Information processing device, information processing method, and program

Abstract

To provide an information processor, a method for processing information, and a program that can hold appropriate imaging data by setting a condition for storing imaging data on the basis of a result of an inference.SOLUTION: An information processor of the present invention includes: an acquisition unit 103 for acquiring medical image data of an inference target generated from imaging data obtained by imaging a subject; an inference unit 104 for inferring presence or absence of an abnormality in medical image data acquired by the acquisition unit 103; and a setting unit 105 for setting a storage condition as a condition of storing in a storage medium, the imaging data on the basis of a result of inference by the inference unit 104.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The disclosure of this specification relates to an information processing device, an information processing method, and a program that set storage conditions for captured data based on an inference result. [Background technology]

[0002] Recently, with the improvement in the performance of medical imaging devices such as CT and MRI, it has become possible to generate high-resolution image data. However, the size of the raw signal data (imaging data) immediately after imaging (before image reconstruction) is large, which puts a strain on storage device capacity. For this reason, it is common to reconstruct and store the tomographic image data used for interpretation, and then delete the imaging data after a few days.

[0003] Patent Document 1 discloses a method for reducing storage capacity by compressing captured data based on the time elapsed since capturing an image, searching for the image, and making a diagnosis based on the image. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Patent No. 2838521 [Patent Document 2] Patent No. 5800595 Summary of the Invention [Problem to be solved by the invention]

[0005] Patent Document 1 discloses a method for reducing storage capacity by compressing imaging data based on elapsed time. However, there are cases where it is desired to reconstruct image data from imaging data with higher resolution than the stored tomographic image data. The technology described in Patent Document 1 has the possibility of deleting imaging data for reconstructing high-resolution image data. [Means for solving the problem]

[0006] The information processing device according to the present invention includes an acquisition unit that acquires medical image data of an inference target generated from imaging data of an object, and the acquisition unit performs the following on the medical image data acquired by the acquisition unit: In the subject An inference unit that infers whether or not there is an abnormality, and a condition for storing the photographed data in a storage medium based on the inference result of the inference unit. and a condition that specifies the storage period of the photographed data. and a setting unit that sets the storage conditions. [Effects of the Invention]

[0007] According to the present invention, appropriate photographic data can be stored by setting storage conditions for the photographic data based on the inference result. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a diagram showing an example of the configuration of a medical image diagnostic system according to a first embodiment. [Figure 2] FIG. 1 is a diagram showing an example of a hardware configuration of an information processing apparatus according to a first embodiment. [Figure 3] FIG. 4 is a flowchart showing a processing flow when receiving imaging data according to the first embodiment. [Figure 4] FIG. 4 is a flowchart showing the flow of a process for setting storage conditions according to the first embodiment. [Figure 5] FIG. 10 is a flowchart showing the flow of a process for setting storage conditions according to the second embodiment. [Figure 6] FIG. 11 is a flowchart showing the flow of a process for setting storage conditions according to the third embodiment. [Figure 7] FIG. 13 is a diagram showing an example of a specific disease name list according to the third embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0009] Hereinafter, an embodiment of the present invention will be described with reference to the drawings.

[0010] [First embodiment] In the first embodiment, an example in which the present invention is applied to a medical image diagnostic system will be described. In the medical field, "image diagnosis" is performed by doctors based on medical image data generated by reconstructing imaging data obtained by imaging devices such as X-ray CT (Computer Tomography) devices and MRI (Magnetic Resonance Imaging) devices. Here, the task of observing medical image data and arriving at a diagnosis is called "image interpretation." In image diagnosis, an image interpretation physician, who is a doctor specializing in image diagnosis, interprets images at the request of, for example, the attending physician. The image interpretation physician makes a comprehensive judgment based on findings obtained from the images (hereinafter referred to as "image findings") and various measurement values, and identifies lesions or symptoms of the patient, i.e., the subject, as abnormalities depicted in the medical image data. The image interpretation physician then uses the image findings and measurement values ​​to write an image interpretation report explaining how the diagnosis was reached and sends the report back to the attending physician who made the request.

[0011] The medical image diagnostic system according to the first embodiment includes an information processing device 100, an imaging device 200, a storage device 300, and an interpretation terminal 400. Fig. 1 is a diagram showing an example of the configuration of the medical image diagnostic system. Fig. 1 also shows an example of the functional configuration of the information processing device 100.

[0012] The imaging device 200 is a device that captures imaging data (signals and images) used in medical examinations. It includes a plain X-ray imaging device (or X-ray device), a CT device, an MRI device, a PET device, a PET / CT device, a SPECT device, an ultrasound imaging device, a fundus camera (or a fundus photography device), an OCT device, etc., as well as a general camera. The data captured by the imaging device 200 (hereinafter referred to as imaging data) is transmitted to the information processing device 100.

[0013] The information processing device 100 is communicably connected to the imaging device 200 and the storage device 300, and generates an image to be used in image diagnosis based on the imaging data received from the imaging device 200. The generated image data is transmitted to the storage device 300.

[0014] The storage device 300 is a device for storing, searching, and communicating electronic data such as image data and imaging data, and is, for example, a PACS (Picture Archiving and Communication Systems). It stores generated images received from the information processing device 100.

[0015] The image interpretation terminal 400 is a terminal used by image interpretation physicians for image interpretation. It is communicably connected to the storage device 300, receives medical image data to be interpreted from the storage device 300, and displays the data on an output device such as a monitor. Furthermore, the image interpretation terminal 400 performs various processes related to viewing and editing images and creating reports in response to operations by the image interpretation physician.

[0016] The configuration of the medical image diagnostic system is not limited to the above. For example, the configuration may include a Radiology Information System (RIS) that handles radiography reservations, image interpretation management, and material inventory management in the radiology department, a system that manages image interpretation reports, and the like.

[0017] Furthermore, the medical image diagnostic system according to the first embodiment is configured to be able to communicate with a medical information system 500. The medical information system 500 is, for example, an HIS (Hospital Information Systems), and is a comprehensive system including a medical administrative accounting system, a medical appointment reservation system, an electronic medical record system, and the like.

[0018] FIG. 2 is a diagram showing an example of the hardware configuration of the information processing device 100. The CPU 11 mainly controls the operation of each component. The main memory 12 stores control programs executed by the CPU 11 and provides a work area when the CPU 11 executes the programs. The magnetic disk 13 stores programs for implementing various application software, including an operating system (OS), device drivers for peripheral devices, and programs for performing the processes described below. The CPU 11 executes the programs stored in the main memory 12 and magnetic disk 13, thereby realizing the functions (software) of the information processing device 100 described below in FIG. 2.

[0019] Display memory 14 temporarily stores display data to be displayed on monitor 15, for example. Monitor 15 is, for example, a CRT monitor or LCD monitor, and displays images, text, etc. based on the data from display memory 14. Mouse 16 and keyboard 17 are used by the user to input pointing and characters, etc., respectively.

[0020] The above components are connected to each other via a common bus 18 so that they can communicate with each other.

[0021] The configuration of the information processing device 100 is not limited to the above. For example, the information processing device 100 may have multiple processors. It may also have a GPU or an FPGA (Field-Programmable Gate Array) in which some of the processing is programmed.

[0022] As shown in FIG. 1, the information processing device 100 includes a photographing data management unit 101, a generation unit 102, an acquisition unit 103, an inference unit 104, a setting unit 105, and a transmission unit 106.

[0023] The photographing data management unit 101 stores photographing data received from the photographing device 200, transmits photographing data in response to requests from other functions, and also stores or deletes photographing data based on manual operations by the user or storage conditions set by the setting unit 105.

[0024] The generation unit 102 generates medical image data to be inferred based on the imaging data by reconstruction, etc. When there are multiple types of medical image data required for the inference by the inference unit 104, the generation unit 102 generates medical image data to be inferred accordingly.

[0025] The acquisition unit 103 acquires, from the generation unit 102, medical image data of an inference target generated from imaging data obtained by imaging a subject.

[0026] The inference unit 104 infers the presence or absence of an abnormality for the inference target medical image data acquired by the acquisition unit 103. An abnormality refers to, for example, a lesion, a disease, or a disease name. For example, the presence or absence of an abnormality can be rephrased as the presence or absence of a lesion, the presence or absence of a disease, the presence or absence of a disease name, or the benign or malignant nature of a lesion. The inference unit 104 infers the presence or absence of an abnormality for the inference target medical image data using a trained inference model generated by a learning process represented by deep learning or machine learning. The inference unit 104 performs inference processing using an inference model trained for purposes such as the presence or absence of a lesion, diagnosing the name of a disease, and differentiating between benign and malignant lesions. When the inference unit 104 performs inference processing using an inference model that performs benign / malignant discrimination, it infers the presence of an abnormality if the lesion site is malignant. The inference unit 104 may also infer the presence or absence of an abnormality based on whether the number of inferred lesion sites is equal to or less than a predetermined number.

[0027] The setting unit 105 sets storage conditions for the captured data, which is the source of the inference target medical image data, based on the inference result of the inference unit 104. The storage conditions are conditions that stipulate at least one of the storage period, compression rate, and whether or not the captured data can be deleted. When it is inferred that the inference target medical image data does not have an abnormality, the setting unit 105 designates the captured data as deletable data. On the other hand, when it is inferred that the inference target medical image data has an abnormality, the setting unit 105 may set the storage period for the captured data as a longer period than when it is inferred that the inference target medical image data has no abnormality. For example, the setting unit 105 may set the storage period for the captured data when it is inferred that the inference target medical image data has an abnormality to five years, and the storage period for the captured data when it is inferred that the inference target medical image data has no abnormality to one year. These storage periods can be set arbitrarily by the operator. In this case, the setting unit 105 may also impose a restriction so that the storage period for the captured data when it is inferred that the inference target medical image data has an abnormality is not shorter than the storage period for the captured data when it is inferred that the inference target medical image data has no abnormality.

[0028] The setting unit 105 also sets storage conditions in which the compression rate of the captured image data when it is inferred that there is an abnormality is lower than when it is inferred that there is no abnormality. These compression rates can be set arbitrarily by the operator. In this case, the setting unit 105 can also impose a restriction so that the compression rate of the captured image data when it is inferred that there is an abnormality in the medical image data to be inferred does not become higher than the compression rate of the captured image data when it is inferred that there is no abnormality in the medical image data to be inferred.

[0029] The setting unit 105 may be set so as not to compress the photographed data when it is inferred that there is an abnormality in the medical image data to be inferred, and may be set so as to compress the photographed data when it is inferred that there is no abnormality in the medical image data to be inferred.

[0030] Alternatively, the setting unit 105 sets a storage condition that prohibits the deletion of the photographed data if an abnormality is found, and permits the deletion of the photographed data if no abnormality is found.

[0031] Furthermore, the setting unit 105 can combine the above-mentioned multiple conditions. For example, the setting unit 105 can set the storage conditions so that the storage period of the captured data when it is inferred that the medical image data to be inferred has an abnormality is longer than the period when it is inferred that the medical image data to be inferred has no abnormality, and so that the compression rate of the captured data when it is inferred that the medical image data to be inferred has an abnormality is lower than the compression rate when it is inferred that the medical image data to be inferred has no abnormality. Furthermore, the setting unit 105 sets the captured data when it is inferred that the medical image data to be inferred has an abnormality as deletable data.

[0032] The transmission unit 106 transmits the interpretation image data and the imaging data to the storage device 300 in accordance with the storage conditions set by the setting unit 105 .

[0033] That is, the information processing device 100 includes an acquisition unit 103 that acquires medical image data to be inferred, which is generated from imaging data of a subject, an inference unit 104 that infers whether or not there is an abnormality in the medical image data acquired by the acquisition unit 103, and a setting unit 105 that sets storage conditions, which are conditions for storing the imaging data in a storage medium, based on the inference results of the inference unit 104.

[0034] In the first embodiment, a case will be described where the imaging device 200 is a CT device, for example. The imaging data is signal image data captured by the CT device, and the medical image data and interpreted image data to be inferred are tomographic image data obtained by reconstructing the signal image.

[0035] In the first embodiment, the retention period for photographed data is set to 72 hours, for example. If the setting unit 105 allows deletion, photographed data is automatically deleted after 72 hours have passed since the photographed date and time. Of course, the retention period for photographed data is not limited to 72 hours, and may be 96 hours, 120 hours, or the like.

[0036] FIG. 3 is a flowchart showing the flow of processing when the information processing device 100 receives photographic data from the photographing device 200.

[0037] In step S3001, the imaging data management unit 101 transmits the imaging data received from the imaging device 200 to the generation unit 102, and the process proceeds to the next step.

[0038] In step S3002, the generator 102 reconstructs the captured image data to generate tomographic image data to be used for image interpretation. This process may be performed by a user, and parameters for generation may also be set manually by the user.

[0039] In step S3003, the transmission unit 106 transmits the interpreted image generated by the generation unit 102 to the storage device 300. Note that, in transmitting data by the transmission unit 106, the interpreted image data may be transmitted together with the photographed data, depending on the setting of the setting unit 105.

[0040] In step S3004, the acquisition unit 103 acquires medical image data to be inferred that has been generated by the generation unit 102 for the imaging data received from the imaging device 200. The acquisition unit 103 may also acquire, from the storage device 300, medical data to be inferred that has been generated by the generation unit 102 for imaging data for which the elapsed time from the imaging date and time exceeds a predetermined retention period. Upon acquiring the medical data to be inferred, the acquisition unit 103 transmits the medical data to the inference unit 104, and the process proceeds to the next step.

[0041] In step S3005, the inference unit 104 infers whether or not there is an abnormality in the medical data to be inferred.

[0042] In step S3006, the setting unit 105 sets storage conditions for the photographic data based on the inference result by the inference unit 104. The storage conditions set by the setting unit 105 are transmitted to the photographic data management unit 101. If the setting unit 105 has set the photographic data to be deletable, the photographic data management unit 101 deletes the photographic data.

[0043] The process of deleting the captured image data described in steps S3004 to S3006 in FIG. 3 is executed when the information processing device 100 receives the captured image data from the image capturing device 200, and is also executed periodically at predetermined intervals.

[0044] 4 is a flowchart illustrating the processing from step S3004 to step S3006 described above. Here, the flow from when the acquiring unit 103 acquires medical data to be inferred to when the setting unit 105 sets storage conditions is described.

[0045] In step S4001, the acquisition unit 103 reconstructs the imaging data generated by the generation unit 102 to acquire medical image data to be inferred. Parameters for reconstruction by the generation unit 102 are set in advance as those required by the inference unit 104 in the inference process. Note that if the inference unit 103 requires imaging data before reconstruction, the generation unit 102 does not perform reconstruction, and the acquisition unit 103 treats the imaging data as medical image data to be inferred. Here, the imaging data includes the imaging date and time, the imaging body part, as well as a case ID and a patient ID that are common to the medical information system 500. This information is retained even after reconstruction and can be used in subsequent steps.

[0046] In step S4002, the inference unit 104 executes an inference process for inferring the presence or absence of an abnormality in the medical image data to be inferred. Here, the inference process by the inference unit 104 may be performed using a trained inference model based on the above-described machine learning. Here, the inference unit 104 will be described using an example in which the inference unit 104 detects the presence or absence of a lesion as an abnormality, but the inference process performed by the inference unit 104, such as inferring a diagnosis and distinguishing between benign and malignant lesions, is not limited to this.

[0047] The inference unit 104 executes a process of inferring the presence or absence of a lesion in the medical image data to be inferred. For detecting the lesion, known techniques such as machine learning and deep learning can be used.

[0048] In step S4003, the setting unit 104 checks the result of the inference by the inference unit 103. If no lesion is detected, the process proceeds to step S4006; otherwise, the process proceeds to step S4004. The setting unit 104 may set the storage conditions for the imaging data without going through the steps described below.

[0049] In step S4004, the setting unit 105 acquires the status of the medical treatment and sets the storage conditions based on the inference result by the inference unit 104 and the status of the diagnosis. The setting unit 105 acquires, as the diagnosis status, a medical record with a matching case ID and patient ID from the medical information system 500, and checks whether a diagnosis has been written after the imaging date and time of the imaging data. If a corresponding diagnosis has been written by a doctor or the like, the process proceeds to step S4006; otherwise, the process proceeds to step S4005. The setting unit 105 may switch the next process by referring to the content written in the diagnosis; for example, the process may proceed to step S4006 only if the part written in the diagnosis corresponds to the imaging part. That is, the setting unit 105 sets the storage conditions for the imaging data based on the consistency between the part written in the medical record by the diagnosis and the inference result by the inference unit 104.

[0050] In step S4005, the setting unit 105 checks whether there is other imaging data managed by the imaging data management unit 101 that has the same case ID, patient ID, and imaging site as the imaging data being processed and has a newer imaging date and time. That is, the setting unit 105 sets the storage conditions for the imaging data depending on whether there is imaging data based on the subject that was captured more recently than the imaging data corresponding to the medical image data to be inferred. If there is corresponding imaging data, the setting unit 105 proceeds to step S4006; otherwise, the setting unit 105 proceeds to step S4007.

[0051] In step S4006, the setting unit 105 sets a storage condition that allows the captured image data being processed to be deleted, and transmits the storage condition to the captured image data management unit 101.

[0052] In step S4007, the setting unit 105 sets a storage condition that prohibits the deletion of the photographic data being processed, and transmits the determination result to the photographic data management unit 101. Note that the storage condition set by the setting unit 105 may specify not only whether or not the photographic data can be deleted, but also a storage period and a compression rate.

[0053] The above-described process can prevent the imaging data from being accidentally deleted. Alternatively, for imaging data that exceeds the retention period, the generating unit 102 may generate medical image data to be used for inference, the inference unit 104 may perform the inference, and the setting unit 105 may set the storage conditions. If the process determines that a lesion exists, no diagnosis has been made, and no next imaging has been performed, the imaging data may still be used for reconstruction, and the imaging data may be locked to prevent deletion.

[0054] (Modification 1 of the first embodiment) In the above description, the imaging data deletion process is automatically performed by the imaging data management unit 101, but it may also be performed manually by a user such as a radiologist or a doctor. In this case, the setting unit 105 in FIG. 4 performs the setting process of the storage conditions, and the result is fed back to the user. For example, when an attempt is made to delete imaging data for which the setting unit 105 has set the storage conditions as non-deletable, a dialog box warning that fact is presented. This makes it possible to prevent necessary imaging data from being easily deleted even when the user manually deletes the data.

[0055] [Second embodiment] In the second embodiment, an example will be described in which the setting unit 105 uses the inference result of the benign / malignant differential diagnosis by the inference unit 104 when setting the storage conditions for the captured data.

[0056] 5 is a flowchart showing the flow of processing in the second embodiment to determine the storage conditions for captured image data in the information processing device 100. This processing may be executed when the captured image data is acquired, or may be executed for captured image data managed by the captured image data management unit 101 for which the elapsed time since the capture date and time exceeds the retention period.

[0057] The processing from steps S4001 to S4002 is the same as that described above with reference to FIG.

[0058] In step S5001, the inference unit 103 infers whether all lesions detected in the inference image are benign or malignant based on the image of the lesion. This inference by the inference unit 104 can be performed, for example, by the method described in Patent Document 2.

[0059] In step S5002, the setting unit 105 checks the inference result of the inference unit 104. If there is no lesion inferred to be malignant, the setting unit 105 proceeds to step S4006, otherwise proceeds to step S4004.

[0060] The processing from steps S4004 to S4007 is the same as that described above with reference to FIG.

[0061] By the process described above, the setting unit 105 can lock the imaging data from being deleted by setting a storage condition that prohibits the imaging data from being deleted when there is an abnormality in the medical image data to be inferred and the abnormal area (lesion area) is malignant. Also, by applying this process to imaging data that has exceeded its retention period, even if the retention period for the imaging data has passed, if a malignant lesion is present and no diagnosis has been made and no new imaging has been performed, the setting unit 105 can determine that the imaging data may still be used for reconstruction and lock the imaging data from being deleted. This can prevent imaging data that is likely to be needed later from being accidentally deleted.

[0062] [Third embodiment] In the third embodiment, an example will be described in which the setting unit 105 uses the result of inferring the disease name by the inferring unit 104 when setting the storage conditions.

[0063] 6 is a flowchart showing the flow of processing in the third embodiment in which the setting unit 105 sets whether or not to delete the captured image data as a storage condition for the captured image data by the information processing device 100. This processing may be executed for the captured image data managed by the captured image data management unit 101, for which the elapsed time from the capture date and time exceeds the retention period.

[0064] In step S6001, the setting unit 105 acquires a medical record with a matching case ID and patient ID from the medical information system 500, and checks whether a diagnosis has been recorded after the imaging date and time. If a corresponding diagnosis has been recorded, the process proceeds to step S6002; otherwise, the process proceeds to step S6003.

[0065] In step S6002, the setting unit 105 acquires the name of the disease from the description of the diagnosis acquired in step S6001, and uses the name for the determination in step S6005.

[0066] In step S6003, the generating unit 102 reconstructs the captured image data to generate an inference image to be used for inference, and the acquiring unit 103 acquires the medical image data of the inference target generated by the generating unit 102.

[0067] In step S6004, the inference unit 104 infers the name of a disease for the medical image data to be inferred, transmits the inference result to the setting unit 105, and proceeds to the next step.

[0068] In step S6005, the setting unit 105 checks whether the disease name obtained in step S6002 or S6004 is included in the specific disease name list. Figure 7 shows an example of the specific disease name list, in which rare disease names and disease names desired for research purposes are registered. If the disease name is not included in the specific disease name list, the process proceeds to step S4006; otherwise, the process proceeds to step S6006.

[0069] In step S6006, the setting unit 105 checks whether the captured data being processed has been saved to a storage medium such as another storage (not shown). The setting unit 105 checks whether the contents are the same by taking differences between the files, and if it is determined that saving has been completed, the process proceeds to step S4006; otherwise, the process proceeds to step S4007.

[0070] The processing from steps S4006 to S4007 is the same as that described above with reference to FIG.

[0071] By the process described above, if a specific disease is expected to be diagnosed, it is determined that the imaging data may still be used for reconstruction, and the imaging data can be locked so that it cannot be deleted. This makes it possible to prevent the accidental deletion of imaging data that is likely to be needed later. Furthermore, by applying this process to imaging data whose retention period has expired, it is possible to prevent the imaging data from being deleted.

[0072] (Modification 1 of the third embodiment) In the above description, the setting unit 105 has been described using an example of whether or not to delete the captured image data as a storage condition, but the setting unit 105 may be configured to save the captured image data based on the inference result by the inference unit 104. For example, if the diagnosis name obtained from the medical information system 500 is included in the specific disease name list, the setting unit 105 may save the captured image data to another storage and, after the saving is complete, delete the captured image data from the captured image data management unit 101. This reduces the effort required for the user to manually save the captured image data.

[0073] [Variations] The present invention can also be realized by supplying a program that realizes one or more functions of the above-described embodiments to a system or device via a network or a storage medium, and having one or more processors in the computer of the system or device read and execute the program. It can also be realized by a circuit (e.g., ASIC) that realizes one or more functions.

[0074] The diagnostic support device in each of the above-described embodiments may be realized as a single device, or may be realized as a combination of multiple devices that can communicate with each other to execute the above-described processing, and both are included in the embodiments of the present invention. The above-described processing may also be executed by a common server device or server group. The multiple devices that make up the diagnostic support device and information processing system only need to be able to communicate at a predetermined communication rate, and do not need to be located in the same facility or the same country.

[0075] Embodiments of the present invention include a form in which a software program that realizes the functions of the above-mentioned embodiments is supplied to a system or device, and the computer of the system or device reads and executes the code of the supplied program.

[0076] Therefore, the program code itself installed on a computer to implement the processes according to the embodiments is also an embodiment of the present invention. Also, the OS running on the computer may perform some or all of the actual processing based on instructions contained in the program read by the computer, and the functions of the above-described embodiments may also be implemented by this processing.

[0077] Appropriate combinations of the above-described embodiments are also included in the embodiments of the present invention. [Explanation of symbols]

[0078] 103 Acquisition Department 104 Reasoning part 105 Settings

Claims

1. an acquisition unit that acquires medical image data of an inference target generated from imaging data of an object; an inference unit that infers the presence or absence of an abnormality in a subject based on the medical image data acquired by the acquisition unit; a setting unit that sets storage conditions that are conditions for storing the photographed data in a storage medium and that define a storage period for the photographed data based on an inference result of the inference unit; An information processing device comprising:

2. The information processing apparatus according to claim 1 , wherein the inference unit infers the presence or absence of an abnormality in the subject based on the medical image data using a trained inference model.

3. A generating unit that generates medical image data from the imaging data, 3. The information processing apparatus according to claim 1, wherein the inference unit performs inference on the medical image data generated by the generation unit.

4. 4. The information processing apparatus according to claim 1, wherein the storage conditions further define at least one of a compression rate and whether or not deletion is permitted.

5. 5. The information processing device according to claim 4, wherein the setting unit sets a longer storage period as the storage condition for the imaging data when the inference unit infers that there is an abnormality in the subject than when the inference unit infers that there is no abnormality in the subject.

6. 5. The information processing device according to claim 4, wherein the setting unit sets a lower compression rate as the storage condition for the imaging data when the inference unit infers that there is an abnormality in the subject than when the inference unit infers that there is no abnormality in the subject.

7. 5. The information processing device according to claim 4, wherein the setting unit does not allow deletion of the imaging data when the inference unit infers that there is an abnormality in the subject, and allows deletion of the imaging data when the inference unit infers that there is no abnormality in the subject.

8. 8. The information processing apparatus according to claim 1, wherein the inference unit infers at least one of a lesion and a disease name as an abnormality in the subject.

9. The information processing apparatus according to claim 8 , wherein the inference unit infers at least one of the number and benignity of the lesion.

10. 10. The information processing apparatus according to claim 9, wherein the inference unit infers that there is no abnormality in the subject when the lesion is benign or the number of lesions is equal to or less than a predetermined number.

11. The information processing device according to any one of claims 1 to 10, characterized in that the setting unit further acquires a diagnostic status for the medical image, and sets storage conditions for the imaging data based on the inference result by the inference unit and the diagnostic status.

12. 12. The information processing device according to claim 11, wherein the setting unit sets a storage condition for the imaging data based on a consistency between the part of the body recorded in the medical record by the diagnosis and the inference result by the inference unit.

13. The information processing device according to any one of claims 1 to 12, characterized in that the setting unit sets storage conditions for the imaging data depending on whether or not, among the imaging data based on the subject, imaging data that was taken more recently than imaging data corresponding to the medical image data to be inferred.

14. An information processing method implemented by a computer, comprising: an acquisition step of acquiring medical image data of an inference target generated from imaging data of an object; an inference step of inferring the presence or absence of an abnormality in the subject based on the medical image data acquired by the acquisition step; a setting step of setting storage conditions that are conditions for storing the photographed data in a storage medium and that specify a storage period for the photographed data based on the inference result in the inference step; An information processing method comprising:

15. A program for executing the information processing method according to claim 14 on a computer.

Images