Analysis device, analysis method, analysis program, and recording medium

Abstract

Provided is a system with which it is possible to analyze medical data while keeping personal information secret. An analysis device is provided with an acquisition unit that acquires unencrypted medical data and second identification information obtained by encrypting the first identification information of a subject from a user terminal, an analysis unit that analyzes the acquired medical data, and a transmission unit that transmits the analysis result analyzed by the analysis unit and second identification information to the user terminal.

Description

Technical Field

[0001] The present disclosure relates to an analysis device, an analysis method, an analysis program, and a recording medium.

Background Art

[0002] For example, Patent Document 1 discloses a medical system including a medical device that observes a subject and a network device that can communicate with the medical device.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

[0004] An analysis device according to an aspect of the present disclosure includes an acquisition unit that acquires medical data of a subject and second identification information obtained by encrypting first identification information of the subject from a user terminal, an analysis unit that analyzes the acquired medical data, and a transmission unit that transmits an analysis result analyzed by the analysis unit and the second identification information to the user terminal.

[0005] An analysis method according to an aspect of the present disclosure includes at least one processor acquiring medical data of a subject and second identification information obtained by encrypting first identification information of the subject from a user terminal, analyzing the acquired medical data, and transmitting an analysis result and the second identification information to the user terminal.

[0006] The analysis device according to each aspect of the present disclosure may be implemented by a computer. In this case, a control program for a computer to implement the analysis system by operating the computer as each part (software element) included in the analysis system and a computer-readable non-transitory recording medium recording the same also fall within the scope of the present disclosure.

Brief Description of Drawings

[0007]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Embodiments for Carrying Out the Invention

[0008] 〔Embodiment 1〕 (Configuration of Analysis System 70) Hereinafter, an embodiment of the present disclosure will be described in detail with reference to the drawings. FIG. 1 is a block diagram showing the configuration of an analysis system 70 according to Embodiment 1 of the present disclosure. The analysis system 70 can be used for a system that remotely analyzes images. The analysis system 70 includes, for example, an analysis device 1 for analyzing medical data and a user terminal 20. The analysis system 70 is communicably connected between the analysis device 1 and the user terminal 20 via the Internet.

[0009] The analysis system 70 receives an image analysis request from the user terminal 20 via an information communication network such as the Internet. The analysis device 1 is a system that analyzes the medical data to be analyzed transmitted from the user terminal 20 and returns the analysis result to the user terminal 20 via the Internet. The user can be anyone who requests the analysis system 70 to analyze medical data. The user is, for example, a medical professional such as a doctor, a medical technician, or a nurse, but is not limited to this.

[0010] In the present disclosure, the case where the medical data is the image data 301 will be described as an example. However, the medical data is not limited to the image data 301, and for example, blood data, blood flow data, or walking data may be used as the medical data. The analysis system 70 may analyze, for example, blood data to perform motion analysis of a patient.

[0011] There may be a plurality of user terminals 20. For example, there may be user terminals 201, 202, and 203 for each medical institution. The user accesses the analysis device 1 via the Internet, for example, and requests the analysis of the image data 301 from the screen displayed on the web page. If analysis requests for the same image data 301 are received from different user terminals 20, each image data 301 may be stored in association with the identification information for each terminal and analyzed. The image data may be in a format compliant with DICOM (Digital Imaging and Communications in Medicine).

[0012] The user terminal 20 may be, for example, a stationary personal computer equipped with a communication function or a mobile terminal such as a tablet terminal. Since there may be a plurality of users, a plurality of user terminals 201, 202, 203... are illustrated, but hereinafter, unless otherwise specified, the target terminal representing all terminals will be referred to as the user terminal 20.

[0013] The analysis device 1 includes a control unit 16 that comprehensively controls each part of the analysis device 1, a storage unit 17 that stores various data used by the control unit 16, and a communication unit 15 for communicating with other devices.

[0014] The control unit 16 includes a communication control unit 11 (transmission unit) that controls the communication unit 15, an acquisition unit 12 that acquires data transmitted from the user terminal 20 via the communication control unit 11, and an analysis unit 13 that analyzes the image data 301.

[0015] The control unit 16 includes at least one processor and at least one memory. The processor can be configured using, for example, at least one general-purpose processor such as an MPU (Micro Processing Unit) or a CPU (Central Processing Unit). The memory may include multiple types of memories such as a ROM (Read Only Memory) and a RAM (Random Access Memory). As an example, the processor realizes the functions of the control unit 16 by expanding and executing various control programs recorded in the ROM of the memory in the RAM. Further, the processor may include a processor configured by an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or a PLD (Programmable Logic Device).

[0016] The storage unit 17 stores the browser image 200, acquisition information 172, and analysis result data 173 (analysis result) described later.

[0017] FIG. 2 is a schematic diagram showing a part of the data flow transmitted and received between the analysis device 1 and the user terminal 20. When the user accesses the analysis device 1 via the Internet for an analysis request of image data 301, the communication control unit 11 acquires a browser image 200, which is an input screen, from the storage unit 17 via the communication unit 15 and displays it on the web page. The user inputs acquisition information 172 including the image data 301 to be analyzed, patient identification information 320 (first identification information), and attribute information 303 into the browser image 200 and transmits it to the analysis device 1.

[0018] The user can input the acquisition information 172 into the browser image 200 and click a "send" button 204 (to be described later) to transmit the acquisition information 172 to the analysis device 1. The method of input by the user is not limited to this. For example, it may be input by drag & drop or by specifying a directory. The image data may be uploaded to the server while maintaining the DICOM file state, or only the pixel values and array information of the image extracted from the DICOM file, or only the minimum attribute information 303 embedded in the DICOM file may be transmitted. By doing so, anonymity can be made more secure. When transmitting the acquisition information 172 to the analysis device 1, the image data 301 and the attribute information 303 are not encrypted, but the patient identification information 320 is encrypted and transmitted as will be described in detail later. Not limited to this, although the image data 301 does not particularly need to be encrypted, the image data 301 may also be encrypted and transmitted. A specific example of the browser image 200 will be described later.

[0019] The type of the image data 301 may be any data that can be transmitted over the Internet. The content of the image is not particularly limited, but depending on the use of the analysis system 70, it may be, for example, a medical X-ray image, a microscopic photograph, a CT (Computer Tomography) image, an MRI (Magnetic Resonance Imaging) image, an ultrasonic image, a PET image, etc. For example, when the analysis system 70 estimates bone density or the like, the type of the image data 301 is an X-ray image of bone, a CT image, an MRI image, etc. The estimation may include calculations. Also, when the analysis system 70 performs pathological determination of cells, the type of the image data 301 is data such as a microscopic photograph of cells. Bone density may be represented by at least one of bone mineral density per unit area (g / cm 2 ), bone mineral density per unit volume (g / cm 3 ), YAM (%), T-score, and Z-score. YAM (%) is an abbreviation of "Young Adult Mean" and may be called young adult mean percent. For example, bone density may be a value represented by bone mineral density per unit area (g / cm 2 ) and YAM (%). Bone density may be an index defined by a guideline or an original index.

[0020] The patient identification information 320 is, for example, information indicating whose image data the image data 301 to be analyzed is, and may be an ID number, or information including age, address, name, and identification number of the image. As the ID number, for example, any combination of a plurality of alphanumeric characters can be used. The identification number of the image may be a number assigned at the time of shooting by the imaging device.

[0021] As described above, the patient identification information 320 is encrypted, for example, when transmitted to the analysis device 1, and the encrypted patient information 302 (second identification information) is generated. Thereby, the image data 301 can be transmitted and analyzed in a state where personal information is concealed.

[0022] The encryption process may be performed by the user terminal 20 that transmits the patient identification information 320, or may be performed by the analysis device 1 that receives it. The method of the encryption process may be a known method and is not limited.

[0023] For example, when the communication control unit 11 receives access from the user terminal 20 via the Internet, it may transmit an encryption application to the user terminal 20. This encryption application is an application that encrypts the patient identification information 320 input to the browser image 200 and decrypts the encrypted patient information 302 transmitted to the user terminal 20 after analyzing the image data 301. According to such a configuration, the user can automatically encrypt and decrypt the patient identification information 320 without encrypting and decrypting the patient identification information 320 by himself / herself. Also, the encrypted second identification information may not be displayed on the user terminal 20. The user can use it without being aware that the identification information is encrypted.

[0024] The attribute information 303 is information including, for example, the name and address of the hospital where the image data 301 was taken, the hospital ID number, the information of the hospital's email address, etc.

[0025] The acquisition unit 12 acquires the encrypted patient information 302 in which the image data 301, the attribute information 303, and the patient identification information 320 included in the acquisition information 172 transmitted from the user terminal 20 are encrypted and sends it to the analysis unit 13. The acquisition unit 12 stores the acquired image data 301, encrypted patient information 302, and attribute information 303 in the storage unit 17 while associating them with each other.

[0026] The analysis unit 13 analyzes the image data 301 acquired from the acquisition unit 12 using the machine model 131. As shown in FIG. 1, the analysis unit 13 includes the machine model 131. The machine model 131 is a trained machine model that has been trained to output predetermined information, which is the analysis result, from the input image data 301. Hereinafter, the analysis content based on the output of the machine model 131 is also referred to as "the analysis result derived by the machine model" or simply "the analysis result". Also, the data including the analysis result is referred to as analysis result data 173. The analysis result data 173 is stored in the storage unit 17 in association with the encrypted patient information 302 and the attribute information 303. The image data 301 may be analyzed in a state of a format compliant with DICOM (Digital Imaging and Communications in Medicine), or may be analyzed in a state of pixel values and array information of an image extracted from a file compliant with DICOM. Alternatively, it may be converted into another image format before being analyzed. Another image format may be a general-purpose image format such as JPG, BMP, TIF, or PNG. By doing so, the machine model created to target images in a general-purpose format can be used as it is.

[0027] Although the machine model 131 is not limited, for example, it may include a convolutional neural network model (NNM; Neural Network Model) for image analysis. Specific examples of the machine model 131 and the analysis result data 173 will be described in detail in Embodiment 2.

[0028] The communication control unit 11 transmits the analysis result data 173, the encrypted patient information 302, and the attribute information 303 analyzed by the analysis unit 13, associated with each other, to the user terminal 20 via the communication unit 15.

[0029] When the user terminal 20 receives the analysis result data 173, the encrypted patient information 302, and the attribute information 303, the encrypted patient information 302 is decrypted, and the patient identification information 320 is generated. At this time, if the analysis device 1 has transmitted the encryption application to the user terminal 20, since the encryption application automatically decrypts the encrypted patient information 302, there is no need for the user to decrypt it. Here, decryption means, for example, restoring the original patient identification information 320 from the encrypted encrypted patient information 302.

[0030] In this way, the user terminal 20 can receive the decrypted patient identification information 320, the analysis result data 173, and the attribute information 303. Thereby, the user terminal 20 can save the analysis result data 173 in association with the patient identification information 320.

[0031] In FIG. 1, the analysis device 1 is described as being arranged together in one housing. However, the analysis device 1 does not necessarily need to be arranged together in one housing. For example, a part of the components included in the analysis device 1 may be arranged as a separate device. Also, a part or all of the components included in the analysis device 1 may be arranged on the cloud.

[0032] According to the analysis system 70 having the above configuration, it is possible to analyze the image data 301 requested for analysis by the user while keeping the personal information confidential. Therefore, even when receiving analysis requests from an unspecified number of users, it is possible to analyze the image data 301 of each user while protecting the personal information.

[0033] The image data 301 may be, for example, medical image data obtained by photographing a subject with an endoscope. More specifically, the image data 301 may include medical image data obtained by photographing a site including at least one of the nasal cavity, esophagus, stomach, duodenum, rectum, large intestine, small intestine, anus, and colon of the subject with an endoscope. By inputting the medical image data of these sites into the machine model 131, for example, an analysis result may be output that identifies a site of interest including at least one of inflammation, polyp, and cancer. In such a case, as the machine model 131, for example, a model learned based on a first learning image including an image with a site of interest and first teacher data indicating the presence of the site of interest, and a second learning image including an image without a site of interest and second teacher data indicating the absence of the site of interest can be used. The first teacher data may include information indicating the degree of inflammation (degree of inflammation) or malignancy (degree of malignancy) of the site of interest. The analysis result may be, for example, a display surrounding the site of interest, a display pointing to the site of interest, or a display that superimposes a color on the site of interest. A configuration may be adopted in which, together with such an analysis result, derivation basis information indicating the basis for which the analysis result was derived is displayed.

[0034] Alternatively, the image data 301 may be, for example, image data obtained by photographing the eyes, skin, etc. of the subject with a digital camera. By inputting the image data 301 of these parts into the machine model 131, for example, an analysis result indicating a notable sign may be output. The notable signs may include signs indicating at least one disease including, for example, glaucoma, cataract, age-related macular degeneration, conjunctivitis, hordeolum, retinopathy, and blepharitis in the case of the eyes. Alternatively, the notable signs may include signs including, for example, skin cancer, urticaria, atopic dermatitis, and herpes in the case of the skin. The analysis result may be a display surrounding these notable signs, a display indicating the notable signs, a display with color superimposed on the notable signs, or a display showing the disease name. As the machine model 131, for example, a model learned based on a first learning image having an image including these notable parts and first teacher data indicating the presence of notable signs, and a second learning image including an image without notable signs and second teacher data indicating the absence of notable signs can be used. A configuration may be adopted in which, together with such an analysis result, derivation basis information indicating the basis for deriving the analysis result is displayed.

[0035] Next, the flow of the analysis method S1 according to the present embodiment will be described with reference to the drawings. FIG. 3 is a flowchart showing the processing flow of the analysis method S1 executed by the control unit 16. As shown in the figure, the analysis method S1 includes steps S11 to S14.

[0036] When the user accesses the analysis device 1, the communication control unit 11 displays, on the web page, a browser image 200, which is an input screen for inputting acquisition information 172 including the image data 301 to be analyzed, patient identification information 320, and attribute information 303 via the communication unit 15 (S11).

[0037] The acquisition unit 12 acquires encrypted patient information 302 in which the image data 301, attribute information 303, and patient identification information 320 included in the acquisition information 172 input to the browser image 200 and transmitted from the user terminal 20 are encrypted (S11).

[0038] The analysis unit 13 analyzes the image data 301 sent from the acquisition unit 12 using the machine model 131 (S13).

[0039] The communication control unit 11 transmits the analysis result data 173 analyzed by the analysis unit 13, the encrypted patient information 302, and the attribute information 303 to the user terminal 20 via the communication unit 15 (S14).

[0040] According to the above analysis method S1, it is possible to analyze the image data 301 requested for analysis by the user while keeping the personal information confidential. Therefore, even when receiving analysis requests from an unspecified number of users, it is possible to perform the analysis while protecting personal information.

[0041] 〔Embodiment 2〕 Other embodiments of the present disclosure will be described below. For convenience of explanation, members having the same functions as those described in the above Embodiment 1 are denoted by the same reference numerals, and the description thereof will not be repeated. In this embodiment, a case where the analysis system 70A analyzes an X-ray image of a bone and outputs bone density, relative comparison of bone density, possibility of fracture (%), etc. will be described as an example.

[0042] (Configuration of the analysis system 70A) FIG. 4 is a block diagram showing the configuration of the analysis system 70A according to Embodiment 2 of the present disclosure. As shown in the figure, the control unit 16 of the analysis device 1A includes a communication control unit 11, an acquisition unit 12, an analysis unit 13, a generation unit 18, and a determination unit 19. Among these, since the communication control unit 11, the acquisition unit 12, and the analysis unit 13 have the same functions as those of these respective units described in Embodiment 1, the description thereof will be omitted here.

[0043] The storage unit 17 stores the image data 301 (medical data), the encrypted patient information 302, and the attribute information 303 acquired by the acquisition unit 12 in an associated manner.

[0044] The generation unit 18 generates information regarding the basis for deriving the analysis result analyzed by the analysis unit 13 (hereinafter referred to as "derivation basis data 311"). The derivation basis data 311 means at least one of the reasons why the machine model 131 derived such an analysis result. For example, the derivation basis data 311 may be information indicating mainly which part of the image the analysis result was derived from. The derivation basis data 311 is at least associated with the encrypted patient information 302 and stored in the storage unit 17. Specific examples of the functions of the generation unit 18 will be described later.

[0045] (Determination unit 19) The determination unit 19 determines whether the encrypted patient information 302 acquired by the acquisition unit 12 is the one in which the patient identification information 320 was actually encrypted. If it is determined that the encrypted patient information 302 is not actually encrypted, the acquisition unit 12 may delete the acquired encrypted patient information 302. By providing such a determination unit 19, if the encrypted patient information 302 transmitted from the user terminal 20 is not the one obtained by encrypting the patient identification information 320, the acquired image data 301 is not analyzed and is deleted together with the encrypted patient information 302 and the attribute information 303. Therefore, the acquisition information 172 including the image data 301 is not stored inside the analysis device 1A. The determination as to whether it is encrypted may be made, for example, from the extension of the encrypted data.

[0046] If it is determined that the encrypted patient information 302 is not actually encrypted, the control unit 16 may transmit, via the communication control unit 11, a message requesting the user terminal 20 to encrypt the patient identification information 320 again and send it.

[0047] In the present disclosure, a configuration in which the analysis device 1A includes a determination unit 19 will be described, but the present disclosure is not limited to this configuration. For example, in the analysis system 70A, the determination unit 19 may be provided in at least any one of the analysis device 1A and the hospital-side server that mediates the transmission of the encrypted patient information 302 from the user terminal 20 to the analysis device 1A. In one example, a configuration in which both the analysis device 1A and the hospital-side server include the determination unit 19 may be used. Further, a configuration in which the user terminal 20 that is the transmission source of the encrypted patient information 302 includes the determination unit 19 may be used.

[0048] (Browser image 200) FIG. 5 is a diagram showing an example of a browser image 200 displayed on a web page for inputting image data 301 and the like when a user accesses the analysis device 1 A via the Internet.

[0049] As shown in the drawing, in the browser image 200, the characters "<Bone density analysis>", which indicate the object of image analysis, are displayed at the top. In the upper left part of the browser image 200, the characters "<Reception>", which indicate that it is a screen for receiving input, are displayed. Below that, the characters "Please place the image to be analyzed here" that prompt the input of the image data to be analyzed and a frame 205 (basis area) indicating an area for pasting (dragging and dropping) the image data are displayed. Further below that, the characters "Please enter the attribute information here" that prompt the input of the patient identification information 320 and the attribute information 303 and the like and an input box 206 are displayed. In the lower right of the browser image 200, a "Transmit" button 204 for prompting transmission is displayed, and in the upper right, a "Return" button 207 for returning to the initial screen of the website is displayed.

[0050] FIG. 6 shows an X-ray image data 300 for requesting bone density analysis as an example of the image data 301. The X-ray image data 300 may be a lumbar X-ray image, a chest X-ray image, etc., or may be an X-ray image taken by a DXA (Dual energy X-ray Absorptiometry) device or the like. In a DXA device that measures bone density using the DXA method, when measuring the bone density of the lumbar spine, X-rays are irradiated from the front of the lumbar spine of the subject. Also, in a DXA device, when measuring the bone density of the proximal femur, X-rays are irradiated from the front of the proximal femur of the subject. Here, "the front of the lumbar spine" and "the front of the proximal femur" are intended to be the directions facing the imaging sites such as the lumbar spine and the proximal femur correctly, and may be the ventral side of the subject's body or the dorsal side of the subject's body. In the MD (micro densitometry) method, the hand is irradiated with X-rays. The ultrasonic method is a method of measuring bone density by applying ultrasonic waves to bones such as the lumbar spine, femur, heel, or tibia. Also, the image data does not have to be an X-ray image, as long as it is an image containing bone information. For example, it can be estimated from MRI (magnetic resonance imaging) images, CT (computed tomography) images, PET images, and ultrasonic images, etc.

[0051] In the present disclosure, the case where the subject for estimating the state of the bone is a human (i.e., "the subject") will be described as an example, but the subject is not limited to humans. The subject for estimating the state of the bone may be a non-human mammal such as a horse family, a cat family, a dog family, a cow family, or a pig family, for example. And the present disclosure includes embodiments in which "the subject" is replaced with "the animal" as long as they are embodiments applicable to these animals.

[0052] In this embodiment, when a user accesses the analysis device 1A via the Internet, the communication control unit 11 may display the browser image 200 on the web page and transmit the encryption application via the communication unit 15. When the user inputs the image data 301, patient identification information 320, and attribute information 303 for which analysis is requested and clicks the "Send" button 204, the patient identification information 320 is encrypted, and the encrypted encrypted patient information 302 is transmitted to the analysis device 1A together with the image data 301 and attribute information 303. Therefore, it is not necessary for the user to perform the encryption process of the patient identification information 320. The encryption process may not be executed when the user clicks the "Send" button 204, but the encryption process may be executed after the click.

[0053] The encryption method may be a known method and is not limited. For example, an encryption method combining a public key and a private key may be used. The encryption may be a method that cannot be decrypted even by the operator of the analysis system 70A. Thereby, even when the user requests image analysis from the operator of the analysis system 70A, it is possible to reduce the risk of leakage of the combination of the image data 301 and the patient identification information 320 to the operator side.

[0054] The acquisition unit 12 acquires the X-ray image data 300, encrypted patient information 302, and attribute information 303 transmitted from the user terminal 20 and transmits them to the analysis unit 13.

[0055] The analysis unit 13 inputs the X-ray image data 300 transmitted from the acquisition unit 12 into the machine model 131, processes the output data from the machine model 131 as necessary, and generates analysis result data 173. The generated analysis result data 173 is associated with at least the encrypted patient information 302 and the attribute information 303 and stored in the storage unit 17.

[0056] The communication control unit 11 acquires the analysis result data 173 associated with the encrypted patient information 302 and the attribute information 303 from the storage unit 17 and transmits it to the user terminal 20 via the communication unit 15.

[0057] When the user terminal 20 receives the analysis result data 173, the encrypted patient information 302 is automatically decrypted, and the patient identification information 320 is generated. The encrypted patient information 302 may be decrypted when the analysis result data 173 is transmitted, or the user may decrypt it himself / herself.

[0058] Thereby, the user terminal 20 can display the analysis result data 173 on the screen together with the patient identification information 320 including the patient's name or identification number, etc.

[0059] FIG. 7 is a diagram showing an example of a browser image 400 displayed on the screen of the user terminal 20 that has received the analysis result data 173. On the browser image 400, the characters "<Bone Density Analysis>" indicating the content of the image analysis are displayed at the top. At the upper left of the browser image 400, the characters "<Analysis Result>" indicating that it is a screen for displaying the analysis result are displayed. Below that, the patient's information may be displayed. Below that, the characters "Your bone density is □ / cm 2 are displayed. In the box 401, the estimated bone density value is displayed. Further below, the characters "Compared with young people, it is □%" may be displayed. In the box 402, the ratio to the young adult mean (YAM) of bone density is displayed. Further below, the characters "Judgment" and in the box 403, the characters such as "Osteopenia" may be displayed. For example, when the ratio to YAM is less than 80%, it is determined as "Osteopenia", and when it is 70% or less, it is determined that there is a possibility of "Osteoporosis". The browser image 400 may have an "End" button 404 and a "Back" button 405. The "Back" button 405 may, for example, return to the previous screen, return to the home screen, or return to a predetermined screen.

[0060] (Generation unit 18) Next, the details of the generation unit 18 will be described. In the present embodiment, the generation unit 18 generates the derivation basis data 311 of the analysis result analyzed by the analysis unit 13. The communication control unit 11 may transmit the derivation basis data 311 generated by the generation unit 18 to the user terminal 20 including the same.

[0061] The analysis result data 173 is based on the output from the machine model 131, but the output from the machine model 131 does not include the process of analysis. Therefore, generally, it is impossible to determine the reliability of the output only by looking at the output from the machine model 131. Therefore, by transmitting the analysis result data 173 including the derivation basis data 311 to the user terminal 20, the user can help improve the sense of trust in the analysis result.

[0062] For example, the derivation basis data 311 may be the processed image data 310 (basis image data) in which new information is added to the image data 301 input to the machine model 131. For example, the new information may be information indicating the area that became the main basis for deriving the analysis result in the image data 301. That is, the processed image may be an image obtained by adding information indicating the area that became the main basis to the input image data. The information indicating the area is information that can identify the range of the area, such as coloring or framing. In image analysis, in many cases, a certain area of the image becomes the main basis for estimation. Therefore, the user can confirm the area that became the basis for the estimation based on the information indicating such an area.

[0063] The processed image data 310 does not necessarily include all the information of the image data 301 input by the user. For example, the processed image data 310 may be the image data obtained by trimming the input image data 301, or may be an image with a lower resolution than the input image data 301. By doing so, the capacity of the data to be transmitted and received can be reduced.

[0064] FIG. 8 is a diagram showing an example of a browser image 500 that transmits the derivation basis data 311 to the user terminal 20 in addition to the analysis result data 173. In the browser image 500, the derivation basis data 311 (processed image data 502 including the area 503) is added to the analysis result data 173 shown in FIG. 7.

[0065] Specifically, in the browser image 500, together with the analysis result 501, the processed image data 502 in which a rectangular area 503 is additionally processed in the input image data (the X-ray image data 300 in FIG. 6) is displayed. As shown in FIG. 8, in the present embodiment, the analysis result 501 derived by the machine model 131 for analyzing the image data and the processed image data 502 including the derivation basis data 311 are displayed on one screen. The browser image 500 may display a "Back" button 506, an "End" button 507, and a "Future Prediction" button 505. The role of the "Future Prediction" button 505 will be described later.

[0066] FIG. 9 is an enlarged schematic diagram of the image of the area 503 in FIG. 8. The area 503 includes four lumbar vertebrae shown as L1 to L4. This indicates that the lumbar vertebrae L1 to L4 are the areas that are the basis for the analysis result. Actually, it is known that the bone density of the lumbar vertebrae L1 to L4 is related to the average value of the bone density of the whole body. That is, the framed area 503 indicates that the analysis result of the machine model 131 is derived based on the bone density of the lumbar vertebrae L1 to L4.

[0067] The region on which the analysis result is based may include the segmented region. Segmentation is to divide an image into several regions. Segmentation is performed to reduce the amount of analysis processing of the machine model 131. That is, the machine model 131 may analyze only the segmented regions. The segmented region may be set within an arbitrary range. The segmented region may be, for example, rectangular, square, or circular. When the segmented region is square, the amount of analysis processing of the machine model 131 can be reduced. When analyzing an X-ray image of the lumbar spine, for example, the range including lumbar vertebrae L1 to L4 is segmented. Therefore, the size of the segmentation region may vary depending on the size of lumbar vertebrae L1 to L4 in the image. The segmentation region may be set to be slightly larger than lumbar vertebrae L1 to L4 or may be set to overlap the sides of lumbar vertebrae L1 to L4 in the arrangement direction of lumbar vertebrae L1 to L4. The segmentation region may be, for example, always of a predetermined size or may have its size set according to the medical image. For example, the segmentation region may identify the positions of lumbar vertebrae L1 to 4, set the length in the arrangement direction of the lumbar vertebrae L1 to L4, and then set the length in the vertical direction of the lumbar vertebrae L1 to L4. The segmentation may be performed by the machine model 131. The machine model 131 may learn an image annotated with the analysis region in order to perform segmentation.

[0068] In addition, the generation unit 18 may generate a heat map of the region that is the basis for the analysis result. In this case, for example, the outer edge of the heat map will indicate the segmentation region. A heat map is a method of representing the magnitude of bone density by the density of an arbitrary color. For example, the generation unit 18 may generate a heat map indicating the degree of attention. Also, a heat map indicating the numerical value of bone density may be generated. Further, the generation unit 18 may generate a heat map indicating the possibility (probability) of fracture. The image used for the heat map may be a still image or a moving image. By showing it as a moving image, for example, by fading various heat maps in order, it becomes easy to visually recognize the relationship between each heat map. Also, when the analysis result is a heat map of bone density that includes areas other than the segmentation region, a part of the segmentation region may be surrounded by a frame.

[0069] The generation unit 18 may acquire from the analysis unit 13 information on the region that is the basis for the analysis result. Specifically, the generation unit 18 may acquire from the analysis unit 13 the region that is the basis for the analysis result, and may generate information indicating that region (such as a frame line surrounding the region 503). The generation unit 18 may acquire from the analysis unit 13 degree-of-attention data, bone density data, or information indicating the possibility of fracture within the region, and generate a heat map. The generation unit 18 may generate any one or more of a heat map indicating degree-of-attention data, a heat map indicating bone density data, and a heat map indicating the possibility of fracture. When the heat map indicating degree-of-attention data, the heat map indicating bone density data, and the heat map indicating the possibility of fracture are overlaid and displayed, the generation unit 18 may make the colors of the heat map indicating degree-of-attention data, the heat map indicating bone density data, and the heat map indicating the possibility of fracture different from each other.

[0070] The mechanical model 131 analyzes, for example, the X-ray image data 300 by means of the NNM. In the NNM, the image is once divided into fine regions, each of which is digitized, and a process of repeatedly performing pooling processing on a plurality of regions to integrate them into a larger region and then digitizing them again is carried out. Therefore, the mechanical model 131 may extract, as a basis region, a region having a numerical value (for example, a relatively large numerical value) that affects the processing result.

[0071] In the example shown in FIG. 8, the processed image data 502 in which the region 503 serving as the basis of the analysis result is superimposed and displayed on the X-ray image data 300 to be analyzed is described. However, the processed image data is not limited to this. For example, the analysis device 1 may transmit the position information (such as coordinates) of the region serving as the basis of the analysis result in the image to be analyzed to the user terminal 20, and cause the user terminal 20 to display the processed image data in which the region is displayed on the image to be analyzed.

[0072] A screen as shown in FIG. 8 can be used when a doctor explains the analysis result to a patient. That is, not only the analysis result is simply explained to the patient, but also which region of the image data the analysis result is based on can be explained. Therefore, not only can the doctor's trust in the analysis result be improved, but also the effect that the patient can easily accept the analysis result can be obtained.

[0073] In the example shown in FIG. 8, the analysis result 501 and the processed image data 502 including the derived basis data 311 are displayed on one screen. However, the "one screen" does not necessarily mean that they are simultaneously displayed on the screen. For example, it may be a screen that is scrolled up and down or left and right for display. That is, the range scrolled up and down or left and right for display on the screen is referred to as "one screen".

[0074] FIG. 10 is a schematic diagram showing an example of a browser image 700 that displays the likelihood of a patient's current fracture estimated from image data analyzed by the analysis unit 13 and the likelihood of the patient having a fracture three years later. The future time period is not limited to three years later and may be any time period (e.g., X years later). This is displayed by clicking on the "Future Prediction" button 505 located in the lower right corner of the browser image 500 shown in FIG. 8.

[0075] The browser image 700 has the text "<Bone Density Analysis>" indicating the subject of the image analysis displayed at the top. At the upper left of the browser image 700, the text "<Future Prediction>" indicating that it is a screen for displaying future predictions is shown. Below that, the patient's information may be displayed. Below that, the text "The likelihood of your femur fracture is □%" is shown. In the box 701, the numerical value of the fracture likelihood estimated at the current time is displayed. Further below, the text "The likelihood of your femur fracture three years later is □%" may be shown. In the box 702, the numerical value of the fracture likelihood predicted three years later is displayed. Also, information regarding the basis of the estimation or prediction may be displayed together in this image.

[0076] Such a screen can be used when a doctor explains the current and future fracture likelihoods to a patient. When information regarding the basis of the estimation or prediction is displayed together, it has the effect of increasing the persuasive power to the patient.

[0077] (Mechanical Model 131) Next, the mechanical model 131 will be described. The mechanical model 131 is a model that estimates the state of bones. The input image data is an image containing bones, and as an analysis result, it outputs an estimation result regarding the state of the bones. For example, the mechanical model 131 is a learned model trained to output an estimation result or a calculation result regarding the state of bones, such as bone density, relative comparison of bone density, presence or absence of fractures, and likelihood of fractures, from an X-ray image of bones. The bone density may be the calculated bone density of the bone part included in the image data, or the average bone density of the whole body estimated from the image data. A known method can be used to calculate the bone density from the image. The relative comparison of bone density is the ratio of the estimated bone density to YAM. The presence or absence of fractures is information indicating whether there is a fracture in the input image data. The likelihood of fractures is the likelihood that the bone at a specific site (such as the femoral neck) will fracture. The estimation result regarding the state of bones may be the estimation result at the time when the image was taken, or may be a prediction at a time point after a predetermined period has elapsed from that time point.

[0078] The mechanical model 131 may output, as an estimation result, at least any one of the bone density estimated at the time when the image data was captured, the bone density predicted at the time point when a predetermined period has elapsed from the time when the image data was captured, the fracture site and its likelihood estimated at the time when the image data was captured, and the fracture site and its likelihood predicted at the time point when a predetermined period has elapsed from the time when the image data was captured.

[0079] (Learning method of the mechanical model 131) Next, a learning method for the machine model 131 will be described. For the learning of the machine model 131, for example, the learning for estimating bone density may be performed using X-ray images of bones for which bone density has been specified as teacher data. The learning for estimating the possibility of fracture may be performed using X-ray images of bones and data on whether or not the patient has fractured within a predetermined period thereafter as teacher data. Relative comparison of bone density does not need to be learned and is obtained by dividing the estimated bone density by YAM. Also, for future prediction learning, it may be performed using X-ray images of bones for which bone density has been specified and data on the bone density or whether or not the patient has fractured after a predetermined period thereafter as teacher data. By including the lifestyle habits of the patient who has become teacher data, such as the amount of exercise, diet, smoking, and drinking, in the teacher data, a machine model 131 that can make more accurate estimations or predictions can be constructed.

[0080] In Embodiment 2, a machine model learned to perform estimations regarding the state of bones such as bone density as the machine model 131 was taken as an example for explanation. In this case, the input image data is an X-ray image of a bone, and the output is an estimation result regarding the state of the bone. However, the machine model 131 is not limited to such a model. For example, the machine model 131 may be a cell pathological analysis model. In this case, the input image data may be a microscopic image of cells, and the output may be the presence or absence of pathological mutations in the cells. Alternatively, the image data may be an X-ray image, a CT image, a mammography image, etc., and the output may be the presence or absence of cancer.

[0081] According to the configuration of the analysis system 70A according to the above Embodiment 2, the derivation basis data 311 can be provided to the user together with the analysis result data 173. Therefore, in addition to the effects of the analysis system 70 according to Embodiment 1, there is an effect that the user's trust in the analysis result can be improved. Also, when explaining to the patient, there is an effect that the patient can easily accept the analysis result.

[0082] Next, the flow of the analysis method S2 executed by the control unit 16 according to Embodiment 2 will be described. The analysis method S2 includes steps S21 to S24. Steps S21 to S23 are the same as steps S11 to S13 described in the analysis method S1 described in Embodiment 1.

[0083] Step S24 is a step in which the communication control unit 11 transmits the analysis result data 173 analyzed by the analysis unit 13, the derivation basis data 311, and the encrypted patient information 302 to the user terminal 20 (not shown).

[0084] According to the above analysis method S2, the derivation basis data 311 can be provided to the user together with the analysis result data 173. Therefore, in addition to the effect of the analysis method S1 according to Embodiment 1, there is an effect that the user's trust in the analysis result can be improved. Further, when explaining to the patient, an effect that the patient can easily accept the analysis result is obtained.

[0085] 〔Example of Realization by Software〕 The functions of the analysis systems 70, 70A (hereinafter referred to as "systems") can be realized by a program for causing a computer to function as the system and a program for causing a computer to function as each part of the system.

[0086] In this case, the above system includes a computer having at least one control device (for example, a processor) and at least one storage device (for example, a memory) as hardware for executing the above program. By executing the above program by this control device and storage device, each function described in each of the above embodiments is realized.

[0087] The above program may be recorded on one or more computer-readable recording media, not temporarily. This recording medium may or may not be provided in the above device. In the latter case, the above program may be supplied to the above device via any wired or wireless transmission medium.

[0088] In addition, part or all of the functions of each of the above-described units can also be realized by a logic circuit. For example, an integrated circuit in which a logic circuit functioning as each of the above-described units is formed is also included in the scope of the present disclosure. In addition to this, for example, it is also possible to realize the functions of each of the above-described units by a quantum computer.

[0089] As described above, the invention according to the present disclosure has been described based on the drawings and examples. However, the invention according to the present disclosure is not limited to each of the above-described embodiments. That is, the invention according to the present disclosure can be variously modified within the scope shown in the present disclosure, and embodiments obtained by appropriately combining the technical means disclosed in different embodiments are also included in the technical scope of the invention according to the present disclosure. That is, it should be noted that those skilled in the art can easily make various deformations or modifications based on the present disclosure. Also, note that these deformations or modifications are included in the scope of the present disclosure.

[0090] (Summary) (Aspect 1) The analysis device according to Aspect 1 of the present disclosure includes an acquisition unit that acquires medical data of a subject and second identification information obtained by encrypting first identification information of the subject from a user terminal, an analysis unit that analyzes the acquired medical data, and a transmission unit that transmits the analysis result analyzed by the analysis unit and the second identification information to the user terminal.

[0091] (Aspect 2) In Aspect 2 of the present disclosure, in the above Aspect 1, the analysis result and the second identification information may be transmitted to the user terminal that decrypts the second identification information.

[0092] (Aspect 3) In Aspect 3 of the present disclosure, in the above Aspect 1 or 2, the user terminal includes an application for performing decryption, and the application may have a function of performing the encryption.

[0093] (Aspect 4) In the case of Aspect 4 of the present disclosure, in the above Aspect 3, the application main body that performs the decoding may be transmitted to the user terminal.

[0094] (Aspect 5) In the case of Aspect 5 of the present disclosure, in any one of the above Aspects 1 to 4, the second identification information may not be displayed on the user terminal.

[0095] (Aspect 6) The analysis device according to Aspect 6 of the present disclosure further includes a determination unit that determines whether or not the acquired second identification information is obtained by encrypting the first identification information in a predetermined manner in any one of the above Aspects 1 to 5. When it is determined that the second identification information is not encrypted in a predetermined manner, the acquisition unit may delete the acquired second identification information.

[0096] (Aspect 7) In the case of Aspect 7 of the present disclosure, in any one of the above Aspects 1 to 6, the medical data may be image data.

[0097] (Aspect 8) In the case of Aspect 8 of the present disclosure, in any one of the above Aspects 1 to 7, the medical data is image data obtained by imaging the bone of the subject, and the analysis unit may output an estimation result regarding the state of the bone of the subject as the analysis result.

[0098] (Aspect 9) The analysis device according to Aspect 9 of the present disclosure further includes a generation unit that generates basis information regarding the basis for deriving the analysis result in any one of the above Aspects 1 to 8, and the transmission unit may transmit the basis information included in the analysis result to the user terminal.

[0099] (Aspect 10) In aspect 10 of the present disclosure, in the above aspect 9, the medical data is image data, and the basis information may be basis image data obtained by adding information indicating a basis region, which is the basis for deriving the analysis result, to the medical data in the medical data.

[0100] (Aspect 11) In aspect 11 of the present disclosure, in the above aspect 10, the basis image data may be image data showing the basis region on the image data.

[0101] (Aspect 12) In aspect 12 of the present disclosure, in the above aspect 8, the analysis unit outputs, as an estimation result, at least any one of the bone density of the subject's bone at the time when the image data was captured, the bone density of the subject's bone at the time when a predetermined period has elapsed since the time when the image data was captured, the site where a fracture is estimated at the time when the image data was captured and the possibility that the fracture has occurred, and the site where a fracture is estimated to occur before a predetermined period elapses since the time when the image data was captured and the possibility that the fracture occurs. Plan the bone density of the subject's bone at the time when a predetermined period has elapsed since the time when the image data was captured, Plan the site where a fracture is estimated at the time when the image data was captured and the possibility that the fracture has occurred, and Plan the site where a fracture is estimated to occur before a predetermined period elapses since the time when the image data was captured and the possibility that the fracture occurs, as an estimation result.

[0102] (Aspect 13) The analysis method according to aspect 13 of the present disclosure includes at least one processor obtaining medical data of a subject and second identification information obtained by encrypting first identification information of the subject from a user terminal, analyzing the obtained medical data, and transmitting the analysis result and the second identification information to the user terminal.

[0103] (Aspect 14) The analysis program according to aspect 14 of the present disclosure is an analysis program for causing a computer to function as the analysis device according to any one of aspects 1 to 12 above, and is a computer program for causing a computer to function as the acquisition unit, the analysis unit, and the transmission unit.

[0104] (Aspect 15) The recording medium according to aspect 15 of the present disclosure is a computer-readable non-transitory recording medium on which the analysis program described in aspect 14 is recorded.

Explanation of Signs

[0105] 1, 1A Analysis device 11 Communication control unit (transmission unit) 12 Acquisition unit 13 Analysis unit 18 Generation unit 19 Judgment unit 20 User terminal 131 Machine model 173 Analysis result data (analysis result) 301 Image data (medical image data) 302 Encrypted patient information (second identification information) 310 Processed image data (basis image data) 311 Derivation basis data (information regarding the derivation basis of the analysis result) 320 Patient identification information (first identification information) 503 Region (basis region)

Claims

1. An acquisition unit that acquires medical data of a subject and second identification information obtained by encrypting first identification information of the subject from a user terminal; An analysis unit that analyzes the acquired medical data; A transmission unit that transmits the analysis result analyzed by the analysis unit and the second identification information to the user terminal; An analysis device comprising:

2. The analysis device according to claim 1, wherein the analysis result and the second identification information are transmitted to the user terminal that decrypts the second identification information. The analysis device according to claim 1.

3. The user terminal includes an application that performs decryption, and the application has a function of performing the encryption. The analysis device according to claim 1.

4. The analysis device according to claim 3, wherein the application main body that performs the decryption is transmitted to the user terminal. The analysis device according to claim 3.

5. The second identification information is not displayed on the user terminal. The analysis device according to any one of claims 1 to 3.

6. The analysis device further comprises a determination unit that determines whether the acquired second identification information is obtained by encrypting the first identification information in a predetermined manner. When it is determined that the second identification information is not encrypted in a predetermined manner, the acquisition unit deletes the acquired second identification information. The analysis device according to any one of claims 1 to 3.

7. The medical data is image data. The analysis device according to any one of claims 1 to 3.

8. The medical data is image data obtained by imaging the bones of the subject. The analysis unit outputs an estimation result regarding the state of the bones of the subject as the analysis result. The analysis device according to any one of claims 1 to 3.

9. The analysis device further comprises a generation unit that generates basis information regarding the basis for deriving the analysis result. The transmission unit transmits the basis information to the user terminal included in the analysis result. The analysis device according to any one of claims 1 to 3.

10. The medical data is image data. The basis information is basis image data obtained by adding information indicating a basis region that is the basis for deriving the analysis result to the image data in the image data. The analysis device according to claim 9.

11. The basis image data is image data showing the basis region on the image data. The analysis device according to claim 10.

12.

12. The basis image data is image data showing the basis region on the image data. The analysis device according to claim 10.

12. The analysis unit outputs, as an estimation result, at least any one of the bone density of the subject's bone at the time when the image data was captured, the bone density of the subject's bone at the time when a predetermined period has elapsed since the time when the image data was captured, the site where a fracture is estimated at the time when the image data was captured and the possibility that the fracture has occurred, and the site where a fracture is estimated to occur before a predetermined period has elapsed since the time when the image data was captured and the possibility that the fracture will occur. The analysis device according to claim 8.

13. At least one processor obtains medical data of a subject and second identification information obtained by encrypting first identification information of the subject from a user terminal; analyzes the obtained medical data; transmits the analysis result and the second identification information to the user terminal; An analysis method including.

14. An analysis program for causing a computer to function as the analysis device according to any one of claims 1 to 3, the analysis program for causing a computer to function as the acquisition unit, the analysis unit, and the transmission unit.

15. A computer-readable non-transitory recording medium recording the analysis program according to claim 14.