Medical image diagnostic system, method for operating medical image diagnostic system, and program

Abstract

To provide a medical image diagnostic system, a medical image diagnostic method and a program for reducing the labor of a doctor in the case of performing image diagnosis to a large amount of medical images such as medical checkup.SOLUTION: And at least one memory storing instructions for execution by the at least one processor, wherein the at least one processor performs first determination for determining whether or not there is an abnormality from a medical image obtained by imaging a subject, and performs second determination for determining whether or not the medical image is normal in a case where it is determined that there is no abnormality in the first determination.SELECTED DRAWING: Figure 3

Description

[Technical Field]

[0001] The present invention relates to a medical image diagnostic system, a medical image diagnostic method, and a program, and more particularly to a technique for diagnosing medical images. [Background technology]

[0002] Systems that use AI (Artificial Intelligence) to detect and diagnose abnormal regions in medical images are known.

[0003] For example, Patent Document 1 discloses a medical image processing system that, regarding abnormal shadow candidates detected from medical images, provides only detection information on abnormal shadow candidates that are questionable as to whether they are true positive abnormal shadows and / or abnormal shadow candidates with low visibility, thereby preventing doctors from overlooking abnormal shadows and improving the efficiency of image interpretation work. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Laid-Open No. 2006-340835 Summary of the Invention [Problem to be solved by the invention]

[0005] For health management, medical checkups are conducted to examine the health status of subjects. In medical checkups, the subjects are mainly healthy individuals, and the diagnostic purpose, target organs, and target diseases are limited. When a possible abnormality is found in a medical image obtained during a medical checkup, a doctor must determine whether it is truly abnormal, diagnose the possible disease, and prepare a detailed report, all of which are important tasks.

[0006] On the other hand, doctors must also review images that show no abnormalities. For example, in health checkups for young people, the likelihood of patients with abnormalities is low, so doctors must review a large number of "images that show no abnormalities," placing a heavy burden on doctors.

[0007] One solution to this problem is to use lesion detection AI to perform image diagnosis. However, lesion detection AI is usually designed to target only specific diseases, and with the vast number of disease types, it is difficult to create AI that can handle all diseases. Furthermore, the amount of training data for rare diseases is small, making it difficult to create lesion detection AI. Furthermore, doctors are responsible for diagnosing unknown diseases for which lesion detection AI cannot be created in the first place. As such, even if the number of lesion detection AIs increases and their accuracy improves, there is still a limit to the final diagnostic accuracy, which has been an issue.

[0008] The present invention has been made in consideration of the above circumstances, and aims to provide a medical image diagnostic system, a medical image diagnostic method, and a program that reduce the burden on doctors when performing image diagnosis on a large number of medical images, such as in health checkups. [Means for solving the problem]

[0009] One aspect of a medical image diagnostic system for achieving the above object is a medical image diagnostic system comprising at least one processor and at least one memory for storing instructions to be executed by the at least one processor, wherein the at least one processor performs a first determination to determine the presence or absence of an abnormality from a medical image obtained by photographing a subject, and, if the first determination determines that no abnormality is present, performs a second determination to determine whether the medical image is normal. An abnormality includes, for example, at least one of a disease, a disorder, and a lesion. A medical image is normal when, for example, the medical image can be said to be an image of a healthy person. A healthy person is a healthy person, for example, one who does not have a disease, a disorder, or a lesion. This aspect can reduce the burden on doctors when performing image diagnosis on a large number of medical images.

[0010] It is preferable that at least one processor displays the diagnostic results of the medical image on the display in a manner different from the first and second cases and the third case for the first case in which the first discrimination determines that there is an abnormality, the second case in which the first discrimination determines that there is no abnormality and the medical image is determined to be abnormal in the second discrimination, and the third case in which the first discrimination determines that there is no abnormality and the medical image is determined to be normal in the second discrimination.

[0011] Preferably, the at least one processor causes the display to display the diagnostic results of the medical images in different ways in the first case and the second case.

[0012] Preferably, the at least one processor performs different post-processing on the medical image in the first case, the second case, and the third case.

[0013] Preferably, the at least one processor performs a first discrimination and a second discrimination for each organ of the subject from the medical image.

[0014] If the medical image is determined to be abnormal in the second discrimination, at least one processor performs a third discrimination to determine whether or not an abnormality is present in the medical image, and it is preferable that the third discrimination be performed with a sensitivity relatively higher than that of the first discrimination.

[0015] Preferably, the at least one processor performs the first discrimination using a first trained model that receives a medical image as input and outputs an abnormality in the medical image.

[0016] It is preferable that the at least one processor performs the second discrimination using a second trained model that, when a medical image is input, outputs whether the medical image is normal or not.

[0017] The second trained model preferably outputs a probability that the input medical image is normal. The second trained model may output a probability that the input medical image is not normal.

[0018] The second trained model is preferably a trained model trained using a training dataset of combinations of normal and abnormal medical images and labels indicating whether they are normal or not.

[0019] One aspect of a medical image diagnostic method for achieving the above object is a medical image diagnostic method comprising: a first determination step of determining whether or not an abnormality exists in a medical image obtained by photographing a subject; and a second determination step of determining whether or not the medical image is normal when the first determination step determines that no abnormality exists. According to this aspect, it is possible to reduce the burden on doctors when performing image diagnosis on a large number of medical images.

[0020] One aspect of a program for achieving the above object is a program for causing a computer to execute the above medical image diagnostic method. This aspect may also include a computer-readable non-transitory storage medium on which this program is recorded. [Effects of the Invention]

[0021] According to the present invention, it is possible to reduce the burden on doctors when performing image diagnosis on a large number of medical images. [Brief explanation of the drawings]

[0022] [Figure 1] FIG. 1 is a block diagram of a medical image diagnostic system according to this embodiment. [Figure 2] FIG. 2 is a flowchart showing a medical image diagnosis method. [Figure 3] FIG. 3 is a process diagram illustrating a medical image diagnosis method. [Figure 4] FIG. 4 is a diagram showing a display form. [Figure 5] FIG. 5 is a diagram showing a display form. [Figure 6] FIG. 6 is a diagram showing a display form. [Figure 7] FIG. 7 is a diagram showing a display form. DETAILED DESCRIPTION OF THE INVENTION

[0023] Preferred embodiments of the present invention will now be described in detail with reference to the accompanying drawings.

[0024] [Configuration of medical image diagnostic system] The medical image diagnostic system according to this embodiment reduces the burden on doctors when performing image diagnosis on a large number of medical images, such as in a health checkup.

[0025] Fig. 1 is a block diagram of a medical image diagnostic system 10 according to this embodiment. As shown in Fig. 1, the medical image diagnostic system 10 includes a modality 12, an image storage server 14, a CAD (Computer-Aided Diagnosis) processing server 16, a result integration CAD processing server 18, and a PACS (Picture Archiving and Communication System) viewer 20.

[0026] The modality 12, image storage server 14, each company's CAD processing server 16, result integration CAD processing server 18, and PACS viewer 20 are each connected to a communication network such as the Internet so as to be able to send and receive data.

[0027] The modality 12 is an imaging device that captures an image of a target area of ​​a subject and generates a medical image. The modality 12 includes, for example, at least one of an X-ray imaging device, a CT (Computed Tomography) device, an MRI (Magnetic Resonance Imaging) device, a PET (Positron Emission Tomography) device, an ultrasound device, and a CR (Computed Radiography) device using a flat X-ray detector.

[0028] The image storage server 14 is a server that manages medical images captured by the modality 12. The image storage server 14 is implemented as a computer equipped with a large-capacity storage device. Software that provides the functions of a data storage system is installed in the computer. The image storage server 14 acquires medical images captured by the modality 12 and stores them in the large-capacity storage device.

[0029] The format of a medical image can be in accordance with the DICOM (Digital Imaging and Communications in Medicine) standard. DICOM tag information defined in the DICOM standard may be added to the medical image. Note that the term "image" in this specification can refer to not only the image itself, such as a photograph, but also image data, which is a signal representing an image.

[0030] The respective company CAD processing server 16 is composed of a plurality of CAD processing servers owned by a plurality of companies. The respective company CAD processing server 16 may be a single CAD processing server. The respective company CAD processing server 16 includes a first discrimination unit 16A. The first discrimination unit 16A includes a program that performs an abnormality detection process for each organ on the medical images acquired from the image storage server 14 and performs a first discrimination to determine the presence or absence of one or more abnormalities from the medical images. An abnormality includes, for example, at least one of a disease, a disorder, and a lesion. The first discrimination result by the first discrimination unit 16A is linked to the medical image in the image storage server 14 and stored in a large-capacity storage device.

[0031] The first discriminator 16A may be provided in the result integration CAD processing server 18.

[0032] The result integration CAD processing server 18 acquires and integrates the first discrimination result from the first discrimination unit 16A. Here, for example, CAD results for different types of diseases, illnesses, and lesions for the same organ in the same input image are integrated for the second discrimination unit 18A. The result integration CAD processing server 18 also includes a second discrimination unit 18A. The second discrimination unit 18A performs normality discrimination processing on medical images acquired from the image storage server 14 that have been discriminated as free of any abnormalities by the first discrimination unit 16A, to determine whether the medical image is normal for each organ. Whether a medical image is normal or not refers, for example, to whether the medical image is an image of a healthy individual. A healthy individual is a healthy individual, for example, one who is free of diseases, illnesses, and lesions. The second discrimination result from the second discrimination unit 18A is associated with the medical image and stored in a large-capacity storage device in the image storage server 14.

[0033] The result integrated CAD processing server 18 is implemented as a personal computer or a workstation. The result integrated CAD processing server 18 includes a processor 18B and a memory 18C. The processor 18B executes instructions stored in the memory 18C.

[0034] The hardware structure of processor 18B is various processors as follows: The various processors include a CPU (Central Processing Unit), which is a general-purpose processor that executes software (programs) and functions as various functional units, a GPU (Graphics Processing Unit), which is a processor specialized for image processing, a PLD (Programmable Logic Device), which is a processor whose circuit configuration can be changed after manufacturing such as an FPGA (Field Programmable Gate Array), and a dedicated electrical circuit, which is a processor having a circuit configuration designed specifically for executing specific processing such as an ASIC (Application Specific Integrated Circuit).

[0035] A single processing unit may be configured with one of these various processors, or may be configured with two or more processors of the same or different types (e.g., multiple FPGAs, a combination of a CPU and an FPGA, or a combination of a CPU and a GPU). Also, multiple functional units may be configured with a single processor. Examples of multiple functional units configured with a single processor include, first, a configuration in which a single processor is configured with a combination of one or more CPUs and software, as typified by a client or server computer, and this processor operates as multiple functional units. Second, a configuration in which a processor is used to realize the functions of an entire system including multiple functional units on a single IC (Integrated Circuit) chip, as typified by an SoC (System On Chip). In this way, the various functional units are configured with one or more of the above-mentioned various processors as a hardware structure.

[0036] Furthermore, the hardware structure of these various processors is, more specifically, an electric circuit made up of a combination of circuit elements such as semiconductor elements.

[0037] The memory 18C stores instructions to be executed by the processor 18B. The memory 18C includes a RAM (Random Access Memory) and a ROM (Read Only Memory), not shown. The processor 18B uses the RAM as a working area, executes software using various programs and parameters, including a medical image processing program, stored in the ROM, and executes various processes of the integrated CAD processing server 18 by using the parameters stored in the ROM, etc.

[0038] The PACS viewer 20 is a terminal device used by a user such as a doctor, and may be, for example, a known image viewer for image interpretation. The PACS viewer 20 may be a personal computer, a workstation, or a tablet terminal.

[0039] The PACS viewer 20 includes an input device 20A and a display 20B. The input device 20A includes a pointing device such as a mouse and an input device such as a keyboard. A user can input instructions to the medical image diagnostic system 10 using the input device 20A. The display 20B displays a screen required for operations on the input device 20A and functions as a part that realizes a GUI (Graphical User Interface). The display 20B displays medical images captured by the modality 12. The display 20B also displays the first discrimination result and the second discrimination result as CAD results. The PACS viewer 20 may be a touch panel display in which the input device 20A and the display 20B are integrated.

[0040] [Medical image diagnostic method] FIG. 2 is a flowchart showing a medical image diagnosis method using the medical image diagnosis system 10. FIG. 3 is a process diagram showing the medical image diagnosis method. The medical image diagnosis method is realized by the processor 18B executing a medical image diagnosis program stored in the memory 18C. The medical image diagnosis program may be provided by a computer-readable non-transitory storage medium. In this case, the result-integrated CAD processing server 18 may read the medical image diagnosis program from the non-transitory storage medium and store it in the memory 18C.

[0041] The medical image diagnosis method is performed for each organ of a subject. Here, the case of diagnosing a CT image of the lungs will be explained as an example.

[0042] In step S1, the processor 18B of the result integrated CAD processing server 18 causes the image storage server 14 to acquire CT images of the subject's lungs taken by the modality 12. The image storage server 14 acquires the CT images taken by the modality 12.

[0043] In step S2 (an example of a "first discrimination step"), the processor 18B inputs the CT image acquired by the image storage server 14 to the company's CAD processing server 16. The company's CAD processing server 16 inputs the CT image to the first discrimination unit 16A and performs a first discrimination (process P1).

[0044] 3, the first discrimination unit 16A includes a company A lesion detection AI 16B for detecting disease α, a company A lesion detection AI 16C for detecting disease β, a company A lesion detection AI 16D for detecting disease γ, a company B lesion detection AI 16E for detecting disease γ, and a company C lesion detection AI 16F for detecting disease β. For example, disease α is lung cancer, disease β is pneumonia, and disease γ is pneumothorax.

[0045] Each of the lesion detection AIs 16B-16F is a trained model (an example of a "first trained model") that outputs diseased areas (lesion areas, examples of "abnormalities") in a CT image of the lungs when the image is input, and each includes a convolutional neural network. Each of the lesion detection AIs 16B-16F is generated by deep learning using labeled images in which a doctor labels each diseased area in the CT image of the lungs as training data.

[0046] Each lesion detection AI 16B-16F is configured to calculate the probability of each disease for each pixel in the CT image, and pixels exceeding a predetermined threshold are considered to be diseased areas. Each lesion detection AI 16B-16F has higher specificity than when lesion detection is performed independently, i.e., the threshold is set relatively high. This allows each lesion detection AI 16B-16F to detect areas that are more likely to be lesions. This is because, even if abnormalities are rare or missed in a health check, the second discrimination by the second discrimination unit 18A can determine that the image is abnormal. Note that the lesion detection AI is not limited to the method of calculating the disease probability for each pixel as described above. For example, it may be designed to extract a rectangular lesion candidate area in an image and output the lesion probability for the rectangular area.

[0047] First discrimination unit 16A inputs the CT image to each of lesion detection AIs 16B to 16F. Each of lesion detection AIs 16B to 16F performs lesion detection processing on the CT image and outputs the results as first discrimination results.

[0048] In step S3, the processor 18B acquires the first discrimination results from the first discrimination unit 16A and integrates them (process P2). The integration is the same as that described above, and therefore will not be described further.

[0049] In step S4, processor 18B determines whether or not an abnormality (here, a lesion) is present in the CT image based on the integrated first discrimination result. Here, it is determined that "an abnormality is present" when one or more lesions are detected by any of lesion detection AIs 16B to 16F. If an abnormality is present in the CT image (an example of the "first case," process P3), the process proceeds to step S5, and if no abnormality is present in the CT image (process P4), the process proceeds to step S6.

[0050] In step S5, the processor 18B causes the display 20B of the PACS viewer 20 to display the CT image containing an abnormality in display mode A, and performs post-processing of processing mode A to clearly indicate to the doctor that the "first discrimination result" is that an abnormality exists in the CT image ("first case") (process P5). Furthermore, the processor 18B adds "type A" incidental information to the CT image and causes it to be stored in the image storage server 14, and ends the processing of this flowchart.

[0051] In step S6 (an example of a "second discrimination step"), the processor 18B inputs a CT image containing no abnormalities to the second discrimination unit 18A. As shown in Fig. 3, the second discrimination unit 18A includes a normality discrimination AI 18D that discriminates whether the medical image is normal or not.

[0052] The normality discrimination AI 18D is a trained model (an example of a "second trained model") that, when a lung CT image is input, determines whether the CT image is normal or not, and includes a convolutional neural network. The normality discrimination AI 18D is generated by deep learning using a training dataset of normal CT images and normal labels, and a training dataset of abnormal CT images and abnormal labels. Note that a normal CT image is a CT image of a healthy subject. An abnormal CT image is a CT image with some kind of abnormality, such as a CT image of a subject with at least one of a disease, illness, or lesion.

[0053] The normality determination AI 18D is generated to output the degree of normality of the input CT image as a numerical value (a score, an example of a "probability"). The normality determination AI 18D outputs that the CT image is abnormal if the normality of the CT image is below a predetermined threshold, and outputs that the CT image is normal if the normality of the CT image is equal to or greater than the threshold. The second determination unit 18A inputs the CT image to the normality determination AI 18D and obtains a second determination result (process P6).

[0054] In step S7, processor 18B determines whether the CT image is normal based on the second discrimination result. If the CT image is not normal (an example of the "second case", process P7), the process proceeds to step S8, and if the CT image is normal (an example of the "third case", process P8), the process proceeds to step S9.

[0055] In step S8, the processor 18B causes the display 20B of the PACS viewer 20 to display the abnormal CT image in display mode B, and performs post-processing of processing mode B to clearly recognize for the doctor that, unlike the "first case," a CT image in which no abnormality is present in the "first discrimination result" has an abnormality present in the "second discrimination result" ("second case") (process P9). Furthermore, the processor 18B assigns "type B" incidental information to the CT image and causes it to be stored in the image storage server 14, thereby terminating the processing of this flowchart.

[0056] On the other hand, in step S9, the processor 18B causes the display 20B of the PACS viewer 20 to display the normal CT image in display format C, and performs post-processing in processing format C so that the doctor can process the "normal CT image" more easily (process P10). Furthermore, the processor 18B adds "type C" incidental information to the CT image and stores it in the image storage server 14, and ends the processing of this flowchart.

[0057] Processor 18B causes display 20B to display the diagnostic results based on the "first determination result" and the "second determination result" in different modes for display form A and display form B, and display form C. Processor 18B may also cause display 20B to display the diagnostic results in different modes for display form A and display form B.

[0058] To clearly inform the doctor of the respective diagnostic results based on the "first discrimination result" and the "second discrimination result," different diagnostic results can be displayed using different display items, description content, or display formats (text, diagram, color, etc.). For example, display format A visually displays the name and area of ​​detected lesions, similar to general CAD. Display format B notifies the doctor that no lesions were detected, but that the results were not clearly normal. Furthermore, display format C indicates that there is a high probability that there is no abnormality, allowing the doctor to skip confirmation and automatically reporting to the patient that there is no abnormality.

[0059] Fig. 4 is a diagram showing display form A. As shown in Fig. 4, in display form A, a CT image I1 is displayed on display 20B, and a marker M1 surrounding the lesion area in CT image I1 is superimposed on the CT image I1. Also, in display form A, an explanatory text T1 for CT image I1, which is an explanatory text T1 regarding the lesion area surrounded by marker M1, is displayed in the area to the right of CT image I1. Here, the lesion area has been detected by lesion detection AI 16B manufactured by Company A that detects disease α (lung cancer), and explanatory text T1 stating "Detected by lung cancer detection CAD manufactured by Company A" is displayed on display 20B.

[0060] Fig. 5 is a diagram showing display form B. As shown in Fig. 5, in display form B, a CT image I2 is displayed on the display 20B, and a marker M2 that surrounds the entire CT image I2 is superimposed on the CT image I2. Also, in display form B, an explanatory text T1 for the CT image I2, which is an explanatory text T2 related to the marker M2, is displayed in the area to the right of the CT image I2. Here, the explanatory text T2 that reads, "No abnormalities have been reported for any CAD. However, the normality determination AI has not determined that the patient is healthy," is displayed on the display 20B.

[0061] FIG. 6 is a diagram showing display form C. As shown in FIG. 6, in display form C, a CT image I3 is displayed on display 20B. Also, in display form C, an explanatory text T3 for CT image I3 is displayed in the area to the right of CT image I3. Here, explanatory text T3 saying "No abnormalities were found by CAD" is displayed on display 20B. Note that, since CT image I3 is likely not abnormal, it is possible to simply display a message indicating that the image is normal without displaying CT image I3, thereby skipping the doctor's confirmation.

[0062] In addition, processor 18B performs post-processing in different ways for processing form A and processing form B, and processing form C, so that a doctor can more easily confirm and judge the diagnostic results based on the ``first discrimination result'' and ``second discrimination result'' and process the medical images.

[0063] For example, a flag is set in processing mode C to allow doctors to easily check the images, and no flag is set in processing modes A and B. In addition, the display order of the interpretation and examination list for doctors to check medical images may be changed so that CT images in processing mode A and B are given priority over CT images in processing mode C.

[0064] In the case of health checkups, it is rare for diseases requiring immediate hospitalization or treatment to be discovered, so there are situations where the results may not be notified on the spot, or the subject may be initially told that the results are normal, and then be informed separately that abnormalities have been found. Therefore, for processing type C, it is possible to have the doctor report "no abnormalities" on the spot, and then later have the results compiled and processed to confirm whether or not there are actually any abnormalities. For example, at the end of the day, a doctor may perform a simple check of all CT images of processing type C that day. If an abnormality is found during the simple check, the doctor can be contacted separately.

[0065] The processor 18B may perform post-processing in different ways for the processing type A and the processing type B.

[0066] As described above, according to the medical image diagnosis method, the first discrimination unit 16A can discriminate whether or not an abnormality exists in a medical image. Furthermore, if the first discrimination unit 16A does not detect an abnormality, the second discrimination unit 18A can discriminate whether or not the medical image is normal. Therefore, the burden on doctors when performing image diagnosis on a large number of medical images can be reduced.

[0067] 〔others〕 If the second discrimination unit 18A discriminates that the medical image is not normal, a third discrimination process may be performed to discriminate the presence or absence of an abnormality from the medical image. The third discrimination process is performed with a higher sensitivity (a lower specificity than the specificity in the first discrimination process) than the sensitivity in the first discrimination process, i.e., with a relatively low threshold value.

[0068] The third discrimination process is performed by the first discrimination unit 16A. The first discrimination unit 16A performs the third discrimination process by setting the sensitivity of each of the lesion detection AIs 16B to 16F higher than in the first discrimination process, i.e., by setting the threshold value relatively low. As a result, the third discrimination process extracts lesions using an evaluation standard that does not tolerate misidentifying non-pathological conditions as pathological, and reports the results to a doctor. If the display format in this case is display format D, it is desirable to increase the sensitivity in display format D to present to the doctor that the lesion has been extracted.

[0069] Fig. 7 is a diagram showing display form D. As shown in Fig. 7, in display form D, a CT image I2 is displayed on display 20B, a marker M2 surrounding the entire CT image I2 is superimposed on the CT image I2, and a marker M3 surrounding the lesion area of ​​the CT image I2 is further superimposed on the CT image I2. Unlike marker M1 in display form A, marker M3 is displayed with a dashed line to indicate that it is a lesion detected with increased sensitivity.

[0070] In addition, in display form D, the explanatory text T1 for the CT image I2, which is explanatory text T4 regarding the marker M3, is displayed in the area to the right of the CT image I2. Here, explanatory text T4 reads, "The normality discrimination CAD did not determine whether the patient was healthy, so the sensitivity was increased and CAD processing was performed again, and lung cancer was detected by the detection CAD manufactured by company A." and is displayed on display 20B.

[0071] 5, a slider bar SB for setting the sensitivity of the first discrimination unit 16A may be displayed in display mode B. When the user increases the sensitivity by operating the slider bar SB using the input device 20A, the third discrimination process may be performed at the set sensitivity, and the display mode may transition to display mode D as shown in FIG.

[0072] Although the present embodiment describes processing of a CT image of the lungs, the present invention is not limited to this. For example, for a CT image including the liver, each of the lesion detection AIs 16B to 16F may extract any one of liver cancer, polycystic cysts, cirrhosis, and fatty liver.

[0073] The technical scope of the present invention is not limited to the scope described in the above embodiments. The configurations and the like in each embodiment can be appropriately combined with each other within the scope that does not deviate from the spirit of the present invention. [Explanation of symbols]

[0074] 10...Medical image diagnostic system 12...Modality 14...Image storage server 16...CAD processing servers of various companies 16A...First discrimination section 16B... Lesion detection AI made by company A 16C... Lesion detection AI made by company A 16D... Lesion detection AI made by company A 16E… Lesion detection AI made by Company B 16F… Lesion detection AI made by Company C 18...Results integrated CAD processing server 18A...Second discrimination section 18B...Processor 18C...Memory 18D…Normal discrimination AI 20...PACS viewer 20A...input device 20B...Display I1...CT image I2...CT image I3...CT image M1...marker M2...marker M3...marker P1 to P10: Medical image diagnosis processes S1 to S9: Each step of medical image diagnosis SB...Slider bar T1...Description T2…Description T3…Description T4…Description

Claims

1. at least one processor; at least one memory storing instructions for execution by said at least one processor; Equipped with The at least one processor performing a first determination of the presence or absence of at least one of a disease, illness, and lesion from a medical image obtained by photographing the subject; When it is determined in the first determination that at least one of a disease, an illness, and a lesion is not present, a second determination is performed to determine whether the medical image is an image of a healthy person; displaying the discrimination result of the medical image on a display in different modes depending on whether the first discrimination determines that at least one of a disease, a disorder, and a lesion is present or whether the first discrimination determines that at least one of a disease, a disorder, and a lesion is absent; Medical imaging diagnostic system.

2. The at least one processor a first case in which the first determination determines that at least one of a disease, illness, and lesion is present; a second case in which the first determination determines that at least one of a disease, illness, and lesion is absent and the medical image is determined to be an image of a healthy person in the second determination; and a third case in which the first determination determines that at least one of a disease, illness, and lesion is absent and the medical image is determined to be an image of a healthy person in the second determination, displaying the diagnostic results of the medical image on a display in a manner different from that of the first and second cases and the third case. The medical image diagnostic system according to claim 1 .

3. The at least one processor displaying the diagnostic results of the medical images on a display in different modes in the first case and the second case; The medical image diagnostic system according to claim 2 .

4. The at least one processor performing different post-processing on the medical image in the first case, the second case, and the third case; The medical image diagnostic system according to claim 2 .

5. The at least one processor performing the first discrimination and the second discrimination for each organ of the subject from the medical image; The medical image diagnostic system according to claim 1 .

6. The at least one processor When the medical image is determined not to be an image of a healthy subject in the second determination, a third determination is performed to determine whether or not at least one of a disease, illness, and lesion is present in the medical image; the third discrimination is performed with a sensitivity relatively higher than that of the first discrimination; The medical image diagnostic system according to claim 1 .

7. The at least one processor performing the first discrimination using a first trained model that, when the medical image is input, outputs at least one of a disease, a disorder, and a lesion in the medical image; The medical image diagnostic system according to claim 1 .

8. The at least one processor The second determination is performed using a second trained model that, when the medical image is input, outputs whether the medical image is an image of a healthy subject. The medical image diagnostic system according to claim 1 .

9. The second trained model outputs a probability that an input medical image is an image of a healthy subject. The medical image diagnostic system according to claim 8 .

10. The second trained model is a trained model trained using a combination of medical images of healthy individuals and medical images of non-healthy individuals and a label indicating whether the image is a medical image of a healthy individual as a training data set. The medical image diagnostic system according to claim 8 .

11. 1. A method of operating a medical imaging diagnostic system comprising at least one processor, comprising: the at least one processor: performing a first determination of the presence or absence of at least one of a disease, illness, and lesion from a medical image obtained by photographing the subject; When it is determined in the first determination that at least one of a disease, an illness, and a lesion is not present, a second determination is performed to determine whether the medical image is an image of a healthy person; displaying the discrimination result of the medical image on a display in different modes depending on whether the first discrimination determines that at least one of a disease, a disorder, and a lesion is present or whether the first discrimination determines that at least one of a disease, a disorder, and a lesion is absent; A method for operating a medical imaging system.

12. A program for causing a computer to execute the method for operating a medical image diagnostic system according to claim 11.

Images