Medical image processing apparatus, medical image processing system, medical image processing method, and program

Abstract

The purpose of the present invention is to provide a medical image processing device, a medical image processing system, a medical image processing method, and a program that make it possible to show the usage status of image processing that can be set to automatic execution. The present invention comprises at least one processor and at least one memory that stores commands to be executed by the at least one processor. The at least one processor: collects usage information about the usage by a user of the results of first image processing that supports the diagnosis of medical images and can be set as automatically executed image processing that is automatically executed on inputted medical images and accompanying information about medical images subjected to the first image processing; and makes a display display the usage information in association with the accompanying information.

Description

Technical Field

[0001] The present invention relates to a medical image processing apparatus, a medical image processing system, a medical image processing method, and a program, and particularly relates to a technique for presenting the usage status of automatically executed image processing.

Background Art

[0002] Cloud services that provide image processing services are known. For example, Patent Document 1 discloses a cloud server that provides advanced image processing services for medical images to clients such as doctors, instructors, students, insurance company agents, patients, and medical researchers in medical institutions.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In a calculation processing system with a pay-per-use system such as a cloud service, the number of processes is directly linked to the user's payment amount. Among the calculation processing systems with a pay-per-use system, in the case of a system that automatically selects and automatically executes image processing from image information such as tag information and site information, it is assumed that a certain number of the processing results will be subject to billing even though the results are not utilized. Also, in the case of a flat-rate calculation processing system, the portion where the results are not utilized becomes a calculation cost. Therefore, in order to reduce expenses for the user, it is necessary to set execution conditions such that unused image processing is not executed. However, in order for the user to optimally set the execution conditions, it is necessary to examine a huge dataset of unused image processing and images, which has the problem of high load.

[0005] The present invention has been made in view of such circumstances, and an object thereof is to provide a medical image processing apparatus, a medical image processing system, a medical image processing method, and a program that present the usage status of image processing that can be set for automatic execution.

Means for Solving the Problems

[0006] One aspect of a medical image processing apparatus for achieving the above object includes at least one processor and at least one memory that stores instructions for causing the at least one processor to execute. The at least one processor is a first image processing for assisting in the diagnosis of medical images, and collects usage information by the user of the result of the first image processing that can be set as an automatic execution image processing automatically executed on the input medical image, and the accompanying information of the medical image that is the object of the first image processing, and associates the usage information and the accompanying information and displays them on a display. According to this aspect, since the usage status of the image processing that can be set as the automatic execution image processing can be presented, the user can determine whether to set the image processing as the automatic execution image processing from the presented usage status.

[0007] The usage information preferably includes at least one of whether the user referred to the result of the first image processing, whether the result of the first image processing contributed to preventing the overlooking of diseases, the reduction amount of the reading time due to the result of the first image processing, whether the measurement result of the first image processing contributed to the improvement of accuracy, and whether the user instructed the execution of the first image processing other than automatic execution.

[0008] The object of the first image processing is preferably a tomographic image, and the accompanying information preferably includes at least one of the slice thickness and the number of slices.

[0009] The at least one processor preferably accepts at least one of deleting the first image processing from the setting of the automatic execution image processing and setting the first image processing as the automatic execution image processing.

[0010] At least one processor preferably proposes an automatic execution condition for automatically executing first image processing based on usage information and accompanying information.

[0011] At least one processor preferably proposes an automatic execution condition in consideration of external factors. Further, the external factors preferably include the seasonality of the disease targeted by the first image processing.

[0012] At least one processor preferably executes the image processing set for the automatic execution image processing.

[0013] One aspect of a medical image processing system for achieving the above object is a medical image processing system including the above medical image processing apparatus and a server that executes the image processing set as the automatic execution image processing.

[0014] One aspect of a medical image processing method for achieving the above object is a first image processing for assisting in the diagnosis of a medical image, which collects usage information by a user of the result of the first image processing that can be set as automatic execution image processing automatically executed on the input medical image, and accompanying information of the medical image targeted by the first image processing, and associates the usage information and the accompanying information and displays them on a display. According to this aspect, since the usage status of the image processing that can be set as the automatic execution image processing can be presented, the user can determine whether to set the image processing as the automatic execution image processing from the presented usage status.

[0015] One aspect of a program for achieving the above object is a program for causing a computer to execute the above medical image processing method. A computer-readable non-transitory storage medium on which this program is recorded may also be included in this aspect. According to this aspect, since the usage status of the image processing that can be set as the automatic execution image processing can be presented, the user can determine whether to set the image processing as the automatic execution image processing from the presented usage status.

Effect of the Invention

[0016] According to the present invention, a user can determine whether to set image processing as automatic execution image processing from the presented usage status.

Brief Description of the Drawings

[0017]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Modes for Carrying Out the Invention

[0018] Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings.

[0019] 〔Overall Configuration of Medical Image Processing System〕 FIG. 1 is an overall configuration diagram of a medical image processing system 10. The medical image processing system 10 is an image processing that captures an image of an inspection target (patient) and supports the diagnosis of a medical image for the captured image, and is a system that automatically executes the image processing set as automatic execution image processing. As shown in FIG. 1, the medical image processing system 10 includes a medical image inspection device 12, a medical image database 14, an image processing evaluation device 16, a user terminal 20, and a cloud server 26.

[0020] The medical imaging device 12, the medical image database 14, the image processing evaluation device 16, and the user terminal 20 are provided within a medical institution such as a hospital, and are respectively connected via the in-hospital network 22 so as to be capable of data transmission and reception. The in-hospital network 22 can apply a LAN (Local Area Network). The in-hospital network 22 may be wired or wireless.

[0021] The in-hospital network 22 is connected to the Internet 24 via a router (not shown). The in-hospital network 22 and the cloud server 26 are respectively connected via the Internet 24 so as to be capable of data transmission and reception.

[0022] The medical imaging device 12 is an imaging device that images an examination target site of an examination target and generates a medical image. The medical imaging device 12 includes at least one of, for example, an X-ray imaging device, a CT (Computed Tomography) device, an MRI (Magnetic Resonance Imaging) device, a PET (Positron Emission Tomography) device, an ultrasonic device, and a CR (Computed Radiography) device using a flat panel X-ray detector.

[0023] The medical image database 14 is a database that manages medical images taken by the medical imaging device 12. The medical image database 14 can apply a computer equipped with a large-capacity storage device. The computer is incorporated with software that provides the function of a database management system.

[0024] The format of the medical image can apply the Dicom (Digital imaging and communications in medicine) standard. The medical image may be added with Dicom tag information defined in the Dicom standard. Note that the term "image" in this specification may include, in addition to the meaning of the image itself such as a photograph, the meaning of image data which is a signal representing the image.

[0025] The image processing evaluation device 16 is an example of a medical image processing device, which collects the usage status of image processing executed in the cloud server 26 and evaluates the image processing from the usage status. The image processing evaluation device 16 can be applied to a personal computer or a workstation. The image processing evaluation device 16 includes a processor 16A and a memory 16B. The processor 16A executes instructions stored in the memory 16B.

[0026] The hardware structure of the processor 16A is various types of processors as shown below. The various processors include a CPU (Central Processing Unit), which is a general-purpose processor that executes software (program) and acts 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 such as an FPGA (Field Programmable Gate Array) whose circuit configuration can be changed after manufacturing, and a dedicated electric circuit, which is a processor having a circuit configuration specifically designed to execute specific processing such as an ASIC (Application Specific Integrated Circuit).

[0027] One processing unit may be composed of one of these various processors, or may be composed of two or more processors of the same or different types (for example, a plurality of FPGAs, or a combination of a CPU and an FPGA, or a combination of a CPU and a GPU). Also, a plurality of functional units may be composed of one processor. As an example of configuring a plurality of functional units with one processor, firstly, as represented by a computer such as a client or a server, one processor is configured by a combination of one or more CPUs and software, and this processor acts as a plurality of functional units. Secondly, as represented by an SoC (System On Chip) or the like, there is a form in which a processor that realizes the functions of an entire system including a plurality of functional units with one IC (Integrated Circuit) chip is used. Thus, various functional units are configured as a hardware structure using one or more of the above various processors.

[0028] Furthermore, the hardware structure of these various processors is more specifically an electrical circuit (circuitry) formed by combining circuit elements such as semiconductor elements.

[0029] Memory 16B stores instructions for the processor 16A to execute. Memory 16B includes a RAM (Random Access Memory) and a ROM (Read Only Memory) not shown in the figure. Processor 16A uses the RAM as a work area and executes software using various programs and parameters including a medical image processing program stored in the ROM, and executes various processes of the image processing evaluation device 16 by using the parameters stored in the ROM or the like.

[0030] The user terminal 20 is a terminal device used by users such as doctors, and for example, a known radiographic image viewer is applied. The user terminal 20 may be a personal computer, a workstation, or a tablet terminal. The user terminal 20 includes an input device 20A and a display 20B. On the display 20B, medical images taken by the medical imaging device 12 and the results of image processing are displayed. Also, information regarding image processing presented by the image processing evaluation device 16 is displayed on the display 20B. The user can input an instruction to the medical image processing system 10 using the input device 20A.

[0031] The cloud server 26 can apply, for example, a server computer, a personal computer, or a workstation. The cloud server 26 performs image processing including at least one of lesion extraction and disease name determination processing on the medical images to be examined. The cloud server 26 can be accessed from the in-hospital networks 22 of a plurality of hospitals via the Internet 24. In this embodiment, the processing performed by the cloud server 26 is a cloud service with a pay-per-use system. The processing performed by the cloud server 26 may be a flat-rate cloud service.

[0032] 〔Functional Configuration of Medical Image Processing System〕 FIG. 2 is a diagram showing the functional configuration and processing process of the medical image processing system 10. The processing process will be described later. As shown in FIG. 2, in addition to the medical imaging device 12 and the user terminal 20 shown in FIG. 1, the medical image processing system 10 includes an image management unit 30, an image processing determination processing unit 32, an automatic execution condition management unit 34, a cloud image processing unit 36, a processing result management unit 38, a processing result usage log management unit 40, and a recommended execution condition / cost-benefit determination processing unit 42.

[0033] The functions of the image management unit 30 are realized by the medical image database 14. The functions of the image processing determination processing unit 32, the automatic execution condition management unit 34, the processing result management unit 38, the processing result usage log management unit 40, and the recommended execution condition / cost-benefit determination processing unit 42 are realized by the image processing evaluation device 16. The functions of the cloud image processing unit 36 are realized by the cloud server 26.

[0034] The image management unit 30 manages medical images taken by the medical image examination device 12. The image processing determination processing unit 32 determines automatic execution image processing to be automatically executed on the medical images taken by the medical image examination device 12. The automatic execution condition management unit 34 holds the automatic execution conditions of the automatic execution image processing. The cloud image processing unit 36 executes image processing on the medical images taken by the medical image examination device 12.

[0035] The image processing executed in the cloud image processing unit 36 is not limited as long as it is image processing on medical images. For example, it includes computer-aided diagnosis (CAD) for extracting lesions and the like in medical images, segmentation processing of parts and lesions and the like, labeling processing of part names and disease names and the like, similar image search, and similar case search.

[0036] The processing result management unit 38 acquires the execution results of the image processing executed by the cloud image processing unit 36. The processing result usage log management unit 40 stores, as logs, the usage information of the results of the image processing by the user and the accompanying information of the medical images that are the targets of the image processing. That is, the processing result usage log management unit 40 stores, as logs, the usage information indicating the usage status of the results of the image processing by the user and the accompanying information of the medical images that are the targets of the image processing. The recommended execution condition / cost-benefit determination processing unit 42 determines the recommended execution conditions of the image processing and its cost-benefit based on the logs accumulated in the processing result usage log management unit 40.

[0037] 〔Medical Image Processing Method〕 FIG. 3 is a flowchart showing a medical image processing method using the medical image processing system 10. The medical image processing method is realized by the processor 16A executing a medical image processing program stored in the memory 16B. The medical image processing program may be provided by a computer-readable non-transitory storage medium. In this case, the image processing evaluation device 16 may read the medical image processing program from the non-transitory storage medium and store it in the memory 16B. Hereinafter, with reference to FIGS. 2 and 3, the processing process of the medical image processing system 10 and the medical image processing method will be described.

[0038] In step S1, the medical image examination device 12 takes a medical image of a patient and stores the taken medical image in the image management unit 30 (process P1). For example, a doctor uses a CT device (not shown) as the medical image examination device 12 to take a CT image (an example of a "tomographic image") of a patient. Here, it is assumed that the CT device has taken a CT image with a slice thickness of 1 mm and 1000 slices. The CT device stores the taken CT image in the image management unit 30.

[0039] In step S2, the image management unit 30 notifies the image processing determination processing unit 32 that a medical image has been stored by the medical image examination device 12 (process P2). Here, the image management unit 30 notifies that a CT image has been imported from the CT device.

[0040] In step S3, the image processing determination processing unit 32 acquires the automatic execution conditions of the automatic execution image processing that is automatically executed from the automatic execution condition management unit 34 (process P3).

[0041] For example, among a plurality of image processes (an example of the "first image process") that can be set as automatic execution image processes in the cloud image processing unit 36, assume that the image processes set as automatic execution image processes are "CAD(1)", "CAD(2)", "Segmentation(1)", "Labeling(1)", and "Labeling(2)". The image process determination processing unit 32 acquires the automatic execution conditions for each of the five types of image processes. The cloud image processing unit 36 executes the automatic execution image process on the images that satisfy the automatic execution conditions. The automatic execution conditions include, for example, at least one of the slice thickness and the number of slices of the CT image. Here, an example in which the automatic execution conditions are set by the slice thickness and the number of slices will be described.

[0042] Note that the parameters of the automatic execution conditions are not limited to the slice thickness and the number of slices of the tomographic image. For example, as the parameters of the automatic execution conditions, FOV (Field of view), Spacing, processing for past images, ImageType (Primary image or Secondary image), Description, device information (manufacturer), patient information (gender, age), contrast information, exposure information, reconstruction information, etc. may be used.

[0043] In step S4, the image process determination processing unit 32 determines the image process to be executed on the CT image saved in step S1 according to the automatic execution conditions acquired in step S3 (process P4).

[0044] Here, as described above, the CT image saved in step S1 has a slice thickness of 1 mm and the number of slices is 1000. For example, when the automatic execution condition of "CAD(1)" is that the slice thickness is 0.5 mm or more and the number of slices is 100 or more, the CT image saved in step S1 satisfies the automatic execution condition of "CAD(1)". Therefore, the image processing determination processing unit 32 selects the image processing for executing "CAD(1)". Also, when the slice thickness of the automatic execution condition of "CAD(2)" is 5 mm or more and the number of slices is 1000 or more, the CT image saved in step S1 does not satisfy the automatic execution condition of "CAD(2)". Therefore, the image processing determination processing unit 32 does not select the image processing for executing "CAD(2)".

[0045] In step S5, the image processing determination processing unit 32 requests the cloud image processing unit 36 to execute the image processing determined in step S4 (process P5).

[0046] In step S6, the cloud image processing unit 36 acquires the CT image saved in the image management unit 30 in step S1, and executes the image processing requested in step S5 on the CT image. Also, the processing result management unit 38 acquires the execution result of the image processing from the cloud image processing unit 36 (process P6).

[0047] In step S7, the user terminal 20 acquires the execution result of the image processing from the processing result management unit 38, and causes the execution result to be displayed on the display 20B according to the user's operation (process P7).

[0048] In step S8, the processing result usage log management unit 40 saves, as a log, the usage information which is the information on the user's use of the execution result in step S7, and the accompanying information of the CT image for which the image processing has been executed (process P8). The usage information includes at least one of whether the user has referred to the result of the image processing, whether the result of the image processing has contributed to the prevention of overlooking diseases, the reduction amount of the reading time due to the result of the image processing, whether the measurement result of the image processing has contributed to the improvement of accuracy, and whether the user has instructed the execution of the image processing other than the automatic execution. The accompanying information includes at least one of the slice thickness and the number of slices of the CT image.

[0049] Here, the processing result usage log management unit 40 saves the log of the automatically executed image processing, but also saves the log of the image processing manually instructed by the user other than the automatic execution.

[0050] By repeating the processing of steps S1 to S8 by the medical image processing system 10, the processing result usage log management unit 40 accumulates the logs. In step S9 (an example of the "collection step"), the recommended execution condition / cost-benefit determination processing unit 42 acquires the accumulated logs (process P9).

[0051] In step S10, the recommended execution condition / cost-benefit determination processing unit 42 calculates the evaluation value of the image processing based on the accumulated logs, and determines the recommended conditions for the automatic execution conditions and their effects. Instead of using all the accumulated logs, the evaluation value may be calculated using the logs for the latest certain period (for example, for one week). The accumulation period of the logs used for the calculation may be settable for each hospital.

[0052] Furthermore, the recommended execution condition / cost-benefit determination processing unit 42 displays and proposes the determined recommended conditions and their effects on the display 20B (process P10).

[0053] The recommended conditions are displayed, for example, when the evaluation value of "CAD(1)" is low, as "We consider that 'CAD(1)' is not necessary." When the evaluation value is low when the slice thickness of "CAD(1)" is 1 to 3 mm, it may be displayed as "For CT images with a slice thickness of 1 to 3 mm, 'CAD(1)' is not necessary."

[0054] In step S11, the user checks the recommended conditions and their effects displayed on the display 20B of the user terminal 20, and sets the automatic execution conditions using the input device 20A. The user may set the displayed recommended conditions as the automatic execution conditions as they are, or may set the desired automatic execution conditions with reference to the displayed recommended conditions. Finally, the user terminal 20 causes the automatically executed condition management unit 34 to store the set automatic execution conditions (process P11). Thereafter, the image processing determination processing unit 32 acquires the newly set automatic execution conditions.

[0055] 〔Screen for recommended conditions / cost-benefit proposal〕 FIG. 4 is an example of a screen for recommending conditions / cost-benefit proposals displayed on the display 20B of the user terminal 20. Here, a pie chart shows the respective percentages of the costs of "CAD(1)", "CAD(2)", "Segmentation(1)", "Labeling(1)", and "Labeling(2)", which are image processes automatically executed in the cloud image processing unit 36, for a certain recent period, and the respective cost amounts are displayed in the pie chart.

[0056] Each area of the pie chart can be selected by the input device 20A. Here, it shows that "CAD(1)" surrounded by a thick frame is selected.

[0057] FIG. 5 is an example of a display screen of the automatic execution conditions of "CAD(1)" that is displayed when "CAD(1)" is selected in the pie chart of FIG. 4 displayed on the display 20B. In the present embodiment, the automatic execution conditions are the slice thickness and the number of slices, and the display of the automatic execution conditions includes a scroll bar 100 representing the automatic execution conditions of the slice thickness and a scroll bar 110 representing the automatic execution conditions of the number of slices. The pie chart of FIG. 4 and the slider bar of FIG. 5 may be simultaneously displayed on the same screen.

[0058] The scroll bar 100 indicates a range from 0.1 mm to 5 mm for the slice thickness. The triangular mark 102 displayed at the upper part of the scroll bar 100 indicates the lower limit value of the currently set automatic execution conditions. Therefore, the images on the right side of the position of the mark 102 (slice thickness greater than the value indicated by the mark 102) are the images that are the targets of automatic execution. Also, the star-shaped mark 104 indicates the lower limit value of the automatic execution conditions recommended by the recommended execution condition / cost-benefit determination unit 42, and the images on the right side of the position of the mark 104 are the images that are the targets of the recommended execution conditions.

[0059] For example, the currently set automatic execution conditions for the slice thickness are 0.5 mm or more, and the recommended automatic execution conditions are 2 mm or more. Note that the upper limit value of the slice thickness may be set as an automatic execution condition.

[0060] Also, the scroll bar 100 has a knob 106 that can move within the range of the scroll bar 100. The user can change the automatic execution conditions by dragging the knob 106 with the input device 20A to change the position of the knob 106. Here, the images on the right side of the position of the knob 106 become the images that are the targets of the automatic execution image processing.

[0061] For example, when the knob 106 is moved from the position of 0.5 mm to the position of 2 mm, the automatic execution condition of the slice thickness is changed from 0.5 mm or more to 2 mm or more. Due to this change in the automatic execution condition, subsequently, the tomographic images with a slice thickness of 0.5 mm to 2 mm will not be automatically executed, and it is expected that the cost will be reduced accordingly in the usage-based cloud service. The recommended execution condition / cost-benefit determination processing unit 42 recalculates the cost of the latest fixed period of "CAD(1)" when the automatic execution condition of the slice thickness of "CAD(1)" is changed from 0.5 mm or more to 2 mm or more, and reflects it in the pie chart shown in FIG. 4.

[0062] On the other hand, the scroll bar 110 indicates a range from 10 slices to 1000 slices. The triangular mark 112 displayed at the upper part of the scroll bar 110 indicates the lower limit value of the currently set automatic execution condition. Therefore, the images on the right side of the position of the mark 112 (the number of slices more than the value indicated by the mark 112) are the images that are the targets of automatic execution. Also, the star mark 114 indicates the lower limit value of the automatic execution condition recommended by the recommended execution condition / cost-benefit determination processing unit 42, and the images on the right side of the position of the mark 114 are the images that are the targets of the recommended execution condition.

[0063] For example, the currently set automatic execution condition for the number of slices is 100 or more, and the recommended automatic execution condition is 200 or more. Note that the upper limit value of the number of slices may be set as the automatic execution condition.

[0064] Also, the scroll bar 110 has a knob 116 that can move within the range of the scroll bar 110. The user can change the automatic execution condition by dragging the knob 116 with the input device 20A to change the position of the knob 116. Here, the images on the right side of the position of the knob 116 become the images that are the targets of the automatic execution image processing.

[0065] For example, when the knob 116 is moved from the 100-sheet position to the 200-sheet position, the automatic execution condition for the number of slices is changed from 100 sheets or more to 200 sheets or more. The recommended execution condition / cost-benefit determination processing unit 42 recalculates the cost for a certain period of the latest "CAD(1)" when the automatic execution condition for the number of slices of "CAD(1)" is changed from 100 sheets or more to 200 sheets or more, and reflects it in the pie chart shown in FIG. 4.

[0066] In this way, the user can check the cost-benefit when changing the automatic execution condition.

[0067] Here, the change in the automatic execution condition of "CAD(1)" has been described, but the automatic execution condition can be set for each image process. In the present embodiment, in addition to "CAD(1)", the automatic execution conditions of "CAD(2)", "Segmentation(1)", "Labeling(1)", and "Labeling(2)" can be set respectively.

[0068] On the screen shown in FIG. 4, the automatic execution condition management unit 34 may receive from the input device 20A the deletion of the image process to be automatically executed. Further, the automatic execution condition management unit 34 may receive from the input device 20A the addition of the image process to be automatically executed. For example, the user can use the input device 20A to add the processes of similar image search and similar case search to the image processes to be automatically executed.

[0069] 〔Calculation of evaluation value〕 The recommended execution condition / cost-benefit determination processing unit 42 may propose an automatic execution condition in consideration of external factors. The external factors include the seasonality of the disease targeted by the image process. The recommended execution condition / cost-benefit determination processing unit 42 calculates, for example, an evaluation value considering the external factors of the image process using the following formula.

[0070] Evaluation value a1 = (number of uses) ÷ (number of processes) Evaluation value a2 = (number of missed detections prevented) ÷ (number of processes) Evaluation value a3 = (seasonality evaluation of image process) × (seasonal coefficient) The final evaluation value a4 = a1 + a2 + a3 Here, the number of processes is the number of case shootings for which image processing was performed in the cloud image processing unit 36, the number of usages is the number of times the user confirmed the execution result on the user terminal 20 (the number displayed on the display 20B), and the number of missed detection preventions is the number of lesions that the user missed but were detected by image processing. The number of missed detection preventions is, for example, when the user makes a diagnosis without using the execution result of the image processing, and after the diagnosis, the execution result is displayed on the display 20B, and the number of lesions not included in the user's diagnosis among the displayed lesions is counted.

[0071] The seasonal evaluation of image processing is a value indicating the presence or absence of seasonality in the occurrence of the disease targeted by the image processing. The seasonal coefficient is a coefficient such that the season in which the occurrence of the disease targeted by the image processing is relatively high has a relatively large value. For example, in the case of a disease that occurs relatively frequently in winter, the seasonal coefficient of the image processing for that disease becomes relatively large in winter.

[0072] It is proposed that if the final evaluation value a4 is equal to or greater than a predetermined threshold, the image processing is maintained as automatic execution image processing, and if it is less than the threshold, the image processing is deleted from the automatic execution image processing. Note that if any one of the evaluation values a1, a2, and a3 is equal to or greater than the threshold, the image processing may be maintained as automatic execution image processing.

[0073] The evaluation value may use the calculation function of a medical economic index (QALY: Quality-adjusted life year).

[0074] 〔Evaluation items other than time reduction / missed detection prevention〕 The recommended execution condition / cost-benefit determination processing unit 42 may propose setting or deleting the automatic execution condition in consideration of other evaluation items such as improvement of measurement accuracy as usage information.

[0075] For example, "the doctor determines that the volume of the lesion is X1 [cm 3 without checking the result of the image processing, and the result of the volume measurement of the image processing executed by the cloud image processing unit 36 is X1 [cm3 X2 [cm] different from 3 shall be "]]

[0076] On the other hand, when the processing result usage log management unit 40 stores, as usage information, a log stating that "the doctor corrected the reading report after checking the result of the volume measurement of the image processing executed by the cloud image processing unit 36", the recommended execution condition / cost-benefit determination processing unit 42 determines that "the volume measurement of the image processing is superior to that doctor and contributed to the improvement of the measurement accuracy", and recommends the image processing for which the volume measurement was performed as the setting of the automatically executed image processing.

[0077] On the other hand, when the processing result usage log management unit 40 stores, as usage information, a log stating that "even after checking the result of the volume measurement of the image processing executed by the cloud image processing unit 36, the doctor did not correct the reading report", it is recommended to determine that "the doctor's volume measurement is superior to that image processing and did not contribute to the improvement of the accuracy", and delete the image processing for which the volume measurement was performed from the setting of the automatically executed image processing.

[0078] In this way, by recommending, as the automatically executed image processing, the image processing that contributed to the improvement of the measurement accuracy such as volume measurement, the measurement accuracy of reading can be improved. Not limited to the improvement of the measurement accuracy, the recommended execution condition / cost-benefit determination processing unit 42 can propose to set or delete as the automatic execution condition according to the contribution degree of each evaluation item related to the reading of medical images.

[0079] 〔Display with Association of Usage Information and Associated Information〕 The medical image processing system 10 may display, on the display 20B, the collected usage information and the associated information in association with each other (an example of the "presentation step").

[0080] FIG. 6 is an example of a summary result screen of the logs accumulated by the processing result usage log management unit 40 and displayed on the display 20B. In this example, the usage information for each piece of associated information regarding the logs of "CAD(1)" is shown as a frequency line graph, specifically showing the number of processes [unit: sheets], the number of uses [unit: sheets], and the number of missed prevention [unit: locations] for each slice thickness.

[0081] When the slice thickness is 0.1 to 1 mm (0.1 mm or more and less than 1 mm), the number of processes is 1000 sheets, while the number of uses is 0 sheets. Therefore, the number of missed prevention is also 0 locations (since the population is 0). When the slice thickness is 1 to 3 mm (1 mm or more and less than 3 mm), the number of processes is 2000 sheets, the number of uses is 1600 sheets, and the number of missed prevention is 2000 locations. When the slice thickness is 3 to 5 mm (3 mm or more and less than 5 mm), the number of processes is 1000 sheets, the number of uses is 0 sheets, and the number of missed prevention is 0 locations. When the slice thickness is 5 mm or more (5 mm or more), the number of processes is 2000 sheets, the number of uses is 1800 sheets, and the number of missed prevention is 1000 locations.

[0082] From this graph, when the slice thickness is 0.1 to 1 mm and 3 to 5 mm, since the results of the image processing are not used, there is no need for automatic execution and it is considered not appropriate as an automatic execution condition. On the other hand, when the slice thickness is 1 to 3 mm and 5 mm or more, it is useful for missed prevention, and it can be seen that it is appropriate as an automatic execution condition.

[0083] Here, the number of processes, the number of uses, and the number of missed prevention for each slice thickness are shown, but the same summary results of the logs may also be displayed for the number of slices.

[0084] By displaying such a summary result of the logs on the display 20B, the medical image processing system 10 enables the user to confirm the conditions suitable for the automatic execution conditions of the automatic execution image processing. It can also be used for the introduction cost of the cloud service and the selection of the plan to be contracted first for the cloud service.

[0085] In this example, the recommended execution condition / cost-benefit determination processing unit 42 may present not only the display of the log aggregation result, but also the recommended conditions for the automatic execution condition when the slice thickness is 1 to 3 mm and when it is 5 mm or more.

[0086] The following (1) to (11) are described in the above embodiment. (1) One aspect of a medical image processing apparatus includes at least one processor and at least one memory that stores instructions for causing the at least one processor to execute. The at least one processor performs a first image processing for assisting in the diagnosis of a medical image, and collects usage information by a user of the result of the first image processing that can be set as an automatic execution image processing automatically executed on the input medical image, and additional information of the medical image that is the target of the first image processing, and associates the usage information and the additional information and displays them on a display. That is, it includes at least one processor and at least one memory that stores instructions for causing the at least one processor to execute. The at least one processor is a first image processing for assisting in the diagnosis of a medical image, and is also a first image processing that can be set as an automatic execution image processing automatically executed on the input medical image, and collects usage information indicating the usage status of the result of the first image processing by the user, and additional information of the medical image that is the target of the first image processing, and associates the usage information and the additional information and displays them on a display. According to this aspect, since the usage status of the image processing that can be set as the automatic execution image processing can be presented, the user can determine whether to set the image processing as the automatic execution image processing from the presented usage status. (2) The usage information preferably includes at least one of whether the user has referred to the result of the first image processing, whether the result of the first image processing has contributed to the prevention of overlooking diseases, the reduction amount of the reading time due to the result of the first image processing, whether the measurement result of the first image processing has contributed to the improvement of accuracy, and whether the user has instructed the execution of the first image processing other than automatic execution. Thereby, it is possible to collect usage information reflecting the contribution degree of the image processing. (3) The object of the first image processing is a tomographic image, and the accompanying information preferably includes at least one of the slice thickness and the number of slices. Thereby, it is possible to collect at least one of the slice thickness and the number of slices of the tomographic image. (4) The at least one processor preferably accepts at least one of deleting the first image processing from the automatic execution image processing setting and setting the first image processing as the automatic execution image processing. Thereby, it is possible to delete the first image processing unnecessary as the automatic execution image processing and set the necessary first image processing. (5) The at least one processor preferably proposes an automatic execution condition for automatically executing the first image processing based on the usage information and the accompanying information. Thereby, the user can know appropriate automatic execution conditions. (6) The at least one processor preferably proposes an automatic execution condition in consideration of external factors. Thereby, it is possible to propose appropriate automatic execution conditions. (7) Further, the external factors preferably include the seasonality of the disease targeted by the first image processing. Thereby, it is possible to propose appropriate automatic execution conditions. (8) The at least one processor preferably executes the image processing set in the automatic execution image processing. Thereby, it is possible to automatically execute the set image processing. (9) One aspect of a medical image processing system includes a medical image processing apparatus (1) to (8) and a server that executes image processing set as automatic execution image processing. According to this aspect, since it is possible to present the usage status of image processing that can be set as automatic execution image processing to be automatically executed, the user can determine whether to set the image processing as automatic execution image processing based on the presented usage status, and can automatically execute the image processing set as automatic execution image processing. (10) One aspect of a medical image processing method is a first image processing for assisting in the diagnosis of medical images, which collects the usage information by the user of the result of the first image processing that can be set as automatic execution image processing automatically executed on the input medical image and the accompanying information of the medical image targeted by the first image processing, and associates the usage information and the accompanying information and displays them on a display. That is, one aspect of the medical image processing method is a first image processing for assisting in the diagnosis of medical images and is also a first image processing that can be set as automatic execution image processing automatically executed on the input medical image, which collects the usage information indicating the usage status of the result of the first image processing by the user and the accompanying information of the medical image targeted by the first image processing, and associates the usage information and the accompanying information and displays them on a display. According to this aspect, since it is possible to present the usage status of image processing that can be set as automatic execution image processing to be automatically executed, the user can determine whether to set the image processing as automatic execution image processing based on the presented usage status. (11) One aspect of a program for achieving the above object is a program for causing a computer to execute the above medical image processing method. A computer-readable non-transitory storage medium on which this program is recorded may also be included in this aspect. According to this aspect, since it is possible to present the usage status of image processing that can be set as automatic execution image processing to be automatically executed, the user can determine whether to set the image processing as automatic execution image processing based on the presented usage status.

[0087] 〔Others〕 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 among the embodiments without departing from the gist of the present invention.

Description of Reference Numerals

[0088] 10…Medical image processing system 12…Medical image examination device 14…Medical image database 16…Image processing evaluation device 16A…Processor 16B…Memory 20…User terminal 20A…Input device 20B…Display 22…In-hospital network 24…Internet 26…Cloud server 30…Image management unit 32…Image processing determination processing unit 34…Automatic execution condition management unit 36…Cloud image processing unit 38…Processing result management unit 40…Processing result usage log management unit 42…Cost-benefit determination processing unit 100…Scroll bar 102…Mark 104…Mark 106…Knob 110…Scroll bar 112…Mark 114…Mark 116…Knob P1~P11…Processes of medical image processing apparatus S1~S11…Steps of medical image processing method

Claims

1. At least one processor; At least one memory storing instructions for causing the at least one processor to execute; Comprising; The at least one processor is configured to: Obtain usage information by a user of a result of first image processing for assisting in diagnosis of a medical image, the first image processing being settable as automatic execution image processing automatically executed on the input medical image, and additional information of the medical image targeted by the first image processing; Associate the usage information and the additional information and display them on a display; A medical image processing apparatus.

2. The usage information includes at least one of whether the user has referred to the result of the first image processing, whether the result of the first image processing has contributed to preventing overlooking of a disease, the reduction amount of reading time due to the result of the first image processing, whether the measurement result of the first image processing has contributed to improvement of accuracy, and whether the user has instructed execution of the first image processing other than the automatic execution. The medical image processing apparatus according to claim 1.

3. The target of the first image processing is a tomographic image, The additional information includes at least one of a slice thickness and a number of slices. The medical image processing apparatus according to claim 1 or 2.

4. The at least one processor is configured to: Accept at least one of deleting the first image processing from the setting of the automatic execution image processing and setting the first image processing as the automatic execution image processing. The medical image processing apparatus according to any one of claims 1 to 3.

5. The at least one processor is configured to: Propose an automatic execution condition for the first image processing to be automatically executed based on the usage information and the additional information. The medical image processing apparatus according to any one of claims 1 to 4.

6. The at least one processor is configured to: Propose the automatic execution condition in consideration of external factors. The medical image processing apparatus according to claim 5.

7. The external factors include seasonality of a disease targeted by the first image processing. The medical image processing apparatus according to claim 6.

8. The at least one processor is configured to: Execute the image processing set for the automatic execution image processing. The medical image processing apparatus according to any one of claims 1 to 7.

9. The medical image processing apparatus according to any one of claims 1 to 8, and A server that executes the image processing set as the automatic execution image processing, A medical image processing system comprising the same.

10. A first image processing for assisting in the diagnosis of a medical image, the use information by the user of the result of the first image processing that can be set as the automatic execution image processing automatically executed on the input medical image, and the medical image targeted by the first image processing Obtaining the associated information, Associating the usage information and the associated information and displaying them on a display, A medical image processing method.

11. A program for causing a computer to execute the medical image processing method according to claim 10.

Images