Information processing device, information processing method, and information processing program

Abstract

Provided is an information processing device comprising at least one processor, wherein the processor acquires a plurality of images to which mutually independent pieces of attribute information are imparted, and restricts, on the basis of the attribute information, an image that can be displayed on a display, among the plurality of images.

Description

Technical Field

[0001] The present disclosure relates to an information processing apparatus, an information processing method, and an information processing program.

Background Art

[0002] Conventionally, image diagnosis using three-dimensional medical images taken by imaging devices such as CT (Computed Tomography) devices and MRI (Magnetic Resonance Imaging) devices has been performed. For example, Japanese Patent Application Laid-Open No. 2009-285147 discloses displaying a single tomographic image representing one tomographic plane included in a three-dimensional medical image on a screen, and being able to specify the tomographic image to be displayed on the screen by sliding a slide bar.

[0003] In addition, medical images are analyzed by CAD (Computer-Aided Detection / Diagnosis) using a discriminator learned by deep learning or the like to detect and / or diagnose a structure of interest such as a lesion included in the medical image. Further, as a technique for assisting in creating a radiology report, Japanese Patent Application Laid-Open No. 2019-153250 discloses generating a sentence for inclusion in a radiology report based on the analysis result of a medical image by CAD.

Summary of the Invention

Problems to be Solved by the Invention

[0004] In recent years, with the progress of imaging devices, the number of tomographic images included in three-dimensional medical images has increased. As a result, when specifying a tomographic image to be displayed on the screen by a slide bar as described in Japanese Patent Application Laid-Open No. 2009-285147, it has sometimes been difficult to specify the tomographic image of interest.

[0005] The present disclosure provides an information processing apparatus, an information processing method, and an information processing program that can easily specify a desired image.

Means for Solving the Problems

[0006] A first aspect of the present disclosure is an information processing apparatus comprising at least one processor, the processor acquires a plurality of images to which independent attribute information has been assigned, and limits the number of images from the plurality to be displayable on a display based on the attribute information.

[0007] A second aspect of this disclosure is that, in the first aspect described above, the processor may enable the display of only the images to which specified attribute information has been assigned from among a plurality of images.

[0008] A third aspect of this disclosure is that, in the first or second aspect described above, the plurality of images are a spatially or temporally consecutive group of images, and the processor may display only those images within a range determined based on specified attribute information from among the plurality of images.

[0009] A fourth aspect of this disclosure is that, in any one of the first to third aspects described above, the processor may display a slider bar on the display for accepting an operation to select an image to be displayed on the display from among a plurality of images, and may limit the operable range of the slider bar based on attribute information.

[0010] A fifth aspect of this disclosure is that in any one of the first to fourth aspects described above, each of the multiple images includes a region of interest, and the attribute information indicates the attributes of the region of interest.

[0011] A sixth aspect of this disclosure is that, in the fifth aspect described above, the region of interest may be the region of a structure included in the image.

[0012] A seventh aspect of this disclosure is that, in the fifth or sixth aspect described above, the region of interest may be a region of abnormal shading contained in the image.

[0013] An eighth aspect of this disclosure is that, in any one of the fifth through seventh aspects described above, the region of interest may be a user-specified region included in the image.

[0014] A ninth aspect of this disclosure is that, in any one of the fifth through eighth aspects described above, the attribute information may indicate the type of area of ​​interest.

[0015] A tenth aspect of this disclosure is one of the fifth through ninth aspects described above, in which the attribute information may represent feature quantities of the region of interest.

[0016] An eleventh aspect of this disclosure is an embodiment of any one of the fifth to tenth aspects described above, in which the processor may extract a region of interest for each of a plurality of images and generate attribute information based on the feature quantities of the extracted region of interest.

[0017] A twelfth aspect of this disclosure is that, in the eleventh aspect described above, the processor may add information indicating the extraction method used to extract the region of interest as attribute information to the source image from which the region of interest was extracted.

[0018] A thirteenth aspect of this disclosure is that, in any one of the first to twelfth aspects described above, the attribute information may indicate the purpose for which the image was taken.

[0019] A fourteenth aspect of this disclosure is that, in any one of the first to thirteenth aspects described above, the attribute information may be entered by the user.

[0020] A fifteenth aspect of this disclosure is an information processing method, which includes acquiring a plurality of images to which independent attribute information has been assigned, and restricting the images from the plurality of images to be displayable on a display based on the attribute information.

[0021] A 16th aspect of the present disclosure is an information processing program for causing a computer to execute a process of acquiring a plurality of images to which attribute information independent of each other is assigned and restricting images that can be displayed on a display among the plurality of images based on the attribute information.

Advantages of the Invention

[0022] According to the above aspect, the information processing apparatus, information processing method, and information processing program of the present disclosure can easily specify a desired image.

Brief Description of the Drawings

[0023] [Figure 1] It is a schematic configuration diagram of an information processing system. [Figure 2] It is a schematic diagram showing an example of a medical image. [Figure 3] It is a block diagram showing an example of the hardware configuration of an information processing apparatus. [Figure 4] It is a block diagram showing an example of the functional configuration of an information processing apparatus. [Figure 5] It is a diagram showing an example of a tomographic image. [Figure 6] It is a diagram showing an example of attribute information. [Figure 7] It is a diagram showing an example of a screen displayed on a display. [Figure 8] It is a diagram showing an example of a screen displayed on a display. [Figure 9] It is a diagram showing an example of a screen displayed on a display. [Figure 10] It is a flowchart showing an example of a first information process. [Figure 11] It is a diagram showing an example of a screen displayed on a display. [Figure 12] It is a flowchart showing an example of a second information process. [Figure 13] It is a diagram showing an example of a screen displayed on a display.

Modes for Carrying Out the Invention

[0024] Hereinafter, with reference to the drawings, examples of embodiments for carrying out the technology of this disclosure will be described in detail.

[0025] [First Exemplary Embodiment] First, with reference to Figure 1, an example of the configuration of the information processing system 1 according to this exemplary embodiment will be described. Figure 1 is a diagram showing the schematic configuration of the information processing system 1. As shown in Figure 1, the information processing system 1 includes a shooting device 2, an image server 4, an image DB (Database) 5, a report server 6, a report DB 7, and an information processing device 10. The shooting device 2, the image server 4, the report server 6, and the information processing device 10 are connected to each other via a wired or wireless network 8, enabling them to communicate with one another.

[0026] The imaging device 2 is a device that generates a medical image G representing the area to be diagnosed by imaging the area of ​​the subject to be diagnosed. Specifically, the imaging device 2 can be a CT scanner, an MRI scanner, or a PET (Positron Emission Tomography) scanner, etc., as appropriate. The imaging device 2 also transmits the captured medical image to the image server 4.

[0027] Figure 2 is a schematic diagram showing an example of medical image G. Medical image G is a CT image consisting of multiple tomographic images T000~Tm (where m is 001 or greater) representing cross-sectional planes from the head to the waist of a single subject (human body). Multiple tomographic images T000~Tm are an example of multiple images in this disclosure. Furthermore, multiple tomographic images T000~Tm (medical image G) are an example of a spatially continuous group of images. Hereinafter, when the multiple tomographic images T000~Tm are not distinguished, they will simply be referred to as "tomographic image T".

[0028] Image Server 4 is a general-purpose computer with a software program installed that provides the functionality of a Database Management System (DBMS). Image Server 4 is connected to Image DB 5. The connection method between Image Server 4 and Image DB 5 is not particularly limited; it may be connected via a data bus, or via a network such as NAS (Network Attached Storage) or SAN (Storage Area Network).

[0029] The image database (DB5) is implemented using storage media such as an HDD (Hard Disk Drive), SSD (Solid State Drive), and flash memory. The image database (DB5) records medical images G taken by the imaging device 2 and the information assigned to the medical images G in association with each other. The assigned information may include identification information such as an image ID (identification) to identify the medical image G, a tomographic ID to identify the tomographic image T, a subject ID to identify the subject, and an examination ID to identify the examination. The assigned information may also include various information related to the imaging, such as the date and time of imaging, the area being imaged, the type of imaging device 2 used to capture the medical image G, imaging conditions, and contrast conditions. Furthermore, the assigned information may include information about the subject, such as the subject's name, age, and gender.

[0030] When the image server 4 receives a medical image G from the imaging device 2, it formats the medical image G into a database format and records it in the image DB 5. Furthermore, when the image server 4 receives a request to view a medical image G from the information processing device 10, it searches the image DB 5 for the medical image G and sends the retrieved medical image G to the information processing device 10 that made the viewing request.

[0031] Report Server 6 is a general-purpose computer with software programs installed that provide the functionality of a database management system. Report Server 6 is connected to Report DB 7. The connection method between Report Server 6 and Report DB 7 is not particularly limited; it may be connected via a data bus, or via a network such as NAS or SAN.

[0032] The report DB7 is implemented using storage media such as an HDD, SSD, and flash memory. The report DB7 records the image interpretation reports generated by the information processing device 10 based on the medical images G. The image interpretation reports recorded in the report DB7 may be entered by the radiologist using the information processing device 10, or they may be generated by a computer based on the results of CAD analysis.

[0033] When the report server 6 receives a radiographic interpretation report from the information processing device 10, it formats the report into a database format and records it in the report DB 7. Furthermore, when the report server 6 receives a request to view a radiographic interpretation report from the information processing device 10, it searches the report DB 7 for the radiographic interpretation report and sends the retrieved report to the information processing device 10 that made the request.

[0034] Network 8 is, for example, a LAN (Local Area Network) and a WAN (Wide Area Network). The imaging device 2, image server 4, image DB 5, report server 6, report DB 7, and information processing device 10 included in the information processing system 1 may be located in the same medical institution or in different medical institutions. In addition, although Figure 1 shows one of each of the imaging device 2, image server 4, image DB 5, report server 6, report DB 7, and information processing device 10, the system is not limited to this, and each device may be composed of multiple devices having similar functions.

[0035] The information processing device 10 according to this exemplary embodiment has a function that assists in easily specifying a desired tomographic image T when interpreting and diagnosing images by restricting the display of only the tomographic image T of interest from among a plurality of tomographic images T captured by the imaging device 2. The detailed configuration of the information processing device 10 will be described below.

[0036] First, with reference to Figure 3, an example of the hardware configuration of the information processing device 10 according to this exemplary embodiment will be described. As shown in Figure 3, the information processing device 10 includes a CPU (Central Processing Unit) 21, a non-volatile storage unit 22, and a memory 23 as a temporary storage area. The information processing device 10 also includes a display 24 such as a liquid crystal display, an input unit 25 such as a keyboard, mouse, touch panel, and buttons, and a network interface 26. The network interface 26 is connected to a network 8 and performs wired or wireless communication. The CPU 21, storage unit 22, memory 23, display 24, input unit 25, and network interface 26 are connected to each other via a bus 28 such as a system bus and a control bus, enabling the exchange of various types of information.

[0037] The storage unit 22 is implemented by a storage medium such as an HDD, SSD, or flash memory. The information processing program 27 of the information processing device 10 is stored in the storage unit 22. The CPU 21 reads the information processing program 27 from the storage unit 22, expands it into memory 23, and executes the expanded information processing program 27. The CPU 21 is an example of the processor of this disclosure. The information processing device 10 can be appropriately applied to, for example, a personal computer, a server computer, a smartphone, a tablet terminal, or a wearable terminal.

[0038] Next, with reference to Figure 4, an example of the functional configuration of the information processing device 10 according to this exemplary embodiment will be described. As shown in Figure 4, the information processing device 10 includes an acquisition unit 30, an extraction unit 32, and a display control unit 34. The CPU 21 executes the information processing program 27, thereby enabling the CPU 21 to function as the acquisition unit 30, the extraction unit 32, and the display control unit 34.

[0039] The acquisition unit 30 acquires multiple tomographic images T from the image server 4. As described above, the tomographic images T are images representing cross-sectional views of the human body. Therefore, each tomographic image T includes regions of structures (hereinafter referred to as "structural regions SA") representing various organs of the human body (e.g., brain, lungs, and liver, etc.) and various tissues that constitute these organs (e.g., blood vessels, nerves, and muscles, etc.). In addition, each tomographic image T may include regions of abnormal shadows (hereinafter referred to as "abnormal regions AA") such as lesions (e.g., tumors, injuries, defects, nodules, and inflammation, etc.) and regions that have become unclear during imaging. Figure 5 shows a tomographic image T100 of the lung as an example of a tomographic image T. In tomographic image T100, the lung region is the structural region SA, and the nodule region is the abnormal region AA.

[0040] The extraction unit 32 extracts regions of interest from each of the multiple tomographic images T. A region of interest is an area of ​​interest in image interpretation and diagnosis, and is, for example, at least one of a structural region SA and an abnormality region AA. That is, each of the multiple tomographic images T contains a region of interest. A known AI (Artificial Intelligence) technique is used as the method for extracting regions of interest. Methods using techniques and methods using image processing can be applied as appropriate. For example, a trained model that takes a tomographic image T as input and is trained to extract and output a region of interest may be used to extract a region of interest from the tomographic image T. Alternatively, for example, by performing image processing such as binarization, background removal, and edge enhancement on the tomographic image T, the edges of the structural region SA and the anomaly region AA may be identified and extracted as regions of interest.

[0041] Furthermore, the extraction unit 32 generates attribute information indicating the attributes of the extracted region of interest and attaches it to the tomographic image T from which the region of interest was extracted. That is, each of the multiple tomographic images T is assigned attribute information that is independent of each other. Attribute information is, for example, information indicating the type of region of interest, specifically, information indicating the type of structure represented by the structural region SA included in the tomographic image T, and the type of lesion represented by the abnormal region AA included in the tomographic image T. As for the method of identifying the type of region of interest by the extraction unit 32, a known method of identification using CAD can be appropriately applied.

[0042] Figure 6 shows an example of attribute information generated by the extraction unit 32 and assigned to each of the multiple tomographic images T. The "Tomographic ID" column in Figure 6 shows the identification information of the tomographic images T, which are assigned sequentially from the head side to the lumbar side of the subject. The "Organ" column shows attribute information indicating the type of organ represented by the structural region SA extracted from the tomographic image T. The "Legacy 1" to "Legacy 3" columns show attribute information indicating the type of lesion represented by the abnormal region AA extracted from the tomographic image T. As shown in Figure 6, multiple pieces of attribute information may be assigned to a single tomographic image T, only one piece may be assigned, or none may be assigned.

[0043] The display control unit 34 controls the display 24 to display a screen for users, such as radiologists, to view tomographic images T. Figure 7 shows an example of screen D1 displayed on the display 24 by the display control unit 34. Screen D1 includes a slider bar 80 for accepting the operation of selecting a tomographic image T to be displayed on the display 24 from among multiple tomographic images T. The slider bar 80 is a GUI (Graphical User Interface) part, also called a slide bar or scroll bar. In the example of screen D1, it corresponds to multiple tomographic images T arranged sequentially from the head side to the waist side, from the top end to the bottom end. The display control unit 34 accepts the user's operation of the position of the slider 82 on the slider bar 80 via the input unit 25, and displays one tomographic image T (tomographic image T100 in the example of Figure 7) corresponding to the position of the slider 82 from among the multiple tomographic images T on screen D1. The dotted arrow attached to the slider 82 in Figure 7 indicates the range of motion of the slider 82 on the slider bar 80, and in the example of Figure 7, the entire slider bar 80 is the range of motion of the slider 82.

[0044] Furthermore, the display control unit 34 displays markers 94 of different shapes at corresponding positions on the slider bar 80 according to the attribute information assigned to each tomographic image T. Screen D1 in Figure 7 includes markers 94 of different shapes positioned next to the slider bar 80. The markers 94 are used to indicate the position on the slider bar 80 of the tomographic image T from which the abnormal region AA has been extracted (i.e., the tomographic image T containing the lesion) among the multiple tomographic images T. The shape of the marker 94 is determined according to the attribute information indicating the type of lesion assigned to the tomographic image T (see Figure 8). For example, the markers 94 may be color-coded according to the attribute information indicating the type of lesion.

[0045] However, in actual image interpretation and diagnosis settings, the structure and / or lesion to be interpreted and diagnosed is predetermined, and it is sometimes sufficient to display only the tomographic image T containing that structure and / or lesion on the display 24. Therefore, there is a need for a technology that can easily select the tomographic image T to be displayed on the display 24, that is, the tomographic image T containing the structure and / or lesion to be interpreted and diagnosed.

[0046] Therefore, the display control unit 34 limits the tomographic images T that can be displayed on the display 24 from among the multiple tomographic images T, based on the attribute information generated by the extraction unit 32. Specifically, the display control unit 34 controls the display so that only the tomographic images T to which the specified attribute information is attached can be displayed from among the multiple tomographic images T.

[0047] A specific example of processing by the display control unit 34 will be described with reference to Figures 7 to 9. In this exemplary embodiment, a form will be described in which the tomographic image T that can be displayed on the display 24 is limited from among the multiple tomographic images T by limiting the operable range of the slider bar 80 based on attribute information. Here, the "operable range of the slider bar 80" only needs to include the portion on the slider bar 80 corresponding to at least one tomographic image T, and is not limited to one range and portion, but may include multiple discontinuous ranges and portions.

[0048] Firstly, the display control unit 34 may determine the tomographic image T that can be displayed on the display 24 according to attribute information (see Figure 6) indicating the type of organ included in the tomographic image T. The screen D1 in Figure 7 includes an organ specification field 90 for accepting the specification of the type of organ. The display control unit 34 displays various organs (for example, brain, lungs, liver, gallbladder, pancreas, and kidneys, etc.) as selectable icons in the organ specification field 90 and accepts the user's specification of at least one type of organ.

[0049] When a user selects at least one icon in the organ selection field 90 via the input unit 25, the display control unit 34 restricts the operable range of the slider bar 80 so that only tomographic images T with attribute information indicating the organ represented by the selected icon can be selected. Figure 8 shows an example of screen D2 displayed on the display 24 by the display control unit 34 when the icon for "lung" is selected in the organ selection field 90 of screen D1. In screen D2, the range of motion of the slider bar 80 (indicated by a dotted arrow) is restricted so that only tomographic images T with attribute information indicating "lung" (see Figure 6) can be selected. As shown in screen D2, the display control unit 34 may highlight the range of motion of the slider 82 (i.e., the operable range of the slider bar 80) by changing the background color or the like.

[0050] Secondly, the display control unit 34 may determine the tomographic images T that can be displayed on the display 24 according to attribute information (see Figure 6) indicating the type of lesion included in the tomographic images T. Screen D2 in Figure 8 includes a lesion specification field 92 for receiving the specification of the type of lesion related to "lung" specified in the organ specification field 90. The display control unit 34 displays various lesions (e.g., nodules, calcifications, spicules, and ground-glass opacities, etc.) as selectable checkboxes in the lesion specification field 92 and accepts the user's specification of at least one type of lesion. The lesion specification field 92 in Figure 8 also includes a marker 94 corresponding to each lesion and the number of tomographic images T to which attribute information indicating each lesion is attached.

[0051] When the user selects at least one lesion in the lesion selection field 92 via the input unit 25, the display control unit 34 restricts the operable range of the slider bar 80 so that only tomographic images T with attribute information indicating the selected lesion can be selected. Figure 9 shows an example of screen D3 displayed on the display 24 by the display control unit 34 when "nodule" is selected in the lesion selection field 92 of screen D2. In screen D3, the range of motion of the slider bar 80 (shown by a dotted line) is restricted so that only tomographic images T with attribute information indicating "nodule" (see Figure 6) can be selected.

[0052] Furthermore, the display control unit 34 may control the display of markers 94 on the slider bar 80 at the corresponding positions for tomographic images T to which specified attribute information has been assigned. In other words, the display control unit 34 may control the display to show only markers 94 corresponding to specified attribute information. In the example of screen D3 in Figure 9, markers 94 are displayed on the slider bar 80 at the corresponding positions for tomographic images T to which attribute information indicating a specified "node" has been assigned.

[0053] Next, the operation of the information processing device 10 according to this exemplary embodiment will be described with reference to Figure 10. In the information processing device 10, the CPU 21 executes the information processing program 27, thereby executing the first information processing shown in Figure 10. The first information processing is executed, for example, when the user gives an instruction to start execution via the input unit 25.

[0054] In step S10, the acquisition unit 30 acquires multiple images (tomographic images T) from the image server 4. In step S12, the extraction unit 32 extracts regions of interest from each of the multiple images acquired in step S10. In step S14, the extraction unit 32 generates attribute information indicating the attributes of the regions of interest extracted in step S12 and attaches it to the source image from which the regions of interest were extracted. In step S16, the display control unit 34 displays a screen on the display 24 that restricts the images that can be displayed on the display 24 based on the attribute information attached in step S14, and terminates this first information processing.

[0055] As described above, the information processing device 10 according to one aspect of the present disclosure comprises at least one processor, which acquires a plurality of images to which independent attribute information is assigned, and restricts the images that can be displayed on the display from among the plurality of images based on the attribute information. In other words, according to the information processing device 10 according to this exemplary embodiment, it is possible to restrict the display of only the tomographic image T of interest from among a plurality of tomographic images T, so that the desired tomographic image T can be easily specified when interpreting and diagnosing images.

[0056] In the first exemplary embodiment described above, the display control unit 34 controls the display to show only the tomographic images T to which the specified attribute information has been assigned. However, the system is not limited to this. The display control unit 34 may also control the display to show only the tomographic images T within a range determined based on the specified attribute information. For example, the display control unit 34 may restrict the operable range of the slider bar 80 so that all tomographic images T included in the range from the first (i.e., the headmost) tomographic image T to which the specified attribute information has been assigned to the last (i.e., the lumbarmost) tomographic image T to which the specified attribute information has been assigned can be selected. In this case, the displayable tomographic images T may include tomographic images T to which the specified attribute information has not been assigned. With this configuration, even if there are omissions in the assignment of attribute information, the tomographic images T to which the desired attribute information has a relatively high probability of being assigned can be selected as the display target.

[0057] Furthermore, the display control unit 34 may perform control to enable the display of tomographic images T to which other attribute information has been pre-associated with the specified attribute information. For example, if attribute information indicating "nodule" is specified, the display control unit 34 may perform control to enable the display of tomographic images T to which attribute information indicating "lung" has been added. Alternatively, for example, if attribute information indicating "lung" is specified, the display control unit 34 may perform control to enable the display of only tomographic images T to which attribute information indicating any lesion has been added from among the tomographic images T to which attribute information indicating "lung" has been added.

[0058] Furthermore, in the first exemplary embodiment described above, the display control unit 34 limits the tomographic images T that can be displayed on the display 24 from among the multiple tomographic images T, by limiting the operable range of the slider bar 80, but the system is not limited to this. For example, when the display control unit 34 displays the tomographic IDs of all tomographic images T in a list format on the display 24, it may perform control to display only the tomographic IDs of tomographic images T to which specified attribute information has been assigned.

[0059] [Second exemplary embodiment] The information processing device 10 according to this second exemplary embodiment has a function to assist in easily specifying a desired tomographic image T when interpreting and diagnosing images by changing the shape of the slider bar 80 to make it easier to select a tomographic image T of interest from among a plurality of tomographic images T. The configuration of the information processing system 1 according to this exemplary embodiment is the same as that of the first exemplary embodiment, so a description is omitted. Furthermore, the hardware configuration of the information processing device 10 according to this exemplary embodiment, as well as the functions of the acquisition unit 30 and the extraction unit 32, are the same as those of the first exemplary embodiment, so a description is omitted.

[0060] The display control unit 34 changes the display format of the slider bar 80, which accepts an operation to select a tomographic image T to be displayed on the display 24 from a group of tomographic images T acquired by the acquisition unit 30, based on the attribute information assigned to each tomographic image T, and displays it on the display 24. Specifically, the display control unit 34 enlarges the portion of the slider bar 80 corresponding to the range of tomographic images T determined based on the specified attribute information from the group of tomographic images T, and displays it on the display 24.

[0061] A specific example of processing by the display control unit 34 will be explained with reference to Figure 11. Figure 11 shows an example of screen D4 displayed on the display 24 by the display control unit 34. Screen D4 is a screen displayed on the display 24 by the display control unit 34 when attribute information indicating "lung" is specified, similar to screen D2 (see Figure 8) described in the first exemplary embodiment above. Screen D4 includes a tomographic image T100, an organ specification field 90, a lesion specification field 92, and a marker 94, similar to screen D2.

[0062] The slider bar 80E on screen D4 is an enlarged version of portion 84 (see Figure 8) of the slider bar 80 on screen D2. Portion 84 is the part of the slider bar 80 that corresponds to the tomographic image T to which attribute information indicating "lung" has been added. The slider bar 80E corresponds to multiple tomographic images T from the first (i.e., the one closest to the head) tomographic image T to which attribute information indicating "lung" has been added, from top to bottom, to the last (i.e., the one closest to the waist) tomographic image T to which attribute information indicating "lung" has been added. With the enlarged slider bar 80E, the entire length from the top to the bottom of the slider bar 80E can be effectively utilized to accept the selection of tomographic images T.

[0063] Furthermore, the display control unit 34 also changes the position of the marker 94 in accordance with the enlargement of portion 84 of the slider bar 80. As shown in screen D2, when attribute information is attached to many tomographic images T, the markers 94 may become crowded together, reducing their visibility. On the other hand, as shown in screen D4, the visibility of the marker 94 can be improved by changing the position of the marker 94 in accordance with the enlargement of portion 84 of the slider bar 80 by the display control unit 34.

[0064] Next, the operation of the information processing device 10 according to this exemplary embodiment will be described with reference to Figure 12. In the information processing device 10, the CPU 21 executes the information processing program 27, thereby executing the second information processing shown in Figure 12. The second information processing is executed, for example, when the user gives an instruction to start execution via the input unit 25.

[0065] In step S20, the acquisition unit 30 acquires a group of images (tomographic images T) from the image server 4. In step S22, the extraction unit 32 extracts regions of interest from each of the group of images acquired in step S20. In step S24, the extraction unit 32 generates attribute information indicating the attributes of the regions of interest extracted in step S22 and adds it to the source image from which the regions of interest were extracted. In step S26, the display control unit 34 displays a screen on the display 24 with the display mode of the slider bar 80 changed based on the attribute information added in step S24, and terminates this second information processing.

[0066] As described above, the information processing device 10 according to one aspect of the present disclosure includes at least one processor, which acquires a spatially or temporally continuous group of images to which each image has independent attribute information, and changes the display form of a slider bar for which an operation to select an image to be displayed on the display from the group of images, based on the attribute information assigned to each image, and displays it on the display. In other words, according to the information processing device 10 of this exemplary embodiment, the display form of the slider bar 80 is changed to make it easier to select a noteworthy tomographic image T from among a plurality of tomographic images T, so that the desired tomographic image T can be easily specified when interpreting and diagnosing. In addition, the position of the marker 94 is also changed in accordance with the change in the display form of the slider bar 80, so that the visibility of the marker 94 can be improved and the desired tomographic image T can be specified more easily.

[0067] In the second exemplary embodiment described above, unlike the first exemplary embodiment, the display control unit 34 does not need to limit the tomographic images T that can be displayed on the display 24. Figure 13 shows an example of screen D5 as a modified version of screen D4 in Figure 11. In screen D5, arrows 86 are added to the upper and lower ends of the slider bar 80E of screen D4. By operating the arrow 86 at the upper end, the zoom range of the slider bar 80E can be moved to correspond to tomographic images T closer to the head. Similarly, by operating the arrow 86 at the lower end, the zoom range of the slider bar 80E can be moved to correspond to tomographic images T closer to the waist.

[0068] In the above exemplary embodiments, the extraction unit 32 has been described in a manner in which it extracts a region of interest, but the system is not limited to this. The region of interest may be a region specified by the user that is included in the tomographic image T. For example, the display control unit 34 may display the tomographic image T on the display 24 and receive a specification of coordinates on the tomographic image T from the user via the input unit 25 to determine the region of interest in the tomographic image T.

[0069] Furthermore, in each of the above exemplary embodiments, the extraction unit 32 may extract various regions of interest by combining multiple methods for extracting regions of interest. For example, the extraction unit 32 may use a combination of pre-trained models for each organ, which are pre-trained to extract regions of structures as structural regions SA and various lesions as abnormal regions AA. Alternatively, the extraction unit 32 may use a combination of multiple image processing filters suitable for each abnormal shadow. In these cases, the extraction unit 32 can extract various regions of interest from each of the multiple tomographic images T by applying the above-mentioned various extraction methods to each of the multiple tomographic images T.

[0070] Furthermore, while the above exemplary embodiments describe examples in which information indicating the type of region of interest extracted by the extraction unit 32 is used as attribute information, the system is not limited to this. The display control unit 34 can restrict which tomographic images T can be displayed on the display 24 from among the multiple tomographic images T, or change the display format of the slider bar 80, based on other attribute information. Other examples of attribute information will be described below.

[0071] Firstly, as described above, if the extraction unit 32 applies multiple different extraction methods in extracting the region of interest, the extraction unit 32 may add information indicating the extraction method used to extract the region of interest as attribute information to the source tomographic image T from which the region of interest was extracted. For example, if multiple different trained models are used in combination for each organ, attribute information indicating the trained model for the brain may be added to the tomographic image T in which the brain region is extracted as a structural region SA by the trained model for the brain, and attribute information indicating the trained model for the lungs may be added to the tomographic image T in which the lung region is extracted as a structural region SA by the trained model for the lungs.

[0072] Secondly, the extraction unit 32 may generate attribute information based on the extracted feature quantities of the region of interest. As described above, abnormal region AA is a region containing abnormal shadows such as lesions and areas that have become unclear in imaging. Specifically, abnormal shadows are identified when pixel values ​​differ from normal values ​​or when the edge shape is abnormal. Therefore, for example, the extraction unit 32 may generate attribute information that indicates the characteristics of abnormal shadows, such as "high density," "low density," and "unevenness."

[0073] Thirdly, attribute information may also be information indicating the purpose for which the tomographic image T was taken. The purpose for which the tomographic image T was taken may be, for example, detailed examination, regular check-up, and follow-up. Information indicating the purpose for which the tomographic image T was taken may be obtained by the acquisition unit 30 from a management server that manages examination orders and electronic medical records, etc.

[0074] Fourth, attribute information may be information entered by the user via the input unit 25. The information entered by the user may be the various types of attribute information described above, or it may be information different from the various types of attribute information described above, such as user-specific comments.

[0075] Furthermore, in the above exemplary embodiments, an example was described in which the extraction unit 32 assigns attribute information to multiple tomographic images T during the process of displaying the tomographic images T on the display 24, but the system is not limited to this. For example, attribute information may be assigned to each of the multiple tomographic images T in advance, and the multiple tomographic images T with assigned attribute information may be recorded in the image DB 5. In this case, in the process of displaying the tomographic images T on the display 24, the acquisition unit 30 can acquire multiple tomographic images T with assigned attribute information in advance, so the attribute information assignment process by the extraction unit 32 can be omitted.

[0076] Furthermore, although the above exemplary embodiments describe different forms of the marker 94 depending on the attribute information, the invention is not limited to these. For example, the display control unit 34 may control the tomographic image T to display one form of marker 94 at the corresponding position on the slider bar 80 for any tomographic image T to which attribute information indicating some kind of lesion has been assigned, regardless of the type of lesion.

[0077] Furthermore, although the above exemplary embodiments describe a configuration in which the screen displayed on the display includes a marker 94, the marker 94 is optional. Even when the marker 94 is omitted, the information processing device 10 according to the first exemplary embodiment restricts the display to only the tomographic image T of interest among the multiple tomographic images T, thus providing the effect of easily specifying the desired tomographic image T. Similarly, even when the marker 94 is omitted, the information processing device 10 according to the second exemplary embodiment changes the display form of the slider bar 80 according to the attribute information, thus providing the effect of easily specifying the desired tomographic image T.

[0078] Furthermore, while the above exemplary embodiments describe examples targeting multiple tomographic images T (medical images G), the technology of this disclosure can also target other types of images. For example, it may target a series of images that are continuous in time, such as video footage captured by a digital camera, surveillance camera, or dashcam. Even when targeting such video footage, the extraction unit 32 can extract regions of interest, such as people, animals, and structures like automobiles, and generate and assign attribute information.

[0079] Furthermore, in each of the above exemplary embodiments, the hardware structure of the processing unit that performs various processes, such as the acquisition unit 30, the extraction unit 32, and the display control unit 34, can be the following types of processors. As mentioned above, these types of processors include a CPU, which is a general-purpose processor that executes software (programs) and functions as various processing units, as well as programmable logic devices (PLDs), such as FPGAs (Field Programmable Gate Arrays), which are processors whose circuit configuration can be changed after manufacturing, and dedicated electrical circuits, such as ASICs (Application Specific Integrated Circuits), which are processors with circuit configurations specifically designed to perform specific processes.

[0080] A single processing unit may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, multiple processing units may be composed of a single processor.

[0081] Examples of configuring multiple processing units with a single processor include, firstly, a configuration where one or more CPUs and software combine to form a single processor, which then functions as multiple processing units, as exemplified by client and server computers. Secondly, a configuration using a processor that realizes the functions of the entire system, including multiple processing units, on a single IC (Integrated Circuit) chip, as exemplified by System on Chip (SoC). Thus, various processing units are configured, in terms of hardware structure, using one or more of the above-mentioned processors.

[0082] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits, which are combinations of circuit elements such as semiconductor devices.

[0083] Furthermore, while the above exemplary embodiments describe a configuration in which the information processing program 27 is pre-stored (installed) in the storage unit 22, the invention is not limited thereto. The information processing program 27 may be provided in the form of a recording medium such as a CD-ROM (Compact Disc Read Only Memory), DVD-ROM (Digital Versatile Disc Read Only Memory), or USB (Universal Serial Bus) memory. Alternatively, the information processing program 27 may be provided in the form of a download from an external device via a network. Moreover, the technology of this disclosure extends not only to the information processing program but also to storage media for non-temporarily storing the information processing program.

[0084] The technology of this disclosure can also be appropriately combined with the exemplary embodiments described above. The descriptions and illustrations shown above are detailed explanations of the parts relating to the technology of this disclosure and are merely examples of the technology of this disclosure. For example, the above descriptions of the configuration, function, operation, and effect are examples of the configuration, function, operation, and effect of the parts relating to the technology of this disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements added, or replaced from the descriptions and illustrations shown above, as long as they do not deviate from the spirit of the technology of this disclosure.

[0085] The disclosure of Japanese Patent Application No. 2021-157274, filed on 27 September 2021, is incorporated herein by reference in its entirety. All documents, patent applications, and technical standards described herein are incorporated herein by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

Claims

1. Equipped with at least one processor, The aforementioned processor, Obtain multiple images, each assigned independent attribute information, A user interface for selecting an image to be displayed on the display from among the aforementioned multiple images is displayed on the display. By restricting the images that can be selected in the user interface based on the attribute information, the images that can be displayed on the display are limited from among the plurality of images. From the plurality of images, the image selected using the user interface is displayed on the display. The attribute information includes at least one of the following: information indicating the attributes of the region of interest contained in each of the plurality of images, and information indicating the purpose for which the images were taken. Information processing device.

2. The aforementioned processor, Of the aforementioned multiple images, only the image to which the specified attribute information is assigned will be displayed. The information processing apparatus according to claim 1.

3. The aforementioned plurality of images are a group of images that are spatially or temporally consecutive, The aforementioned processor, Of the aforementioned multiple images, only those images within a range determined based on the specified attribute information can be displayed. The information processing apparatus according to claim 1 or claim 2.

4. The aforementioned processor, A slider bar is displayed on the display to accept the operation of selecting an image from the plurality of images to be displayed on the display. Based on the attribute information, the operable range of the slider bar is limited. The information processing apparatus according to claim 1 or claim 2.

5. Each of the aforementioned images contains a region of interest, The attribute information indicates the attributes of the region of interest. The information processing apparatus according to claim 1 or claim 2.

6. The region of interest is the region of the structure included in the image. The information processing apparatus according to claim 5.

7. The region of interest is the region of abnormal shadows contained in the image. The information processing apparatus according to claim 5.

8. The region of interest is a region included in the image that is specified by the user. The information processing apparatus according to claim 5.

9. The attribute information indicates the type of the area of ​​interest. The information processing apparatus according to claim 5.

10. The attribute information indicates the feature quantities of the region of interest. The information processing apparatus according to claim 5.

11. The aforementioned processor, For each of the aforementioned multiple images, the region of interest is extracted. Based on the extracted features of the region of interest, the attribute information is generated. The information processing apparatus according to claim 5.

12. The aforementioned processor, Information indicating the extraction method used to extract the region of interest is added to the source image of the region of interest as attribute information. The information processing apparatus according to claim 11.

13. The attribute information indicates the purpose for which the image was taken. The information processing apparatus according to claim 1 or claim 2.

14. The aforementioned attribute information is entered by the user. The information processing apparatus according to claim 1 or claim 2.

15. Obtain multiple images, each assigned independent attribute information, A user interface for selecting an image to be displayed on the display from among the aforementioned multiple images is displayed on the display. By restricting the images that can be selected in the user interface based on the attribute information, the images that can be displayed on the display are limited from among the plurality of images. From the plurality of images, the image selected using the user interface is displayed on the display. The attribute information includes at least one of the following: information indicating the attributes of the region of interest contained in each of the plurality of images, and information indicating the purpose for which the images were taken. An information processing method in which a computer performs the processing.

16. Obtain multiple images, each assigned independent attribute information, A user interface for selecting an image to be displayed on the display from among the aforementioned multiple images is displayed on the display. By restricting the images that can be selected in the user interface based on the attribute information, the images that can be displayed on the display are limited from among the plurality of images. From the plurality of images, the image selected using the user interface is displayed on the display. The attribute information includes at least one of the following: information indicating the attributes of the region of interest contained in each of the plurality of images, and information indicating the purpose for which the images were taken. An information processing program that causes a computer to perform a task.

Images