Medical image display device, method, and program

Abstract

The medical image display device, method, and program according to the present invention enable reduction in burden on a physician when interpreting a medical image. The medical image display device is provided with at least one processor. The processor acquires a detection result for at least one region of interest included in a medical image and detected by analyzing said medical image, identifies, in the medical image, at least one attention region that has drawn a user's attention, and causes the detection result for the region of interest and the identification result for the attention region to be displayed distinctively from each other on a display.

Description

[Technical Field]

[0001] The present disclosure relates to a medical image display device, a method, and a program. [Background technology]

[0002] In recent years, advances in medical equipment such as CT (Computed Tomography) and MRI (Magnetic Resonance Imaging) have made it possible to perform diagnostic imaging using higher quality, higher resolution medical images. In particular, diagnostic imaging using CT and MRI images allows for accurate identification of lesion areas, leading to the provision of appropriate treatment based on the results of such identification.

[0003] Medical images are also analyzed using computer-aided diagnosis (CAD) software, which uses a learning model based on machine learning techniques such as deep learning, to detect disease regions, such as lesions, contained in the medical image as regions of interest. The analysis results generated by the CAD analysis process are associated with examination information, such as the patient's name, gender, age, and the modality used to acquire the medical image, and are stored in a database for use in diagnosis. Doctors interpret the medical images using their own image-reading terminals, referring to the delivered medical images and analysis results. Based on the analysis results, annotations are then added to the region of interest, including the disease, contained in the medical image. For example, annotations include a region surrounding the region of interest, an arrow indicating the region of interest, the type and size of the disease, and so on. The radiologist then creates an interpretation report by referring to the annotations added to the region of interest.

[0004] Meanwhile, the results of medical image analysis using the CAD described above are often used as a secondary interpretation (second reading) in clinical settings. For example, when interpreting an image, a doctor first interprets the medical image without referring to the CAD analysis results. Then, a medical image annotated based on the CAD analysis results is displayed, and the doctor performs a secondary interpretation of the medical image while referring to the annotations. By performing such primary and secondary interpretations, it is possible to prevent disease areas from being overlooked.

[0005] Furthermore, methods for efficiently performing primary and secondary image interpretation have been proposed. For example, Patent Document 1 proposes a method for displaying CAD analysis results and doctor interpretation results in an overlapping or parallel display. Patent Document 1 also proposes a method for extracting features from a medical image that has not been checked by a doctor but has been checked by CAD and, when the doctor re-reads the image and determines that the image is abnormal, and storing the extracted features in a database. [Prior art documents] [Patent documents]

[0006] [Patent Document 1] Japanese Patent Application Laid-Open No. 2006-115921 Summary of the Invention [Problem to be solved by the invention]

[0007] However, in the method described in Patent Document 1, the analysis results by CAD and the interpretation results by a doctor are superimposed or displayed side by side. This makes it difficult to determine where in the medical image an abnormality detected by CAD but not detected by the doctor's interpretation, or an abnormality detected by the doctor's interpretation but not detected by CAD, is located. This places a heavy burden on doctors when interpreting medical images.

[0008] The present disclosure has been made in consideration of the above circumstances, and aims to reduce the burden on doctors when interpreting medical images. [Means for solving the problem]

[0009] A medical image display device according to the present disclosure includes at least one processor, The processor obtains a detection result of at least one region of interest included in the medical image, the region of interest being detected by analyzing the medical image; Identifying at least one region of interest in the medical image that is of interest to a user; The results of detecting the region of interest and the results of identifying the region of interest are displayed separately on the display.

[0010] In the medical image display device according to the present disclosure, the processor collates the detection result of the region of interest with the identification result of the region of interest, thereby identifying a non-interest region of interest other than the region of interest among the regions of interest included in the detection result,

[0011] It may also be possible to highlight non-attention regions of interest.

[0012] In addition, in the medical image display device according to the present disclosure, the processor collates the detection result of the region of interest with the identification result of the region of interest to identify a region of interest other than the region of interest included in the detection result, The region of interest may be highlighted.

[0013] In addition, in the medical image display device according to the present disclosure, when the medical image is a three-dimensional image made up of a plurality of tomographic images, the processor displays a paging slider that schematically indicates the positions of the tomographic planes of the plurality of tomographic images, By comparing the detection result of the region of interest with the identification result of the region of interest, a tomographic image including a non-interest region other than the region of interest is identified from the region of interest included in the detection result; The position of the identified tomographic plane of the tomographic image may be highlighted on the paging slider.

[0014] In addition, in the medical image display device according to the present disclosure, the processor may distinguish and highlight the positions of the cross-sectional planes of a tomographic image in which all of the regions of interest included are non-regions of interest and the positions of the cross-sectional planes of a tomographic image in which some of the regions of interest included are non-regions of interest.

[0015] In addition, in the medical image display device according to the present disclosure, the processor may analyze the medical image to obtain a detection result of at least one region of interest included in the medical image.

[0016] In addition, in the medical image display device according to the present disclosure, the processor may specify the region of interest based on a user operation when interpreting a medical image.

[0017] The medical image display method according to the present disclosure includes: acquiring a detection result of at least one region of interest included in the medical image, the region of interest being detected by analyzing the medical image; Identifying at least one region of interest in the medical image that is of interest to a user; The results of detecting the region of interest and the results of identifying the region of interest are displayed separately on the display.

[0018] The medical image display method according to the present disclosure may be provided as a program for causing a computer to execute the method. [Effects of the Invention]

[0019] According to the present disclosure, the burden on doctors when interpreting medical images can be reduced. [Brief explanation of the drawings]

[0020] [Figure 1] FIG. 1 is a diagram showing a schematic configuration of a medical information system to which a medical image display device according to a first embodiment of the present disclosure is applied. [Figure 2] FIG. 1 is a diagram showing a schematic configuration of a medical image display device according to a first embodiment; [Figure 3]Functional configuration diagram of a medical image display device according to a first embodiment [Figure 4] A diagram showing the results of detection of a region of interest by the analysis unit. [Figure 5] A diagram showing the display screen of the target medical image. [Figure 6] A diagram showing the results of a radiologist identifying a region of interest in a tomographic image. [Figure 7] FIG. 10 is a diagram showing a display screen of a detection result of a region of interest and a specified result of a region of interest of interest in the first embodiment. [Figure 8] 1 is a flowchart showing a process performed during primary interpretation in the first embodiment; [Figure 9] 1 is a flowchart showing the processing performed during secondary interpretation in the first embodiment; [Figure 10] FIG. 10 is a diagram showing a display screen of a detection result of a region of interest and a specified result of a region of interest of interest in the second embodiment. [Figure 11] FIG. 10 is a diagram showing a display screen of a detection result of a region of interest and a specified result of a region of interest of interest in the second embodiment. [Figure 12] A diagram showing a display screen highlighting an area of ​​interest that was identified by the radiologist but not detected by the analysis unit. [Figure 13] FIG. 10 is a diagram showing a display screen on which a mark indicating a region of interest is further added. [Figure 14] A diagram showing the positional relationship between a region of interest and a region of interest. [Figure 15] A diagram showing the positional relationship between a region of interest and a region of interest. [Figure 16] A diagram showing the positional relationship between a region of interest and a region of interest. DETAILED DESCRIPTION OF THE INVENTION

[0021] Hereinafter, embodiments of the present disclosure will be described with reference to the drawings. First, the configuration of a medical information system 1 to which a medical image display device according to this embodiment is applied will be described. FIG. 1 is a diagram showing a schematic configuration of the medical information system 1. The medical information system 1 shown in FIG. 1 is a system for capturing an examination target region of a subject, storing the medical images acquired by capturing the images, having a radiologist interpret the medical images and create an interpretation report, and allowing the requesting doctor from the medical department to view the interpretation report and observe the details of the medical image to be interpreted, based on an examination order from a doctor from a medical department using a known ordering system.

[0022] As shown in Figure 1, the medical information system 1 is composed of multiple imaging devices 2, multiple interpretation WSs (Workstations) 3 which are interpretation terminals, a medical treatment WS 4, an image server 5, an image database (hereinafter referred to as image DB (DataBase)) 6, a report server 7, and a report database (hereinafter referred to as report DB) 8, all of which are connected in a state where they can communicate with each other via a wired or wireless network 10.

[0023] Each device is a computer installed with an application program that causes the device to function as a component of the medical information system 1. The application program is stored in an externally accessible state in a storage device of a server computer connected to the network 10 or in network storage, and is downloaded and installed into the computer upon request. Alternatively, the application program is recorded on a recording medium such as a DVD (Digital Versatile Disc) or CD-ROM (Compact Disc Read Only Memory) and distributed, and then installed into the computer from the recording medium.

[0024] The imaging device 2 is a device (modality) that captures an image of a diagnostic target part of a subject, thereby generating a medical image representing the diagnostic target part. Specifically, it is a plain X-ray imaging device, a CT device, an MRI device, a PET (Positron Emission Tomography) device, etc. The medical image generated by the imaging device 2 is transmitted to the image server 5 and stored in the image DB 6.

[0025] The image interpretation WS3 is a computer used by, for example, a radiologist to interpret medical images and create image interpretation reports, and includes the medical image display device 20 according to the first embodiment. The image interpretation WS3 performs tasks such as sending requests to the image server 5 to view medical images, performing various image processing on medical images received from the image server 5, displaying the medical images, and accepting input of findings related to the medical images. The image interpretation WS3 also performs tasks such as creating image interpretation reports, sending requests to the report server 7 to register and view image interpretation reports, and displaying image interpretation reports received from the report server 7. These processes are performed by the image interpretation WS3 executing software programs for each process.

[0026] The medical treatment WS4 is a computer used by doctors in the medical department to observe images in detail, view radiology reports, and create electronic medical records, and is composed of a processing device, a display device such as a monitor, and input devices such as a keyboard and a mouse. The medical treatment WS4 sends image viewing requests to the image server 5, displays images received from the image server 5, requests radiology reports to the report server 7, and displays radiology reports received from the report server 7. These processes are performed by the medical treatment WS4 executing software programs for each process.

[0027] The image server 5 is a general-purpose computer installed with a software program that provides the functions of a database management system (DBMS). The image server 5 also has storage in which the image DB 6 is configured. This storage may be a hard disk device connected to the image server 5 via a data bus, or a disk device connected to a NAS (Network Attached Storage) or SAN (Storage Area Network) connected to the network 10. When the image server 5 receives a request to register a medical image from the imaging device 2, it formats the medical image in a database format and registers it in the image DB 6.

[0028] The image DB 6 stores image data and additional information of medical images acquired by the imaging device 2. The additional information includes, for example, an image ID (identification) for identifying each medical image, a patient ID for identifying the subject, an examination ID for identifying the examination, a unique ID (UID: unique identification) assigned to each medical image, the examination date and time when the medical image was generated, patient information such as the type of imaging device used in the examination to acquire the medical image, the patient's name, age, and sex, the examination site (imaging site), imaging information (imaging protocol, imaging sequence, imaging method, imaging conditions, use of contrast agent, etc.), and a series number or collection number when multiple medical images are acquired in one examination.

[0029] In addition, when the image server 5 receives a viewing request from the image interpretation WS3 and medical treatment WS4 via the network 10, it searches for medical images registered in the image DB6 and transmits the searched medical images to the image interpretation WS3 and medical treatment WS4 that made the request.

[0030] A software program that provides a general-purpose computer with the functions of a database management system is installed in the report server 7. When the report server 7 receives a request to register an interpretation report from the interpretation WS 3, it converts the interpretation report into a database format and registers it in the report DB 8.

[0031] The report DB 8 registers image interpretation reports created by image interpretation physicians using the image interpretation WS 3. The image interpretation report may include information such as the medical image to be interpreted, an image ID for identifying the medical image, an image interpretation physician ID for identifying the image interpretation physician who performed the image interpretation, the disease name, location information of the disease, and information for accessing the medical image.

[0032] In addition, when the report server 7 receives a request to view an interpretation report from the interpretation WS3 and medical treatment WS4 via the network 10, it searches for the interpretation report registered in the report DB8 and sends the retrieved interpretation report to the interpretation WS3 and medical treatment WS4 that made the request.

[0033] In this embodiment, the diagnostic target is the chest and abdomen of a human body, the medical image is a three-dimensional CT image consisting of multiple cross-sectional images including the chest and abdomen, and by interpreting the CT image, an interpretation report including findings about diseases of the lungs, liver, etc. included in the chest and abdomen is created. Note that the medical image is not limited to a CT image, and any medical image such as an MRI image or a simple two-dimensional image obtained by a simple X-ray imaging device can be used.

[0034] In this embodiment, when creating an interpretation report, the interpreting physician first displays the medical image on the display 14 and interprets the medical image with his or her own eyes. Then, the medical image is analyzed using the medical image display device of this embodiment to detect a region of interest contained in the medical image, and the second interpretation is performed using the detection result. The first interpretation is called the primary interpretation, and the second interpretation using the detection result of the region of interest by the medical image display device of this embodiment is called the secondary interpretation.

[0035] The network 10 is a wired or wireless local area network that connects various devices within the hospital. If the interpretation WS3 is installed in other hospitals or clinics, the network 10 may be configured by connecting the local area networks of each hospital via the Internet or a dedicated line.

[0036] Next, a medical image display device according to a first embodiment will be described. Fig. 2 describes the hardware configuration of the medical image display device according to the first embodiment. As shown in Fig. 2, the medical image display device 20 includes a CPU (Central Processing Unit) 11, non-volatile storage 13, and memory 16 as a temporary storage area. The medical image display device 20 also includes a display 14 such as a liquid crystal display, an input device 15 including a keyboard and a pointing device such as a mouse, and a network I / F (Interface) 17 connected to a network 10. The CPU 11, storage 13, display 14, input device 15, memory 16, and network I / F 17 are connected to a bus 18. The CPU 11 is an example of a processor in the present disclosure.

[0037] The storage 13 is realized by a hard disk drive (HDD), a solid state drive (SSD), a flash memory, etc. The storage 13 as a storage medium stores a medical image display program 12. The CPU 11 reads the medical image display program 12 from the storage 13, expands it in the memory 16, and executes the expanded medical image display program 12.

[0038] Next, the functional configuration of the medical image display device according to the first embodiment will be described. Fig. 3 is a diagram showing the functional configuration of the medical image display device according to the first embodiment. As shown in Fig. 3, the medical image display device 20 includes an information acquisition unit 21, an analysis unit 22, an attention region identification unit 23, a matching unit 24, and a display control unit 25. When the CPU 11 executes the medical image display program 12, the CPU 11 functions as the information acquisition unit 21, the analysis unit 22, the attention region identification unit 23, the matching unit 24, and the display control unit 25.

[0039] The information acquisition unit 21 acquires a target medical image G0 to be processed for creating an interpretation report from the image server 5 in response to an instruction from the radiology doctor, who is the operator, via the input device 15. In this embodiment, the target medical image G0 is a three-dimensional CT image made up of multiple tomographic images acquired by imaging the chest and abdomen of a human body.

[0040] The analysis unit 22 detects an area of ​​an abnormal shadow included in the target medical image G0 as a region of interest. The analysis unit 22 detects an area of ​​an abnormal shadow from the target medical image G0 as a region of interest using a known computer-aided image diagnosis (i.e., CAD) algorithm.

[0041] The types of abnormal shadows include tumors, pleural effusions, nodules, calcifications, and fractures, depending on the location of the subject included in the target medical image G0. The analysis unit 22 detects regions of abnormal shadows included in multiple types of organs included in the target medical image G0 as regions of interest. To detect the regions of interest, the analysis unit 22 has a learning model 22A that has been machine-trained to detect abnormal shadows as regions of interest from the target medical image G0.

[0042] The learning model 22A consists of a convolutional neural network (CNN) that has undergone deep learning using training data to determine whether each pixel (voxel) in the target medical image G0 represents an abnormal shadow.

[0043] The learning model 22A is constructed by training a CNN using a large number of training data, including training images containing abnormal shadows and ground truth data representing the regions and characteristics of the abnormal shadows in the training images, as well as training images containing no abnormal shadows. The learning model 22A derives a likelihood (likelihood) indicating that each pixel in a medical image is an abnormal shadow, and detects, as a region of interest, a region consisting of pixels whose likelihood is equal to or greater than a predetermined threshold. Here, the likelihood is a value between 0 and 1.

[0044] The learning model 22A may be one that detects abnormal shadows from a three-dimensional medical image, or one that detects abnormal shadows from each of a plurality of tomographic images that make up the target medical image G0.

[0045] As the learning model 22A, in addition to a convolutional neural network, any learning model such as a support vector machine (SVM) can be used.

[0046] 4 is a diagram showing the result of detection of a region of interest by the analysis unit 22. In this embodiment, the target medical image G0 is a CT image of the chest and abdomen of a human body, and is made up of a plurality of axial cross-sectional images Dk (k=1 to m). In this embodiment, it is assumed that the region of interest is detected in tomographic images D4, D8, and D20 of the plurality of tomographic images Dk, as shown in FIG.

[0047] 4, two abnormal shadows are detected as regions of interest R1 and R2 in tomographic image D4, and are respectively surrounded by rectangular marks 41 and 42. Furthermore, three abnormal shadows are detected as regions of interest R3 to R5 in tomographic image D8, and are respectively surrounded by rectangular marks 43 to 45. Furthermore, two abnormal shadows are detected as regions of interest R6 and R7 in tomographic image D20, and are respectively surrounded by rectangular marks 46 and 47.

[0048] The region-of-interest identifying unit 23 identifies a region of interest that the radiologist has focused on in the target medical image G0. Specifically, as a primary interpretation, the radiologist displays the target medical image G0 on the display 14, interprets the target medical image G0, and identifies any abnormal shadows that he or she finds as a region of interest. FIG. 5 is a diagram showing a display screen of the target medical image. As shown in FIG. 5, the display screen 50 includes an image display area 51 and a text display area 52. The image display area 51 displays switchable tomographic images representing cross-sectional planes of the target medical image G0. In FIG. 5, the image display area 51 displays the tomographic image D8 shown in FIG. 4. The text display area 52 contains the findings of the radiologist who interpreted the displayed tomographic image.

[0049] The radiologist can switch between the tomographic images displayed in the image display area 51 by using the input device 15. Specifically, the radiologist can switch between the tomographic images displayed in the image display area 51 by rotating the scroll button of the mouse serving as the input device 15. During the primary interpretation, the radiologist clicks the mouse serving as the input device 15 at the position of the abnormal shadow of interest. As a result, an arrow-shaped mark 31 is added to the clicked position as shown in FIG. 5. As the mark, in addition to an arrow, a rectangle surrounding the abnormal shadow, the outline of the abnormal shadow, or the like can be used.

[0050] The coordinates of the clicked position are stored in the memory 16 as the position of the region of interest. Alternatively, a mark may not be added to the clicked position. The region of interest identifying unit 23 identifies the abnormal shadow to which a mark has been added as the region of interest. Alternatively, if no mark has been added, the region of interest identifying unit 23 identifies the abnormal shadow at the clicked position as the region of interest.

[0051] The image interpreting physician may specify the region of interest as a range by surrounding the region of interest with a rectangular region or tracing the contour of the region of interest. In this case, the region of interest specifying unit 23 specifies the region of interest as a range.

[0052] Furthermore, the radiologist can use the input device 15 to input a finding about the target medical image G0 into the text display area 52. In FIG. 5, the finding "A nodule of about 1 cm is seen in the right lung." is written in the text display area 52.

[0053] FIG. 6 shows the results of the radiologist identifying regions of interest in a tomographic image. As shown in FIG. 6, in tomographic image D4, neither of the two abnormal shadows detected by the analysis unit 22 as regions of interest R1 and R2 has a mark attached. Therefore, these two abnormal shadows are not identified as regions of interest. In tomographic image D8, the two abnormal shadows detected by the analysis unit 22 as regions of interest R3 and R5 have marks 31 and 32 attached, respectively, and these two abnormal shadows are identified as regions of interest. On the other hand, the one abnormal shadow detected by the analysis unit 22 as region of interest R4 has no mark attached, and therefore this abnormal shadow is not identified as a region of interest. In tomographic image D20, the two abnormal shadows detected by the analysis unit 22 as regions of interest R6 and R7 have marks 33 and 34 attached, respectively, and these two abnormal shadows are identified as regions of interest.

[0054] When the image interpretation doctor has finished the primary image interpretation, he or she selects the confirmation button 57 on the display screen 50. This starts the secondary image interpretation.

[0055] During secondary interpretation, the matching unit 24 matches the region of interest detection result by the analysis unit 22 with the region of interest identification result by the region of interest identification unit 23 to identify non-attention regions of interest other than the regions of interest detected by the analysis unit 22. In the first embodiment, as shown in FIG. 6, no region of interest is identified in the tomographic image D4. Furthermore, in the tomographic image D8, the regions of interest R3 and R5 detected by the analysis unit 22 are identified as regions of interest, but the region of interest R4 is not identified as a region of interest. Furthermore, in the tomographic image D20, the regions of interest R6 and R7 detected by the analysis unit 22 are identified as regions of interest. Therefore, the matching unit 24 identifies the regions of interest R1 and R2 detected by the analysis unit 22 in the tomographic image D4 and the region of interest R4 detected by the analysis unit 22 in the tomographic image D8 as non-attention regions of interest. Note that the regions of interest R3, R5, R6, and R7 identified as regions of interest become the regions of interest of interest.

[0056] The display control unit 25 distinguishes between the detection result of the region of interest by the analysis unit 22 and the identification result of the region of interest by the region of interest identification unit 23 and displays them on the display 14. In this embodiment, the display control unit 25 highlights the non-attention region of interest among the regions of interest included in the detection result by adding a mark to the non-attention region of interest identified by the matching unit 24.

[0057] FIG. 7 is a diagram showing a display screen showing the results of detecting a region of interest and the results of identifying a region of interest of interest in the first embodiment. Note that in FIG. 7, the same components as those in FIG. 6 are assigned the same reference numerals, and detailed description thereof will be omitted. As shown in FIG. 7, a tomographic image D8 is displayed in the image display area 51 of the display screen 60. In the tomographic image D8, rectangular marks 43 to 45 are assigned to the regions of interest R3 to R5 detected by the analysis unit 22, respectively. Furthermore, among the regions of interest R3 to R5, a region of interest R4, which is a non-target region of interest, is highlighted by being assigned a circular mark 61 in the upper left corner of the rectangular mark 44. Note that the mark 61 is not limited to a circle, and can have any shape or color, such as a star or triangle. Instead of assigning a circular mark, the color of the rectangular mark surrounding the region of interest may be changed, or the line type of the rectangular mark may be changed.

[0058] When the tomographic image D4 is displayed in the image display area 51 instead of the tomographic image D8, the regions of interest R1 and R2 detected by the analysis unit 22 are both non-target regions of interest, and therefore the rectangular marks 41 and 42 surrounding the regions of interest R1 and R2 are each given a circular mark 61. When the tomographic image D20 is displayed in the image display area 51 instead of the tomographic image D8, the regions of interest R6 and R7 detected by the analysis unit 22 are both target regions of interest, and therefore the rectangular marks 46 and 47 surrounding the regions of interest R6 and R7 are not given a circular mark 61.

[0059] The radiologist can confirm the presence of an abnormal shadow that may have been overlooked during the initial interpretation based on the presence or absence of a circular mark 61 attached to the rectangular mark. For example, as shown in FIG. 7, a circular mark 61 is attached to the rectangular mark 44 surrounding the region of interest R4 detected by the analysis unit 22. This allows the radiologist to easily confirm the presence of an abnormal shadow in the right lung that was overlooked during the initial interpretation. In this case, the radiologist can enter a finding about the confirmed abnormal shadow in the text display area 52. For example, if the region of interest R4 is a tumor, the radiologist can enter a finding such as "A tumor approximately 1 cm in size is seen in the right lung" in the text display area 52, as shown in FIG. 7.

[0060] When the radiologist selects the confirm button 58, an interpretation report is created that includes the findings entered in the text display area 52. The created interpretation report is saved in the storage 13 together with the target medical image G0 and the detection results for the region of interest. Thereafter, the created interpretation report is transferred to the report server 7 together with the target medical image G0 and the detection results. The report server 7 saves the transferred interpretation report together with the target medical image G0 and the detection results.

[0061] Next, the processing performed in the first embodiment will be described. FIG. 8 is a flowchart showing the processing performed during primary interpretation in the first embodiment, and FIG. 9 is a flowchart showing the processing performed during secondary interpretation in the first embodiment. It is assumed that the target medical image G0 to be interpreted is acquired from the image server 5 by the information acquisition unit 21 and stored in the storage 13. The processing is initiated when an instruction to create an interpretation report is given by the radiologist, and the display control unit 25 displays the target medical image G0 on the display 14 (step ST1). Next, the region-of-interest identification unit 23 identifies the region of interest that the radiologist has focused on in the target medical image G0 based on an instruction given by the radiologist using the input device 15 (step ST2). In this state, the radiologist can input a comment about the region of interest in the text display area 52.

[0062] Next, by selecting the confirmation button 57, it is determined whether or not an instruction to start secondary interpretation has been given (step ST3), and if step ST3 is negative, the process returns to step ST1. If step ST3 is positive, the primary interpretation ends and secondary interpretation begins.

[0063] During the secondary interpretation, first, the analysis unit 22 analyzes the target medical image G0 to detect at least one region of interest contained in the target medical image G0 (step ST11). The analysis of the target medical image G0 may be performed immediately after the information acquisition unit 21 acquires the target medical image G0 from the image server 5. In this case, the analysis result is stored in the storage 13, and the stored analysis result is used for subsequent processing.

[0064] Next, the matching unit 24 matches the detection result of the region of interest by the analysis unit 22 with the identification result of the region of interest by the region of interest identification unit 23, thereby identifying non-regions of interest other than the region of interest of interest from among the regions of interest detected by the analysis unit 22 (step ST12).

[0065] Furthermore, the display control unit 25 distinguishes between the result of detecting the region of interest by the analysis unit 22 and the result of identifying the region of interest by the region of interest identifying unit 23 and displays them on the display 14 (displaying them separately; step ST13). 14 While viewing the display, the user inputs a comment in the text display area 52 if necessary.

[0066] Next, an interpretation report is created using the findings entered by the radiologist (step ST14). When the radiologist selects the confirm button 58, the created interpretation report is stored in the storage 13 together with the target medical image G0 and the detection results (step ST15). Furthermore, the created interpretation report is transferred to the report server 7 together with the target medical image G0 and the detection results (step ST16), and the secondary interpretation process is completed.

[0067] As described above, in the first embodiment, the result of detecting a region of interest by the analysis unit 22 and the result of identifying a region of interest by the region-of-interest identifying unit 23 are displayed separately on the display 14. This allows the radiologist to easily confirm the presence of an abnormal shadow that may have been overlooked during the primary interpretation, thereby reducing the burden on the physician when interpreting medical images.

[0068] Next, a second embodiment of the present disclosure will be described. Note that the configuration of the medical image display device according to the second embodiment is the same as the configuration of the medical image display device according to the first embodiment shown in Fig. 3, and only the processing performed is different. Therefore, a detailed description of the device will be omitted here.

[0069] In the first embodiment, the non-interested regions of interest among the regions of interest detected in the tomographic image are highlighted by adding circular marks to the non-interested regions of interest. In the second embodiment, the display control unit 25 displays a paging slider that schematically indicates the positions of the tomographic planes of multiple tomographic images, and the positions of the tomographic planes of the tomographic images including the non-interested regions of interest, which are regions of interest other than the interested region of interest, among the regions of interest included in the detection result, are highlighted on the paging slider, which is different from the first embodiment.

[0070] Fig. 10 is a diagram showing a display screen for showing the results of detecting a region of interest and the results of identifying a region of interest of interest in the second embodiment. In Fig. 10, the same components as those in Fig. 7 are given the same reference numerals, and detailed description thereof will be omitted. As shown in Fig. 10, a tomographic image D8 is displayed in the image display area 51 of the display screen 65. A paging slider 70 is also displayed on the tomographic image D8. The paging slider 70 schematically shows the positions of the tomographic planes of the tomographic images D1 to Dm from top to bottom, and a slider 72 is displayed at the position of the tomographic plane of the tomographic image currently being displayed. Furthermore, marks 73 to 75 indicating that the region of interest is included are added to the positions of the tomographic planes on the paging slider 70 that correspond to the tomographic images D4, D8, and D20 that include the region of interest.

[0071] 6, the tomographic image D4 includes regions of interest R1 and R2 detected by the analysis unit 22, but the regions of interest R1 and R2 are not specified as regions of interest of interest. Furthermore, the tomographic image D8 includes regions of interest R3 to R5 detected by the analysis unit 22, but the region of interest R4 among these regions of interest is not specified as a region of interest of interest. In the second embodiment, the display control unit 25 highlights the positions of the tomographic planes of the tomographic image including the non-regions of interest on the paging slider 70.

[0072] In particular, in the second embodiment, the positions of the tomographic planes of tomographic images in which all included regions of interest are non-interest regions of interest are distinguished from the positions of the tomographic planes of tomographic images in which some included regions of interest are non-interest regions of interest and are highlighted. Specifically, of the marks 73 to 75 indicating the tomographic planes of tomographic images including regions of interest, the display control unit 25 adds a black circle mark 76 to the left of the mark 73 corresponding to the tomographic plane of tomographic image D4 in which all included regions of interest are non-interest regions of interest. In addition, the display control unit 25 adds a white circle mark 77 to the left of the mark 74 corresponding to the tomographic plane of tomographic image D8 in which some included regions of interest are non-interest regions of interest.

[0073] As described above, in the second embodiment, the positions of the tomographic planes of the tomographic images including the non-target regions of interest among the regions of interest included in the detection results are highlighted on the paging slider 70. This allows the radiologist to easily confirm the presence of tomographic images including abnormal shadows that may have been overlooked during the primary interpretation, thereby reducing the burden on the physician when interpreting medical images.

[0074] In the second embodiment, the positions of the slice planes of a tomographic image in which all of the regions of interest are non-target regions of interest are distinguished from the positions of the slice planes of a tomographic image in which only a portion of the regions of interest are non-target regions of interest. This allows the radiologist to distinguish between a tomographic image containing an abnormal shadow that was completely overlooked during primary interpretation and a tomographic image containing an abnormal shadow that was partially overlooked. This reduces the burden on the physician when interpreting medical images.

[0075] 11, in the second embodiment, a circular mark 61 may be added to the region of interest R4, which is a non-target region of interest among the regions of interest R3 to R5 detected by the analysis unit 22, in addition to the rectangular mark 44, as in the first embodiment. When the tomographic image D4 is displayed, circular marks may be added to the rectangular marks 41 and 42 surrounding the regions of interest R1 and R2.

[0076] In the second embodiment, the positions of the tomographic plane of a tomographic image in which all of the included regions of interest are non-target regions of interest and the positions of the tomographic plane of a tomographic image in which some of the included regions of interest are non-target regions of interest are distinguished and highlighted, but this is not limited to this.The positions of the tomographic plane of a tomographic image in which all of the included regions of interest are non-target regions of interest and the positions of the tomographic plane of a tomographic image in which some of the included regions of interest are non-target regions of interest may be given the same mark without distinguishing between them.

[0077] In the first and second embodiments, a non-interested region of interest is identified from among the regions of interest included in the detection results, and the non-interested region of interest is highlighted, but this is not limited to this. It is also possible to identify a region of interest other than the region of interest included in the detection results by the analysis unit 22 from among the regions of interest identified by the radiologist, and highlight the identified region of interest. That is, it is also possible to highlight a region of interest identified by the radiologist but not detected by the analysis unit 22.

[0078] FIG. 12 is a diagram showing a display screen in which regions of interest that were identified by the radiologist but could not be detected by the analysis unit 22 are highlighted. In FIG. 12, the same components as those in FIG. 7 are assigned the same reference numerals, and detailed description thereof will be omitted. As shown in FIG. 12, a tomographic image D8 is displayed in the image display area 51 of the display screen 80. Assume that all three abnormal shadows included in the tomographic image D8 are identified as regions of interest R3 to R5. Assume that the analysis unit 22 detects two abnormal shadows in the right lung as regions of interest R3 and R4. In this case, marks 33 and 34 indicating that the regions of interest are regions of interest are assigned to the regions of interest R3 and R4, and rectangular marks 43 and 44 indicating that the regions of interest are regions of interest detected by the analysis unit 22 are assigned to the regions of interest R3 and R4. On the other hand, only mark 35 indicating that the region of interest R5 is a region of interest is assigned to the region of interest R5. As a result, the region of interest R5 that was identified by the radiologist but could not be detected by the analysis unit 22 is highlighted.

[0079] In the first embodiment, a circular mark 61 is added to highlight the non-attention region of interest, but the present invention is not limited to this. In addition to or instead of the mark for highlighting the non-attention region of interest, a mark indicating that the attention region of interest is a attention region of interest may be added to the attention region of interest. Fig. 13 is a diagram showing a display screen on which a mark indicating that the attention region of interest is a attention region of interest is further added. In Fig. 13, the same components as those in Fig. 7 are assigned the same reference numerals, and detailed description thereof will be omitted.

[0080] 13, a tomographic image D8 is displayed in the image display area 51 of the display screen 85. In the tomographic image D8, rectangular marks 43 to 45 are attached to the regions of interest R3 to R5 detected by the analysis unit 22, respectively. Furthermore, of the regions of interest R3 to R5 detected by the analysis unit 22, a circular mark 61 is attached to the region of interest R4, which is a non-attention region of interest, in addition to the rectangular mark 44. Furthermore, arrow-shaped marks 33 and 35, which indicate that the regions of interest R3 and R5 are attention regions of interest, are attached to them, respectively.

[0081] Furthermore, in the first and second embodiments, the position of the region of interest identified by the radiologist may differ from the position of the region of interest detected by the analysis unit 22. For example, as shown in FIG. 14 , the position identified by the radiologist for an abnormal shadow 90 is position 91 indicated by an x, and the abnormal shadow detected by the analysis unit 22 is region of interest 92. In this case, a non-attention region of interest may be identified based on the positional relationship between the region of interest 92 and position 91. For example, if the distance between the center of gravity of the region of interest 92 detected by the analysis unit 22 and position 91 is equal to or greater than a predetermined threshold value Th1, the region of interest 92 may be identified as a non-attention region of interest. Furthermore, if the shortest distance between position 91 and the outer edge of the region of interest 92 is equal to or greater than a predetermined threshold value Th2, the region of interest 92 may be identified as a non-attention region of interest.

[0082] Note that the analysis unit 22 may detect a region of interest based on a point representing the position of the region of interest. For example, the center of gravity of the region of interest may be detected as the region of interest. In such a case, a non-attention region of interest may be identified based on the positional relationship between the point representing the detected region of interest and position 91. For example, when the distance between the point representing the region of interest 92 detected by the analysis unit 22 and position 91 is equal to or greater than a predetermined threshold value Th3, the region of interest 92 may be identified as a non-attention region of interest.

[0083] In some cases, the radiologist may specify the region of interest by a range rather than a point. In such cases, the non-attention region of interest may be specified based on the degree of overlap between the specified region of interest and the region of interest. For example, as shown in FIG. 15 , if the region of interest 93 specified by the radiologist overlaps with the region of interest 92 detected by the analysis unit 22, the region of interest 92 may be specified as the attention region of interest; otherwise, the region of interest 92 may be specified as the non-attention region of interest. Furthermore, the area of ​​the overlapping region between the region of interest 93 specified by the radiologist and the region of interest 92 detected by the analysis unit 22 may be derived, and if the ratio of the derived area to the region of interest 93 or the region of interest 92 is less than a predetermined threshold value Th4, the region of interest 92 may be specified as the non-attention region of interest.

[0084] In addition, there are cases where the radiologist specifies the region of interest by a range rather than a point, and the analysis unit 22 detects the region of interest by a point. In such cases, a non-attention region of interest may be specified depending on whether or not the point representing the region of interest detected by the analysis unit 22 is within the region of interest specified by the radiologist. For example, as shown in FIG. 16 , if a point 94 representing the region of interest detected by the analysis unit 22 is not within the region of interest 93 specified by the radiologist, the region of interest 94 may be specified as a non-attention region of interest.

[0085] Furthermore, in each of the above embodiments, the analysis unit 22 detects a region of interest from the target medical image G0, but this is not limited to this. The target medical image G0 may be analyzed by an analysis device provided separately from the medical image display device 20 according to this embodiment, and the analysis results obtained by the analysis device may be acquired by the information acquisition unit 21. In addition, the medical WS 4 may also be capable of analyzing medical images. In such cases, the analysis results obtained by the medical WS 4 may be acquired by the information acquisition unit 21 of the medical image display device 20 according to this embodiment. Furthermore, if the analysis results are registered in the image database 6 or the report database 8, the information acquisition unit 21 may acquire the analysis results from the image database 6 or the report database 8.

[0086] In addition, in the above-described embodiments, the technology of the present disclosure is applied to the case where an interpretation report is created using medical images in which the diagnostic target is the lungs or the liver, but the diagnostic target is not limited to the lungs or the liver. In addition to the lungs, any part of the human body, such as the heart, brain, kidneys, and limbs, can be the diagnostic target.

[0087] Furthermore, in each of the above embodiments, the following various processors can be used as the hardware structure of the processing units that perform various processes, such as the information acquisition unit 21, the analysis unit 22, the region-of-interest identification unit 23, the matching unit 24, and the display control unit 25. As described above, the various processors include a CPU, which is a general-purpose processor that executes software (programs) and functions as various processing units, as well as dedicated electrical circuits that are processors having a circuit configuration specifically designed to perform specific processes, such as a programmable logic device (PLD), which is a processor whose circuit configuration can be changed after manufacture, such as an FPGA (Field Programmable Gate Array), and an ASIC (Application Specific Integrated Circuit).

[0088] A single processing unit may be configured with one of these various processors, or may be configured with 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). Also, multiple processing units may be configured with a single processor.

[0089] Examples of configuring multiple processing units with a single processor include, first, a form in which one processor is configured with a combination of one or more CPUs and software, and this processor functions as multiple processing units, as typified by computers such as client and server. Second, a form in which a processor is used to realize the functions of an entire system including multiple processing units with a single IC (Integrated Circuit) chip, as typified by systems on chips (SoCs). In this way, various processing units are configured using one or more of the above-mentioned various processors as a hardware structure.

[0090] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements. [Explanation of symbols]

[0091] 1 Medical Information System 2. Imaging equipment 3 Image Reading Workshop 4. Medical Workshop 5 Image Server 6. Image Database 7 Report Server 8 Report DB 10 Network 11 CPU 12 Medical image display program 13. Storage 14 Display 15 Input Devices 16 memory 17 Network I / F 18 Bus 20 Medical image display device 21 Information Acquisition Department 22 Analysis Department 22A Learning Model 23. Region of interest identification unit 24 Matching unit 25 Display control unit 31~34 Arrow marks 41~47 Rectangular marks 50,60,65,80,85 display screen 51 Image display area 52 Text display area 57 Confirm button 58 Confirm button 61 Circular Mark 70 Paging Slider 72 slider 73~75 marks 90 Abnormal shadow 91,93 Areas of Interest 92,94 Area of ​​interest

Claims

1. at least one processor; The processor: obtaining a detection result of at least one region of interest included in the medical image, the region of interest being detected by analyzing the medical image; Identifying at least one region of interest in the medical image that is of interest to a user; displaying the detection result of the region of interest and the identification result of the region of interest separately on a display; When the medical image is a three-dimensional image consisting of a plurality of tomographic images, a paging slider is displayed that schematically indicates the positions of the tomographic planes of the plurality of tomographic images; By comparing the detection result of the region of interest with the identification result of the region of interest, a tomographic image including a non-attention region of interest other than the region of interest is identified from the region of interest included in the detection result; When highlighting the position of the tomographic plane of the identified tomographic image on the paging slider, the medical image display device distinguishes and highlights the position of the tomographic plane of the tomographic image in which all of the regions of interest included are the non-regions of interest and the position of the tomographic plane of the tomographic image in which only some of the regions of interest included are the non-regions of interest.

2. the processor identifies a non-attention region of interest other than the region of interest among the regions of interest included in the detection result by comparing the detection result of the region of interest with the identification result of the region of interest; The medical image display device according to claim 1 , wherein the non-attention region of interest is highlighted.

3. the processor identifies a region of interest other than the region of interest included in the detection result by comparing the detection result of the region of interest with the identification result of the region of interest; The medical image display device according to claim 1 , wherein the region of interest is highlighted.

4. The medical image display device according to claim 1 , wherein the processor acquires a detection result of at least one region of interest included in the medical image by analyzing the medical image.

5. The medical image display device according to claim 1 , wherein the processor identifies the region of interest based on an operation of the user when interpreting the medical image.

6. obtaining a detection result of at least one region of interest included in the medical image, the region of interest being detected by analyzing the medical image; Identifying at least one region of interest in the medical image that is of interest to a user; displaying the detection result of the region of interest and the identification result of the region of interest separately on a display; When the medical image is a three-dimensional image consisting of a plurality of tomographic images, a paging slider is displayed that schematically indicates the positions of the tomographic planes of the plurality of tomographic images; By comparing the detection result of the region of interest with the identification result of the region of interest, a tomographic image including a non-attention region of interest other than the region of interest is identified from the region of interest included in the detection result; A medical image display method in which, when highlighting the positions of the slice planes of the identified tomographic images on the paging slider, the positions of the slice planes of the tomographic images in which all of the regions of interest are the non-target regions of interest are distinguished from the positions of the slice planes of the tomographic images in which some of the regions of interest are the non-target regions of interest.

7. obtaining a detection result of at least one region of interest included in the medical image, the region of interest being detected by analyzing the medical image; A procedure for identifying at least one region of interest that a user has focused on in the medical image; a procedure for displaying a result of detecting the region of interest and a result of identifying the region of interest on a display in a distinguishable manner; When the medical image is a three-dimensional image consisting of a plurality of tomographic images, a paging slider is displayed that schematically indicates the positions of the tomographic planes of the plurality of tomographic images; a step of identifying a tomographic image including a non-attention region of interest other than the region of interest from among the regions of interest included in the detection result by comparing the detection result of the region of interest with the identification result of the region of interest; a medical image display program that causes a computer to execute a procedure for highlighting the positions of the slice planes of the identified tomographic image on the paging slider, by distinguishing and highlighting the positions of the slice planes of the tomographic image in which all of the regions of interest included are the non-regions of interest and the positions of the slice planes of the tomographic image in which some of the regions of interest included are the non-regions of interest.

Images