vessels in the fundus image data 102 as shown in FIG. 8 or FIG. 9 (step S1104).
[0077] In the first retinopathy (Mild), capillary pools occur. In the third retinopathy (Proliferative), neovascularization occurs. Therefore, in order to prevent the deletion of shape data of capillary pools and neovascularization, the correction in step S1104 does not allow deletion of shape data among addition, modification, and deletion. Then, the fundus image data correction process (step S702) ends and proceeds to the next process.
[0078] On the other hand, if the diagnosis result Rij is neither the first retinopathy (Mild) nor the third retinopathy (Proliferative) (step S1103: No), the diagnosis result Rij corresponds to the second retinopathy (Moderate or Severe). Therefore, the AI server 130 corrects the shape data of the blood vessels in the fundus image data 102 as shown in FIG. 8 or FIG. 9 (step S1105).
[0079] In the second retinopathy (moderate or severe), a certain range of avascular field exists. Therefore, in order to prevent the addition of vascular shape data to the avascular field, the correction in step S1105 does not allow the addition of shape data among the addition, modification, and deletion. Note that even if a change results in the addition of vascular shape data to the avascular field, this corresponds to the addition of shape data, and therefore such a correction is not allowed. Then, the fundus image data correction process (step S702) is terminated and the process moves to the next process.
[0080] In this way, the AI server 130 corrects the shape data indicating the eye tissue according to the diagnosis result Rij, thereby preventing the diagnosis result Rij from being changed before and after the correction. This allows the secondary use of the corrected fundus image data 802 with no change in the diagnosis result Rij by ensuring the identity of the diagnosis result Rij before and after the correction while taking into consideration the privacy of the patient i. This also makes it possible to suppress a decrease in the prediction accuracy of the learning model used for fundus image diagnosis by the AI server 130 when a combination of the corrected fundus image data 802 and the diagnosis result Rij is used as learning data.
[0081] <Example of functional configuration of information processing system> Fig. 13 is a block diagram showing an example of a functional configuration of the information processing system according to the first embodiment. In Fig. 13, the information processing device 1300 is a computer including the image acquisition device 400 (terminal 112, in-hospital server 113) and the management server 120. The information processing device 1300 includes an acquisition unit 1301, a first transmission unit 1302, and a first reception unit 1303. Specifically, the acquisition unit 1301, the first transmission unit 1302, and the first reception unit 1303 are realized by, for example, causing the processor 201 to execute a program stored in the storage device 202 shown in Fig. 2.
[0082] The acquiring unit 1301 acquires various data by the image acquiring device 400. Specifically, for example, as shown in steps S411 to S413 of Fig. 4, the acquiring unit 1301 acquires patient information and diagnostic information Dij of a target patient i from the patient information DB 114 by the image acquiring device 400. The diagnostic information Dij includes the consent information 103. In addition, the acquiring unit 1301 acquires an anonymous ID as identification information unique to the fundus image data 102 by executing an anonymization process of the patient information by the management server 120 as shown in step S422 of Fig. 4.
[0083] In addition, as shown in steps S425 and S426 of Figure 4, the acquisition unit 1301 acquires the diagnostic result data 105 of patient i based on the patient information identified from the anonymized ID included in the anonymized diagnostic result data 107 from the AI server 130 and the diagnostic result Rij included in the anonymized diagnostic result data 107, and stores it in the management server 120.
[0084] The first transmission unit 1302 transmits various data by the image acquisition device 400. Specifically, for example, as shown in step S415 of Fig. 4, when the first consent information 103a indicates permission for transmission, the first transmission unit 1302 transmits the diagnostic data 104 including the patient information of the patient i, the fundus image data 102, and the second consent information 103b to the management server 120 by the image acquisition device 400. Also, as shown in step S423 of Fig. 4, the first transmission unit 1302 transmits the anonymized diagnostic data 106 including the anonymized ID, the fundus image data 102, and the second consent information 103b to the AI server 130 by the management server 120.
[0085] The first receiving unit 1303 receives various data from the image acquisition device 400. Specifically, for example, the first receiving unit 1303 receives the anonymized diagnostic result data 107 from the AI server 130, as shown in step S424 of FIG. 4. The first receiving unit 1303 also receives completion information indicating that reception of the anonymized diagnostic result data 107 has been completed in step S424 from the image acquisition device 400. The first receiving unit 1303 also receives the diagnostic result data 105 from the management server 120 from the image acquisition device 400.
[0086] The AI server 130 includes a second receiving unit 1311, an image diagnosis unit 1312, a second transmitting unit 1313, a data control unit 1314, a learning unit 1315, a correction unit 1316, and a learning DB 131. The second receiving unit 1311, the image diagnosis unit 1312, the second transmitting unit 1313, the data control unit 1314, the learning unit 1315, and the correction unit 1316 are specifically realized by, for example, having the processor 201 execute a program stored in the storage device 202 shown in FIG. 2. The learning DB 131 is specifically realized by, for example, the storage device 202 shown in FIG. 2.
[0087] The second receiving unit 1311 receives the anonymized diagnostic data 106 transmitted from the first transmitting unit 1302 of the information processing device 1300 as shown in step S431 of FIG.
[0088] As shown in step S432 of FIG. 4, the image diagnosis unit 1312 performs machine learning or deep learning. More specifically, for example, the image diagnosis unit 1312 inputs fundus image data into a learning model in which updated learning parameters are applied to CNN, performs fundus image diagnosis, and outputs the severity as the diagnosis result Rij to the second transmission unit 1313.
[0089] The second transmitting unit 1313 transmits the anonymized diagnostic result data including the diagnostic result Rij to the first receiving unit 1303 of the information processing device 1300 as shown in step S434 in FIG.
[0090] The data control unit 1314 executes the fundus image data handling process of Fig. 7 and Fig. 10 as shown in step S433 of Fig. 4. Specifically, for example, the data control unit 1314 has a storage unit 1341 and an erasing unit 1342. If the secondary use flag is OK, the storage unit 1341 stores learning data that is a combination of the fundus image data 102 diagnosed by the image diagnosis unit 1312 and the diagnosis result Rij, and if the secondary use flag is NG, the erasing unit 1342 erases the fundus image data 102 diagnosed by the image diagnosis unit 1312.
[0091] The learning unit 1315 generates a learning model by providing the learning data set in the learning DB 131 to the CNN and updating the learning parameters of the CNN.
[0092] The correction unit 1316 corrects the fundus image data 102 diagnosed by the image diagnosis unit 1312, as shown in step S702 in Fig. 7 and Fig. 10. In this case, if the secondary use flag is OK, the storage unit 1341 stores learning data that is a combination of the corrected fundus image data 802 corrected by the correction unit 1316 and the diagnosis result Rij. In addition, the correction unit 1316 inputs the corrected fundus image data 802 to the latest learning model by the learning unit 1315, thereby obtaining the diagnosis result Rij for the corrected fundus image data 802. In this case, the correction unit 1316 may perform correction of the fundus image data 102 until the diagnosis results Rij before and after the correction match.
[0093] In this way, in the first embodiment, by ensuring the identity of the diagnosis result Rij before and after the correction while taking into consideration the privacy of the patient i, it is possible to perform secondary use of the corrected fundus image data 802 with no change in the diagnosis result Rij. This also makes it possible to suppress a decrease in prediction accuracy by the learning model used for fundus image diagnosis by the AI server 130 when a combination of the corrected fundus image data 802 and its diagnosis result Rij is used as learning data.
[0094] In addition, the image acquisition device 400 may generate the first consent information 103a and the second consent information 103b when the image diagnosis of the patient i is the first time, and may use the first consent information 103a and the second consent information 103b generated when the image diagnosis of the patient i is the second time or later. This eliminates the need to reset the consent information 103, improving convenience.
[0095] Furthermore, the image acquisition device 400 may generate the first consent information 103a and the second consent information 103b when the image diagnosis of the patient i is the first time, and may output an update request for the second consent information 103b using the first consent information 103a generated when the image diagnosis of the patient i is the second time or later. The update request may be displayed, for example, on the display screen of the terminal 112. When the update request is displayed on the display screen, the patient i or the doctor sets the secondary use flag, which is the second consent information 103b, to "1" (OK) or "0" (NG). After the setting, the in-hospital server 113 refers to the first consent information 103a and determines whether to transmit it to the management server 120, and if it is to be transmitted, transmits the diagnostic data 104 to the management server 120.
[0096] This eliminates the need to reset the first consent information 103a, improving convenience, and by prompting the patient i to reconfirm the second consent information 103b, improving privacy protection. EXAMPLES
[0097] Next, a second embodiment will be described. In the first embodiment, the AI server 130 has the learning DB 131, but in the second embodiment, an example in which the AI server 130 and the learning DB 131 are separated will be described. The learning DB 131 is held by a DB server 1400 that is different from the AI server 130. The functions of the DB server 1400 may be performed by the management server 120. Note that in the second embodiment, the differences from the first embodiment will be described, so that the same reference numerals will be used for the same contents as in the first embodiment, and description thereof will be omitted.
[0098] 14 is an explanatory diagram showing an example of an operation sequence of the information processing system 100 according to the second embodiment. The AI server 130 acquires learning parameters from the DB server 1400 and executes fundus image diagnosis (step S1432). The difference from step S432 is that the learning parameters are acquired from the DB server 1400.
[0099] After performing fundus image diagnosis (step S1432), the AI server 130 transmits the anonymized diagnostic data 106 to the DB server 1400 (step S1401). In this case, the DB server 1400 executes a process for handling the fundus image data 102 (step S1433). Meanwhile, the AI server 130 erases the fundus image data 102 to prevent leakage (step S1402). The AI server 130 also acquires a learning data set from the learning DB 131 and executes a learning process (step S1434). The difference from step S434 is that the learning data set is acquired from the DB server 1400. Then, the AI server 130 ends the process on the received fundus image and goes into a standby state for receiving the next fundus image to be received.
[0100] Fig. 15 is a flowchart showing a detailed example of the processing procedure of the handling process (step S432) of the fundus image data 102 shown in Fig. 14. When the DB server 1400 receives the anonymized diagnostic data 106, if the secondary use flag, which is the second consent information 103b, is "0" indicating that secondary use is not permitted (NG) (step S601: No), the DB server 1400 erases the fundus image data 102 and ends the handling process of the fundus image data 102 (step S1433).
[0101] On the other hand, if the secondary use flag, which is the second consent information 103b, is "1" indicating that secondary use is permitted (OK) (step S601: Yes), the DB server 1400 executes a correction process for the fundus image data 102 (step S702). Then, the DB server 1400 transmits the corrected fundus image data 802 to the AI server 130 (step S1511).
[0102] When the AI server 130 receives the corrected fundus image data 802 from the DB server 1400, the AI server 130 inputs the corrected fundus image data 802 into the learning model and re-executes the fundus image diagnosis (step S1501). Then, the AI server 130 transmits the re-diagnosis result Rij to the DB server 1400 (step S1502).
[0103] The DB server 1400 receives the re-diagnosis result Rij from the AI server 130 (step S1512). Then, the DB server 1400 judges whether the re-diagnosis result Rij matches the diagnosis result Rij of the fundus image data 102 before correction (step S1002). If they do not match (step S1002: No), the process returns to step S702, and the DB server 1400 re-corrects the fundus image data 102 (step S702). If they match (step S1002: Yes), the DB server 1400 stores the corrected fundus image data 802 and the re-diagnosis result Rij in the learning DB 131 as learning data (step S704). This ends the processing of handling the fundus image data 102 (step S1433).
[0104] <Example of functional configuration of information processing system> Fig. 16 is a block diagram showing an example of a functional configuration of an information processing system according to Example 2. In Fig. 16, the data control unit 1600 of the AI server 130 has a deletion unit 1342 and a third transmission unit 1601, and the DB server 1400 has a learning DB 131 and a storage unit 1602. When the secondary use flag is OK, the third transmission unit 1601 transmits the corrected fundus image data 802 and the diagnosis result Rij to the DB server 1400. The storage unit 1602 stores the corrected fundus image data 802 and the diagnosis result Rij from the third transmission unit 1601 in the learning data set of the learning DB 131 as learning data.
[0105] In this way, also in the second embodiment, by ensuring the identity of the diagnosis result Rij before and after the correction while taking into consideration the privacy of the patient i, it is possible to perform secondary use of the corrected fundus image data 802 with no change in the diagnosis result Rij. This also makes it possible to suppress a decrease in prediction accuracy by the learning model used for fundus image diagnosis by the AI server 130 when a combination of the corrected fundus image data 802 and its diagnosis result Rij is used as learning data.
[0106] The present invention is not limited to the above, and may be implemented by any combination of the above. 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]
[0107] 100 Information processing system, 101 In-hospital system, 102 Fundus image data, 103 Consent information, 103a First consent information, 103b Second consent information, 104 Diagnosis data, 105 Diagnosis result data, 106 Anonymized diagnosis data, 107 Anonymized diagnosis result data, 111 Ophthalmic device, 112 Terminal, 113 In-hospital server, 114 Patient information DB, 120 Management server, 130 AI server, 131 Learning DB, 201 Processor, 202 Storage device, 400 Image acquisition device, 802 Corrected fundus image data, 1300 Information processing device, 1301 Acquisition unit, 1302 First transmission unit, 1303 First reception unit, 1311 Second reception unit, 1312 Image diagnosis unit, 1313 Second transmission unit, 1314 Data control unit, 1315 Learning unit, 1316 Correction unit, 1341 storage unit, 1342 deletion unit, 1400 DB server, 1601 third transmission unit, 1602 storage unit, Dij diagnostic information, Rij diagnostic result
Claims
[Claim 1] An information processing system including: an image acquisition device that acquires image data of a patient's eye to be examined; a first information processing device that can communicate with the image acquisition device and stores the image data of the patient's eye; and a second information processing device that can communicate with the first information processing device and performs image diagnosis using the image data of the patient's eye, The image acquisition device includes: a first generation process for generating first consent information indicating permission or non-permission to transmit the test eye image data to the first information processing device, and second consent information indicating permission or non-permission to reuse the test eye image data in the second information processing device after image diagnosis in the second information processing device; a first transmission process for transmitting, to the first information processing device, first transmission data including patient information of the patient, the eye image data to be examined, and the second consent information when the first consent information indicates permission to transmit; The first information processing device, a storage process for storing the subject's eye image data when the first transmission data is received from the image acquisition device; a second generation process for generating identification information unique to the subject's eye image data when the first transmission data is received; a second transmission process of transmitting second transmission data including the identification information, the test eye image data, and the second consent information to the second information processing device; The second information processing device is an image diagnosis process for performing an image diagnosis based on the subject's eye image data when the second transmission data is received from the first information processing device; data processing for erasing the test eye image data after the image diagnostic processing when the second consent information indicates that reuse of the test eye image data is not permitted, and storing the test eye image data and an image diagnostic result by the image diagnostic processing in a database when the second consent information indicates that reuse of the test eye image data is permitted; a third transmission process of transmitting third transmission data including the identification information and the image diagnosis result to the first information processing device; An information processing system that executes the above.
Citation Information
Patent Citations
Medical information management system and medical information management method
JP2006201830A
Distributed machine learning system, apparatus, and method
JP2019526851A
Diagnosis support device, learning device, diagnosis support method, learning method, and program
WO2019142910A1
Ophthalmologic information processing system, ophthalmologic information processing server, and ophthalmologic information processing method
JP2015221276A
