Information processing system

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

Description

Incorporation by Reference

[0001] This application claims priority from U.S. Provisional Patent Application No. 62 / 880,961, filed on July 31, 2019, the content of which is incorporated into this application by reference. Technical Field

[0002] The present invention relates to an information processing system, an information processing apparatus, an image acquisition apparatus, an information processing method, an image acquisition method, and a program. Background Art

[0003] An ophthalmic information processing server capable of performing ophthalmic image analysis is known (see Patent Document 1). There is a need for a system that increases the degree of freedom in diagnosis for the requester. Prior Art Literature Patent Literature

[0004] Patent Document 1 Japanese Patent No. 5951086 Summary of Invention

[0005] An information processing system comprising one aspect of the invention disclosed in this application includes: an image acquisition device for acquiring image data of a patient's eye; a first information processing device that can communicate with the image acquisition device and stores the image data of the eye; a second information processing device that can communicate with the first information processing device and obtains a first diagnostic result by artificial intelligence from the image data of the eye; and a third information processing device that can communicate with the first information processing device and obtains a second diagnostic result by a radiologist from the image data of the eye. The image acquisition device performs a first generation process for generating diagnostic method information indicating a diagnosis by artificial intelligence and / or a diagnosis by a radiologist, and a first transmission process for transmitting first transmission data including the image data of the eye and the diagnostic method information to the first information processing device. The first information processing device, upon receiving the first transmission data from the image acquisition device, performs a storage process for storing the image data of the eye, and a second transmission process for transmitting second transmission data including the image data of the eye 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 this application, is capable of communicating with an image acquisition device that acquires image data of a patient's eye and stores the image data of the eye and includes a receiving unit that receives first transmission data transmitted from the image acquisition device, which includes diagnostic method information indicating whether it is an image diagnosis by artificial intelligence and / or an image diagnosis by a physician and the image data of the eye; a generating unit that generates second transmission data which includes the image data of the eye; a second information processing device that performs an image diagnosis by artificial intelligence and outputs a first diagnosis result; and a third information processing device that performs an image diagnosis by a radiologist and outputs a second diagnosis result, and a control unit that determines the destination of the second transmission data based on the diagnostic method information; and a transmitting unit that transmits the second transmission data to the destination determined by the control unit.

[0007] An image acquisition device comprising one aspect of the invention disclosed in this application, comprising: an acquisition unit capable of communicating with a first information processing device that stores image data of a patient's eye, and acquiring the image data of the eye; a generation unit that generates first transmission data including diagnostic method information indicating whether the image diagnosis is performed by artificial intelligence and / or by a radiologist, and the image data of the eye; and a transmission unit that transmits the first transmission data to the first information processing device.

[0008] An information processing method that constitutes one aspect of the invention disclosed in this application is performed by a first information processing device that can communicate with an image acquisition device that acquires image data of a patient's eye and / or that stores the image data of the eye, and includes the following: the first information processing device receives first transmission data transmitted from the image acquisition device, which includes diagnostic method information indicating whether it is an image diagnosis by artificial intelligence and / or an image diagnosis by a physician and the image data of the eye; the first information processing device generates second transmission data which includes the image data of the eye; the first information processing device determines the destination of the second transmission data based on the diagnostic method information from a second information processing device that performs an image diagnosis by artificial intelligence and outputs a first diagnosis result, and a third information processing device that performs an image diagnosis by a radiologist and outputs a second diagnosis result; and the first information processing device transmits the second transmission data to the determined destination.

[0009] An information processing method that constitutes one aspect of the invention disclosed in this application is performed by an image acquisition device that can communicate with a first information processing device that stores a patient's eye image data and acquires the eye image data, and includes the following steps: the image acquisition device acquires the eye image data; the image acquisition device generates first transmission data including diagnostic method information indicating whether it is an image diagnosis by artificial intelligence and / or an image diagnosis by a radiologist and the eye image data; and the image acquisition device transmits the first transmission data to the first information processing device.

[0010] A program representing one aspect of the invention disclosed in this application causes a first information processing device, which is communicable with an image acquisition device that acquires image data of a patient's eye and stores the image data of the eye, to perform information processing, including: receiving first transmission data transmitted from the image acquisition device, which includes diagnostic method information indicating whether it is an image diagnosis by artificial intelligence and / or an image diagnosis by a physician, and the image data of the eye; generating second transmission data which includes the image data of the eye; and from a second information processing device that performs an image diagnosis by artificial intelligence and outputs a first diagnosis result, and a third information processing device that performs an image diagnosis by a radiologist and outputs a second diagnosis result, to determine the destination of the second transmission data based on the diagnostic method information, and to transmit the second transmission data to the determined destination.

[0011] A program that constitutes one aspect of the invention disclosed in this application is a program that causes an image acquisition device, which is able to communicate with a first information processing device that stores image data of a patient's eye, to perform an image acquisition process, and which performs the following processes: a process to acquire the image data of the eye; a process to generate first transmission data including diagnostic method information indicating whether it is an image diagnosis by artificial intelligence and / or an image diagnosis by a radiologist and the image data of the eye; and a process to transmit the first transmission data to the first information processing device. [Brief explanation of the drawing]

[0012] [Figure 1] This is an explanatory diagram showing an example configuration of the medical imaging system in Example 1. [Figure 2] This is a block diagram showing an example of the computer's hardware configuration in Example 1. [Figure 3] This is a block diagram showing an example of the functional configuration of the management server in Example 1. [Figure 4] This is a block diagram showing an example of the functional configuration of the diagnostic server in Example 1. [Figure 5] This is a block diagram showing an example of the functional configuration of the in-hospital server in Example 1. [Figure 6]FIG. 1 is a block diagram showing an example functional configuration of a terminal in Embodiment 1. [Figure 7] FIG. 2 is a block diagram showing an example functional configuration of an image reading server in Embodiment 1. [Figure 8] FIG. 3 is a sequence diagram showing an example of image diagnostic processing in Embodiment 1. [Figure 9] FIG. 4 is an example of a patient information DB in Embodiment 1. [Figure 10] FIG. 5 is an example of an input screen for setting an AI / image reading flag in Embodiment 1. [Figure 11] FIG. 6 is a flowchart showing an example of processing for setting an AI / image reading flag in Embodiment 1. [Figure 12] FIG. 7 is an example of a data structure of anonymized diagnostic target data in Embodiment 1. [Figure 13] FIG. 8 is an example of a display screen that displays a diagnostic result in Embodiment 1. [Figure 14] FIG. 9 is another example of a display screen that displays a diagnostic result in Embodiment 1. DETAILED DESCRIPTION OF THE INVENTION

[0013] Hereinafter, embodiments of the present invention will be described with reference to the accompanying drawings. It should be noted that the present embodiment is merely an example for realizing the present invention, and does not limit the technical scope of the present invention. In each drawing, common components are denoted by the same reference numerals. EXAMPLES

[0014] FIG. 1 is an explanatory diagram showing a configuration example of the image diagnostic system according to the present embodiment. The image diagnostic system includes a management server 100, a diagnostic server 200, and an image reading server 250. The image diagnostic system also includes an in-hospital server 300, a terminal 400, and an imaging device 500 installed in, for example, a hospital, a clinic, or a health examination facility. The in-hospital server 300, the terminal 400, and the imaging device 500 are each connected via a network.

[0015] The imaging device 500 is an ophthalmologic apparatus for photographing the fundus, and examples thereof include a fundus camera, a scanning laser ophthalmoscope, and optical coherence tomography. The imaging device 500 is connected to the terminal 400. The imaging device 500 photographs the subject's eye to be examined, and generates fundus image data of the right eye and the left eye of the examined eye. The generated fundus image data is transmitted to the terminal 400.

[0016] In addition, the fundus image data may be any one of fundus image data captured by a fundus camera, fundus image data captured by a scanning laser ophthalmoscope, or tomographic data of the fundus captured by optical coherence tomography. Alternatively, the fundus image data may be a fundus image data set that is a combination of two or more of the aforementioned data. Note that the imaging device 500 may also be configured to photograph not only the fundus but also the anterior segment of the examined eye to generate anterior segment image data. The fundus image data and the anterior segment image data are examples of examined eye image data.

[0017] The terminal 400 is an example of an image acquisition device, and is a computer such as a personal computer (PC) or a tablet used by a requesting doctor, an operator of ophthalmic equipment, or the like. The terminal 400 is connected to the in-hospital server 300. The terminal 400 transmits AI / interpretation information, patient information, and fundus image data to the in-hospital server 300. The AI / interpretation information is information indicating a diagnostic method: whether the diagnosis is performed by the AI 220 mounted on the diagnostic server 200 which is the server of the first requester, or by an image reading doctor at a facility where the image reading server 250 which is the server of the second requester is installed, or by both of them.

[0018] Furthermore, AI / image interpretation information may be stored as AI / image interpretation flags (01: AI-based image diagnosis, 10: image diagnosis by a radiologist, 11: image diagnosis by both AI and radiologist). AI / image interpretation information also serves as destination specification information, allowing the requester to specify whether they want an AI-based image diagnosis, an image diagnosis by a radiologist, or both. Similarly, the AI / image interpretation flags can also function as destination specification information flags.

[0019] The 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 hospital server 300 is connected to the management server 100 via a network. The 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 / interpretation information received from the terminal 400 into a dataset. The hospital server 300 then transmits the diagnostic target data to the management server 100. Note that some or all of the patient information and AI / interpretation information in the diagnostic target data may be generated by the hospital server 300. In addition, fundus image data captured by the imaging 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 the diagnostic target data in which some of the information (e.g., patient information) received from the hospital server 300 has been anonymized. 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 the destination for requesting (transmitting) fundus image data, and transmits the anonymized diagnostic target data to the selected server.

[0021] Furthermore, the management server 100 receives image diagnostic results from the diagnostic server 200 and / or the image interpretation server 250 and transmits them to the in-hospital server 300 and terminal 400. The function of saving fundus image data may be configured to save it in an image database (not shown) of the management server 100 instead of the in-hospital server 300. Small clinics may not have an in-hospital server, in which case the management server 100 may take on the functions of the in-hospital server 300.

[0022] Furthermore, if the AI / image interpretation information is an AI / image interpretation flag generated by the in-hospital server 300 or terminal 400, the management server 100 will determine the destination server for the anonymized diagnostic 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 anonymized diagnostic target data, it performs image diagnosis on the fundus image data contained in the anonymized diagnostic target data using the AI ​​220 and transmits the encrypted diagnostic results to the management server 100. The AI ​​220 can determine the symptom level of a predetermined disease such as diabetic retinopathy, or it can determine whether or not symptoms of one or more diseases are present.

[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 a radiologist is located. When the image interpretation server 250 receives anonymized diagnostic data, it displays the fundus images contained in the anonymized diagnostic data on a display or the like, and accepts input of diagnostic results for the fundus image data from the radiologist or the like. The image interpretation server 250 encrypts the input diagnostic results and transmits the encrypted diagnostic results to the management server 100.

[0025] Furthermore, any devices included in the diagnostic imaging system may be connected to each other. Also, some or all of the functions of each device included in the diagnostic imaging system may be included in other devices, or some or all of the aforementioned devices may be integrated. Specifically, for example, terminal 400 and imaging equipment 500 may be integrated, or the in-hospital server 300 and terminal 400 may be integrated.

[0026] For the sake of explanation, Figure 1 shows one diagnostic server 200 and one image interpretation server 250, but the image diagnostic system may include multiple diagnostic servers 200 and multiple 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] Figure 2 is a block diagram showing an example of the hardware configuration of the computers that make up the management server 100, diagnostic server 200, image interpretation server 250, in-hospital server 300, and terminal 400, respectively. 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 internal signal lines 606.

[0028] The processor 601 executes a program stored in the memory device 602. The memory device 602 includes memory. The memory includes ROM, which is a non-volatile memory element, and RAM, which is a volatile memory element. ROM stores data and programs (e.g., BIOS). RAM is a high-speed, volatile memory element such as DRAM (Dynamic Random Access Memory), and temporarily stores the program executed by the processor 601 and the data used during program execution.

[0029] Furthermore, the memory device 602 includes an auxiliary storage device. The auxiliary storage device is a high-capacity, non-volatile storage device such as a magnetic storage device (HDD) or flash memory (SSD), and stores the program executed by the processor 601 and the data used when the program is executed. That is, the program is read from the auxiliary storage device, loaded into memory, and executed by the processor 601.

[0030] The input device 603 is a device that receives input from the operator, such as a keyboard or mouse. The output device 604 is a device that outputs the results of program execution in a format that the operator can see, such as a display or printer. The input device 603 and the output device 604 may be integrated, such as in 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 program executed by processor 601 is provided to computer 600 via removable media (such as CD-ROM or flash memory) or a network, and stored in a non-volatile auxiliary storage device, which is a non-temporary storage medium. For this reason, computer 600 should have an interface for reading data from the removable media.

[0032] Furthermore, the management server 100, diagnostic server 200, image interpretation server 250, in-hospital server 300, and terminal 400 are each computer systems that are physically located on a single computer 600, or on multiple logically or physically configured computers 600. They may operate in separate threads on the same computer 600, or they may operate on virtual computers built on multiple physical computing resources.

[0033] Figure 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 diagnostic result data generation unit 104. The anonymization processing unit 101 anonymizes patient information contained in the diagnostic target data transmitted from the in-hospital server 300. The server selection unit 102 selects the server to which the diagnostic target data will be sent (the server to which the image diagnosis will be requested) based on the AI / image interpretation information contained in the diagnostic target data.

[0034] The display screen generation unit 103 generates screen information to be displayed on the output device 604. The diagnostic result data generation unit 104 decrypts the encrypted diagnostic results received from the diagnostic server 200 and transmits them to the in-hospital server 300.

[0035] The functional units included in the management server 100 are implemented by the processor 601 of the computer 600 that implements the management server 100. Specifically, the processor 601 functions as an anonymization processing unit 101 by operating according to an anonymization processing program loaded into the memory included in the storage device 602, and functions as a server selection unit 102 by operating according to a server selection program loaded into the 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 implemented by the processor 601 operating according to programs loaded into memory.

[0036] The management server 100 holds server selection information 110. The server selection information 110 is information consisting of a lookup table that shows the correspondence between AI / image interpretation information and the server to which the image diagnosis is requested (diagnosis server 200 and / or image interpretation server 250). However, if the destination server for the anonymized diagnostic data is determined by the terminal 400 or the in-hospital server 300, the management server 100 does not need to hold server selection information 110.

[0037] The server selection information 110 is stored in the auxiliary storage device included in the storage device 602 of the computer 600 that implements the management server 100. Similarly, information and databases held by other devices are also stored in the auxiliary storage device included in the storage device 602 of the computer 600 that implements those other devices.

[0038] In this embodiment, the information used by each device included in the medical imaging system may be represented in any data structure, regardless of the data structure. For example, a data structure appropriately selected from tables, lists, databases, or queues can store the information.

[0039] Figure 4 is a block diagram showing an example of the functional configuration of the diagnostic server 200. The diagnostic server 200 includes an image diagnostic 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 diagnostic model 211. The learning DB 210 is a database for constructing the image diagnostic model 211. The image diagnostic model 211 is a model that outputs a diagnostic 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 on fundus image data included in the anonymized diagnostic target data received from the management server 100, using the image diagnosis model 211, and determines the grade of diabetic retinopathy.

[0041] The learning information management unit 202 stores the fundus image data and image diagnosis results included in the anonymized diagnostic target data in the learning DB 210 as training data for the 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 generation unit 203 generates a diagnosed fundus image by overlaying marks indicating the location of lesions and the name of the disease onto the diagnosed fundus image. The management unit 204 manages the version and updates of the AI ​​220. The management unit 204 also packages the diabetic retinopathy grade and the diagnosed fundus image (if created by the diagnostic screen generation unit 203) as a diagnostic result. Then, it links the diagnostic result with anonymous patient information and generates AI diagnostic result information. The generated AI diagnostic result information is sent to the management server 100.

[0043] Furthermore, the diagnostic server 200 does not need to have a learning function for the image diagnostic model 211. In other words, the diagnostic server 200 may continue to perform image diagnostics without updating the image diagnostic model 211, keeping a predetermined image diagnostic model 211 fixed. In this case, the diagnostic server 200 does not need to have a learning information management unit 202 and a learning DB 210.

[0044] Figure 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 the patient information DB 310. The in-hospital server 300 may also hold server selection information, in which case the in-hospital server 300 may use the server selection information to determine the destination server for the anonymized diagnostic data.

[0045] The anonymization processing unit 301 anonymizes patient information included in the diagnostic data. The patient information management unit 302 stores patient information included in the diagnostic data in the patient information DB 310, or retrieves patient information from the patient information DB 310 and adds it to the diagnostic data. The display screen generation unit 303 generates screen information to be displayed on the output device 604. The patient information DB 310 holds patient personal information and diagnostic history information.

[0046] If the hospital server 300 has server selection information, this server selection information is similar to the server selection information 110 held by the management server 100, and consists of information such as a lookup table showing the correspondence between AI / image interpretation information and servers (diagnostic server 200 and / or image interpretation server 250).

[0047] Figure 6 is a block diagram showing an example of the functional configuration of terminal 400. Terminal 400 includes a diagnostic target data generation unit 401, an AI / image interpretation information setting unit 402, and a display screen generation unit 403. The diagnostic target data generation unit 401 generates diagnostic target data including patient information, additional information, and fundus image data. The AI / image interpretation information setting unit 402 acquires information for selecting a server to perform image diagnosis. The display screen generation unit 403 generates screen information to be displayed on the output device 604.

[0048] Terminal 400 may maintain server selection information, in which case terminal 400 may use the server selection information to determine the destination server for the anonymized diagnostic data. The server selection information maintained by terminal 400, similar to the server selection information 110, indicates, for example, the correspondence between AI / image interpretation information and a server (diagnostic server 200 and / or image interpretation server 250). Note that terminal 400 may maintain server selection information, in which case terminal 400 may use the server selection information to determine the destination server for the anonymized diagnostic data.

[0049] If terminal 400 has server selection information, this server selection information is similar to the server selection information 110 held by management server 100, and consists of information such as a lookup table showing the correspondence between AI / image interpretation information and servers (diagnostic server 200 and / or image interpretation server 250).

[0050] Figure 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 generation unit 251, a diagnostic information management unit 252, and a management unit 253. The image interpretation server 250 also maintains, for example, a diagnostic information DB 260 that stores a collection of diagnostic cases.

[0051] The diagnostic screen generation unit 251 generates a diagnostic screen based on instructions from a radiologist at a radiology facility that owns the image interpretation server 250. This screen uses fundus image data and anonymized patient information (such as gender and age, which are necessary for the radiologist's diagnosis but do not identify the individual) transmitted from the management server 100. The generated diagnostic screen data is then displayed on a display (not shown). The radiologist interprets the fundus image on the diagnostic screen and determines the grade of diabetic retinopathy (furthermore, other lesions may be discovered).

[0052] The radiologist then enters the grade of diabetic retinopathy in the diagnostic result input field on the diagnostic screen. The radiologist may also enter their findings and any other lesions discovered in the comment field on the diagnostic screen. Furthermore, marks and text may be added to the displayed fundus image. The diagnostic screen generation unit 251 may also display data from the diagnostic information DB 260 in response to the radiologist's request, allowing it to access the diagnostic case collection.

[0053] The diagnostic information management unit 252 packages the grade of diabetic retinopathy, the text entered by the radiologist, and the fundus image data annotated by the radiologist into a diagnostic result via a diagnostic screen. Then, the management unit 253 links the radiologist's information (name, radiologist code, etc.) and the diagnostic result with anonymous patient information to generate radiologist diagnostic result information. Finally, it sends the radiologist diagnostic result information to the management server 100.

[0054] Figure 8 is a sequence diagram showing an example of image diagnostic processing. In Figure 8, a server to perform image diagnosis is selected based on AI / image interpretation information.

[0055] First, the diagnostic data generation unit 401 of terminal 400 accepts patient information via the input device 603 (S801). The patient identification ID, as well as the patient's age, gender, address, medical history, medication history, and interview results are all examples of patient information. For patients whose information is already registered in the patient information DB 310, the diagnostic data generation unit 401 can, for example, accept the input of the patient identification ID and obtain other information from the registered information corresponding to that ID.

[0056] The diagnostic data generation unit 401 acquires the image data of both the left and right eyes of the patient transmitted from the imaging device 500 (S802). In this embodiment, image data of both eyes may be acquired, or fundus image data of only one eye, the left or the right eye, may be acquired. The diagnostic data generation unit 401 generates a left / right eye flag indicating whether the fundus image data is from both eyes, the right eye only, or the left eye only. The diagnostic data generation unit 401 may acquire fundus image data from a device other than the imaging 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 the AI / image interpretation flag as AI / image interpretation information, or it may collect information necessary for the management server 100 to determine the destination server as AI / image interpretation information. Details of step S803 will be described later.

[0058] Next, the diagnostic data generation unit 401 transmits the diagnostic data, including patient information, left and right eye flags, fundus image data, and AI / interpretation information, to the management server 100 via the in-hospital server 300 (S804). The patient information management 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 there is any missing patient information received from terminal 400, the patient information management unit 302 may refer to the patient information database 310 to obtain additional patient information and supplement the diagnostic data. Specifically, for example, if the patient information received from terminal 400 consists only of a patient identification ID, the patient information management unit 302 will obtain the patient information corresponding to that ID from the patient information database 310 and send the diagnostic data, including the obtained 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 diagnostic history information included in the received diagnostic data using a predetermined algorithm (S805). As part of the anonymization processing, the anonymization processing unit 101 performs processes 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 name and disease name. The anonymization processing unit 101 may anonymize only a portion of the patient information and diagnostic history information (for example, only sensitive information related to privacy). Furthermore, the anonymization processing of patient information may be performed in advance by the anonymization processing unit 301 of the hospital server 300 before the diagnostic 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 image interpretation server 250 based on the AI / image interpretation information (e.g., AI / image interpretation flag) included in the received diagnostic target data, and transmits the anonymized diagnostic target data, which includes anonymized patient information, eye image data, and AI / image interpretation information, to the selected diagnostic server 200 (S806).

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

[0063] Next, the diagnostic server 200 and / or image interpretation server 250, which have received the anonymized diagnostic data, begin the process of performing image diagnosis on the fundus image data contained in the received anonymized diagnostic data (S807). When the diagnostic server 200 receives the anonymized diagnostic 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., when performing AI-based diagnosis in the image diagnosis.

[0064] Furthermore, when the image interpretation server 250 receives anonymized diagnostic data, the diagnostic information management unit 252 may send diagnostic information, including the image data of the eye being examined 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 image data of the eye being examined as learning data in the learning DB 210, and updates the image diagnostic model 211 based on the updated learning DB 210. This allows the diagnostic server 200 to perform AI 220 training even if it has not been requested to perform an image diagnosis.

[0065] When the image interpretation server 250 receives anonymized diagnostic data, the diagnostic screen generation unit 251 displays the anonymized patient information, right eye / left eye flags, and the image data of the eye being examined on the output device 604 (display) of the image interpretation server 250. The diagnostic screen generation unit 251 of the image interpretation server 250 accepts input of image diagnostic results from the user of the image interpretation server 250 (e.g., a radiologist) via the input device 603.

[0066] The diagnostic server 200 and / or image interpretation server 250 that performed the fundus image diagnosis generate diagnostic result information. Specifically, if the diagnostic server 200 performed the fundus image diagnosis in step S807, the diagnostic screen generation unit 203 generates a diagnosed fundus image (an example of the first diagnostic result) on which marks indicating the location of lesions and the name of the disease are superimposed.

[0067] Furthermore, when the image interpretation server 250 starts the process of performing image diagnosis in step S807, the diagnostic information management unit 252 packages the grade of diabetic retinopathy, the text entered by the radiologist, and the fundus image data with annotations made by the radiologist into a diagnostic result via the diagnostic screen. The management unit 253 links the information of the radiologist who performed the interpretation, the diagnostic result, and the anonymous patient information to generate radiologist diagnosis result information (an example of a second diagnostic result).

[0068] Next, the diagnostic server 200 and / or image interpretation server 250 that generated the image diagnostic results encrypt the image diagnostic results (which are the diagnosed fundus images if the diagnosis was made by the diagnostic server 200, and the radiologist's diagnostic result information (such as the diagnosed disease name, lesion grade, and radiologist's findings) if the diagnosis was made by a radiologist on the image interpretation server 250) using the encryption key they hold, generate encrypted image diagnostic results, and send them to the management server 100 (S809). In step S809, anonymization may be performed instead of or in addition to encryption.

[0069] Next, the diagnostic result data generation unit 104 of the management server 100 decrypts the received encrypted image diagnostic results using the decryption key held by the management server 100 (S810). If the received image diagnostic results were anonymized, the diagnostic result data generation unit 104 restores the anonymized patient information of the image diagnostic results. Then, it links the decrypted image diagnostic results with the patient information of the patient before anonymization.

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

[0071] Furthermore, if the management server 100 does not receive encrypted image diagnostic results from the server that sent the anonymized diagnostic data even after a predetermined period of time has elapsed, it may send the anonymized data to another server and request image diagnostics from that server.

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

[0073] Alternatively, the display screen generation unit 103 of the management server 100 may generate display screen information based on the image diagnosis results and patient information and send it to the in-hospital server 300, and the in-hospital server 300 and terminal 400 may display the display screen according to the generated information.

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

[0075] Figure 9 shows an example of a patient information database 310. The patient information database 310 includes a patient information field 3101 and a diagnosis history information field 3102. The patient information field 3101 stores, for example, each patient's personal information. The diagnosis history information field 3102 stores the diagnosis history of fundus image data from the diagnosis server 200 and the image interpretation server 250. In the example in Figure 8, the diagnosis history records fundus image data, diagnosis results, the date the fundus images were taken, and identification information of the diagnosis server 200 and / or image interpretation server 250 that performed the image diagnosis.

[0076] The following describes the details of the AI / image interpretation information setting process in step S803. In the following example, in step S803, the AI / image interpretation information setting unit 402 of terminal 400 sets the AI / image interpretation flag as AI / image interpretation information. In this case, the management server 100 determines the destination server for 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 and the communication IF 605. Figure 10 shows 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 patient information such as an ID to identify the patient, and information about the eye image, such as the date and time the eye image was taken. The left eye image display area 1002 displays, for example, the left eye image. The right eye image display area 1003 displays the right eye image.

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

[0080] In the example shown in Figure 10, "radiologist" is selected in the diagnostic method selection area 1004, meaning the AI / image interpretation flag "10," which indicates the image interpretation server 250, is selected. When the send button 1005 is selected, the AI / image interpretation flag selected in the diagnostic method selection area 1004 is set. This allows the user of terminal 400 to perform image diagnosis using the desired server.

[0081] Furthermore, if terminal 400 holds server selection information, the AI / image interpretation information setting unit 402 may, in step S803, acquire predetermined information and set an AI / image interpretation flag in the server selection information held by terminal 400 that indicates the destination server corresponding to the acquired information. The patient's diagnostic history information shown in the patient information DB 310 of the in-hospital server 300 is an example of such predetermined information.

[0082] Figure 11 is a flowchart illustrating 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 obtains the patient's diagnostic history from the patient information DB 310 of the hospital server 300 as AI / image interpretation information (S1101).

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

[0084] Next, the AI / image interpretation information setting unit 402 determines whether the image diagnostic 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 diagnostic 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 terminates the process in 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 process in step S802.

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

[0088] The processing shown in Figure 10 allows patients to receive balanced image diagnoses from both the diagnostic server 200 and the image interpretation server 250, without being biased towards any particular server. On the other hand, if a physician or patient using terminal 400 prefers a specific server, an AI / image interpretation flag may be set to indicate the same server as the source of the image diagnosis in the most recent diagnosis history. Furthermore, for example, in the initial diagnosis of a 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 specialty of the doctor using the terminal 400. Specifically, for example, the AI / image interpretation information setting unit 402 accepts input of a medical specialty, sets an AI / image interpretation flag indicating the diagnostic server 200 if the specialty is ophthalmology, and sets an AI / image interpretation flag indicating the image interpretation server 250 if the specialty is something other than ophthalmology (e.g., internal medicine).

[0090] This allows physicians with expertise in ophthalmology to obtain sufficient diagnostic results even with image diagnosis performed by the diagnostic server 200 using AI220 for rapid diagnosis, while physicians other than ophthalmologists can obtain diagnostic results supplemented with the expertise of a radiologist. Furthermore, if the image diagnosis performed by AI220 is considered to have more comprehensive insights than the image diagnosis performed by a radiologist, the AI / radiology flag may be set to indicate the diagnostic server 200 when the physician's specialty is not ophthalmology, and to indicate the radiology server 250 when the physician's specialty is ophthalmology.

[0091] Furthermore, in step S803, the AI / image interpretation information setting unit 402 may set an AI / image interpretation flag based on information about the installation location of the imaging device 500. Specifically, the terminal 400 holds information indicating the correspondence between the identification information of the imaging device 500 and its installation location. The AI / image interpretation information setting unit 402 acquires the identification information of the imaging device 500 that captured the eye image of the subject and identifies the installation location of the imaging device 500. If the installation location is an institution with ophthalmologists, 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 diagnostic server 200, and if it is an institution without ophthalmologists, such as an internist, it sets an AI / image interpretation flag indicating the image interpretation server 250.

[0092] As a result, institutions with knowledgeable ophthalmologists, such as hospitals with diabetes centers or ophthalmology departments, can obtain sufficient diagnostic results even with image diagnosis performed by the diagnostic server 200 using AI220 for rapid diagnosis, and physicians other than ophthalmologists, such as internal medicine specialists, can obtain diagnostic results supplemented with the expertise of radiologists.

[0093] Furthermore, if it is considered that the image diagnosis performed by AI220 has more extensive knowledge than that performed by a radiologist, the AI / image interpretation flag may be set to indicate the diagnostic server 200 if the installation location is an institution without ophthalmologists, such as an internist, and the AI / image interpretation flag may be set to indicate the image interpretation server 250 if the installation location is an institution with ophthalmologists, such as a diabetes center or a hospital with an ophthalmology department. Alternatively, the AI / image interpretation flag may be set based on the installation location of the terminal 400 or the in-hospital server 300 in the same manner as described above.

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

[0095] While the diagnostic server 200 automatically performs diagnoses using AI 220, the image interpretation server 250 often incurs higher diagnostic costs due to the labor costs of the radiologist. Therefore, as mentioned above, by setting the AI / image interpretation flag based on the pricing information of the diagnostic course, users can receive an appropriate diagnosis according to the price. For example, if image diagnosis using AI 220 is more expensive, the AI / image interpretation flag may be set to indicate the diagnostic server 200 when the price is above a predetermined threshold, and to indicate the image interpretation server 250 when the price is below that threshold.

[0096] In addition, in step S803, the AI / image interpretation information setting unit 402 may set the AI / image interpretation flag based, for example, on the schedule information of the radiologist performing the image diagnosis using the image interpretation server 250.

[0097] Specifically, the AI / image interpretation information setting unit 402 periodically acquires schedule information of radiologists performing image diagnoses from the image interpretation server 250 (for example, information indicating when image diagnoses can be performed, such as the radiologist's availability). The AI / image interpretation information setting unit 402, for example, refers to the schedule information and sets an AI / image interpretation flag indicating the diagnostic server 200 if the time until the radiologist can start the image diagnose is greater than or equal to 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] This allows for rapid image diagnosis via AI220 on diagnostic server 200 if the radiologist's schedule is full, and image diagnosis based on the radiologist's expertise if the radiologist's schedule is free.

[0099] Furthermore, in step S803, the AI / image interpretation information setting unit 402 may set an AI / image interpretation flag based, for example, on the symptoms and / or diagnostic classification of the target to be diagnosed desired by the doctor or other person using the terminal 400.

[0100] Specifically, the AI / image interpretation information setting unit 402 accepts input of the symptoms to be diagnosed and / or the diagnostic classification, and sets an AI / image interpretation flag indicating a server capable of performing image diagnosis based on those symptoms and / or the diagnostic classification. The terminal 400 is assumed to have pre-stored information indicating the symptoms and / or diagnostic classifications that can be diagnosed by the diagnostic server 200 and the image interpretation server 250 (the doctor performing the 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 field of view of the eye image taken by the imaging device 500. Specifically, the AI / image interpretation information setting unit 402 obtains the field of view of the eye image taken by the imaging device 500 from the imaging device 500. The AI / image interpretation information setting unit 402 may also store in advance a correspondence between the ID of the imaging device 500 and the field of view, and obtain the field of view according to that correspondence.

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

[0103] This allows patients to receive image-based diagnoses using images of the examined eye from the field of view that the radiologists using the AI220 on the diagnostic server 200 and the image interpretation server 250 are proficient in (for example, those who can make highly accurate diagnoses).

[0104] In the example described above, terminal 400 collects the necessary information and sets the AI / image interpretation flag. However, the hospital server 300 or management server 100 may also collect the necessary information and set the AI / image interpretation flag.

[0105] Furthermore, even if the AI / image interpretation flag is set from the input screen 1000 in Figure 10, the AI / image interpretation information setting unit 402 may select the AI / image interpretation flag based on the information described above. If the AI / image interpretation flag set from 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 the display via the display screen generation unit 403 and recommend it to the user, or it may set the AI / image interpretation flag selected by the AI / image interpretation information setting unit 402.

[0106] Furthermore, while the above example described a case where the AI / image interpretation flag is determined from one type of information, the AI / image interpretation flag may also be determined from multiple types of information. Specifically, for example, conditional branching based on the values ​​indicated by the multiple types of information may be described in the server selection information 110, and the AI / image interpretation flag may be determined from the values ​​of the multiple types of information.

[0107] Figure 12 shows an example of the data structure of anonymized diagnostic data transmitted from the management server 100 to the diagnostic server 200. The anonymized diagnostic 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] Header 701 contains information such as defining the data format of the data to be diagnosed, and information such as the source and destination of the data to be diagnosed. DICOM data 702 contains information such as the format of the medical image (fundus image) data captured by the imaging device 500, and information defining the communication protocol between medical devices, including the imaging device 500.

[0109] User data 703 includes, for example, an AI / interpretation flag, left / right eye flag, anonymized patient information, and additional information. The left / right eye flag is a flag (for example, one of the values ​​L, R, or LR) that indicates whether the fundus image data 704 is image data from the right eye, the left eye, or both eyes.

[0110] Additional information includes, for example, attribute information of the captured image such as the device information of the imaging device 500, information about the hospital and doctor using the terminal 400, and the name of the disease being diagnosed. The field of view, modality, and resolution of the image (image of the eye being examined) captured by the imaging device 500, as well as the device ID of the imaging device 500, are all examples of device information.

[0111] Modality refers to information indicating the type of imaging device 500 (e.g., fundus camera, scanning laser ophthalmoscope, optical coherence tomography, etc.) or the type of medical image captured by imaging device 500 (e.g., fundus images or angiography images captured with red laser or near-infrared laser, etc.). Furthermore, the names of doctors and hospitals using terminal 400, and the locations where the terminals are installed (information on medical departments such as ophthalmology, internal medicine, or diabetology, as well as information on facilities such as opticians or health checkup facilities) are examples of relevant facility information.

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

[0113] Figure 13 shows the display screen (screen layout) for displaying the diagnostic results. The display screen 1300 includes a patient information display area 1301, a referral information display area 1302, an additional information display area 1303, a diagnostic result display area 1304, and a second opinion button 1305.

[0114] The patient information display area 1301 displays patient information included in the diagnostic imaging data. The referral information display area 1302 displays information about the referral agency that performed the diagnostic imaging. If the diagnostic imaging was performed by the artificial intelligence of the diagnostic server 200, the referral information display area 1302 displays the ID or server name of the AI ​​220 that performed the diagnostic imaging.

[0115] When fundus image data is sent to the image interpretation server 250 and an image diagnosis is performed by a radiologist, the requester information display area 1302 displays the ID or server name of the image interpretation server, the name of the radiology facility that owns the image interpretation server, and the names of the facility and physician who performed the image diagnosis.

[0116] The additional information display area 1303 displays some or all of the additional information (field of view, resolution, diagnosis type, etc.) included in the data to be diagnosed. The diagnosis result display area 1304 displays information indicating the diagnosis result of the fundus image data. In the example in Figure 13, the fundus images of both eyes, a bar indicating the symptom level of diabetic retinopathy in both eyes, and the findings for both eyes are displayed in the diagnosis result display area 1304.

[0117] In the example shown in Figure 13, a right-pointing arrow (indicator) showing 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, while a left-pointing arrow showing 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 differences in symptom levels by simply glancing at the diagnostic result display area 1304.

[0118] The second opinion button 1305 is a button for requesting a second opinion from another server. When the diagnostic server 200 performs an image diagnosis and the second opinion button 1305 is selected, the management server 100 is notified to send the anonymized image diagnosis data to the image interpretation server 250.

[0119] Furthermore, when fundus image data is sent to the image interpretation server 250 and an image diagnosis is performed by a radiologist, if the second opinion button 1305 is selected, the management server 100 is notified to send anonymized image diagnosis data to the diagnosis server 200. This allows doctors and patients to receive a second opinion from another server after reviewing the image diagnosis results.

[0120] Furthermore, the second opinion button 1305 may be displayed only when the symptoms are worse than a predetermined level in the image diagnostic results (for example, Mild or lower in Figure 13). Alternatively, if the symptoms are worse than a predetermined level in the image diagnostic results, the second opinion button 1305 may not be displayed, and the system may automatically receive image diagnostics from another server.

[0121] Furthermore, if image diagnosis is performed by the AI ​​220 of the diagnostic server 200, which can diagnose the presence or absence of a disease but cannot diagnose the symptom level of that disease, the second opinion button 1305 may be displayed. In addition, the management server 100 may maintain correspondence information between a disease and a server that can diagnose the symptom level of that 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 then send information indicating the identified server to the in-hospital server 300 for display, or it may send the anonymized diagnostic data again to the identified server to request image diagnosis.

[0123] Furthermore, the diagnostic server 200 and / or 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, a second opinion instruction is generated when the AI ​​220 of the diagnostic server 200 determines that a second opinion is necessary (for example, when it determines that a disease has occurred), or when the image interpretation server 250 receives input of a second opinion instruction from a user (for example, a radiologist).

[0124] The second opinion button 1305 may be displayed only if a second opinion request is included in the encrypted image diagnostic results, or if a second opinion request is included in the encrypted image diagnostic results, the second opinion button 1305 may not be displayed, and the system may automatically receive image diagnostics from another server.

[0125] Figure 14 shows an example of a display screen showing the diagnostic results when a second opinion is obtained. In Figure 14, the initial diagnosis was made by artificial intelligence (referral agency 1), and the second opinion was made by a radiologist (referral agency 2). The display screen 1400 includes a patient information display area 1401, a referral agency information display area 1402, an additional information display area 1403, a diagnostic result display area 1404, and another second opinion button 1406. The content displayed in the patient information display area 1401 and the additional information display area 1403 is the same as the content displayed in the patient information display area 1301 and the additional information display area 1303 in Figure 13, respectively.

[0126] Let's explain the differences from Figure 13. The requester information display area 1402 displays information for requester 1 and requester 2. In Figure 14, requester 1 is displayed as "Diagnostic Server A," and requester 2 displays 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 names of the facility and physician that performed the image diagnosis.

[0127] The diagnostic results display area 1404 displays the images of both eyes examined, a bar indicating the symptom level of diabetic retinopathy in both eyes, and the findings for both eyes, for both the initial diagnosis and the second opinion diagnosis. If the other second opinion button 1406 is operated, a further second opinion diagnosis can be obtained from another referral source 3, which is different from both referral source 1 and referral source 2. In this case, the management server 100 selects a third referral source server, different from diagnostic server A and image interpretation server A, as a candidate for the diagnostic source.

[0128] As shown in the display screen 1400 in Figure 14, by displaying the two diagnostic results together, users of the in-hospital server 300 and terminal 400 can obtain a more accurate diagnostic result that combines these two.

[0129] It should be noted that the present invention is not limited to the above, and may be any combination thereof. Furthermore, other embodiments that can be conceivable within the scope of the technical idea 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 Image Interpretation 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 / Image Interpretation Information Setting Unit, 403 Display Screen Generation Unit, 600 Computer, 601 Processor, 602 Storage Device, 603 Input Device, 604 Output device, 605 communication interface

Claims

1. An information processing device capable of communicating with a first image diagnostic device that performs image diagnosis on a patient's eye image data using artificial intelligence, and a second image diagnostic device that performs image diagnosis on the said eye image data by a radiologist, A generation unit generates diagnostic method information indicating a diagnosis by artificial intelligence and / or a diagnosis by a radiologist, based on at least one of the following: image diagnosis results for the eye image data of the subject, past diagnosis history, number of diagnoses, the medical department of the doctor using the image acquisition device, the location where the medical department is set up, fee information for the diagnosis course, the radiologist's schedule, the symptoms to be diagnosed, the diagnostic classification, and the field of view of the eye image data of the subject. A determination unit that determines, based on the diagnostic method information, whether to send the image data of the eye to the first diagnostic imaging device only, to the second diagnostic imaging device only, or to both the first and second diagnostic imaging devices, A transmission unit that transmits the image data of the eye being examined and the diagnostic method information according to the judgment result, The system includes a receiving unit that receives image diagnostic results, including second opinion instruction information, from the first or second image diagnostic device, The transmitting unit is an information processing device that, based on the image diagnosis results, sends the image data of the eye under examination to an image diagnosis device different from the image diagnosis device that sent the image diagnosis results.

2. An information processing apparatus according to claim 1, The transmitting unit is an information processing device that transmits the image data of the eye to the second image diagnostic device when the receiving unit receives the image diagnostic result including the second opinion instruction information from the first image diagnostic device.

3. An information processing apparatus according to claim 1, The transmitting unit is an information processing device that transmits the image data of the eye to the first image diagnostic device when the receiving unit receives the image diagnostic result including the second opinion instruction information from the second image diagnostic device.

Images