Document creation support device, document creation support method, and document creation support program

Abstract

A document creation assistance device that acquires information representing multiple regions of interest contained in a medical image, derives evaluation indicators for each of the multiple regions of interest as subjects for a medical treatment document, and on the basis of the evaluation indicators, generates text including a description relating to at least one of the multiple regions of interest.

Description

[Technical Field]

[0001] The present disclosure relates to a document creation support device, a document creation support method, and a document creation support program. [Background technology]

[0002] Conventionally, techniques have been proposed for improving the efficiency of creating medical documents such as radiology reports by doctors. For example, Japanese Patent Laid-Open Publication No. 7-031591 discloses a technique for detecting the type and location of an abnormality contained in a medical image and generating a radiology report including the type and location of the detected abnormality based on a fixed phrase.

[0003] Furthermore, International Publication No. 2020 / 209382 discloses a technology for creating medical documents using findings that represent characteristics of abnormal shadows contained in medical images. Summary of the Invention [Problem to be solved by the invention]

[0004] However, with the techniques described in JP 7-031591 A and WO 2020 / 209382 A, when a medical image contains multiple regions of interest, such as abnormal shadows, a sentence is generated for each region of interest, and the generated sentences are listed. Therefore, when a medical document is created using multiple sentences listed, the medical document may not be easy to read. In other words, the techniques described in JP 7-031591 A and WO 2020 / 209382 A may not be able to adequately support the creation of medical documents.

[0005] The present disclosure has been made in consideration of the above circumstances, and aims to provide a document creation support device, a document creation support method, and a document creation support program that can appropriately support the creation of medical documents even when a medical image contains multiple regions of interest. [Means for solving the problem]

[0006] The document creation support device of the present disclosure is a document creation support device that includes at least one processor, which acquires information representing multiple regions of interest contained in a medical image, derives evaluation indicators for each of the multiple regions of interest as targets for medical documents, and generates text including a description of at least one of the multiple regions of interest based on the evaluation indicators.

[0007] In the document creation assistance device of the present disclosure, the processor may determine, from among a plurality of regions of interest, a region of interest to be included in the text, according to the evaluation index.

[0008] Furthermore, in the document creation assistance device of the present disclosure, the processor may determine, in accordance with the evaluation index, whether or not to include in the text a feature of the region of interest to be included in the text.

[0009] In addition, in the document creation assistance device of the present disclosure, the processor may determine the order of description of the regions of interest to be included in the text according to the evaluation index.

[0010] Furthermore, in the document creation assistance device of the present disclosure, the processor may determine the amount of description in the text for the region of interest to be included in the text according to the evaluation index.

[0011] In addition, the document creation support device of the present disclosure may have an evaluation index as an evaluation value, and the processor may generate text including descriptions of areas of interest in order of highest evaluation value, with a predetermined upper limit of the number of characters.

[0012] In addition, in the document creation support device of the present disclosure, the processor may generate the text in a sentence format.

[0013] In addition, in the document creation assistance device of the present disclosure, the processor may generate the text in a bulleted list format or a table format.

[0014] In addition, in the document creation assistance device of the present disclosure, the processor may derive an evaluation index depending on the type of the region of interest.

[0015] In addition, in the document creation support device of the present disclosure, the processor may derive an evaluation index depending on whether or not there is a change from the same region of interest detected in a previous inspection.

[0016] In addition, the document creation support device of the present disclosure may have an evaluation index that is an evaluation value, and the processor may increase the evaluation value of an area of ​​interest that has changed from the same area of ​​interest detected in a previous inspection compared to the evaluation value of an area of ​​interest that has not changed.

[0017] Furthermore, in the document creation support device of the present disclosure, the processor may derive the evaluation index depending on whether the same region of interest was detected in a previous inspection.

[0018] In the document creation support device of the present disclosure, the region of interest may be a region including an abnormal shadow.

[0019] In addition, in the document creation support device of the present disclosure, the evaluation index is an evaluation value, and when displaying text, the processor may control the display of descriptions of areas of interest that have a higher evaluation value than when detected in a previous inspection in a manner that makes them distinguishable from descriptions of other areas of interest.

[0020] In addition, in the document creation assistance device of the present disclosure, the processor may change the display mode of the description related to the region of interest included in the text depending on the evaluation index.

[0021] In addition, the document creation support device of the present disclosure may have a processor that controls the display of the derived evaluation index, accepts corrections to the evaluation index, and generates text based on the evaluation index that reflects the accepted corrections.

[0022] In addition, the document creation support method disclosed herein is a method in which a processor provided in the document creation support device acquires information representing multiple areas of interest contained in a medical image, derives evaluation indicators for each of the multiple areas of interest as targets for medical documents, and generates text including a description of at least one of the multiple areas of interest based on the evaluation indicators.

[0023] In addition, the document creation support program disclosed herein is intended to cause a processor provided in the document creation support device to perform the following process: acquire information representing multiple regions of interest contained in a medical image, derive evaluation indices for each of the multiple regions of interest as targets for medical documents, and generate text including a description of at least one of the multiple regions of interest based on the evaluation indices. [Effects of the Invention]

[0024] According to the present disclosure, it is possible to appropriately support the creation of medical documents even when a medical image includes multiple regions of interest. [Brief explanation of the drawings]

[0025] [Figure 1] FIG. 1 is a block diagram showing a schematic configuration of a medical information system. [Figure 2] FIG. 2 is a block diagram showing an example of a hardware configuration of the document creation support device. [Figure 3] FIG. 10 is a diagram illustrating an example of an evaluation value table. [Figure 4] FIG. 2 is a block diagram showing an example of a functional configuration of the document creation support device. [Figure 5] FIG. 1 is a diagram illustrating an example of text in a sentence format. [Figure 6] FIG. 10 is a diagram illustrating an example of text in bulleted format. [Figure 7] FIG. 1 is a diagram illustrating an example of text in a tabular format. [Figure 8] 10 is a flowchart illustrating an example of a document creation support process. [Figure 9] FIG. 1 is a diagram illustrating an example of text in a sentence format. [Figure 10] FIG. 10 is a diagram showing an example of text in tab format. [Figure 11] FIG. 10 is a diagram showing an example of text in a sentence format according to a modified example. [Figure 12] FIG. 10 is a diagram for explaining a process related to correction of an evaluation value. [Figure 13] FIG. 10 is a diagram for explaining a process related to correction of an evaluation value. DETAILED DESCRIPTION OF THE INVENTION

[0026] Hereinafter, examples of embodiments for carrying out the technology of the present disclosure will be described in detail with reference to the drawings.

[0027] First, the configuration of a medical information system 1 to which a document creation support device according to the disclosed technology is applied will be described with reference to Fig. 1. The medical information system 1 is a system for capturing images of a subject's diagnostic target area and storing the medical images obtained by capturing the images, based on an examination order from a doctor of a medical department using a known ordering system. The medical information system 1 is also a system for allowing a radiologist to interpret the medical images and create an interpretation report, and for a doctor of the requesting medical department to view the interpretation report and observe the details of the medical image to be interpreted.

[0028] 1, a medical information system 1 according to this embodiment includes a plurality of imaging devices 2, a plurality of interpretation workstations (WS) 3 which are interpretation terminals, a medical department WS4, an image server 5, an image database (DB) 6, an interpretation report server 7, and an interpretation report DB 8. The imaging devices 2, the interpretation WS3, the medical department WS4, the image server 5, and the interpretation report server 7 are connected to each other in a communicable state via a wired or wireless network 9. The image DB 6 is connected to the image server 5, and the interpretation report DB 8 is connected to the interpretation report server 7.

[0029] The imaging device 2 is a device that generates a medical image representing a diagnostic target region of a subject by capturing an image of the diagnostic target region. The imaging device 2 may be, for example, a plain X-ray imaging device, an endoscope device, a CT (Computed Tomography) device, an MRI (Magnetic Resonance Imaging) device, or a PET (Positron Emission Tomography) device. The medical image generated by the imaging device 2 is transmitted to and stored in the image server 5.

[0030] The department WS4 is a computer used by doctors in the department to perform detailed observations of medical images, view radiology reports, create electronic medical records, etc. The department WS4 executes software programs for each process, such as creating a patient's electronic medical record, requesting the image server 5 to view images, and displaying medical images received from the image server 5. The department WS4 also executes software programs for each process, such as automatically detecting or highlighting areas suspected of disease in medical images, requesting the radiology report server 7 to view radiology reports, and displaying radiology reports received from the radiology report server 7.

[0031] A software program that provides a general-purpose computer with the functions of a database management system (DBMS) is installed in the image server 5. When the image server 5 receives a request to register a medical image from the imaging device 2, it converts the medical image into a database format and registers it in the image DB 6.

[0032] The image DB 6 stores image data representing medical images acquired by the imaging device 2 and associated information associated with the image data. The associated information includes, for example, an image ID (identification) for identifying each medical image, a patient ID for identifying the patient who is the subject, an examination ID for identifying the examination details, and a unique ID (UID) assigned to each medical image. The associated information also includes the examination date and time when the medical image was generated, the type of imaging device used in the examination to acquire the medical image, patient information (e.g., the patient's name, age, and gender), the examination site (i.e., the imaging site), imaging information (e.g., the imaging protocol, imaging sequence, imaging technique, imaging conditions, and whether or not a contrast agent was used), and a series number or acquisition number when multiple medical images are acquired in a single examination. When the image server 5 receives a viewing request from the image interpretation workstation 3 via the network 9, it searches for medical images registered in the image DB 6 and transmits the searched medical images to the image interpretation workstation 3 that made the request.

[0033] A software program that provides a general-purpose computer with the functions of a DBMS is installed in the image interpretation report server 7. When the image interpretation report server 7 receives a registration request for an image interpretation report from the image interpretation WS 3, it converts the image interpretation report into a database format and registers it in the image interpretation report database 8. When it receives a search request for an image interpretation report, it searches the image interpretation report DB 8 for that image interpretation report.

[0034] The interpretation report DB8 stores an interpretation report that contains information such as an image ID that identifies the medical image to be interpreted, an interpretation physician ID that identifies the imaging diagnostician who performed the interpretation, the name of the lesion, location information of the lesion, findings, and the certainty of the findings.

[0035] The network 9 is a wired or wireless local area network that connects various devices within the hospital. If the interpretation WS3 is installed in another hospital or clinic, the network 9 may be configured to connect the local area networks of each hospital via the Internet or a dedicated line. In either case, it is preferable that the network 9 be configured to enable high-speed transfer of medical images, such as an optical network.

[0036] The image interpretation WS3 requests the image server 5 to view medical images, performs various image processing on medical images received from the image server 5, displays the medical images, analyzes the medical images, highlights the medical images based on the analysis results, and creates an interpretation report based on the analysis results. The image interpretation WS3 also supports the creation of an interpretation report, requests the image interpretation report server 7 to register and view the interpretation report, and displays the interpretation report received from the image interpretation report server 7. The image interpretation WS3 performs each of the above processes by executing a software program for each process. The image interpretation WS3 includes a document creation support device 10 (described later). Of the above processes, processes other than those performed by the document creation support device 10 are performed by well-known software programs, and therefore detailed descriptions are omitted here. Alternatively, processes other than those performed by the document creation support device 10 may not be performed in the image interpretation WS3, but a separate computer that performs the processes may be connected to the network 9, and the requested processes may be performed by that computer in response to a processing request from the image interpretation WS3. The document creation support device 10 included in the image interpretation WS 3 will be described in detail below.

[0037] Next, the hardware configuration of the document creation support device 10 according to this embodiment will be described with reference to Fig. 2. As shown in Fig. 2, the document creation support device 10 includes a CPU (Central Processing Unit) 20, a memory 21 as a temporary storage area, and a non-volatile storage unit 22. The document creation support device 10 also includes a display 23 such as a liquid crystal display, an input device 24 such as a keyboard and a mouse, and a network I / F (Interface) 25 connected to a network 9. The CPU 20, memory 21, storage unit 22, display 23, input device 24, and network I / F 25 are connected to a bus 27.

[0038] The storage unit 22 is realized by a hard disk drive (HDD), a solid state drive (SSD), a flash memory, or the like. The storage unit 22 serving as a storage medium stores a document creation support program 30. The CPU 20 reads the document creation support program 30 from the storage unit 22, expands it in the memory 21, and executes the expanded document creation support program 30.

[0039] The storage unit 22 also stores an evaluation value table 32. FIG. 3 shows an example of the evaluation value table 32. As shown in FIG. 3, the evaluation value table 32 stores, for each type of abnormal shadow, an evaluation value for that abnormal shadow as a target of a medical document. An example of a medical document is a radiology report. In this embodiment, a higher evaluation value is assigned to an abnormal shadow with a higher priority in the radiology report. FIG. 3 shows an example in which the evaluation value for hepatocellular carcinoma is a value representing "High" and the evaluation value for liver cysts is a value representing "Low." That is, this example shows that hepatocellular carcinoma has a higher evaluation value as a target of a radiology report than liver cysts. Note that, in the example of FIG. 3, the evaluation value is expressed as two levels, "High" and "Low," but the evaluation value may be a value with three or more levels or may be a continuous value. The above evaluation value is an example of an evaluation index related to the disclosed technology.

[0040] The evaluation value table 32 may be a table in which severity is associated with each disease name of an abnormal shadow as an evaluation value. In this case, the evaluation value may be, for example, a numerical value for each disease name, or an evaluation index such as "MUST" or "WANT." Here, "MUST" means that it must be included in the radiology report, and "WANT" means that it may or may not be included in the radiology report. In the example of FIG. 3, hepatocellular carcinoma is relatively often severe, while liver cysts are relatively often benign. Therefore, for example, the evaluation value for hepatocellular carcinoma is "MUST," and the evaluation value for liver cysts is "WANT."

[0041] Next, the functional configuration of the document creation support device 10 according to this embodiment will be described with reference to Fig. 4. As shown in Fig. 4, the document creation support device 10 includes an acquisition unit 40, an extraction unit 42, an analysis unit 44, a derivation unit 46, a generation unit 48, and a display control unit 50. When the CPU 20 executes the document creation support program 30, the document creation support device 10 functions as the acquisition unit 40, the extraction unit 42, the analysis unit 44, the derivation unit 46, the generation unit 48, and the display control unit 50.

[0042] The acquisition unit 40 acquires a medical image of a diagnostic target (hereinafter referred to as a "diagnostic target image") from the image server 5 via the network I / F 25. In the following, an example will be described in which the diagnostic target image is a CT image of the liver.

[0043] The extraction unit 42 uses a trained model M1 for detecting abnormal shadows as an example of a region of interest in the diagnostic target image acquired by the acquisition unit 40 to extract a region including an abnormal shadow.

[0044] Specifically, the extraction unit 42 extracts a region containing an abnormal shadow using a trained model M1 for detecting abnormal shadows from a diagnostic target image. An abnormal shadow refers to a shadow that is suspected to be a disease, such as a nodule. The trained model M1 is configured, for example, by a convolutional neural network (CNN) that receives a medical image as input and outputs information related to the abnormal shadow contained in the medical image. The trained model M1 is a model trained by machine learning using, for example, as training data, many combinations of medical images containing abnormal shadows and information identifying regions in the medical images where the abnormal shadows exist.

[0045] The extraction unit 42 inputs a diagnostic target image to the trained model M1. The trained model M1 outputs information identifying an area containing an abnormal shadow included in the input diagnostic target image. The extraction unit 42 may extract an area containing an abnormal shadow using a known computer-aided diagnosis (CAD) or may extract an area specified by a user as an area containing an abnormal shadow.

[0046] The analysis unit 44 analyzes each abnormal shadow extracted by the extraction unit 42 and derives findings for the abnormal shadow. Specifically, the extraction unit 42 derives findings for the abnormal shadow, including the type of abnormal shadow, using a trained model M2 for deriving findings for the abnormal shadow. The trained model M2 is configured, for example, by a CNN that receives as input a medical image containing an abnormal shadow and information identifying the area in the medical image where the abnormal shadow exists, and outputs findings for the abnormal shadow. The trained model M2 is a model trained by machine learning using, for example, numerous combinations of medical images containing an abnormal shadow, information identifying the area in the medical image where the abnormal shadow exists, and findings for the abnormal shadow as training data.

[0047] The analysis unit 44 inputs the diagnostic target image and information identifying the region containing the abnormal shadow extracted from the diagnostic target image by the extraction unit 42 to the trained model M2. The trained model M2 outputs findings of the abnormal shadow contained in the input diagnostic target image. Examples of findings of the abnormal shadow include the position, size, presence or absence of calcification, whether it is benign or malignant, presence or absence of marginal irregularities, and type of abnormal shadow.

[0048] The derivation unit 46 acquires information representing a plurality of abnormal shadows included in the diagnostic target image from the extraction unit 42 and the analysis unit 44. This information representing the abnormal shadows includes, for example, information identifying the region in which the abnormal shadows extracted by the extraction unit 42 exist, and information including findings of the abnormal shadows derived by the analysis unit 44 for the abnormal shadows. The derivation unit 46 may acquire the information representing the plurality of abnormal shadows included in the diagnostic target image from an external device such as the department WS4. In this case, the extraction unit 42 and the analysis unit 44 are provided in the external device.

[0049] The deriving unit 46 then derives an evaluation value for each of the abnormal shadows represented by the acquired information as a target for the radiology report. The deriving unit 46 derives the evaluation value for the abnormal shadow depending on the type of the abnormal shadow.

[0050] Specifically, the deriving unit 46 refers to the evaluation value table 32 and obtains, for each of the plurality of abnormal shadows, an evaluation value associated with the type of the abnormal shadow, thereby deriving an evaluation value for each of the plurality of abnormal shadows.

[0051] The generation unit 48 generates text including a description of at least one of the plurality of abnormal shadows based on the evaluation value derived by the derivation unit 46. In this embodiment, the generation unit 48 generates text in a sentence format including findings regarding the plurality of abnormal shadows. At this time, the generation unit 48 determines the order in which the findings of the abnormal shadows to be included in the text according to the evaluation value. Specifically, the generation unit 48 generates text including the findings of the plurality of abnormal shadows in order from highest to lowest evaluation value.

[0052] When generating a finding sentence, the generation unit 48 generates the finding sentence, for example, by inputting the finding into a recurrent neural network that has been trained to generate text from input words. Fig. 5 shows an example of text including finding sentences for multiple abnormal shadows generated by the generation unit 48. The example in Fig. 5 shows a sentence-format text including, in descending order of evaluation value, a finding sentence summarizing findings for two abnormal shadows of hepatocellular carcinoma and a finding sentence summarizing findings for three abnormal shadows of liver cysts.

[0053] The generation unit 48 may generate text including descriptions of multiple abnormal shadows in a bulleted format or in a table format. FIG. 6 shows an example of text generated in a bulleted format, and FIG. 7 shows an example of text generated in a table format. In the example of FIG. 6, similar to the example of FIG. 5, bulleted text including a statement summarizing findings for two abnormal shadows of hepatocellular carcinoma and a statement summarizing findings for three abnormal shadows of liver cysts is shown. In the example of FIG. 7, tabular text including findings for each of the two abnormal shadows of hepatocellular carcinoma and each of the three abnormal shadows of liver cysts is shown. Furthermore, as shown in FIG. 10 as an example, the generation unit 48 may generate text including descriptions of multiple abnormal shadows in a tab-switchable format. The upper part of FIG. 10 shows an example in which a tab with an evaluation value of "High" is specified, and the lower part of FIG. 10 shows an example in which a tab with an evaluation value of "Low" is specified.

[0054] The display control unit 50 controls the display of the text generated by the generation unit 48 on the display 23. The user corrects the text displayed on the display 23 as necessary and creates an interpretation report.

[0055] Next, the operation of the document creation support device 10 according to this embodiment will be described with reference to Fig. 8. The document creation support process shown in Fig. 8 is executed by the CPU 20 executing the document creation support program 30. The document creation support process shown in Fig. 8 is executed, for example, when a command to start execution is input by the user.

[0056] 8, the acquisition unit 40 acquires a diagnostic target image from the image server 5 via the network I / F 25. In step S12, the extraction unit 42, as described above, uses the trained model M1 to extract regions including abnormal shadows in the diagnostic target image acquired in step S10. In step S14, the analysis unit 44, as described above, uses the trained model M2 to analyze each abnormal shadow extracted in step S12 and derive findings of the abnormal shadow.

[0057] In step S16, as described above, the derivation unit 46 refers to the evaluation value table 32 and obtains, for each of the plurality of abnormal shadows extracted in step S12, the evaluation value associated with the type of abnormal shadow derived in step S14, thereby deriving an evaluation value for each of the plurality of abnormal shadows.

[0058] In step S18, the generation unit 48 generates text including a description of the multiple abnormal shadows extracted in step S12 based on the evaluation value derived in step S16, as described above. In step S20, the display control unit 50 controls the display of the text generated in step S18 on the display 23. When the processing of step S20 ends, the document creation support processing ends.

[0059] As described above, according to this embodiment, it is possible to appropriately support the creation of medical documents even when a medical image includes multiple regions of interest.

[0060] In the above embodiment, a case where an abnormal shadow region is applied as the region of interest has been described, but the present invention is not limited to this. An organ region or an anatomical structure region may be applied as the region of interest. When an organ region is applied as the region of interest, the type of region of interest refers to the name of the organ. When an anatomical structure region is applied as the region of interest, the type of region of interest refers to the name of the anatomical structure.

[0061] Furthermore, in the above embodiment, the generation unit 48 determines the order of the findings of abnormal shadows to be included in the text based on the evaluation value. However, the present invention is not limited to this. The generation unit 48 may determine, from among multiple abnormal shadows, which abnormal shadows to include in the text based on the evaluation value. In this case, the generation unit 48 may include, in the text, only abnormal shadows with evaluation values ​​equal to or greater than a threshold value. An example of text in this embodiment is shown in FIG. 9. The example in FIG. 9 shows text that includes findings summarizing findings for two abnormal shadows of hepatocellular carcinoma with an evaluation value of "High," but does not include findings for three abnormal shadows of liver cysts with an evaluation value of "Low."

[0062] Alternatively, for example, the generation unit 48 may determine whether to include characteristics of an abnormal shadow in the text based on the evaluation value. In this case, the generation unit 48 may include, in the text, a finding statement indicating the characteristics of an abnormal shadow for an abnormal shadow with an evaluation value equal to or greater than a threshold value among a plurality of abnormal shadows. In this case, the generation unit 48 may include, in the text, the type of abnormal shadow for an abnormal shadow with an evaluation value less than a threshold value among a plurality of abnormal shadows, but may not include, in the text, a finding statement indicating the characteristics of the abnormal shadow. Specifically, as shown in FIGS. 5 and 6 , the generation unit 48 may include, in the text, a finding statement indicating the type of abnormal shadow and the characteristics of the abnormal shadow for an abnormal shadow of hepatocellular carcinoma with an evaluation value of “High,” and may include, in the text, a finding statement indicating the type of abnormal shadow for an abnormal shadow of a liver cyst with an evaluation value of “Low,” but may not include, in the text, a finding statement indicating the characteristics of the abnormal shadow.

[0063] Alternatively, for example, the generation unit 48 may determine the amount of description of an abnormal shadow to be included in the text depending on the evaluation value. In this case, the generation unit 48 may increase the upper limit of the number of characters for the description of the abnormal shadow to be included in the text as the evaluation value of the abnormal shadow to be included in the text increases. Alternatively, for example, the generation unit 48 may generate text including descriptions of abnormal shadows in descending order of evaluation value, with the upper limit being a predetermined number of characters. In this case, the upper limit may be changeable by the user by operating a scroll bar, etc.

[0064] Furthermore, when displaying the text generated by the generation unit 48 on the display 23, the display control unit 50 may change the display mode of the description regarding the abnormal shadow included in the text depending on the evaluation value. Specifically, as shown in FIG. 11 as an example, the display control unit 50 controls the display of the description regarding the abnormal shadow whose evaluation value is equal to or greater than a threshold (e.g., evaluation value "High") in black text, and the description regarding the abnormal shadow whose evaluation value is less than the threshold (e.g., evaluation value "Low") in gray text, which is a lighter color than black. When the user performs an operation such as clicking on the description regarding the abnormal shadow whose evaluation value is less than the threshold, the display control unit 50 may display the description in the same mode as the description regarding the abnormal shadow whose evaluation value is equal to or greater than the threshold. Furthermore, the user may be able to merge the description regarding the abnormal shadow whose evaluation value is less than the threshold with the description regarding the abnormal shadow whose evaluation value is equal to or greater than the threshold by dragging and dropping it.

[0065] Furthermore, for example, the display control unit 50 may perform control to display, in response to a user instruction, a description regarding an abnormal shadow that was not displayed on the display 23 according to the evaluation value. Furthermore, when the user manually inputs text for the displayed text, the display control unit 50 may perform control to display a description similar to the text manually input by the user from among descriptions regarding abnormal shadows whose evaluation value is less than a threshold value.

[0066] Furthermore, for example, the generating unit 48 may correct the evaluation value according to the examination purpose of the diagnostic target image. Specifically, the generating unit 48 corrects the evaluation value of an abnormal shadow that matches the examination purpose of the diagnostic target image to a higher value. For example, if the examination purpose is "presence or absence of emphysema," the generating unit 48 corrects the evaluation value of an abnormal shadow including emphysema to a higher value. For example, if the examination purpose is "checking the size of an aneurysm," the generating unit 48 corrects the evaluation value of an abnormal shadow including an aneurysm to a higher value.

[0067] In the above embodiment, the derivation unit 46 derives an evaluation value for each of a plurality of abnormal shadows according to the type of abnormal shadow. However, this is not limiting. For example, the derivation unit 46 may derive an evaluation value according to whether or not the same abnormal shadow has changed from the same abnormal shadow detected in a previous examination. In this case, the derivation unit 46 may set a higher evaluation value for an abnormal shadow that has changed from the previous medical image, among the abnormal shadows included in the most recent diagnostic target image, when the same abnormal shadow has been detected in a medical image of the same subject and the same imaging site in a previous examination. The evaluation value for an abnormal shadow that has changed from the previous medical image may be higher than the evaluation value for an abnormal shadow that has not changed. This is useful for following up on abnormal shadows detected in previous examinations. Examples of changes in abnormal shadows include changes in the size of the abnormal shadow and changes in the progression of a disease. In this case, the derivation unit 46 may ignore errors by considering changes that are less than a predetermined amount as no change.

[0068] Alternatively, for example, the derivation unit 46 may derive the evaluation value depending on whether the same abnormal shadow was detected in a previous examination. In this case, the derivation unit 46 may set a higher evaluation value for an abnormal shadow included in the most recent diagnostic target image, which was not detected in a medical image of the same subject and the same imaging site in a previous examination, than for a detected abnormal shadow. This is useful for drawing the user's attention to a newly appeared abnormal shadow. Alternatively, for example, the derivation unit 46 may set the highest evaluation value for an abnormal shadow that has been previously reported in an image interpretation report.

[0069] Furthermore, for example, when displaying text, the display control unit 50 may control the display of a description of an abnormal shadow that has a higher evaluation value than when it was detected in a previous examination so that it can be distinguished from other descriptions of abnormal shadows. Specifically, the display control unit 50 controls the display of a description of an abnormal shadow that had an evaluation value below a threshold when it was detected in a previous examination and has an evaluation value equal to or greater than the threshold in the current examination so that it can be distinguished from other descriptions of abnormal shadows. In this case, an example of a distinguishable display is to use a different font size or a different font color.

[0070] Furthermore, the above multiple evaluation values ​​may be combined. In this case, the evaluation value is calculated, for example, by the following formula (1). Evaluation value = V1 × V2 × V3 (1) V1 is, for example, an evaluation value that is quantified and set in advance for each type of abnormal shadow in the evaluation value table 32. V2 is, for example, a value that indicates whether there is a change from the same abnormal shadow detected in a previous examination and whether the same abnormal shadow was detected in the previous examination. For example, V2 is set to "1.0" if the same abnormal shadow was detected in the previous examination and there was a change; "0.5" if the same abnormal shadow was detected in the previous examination and there was no change; and "1.0" if the same abnormal shadow was not detected in the previous examination. Furthermore, V3 is set to "1.0" if the abnormal shadow matches the examination purpose of the diagnostic target image and "0.5" if the abnormal shadow does not match the examination purpose of the diagnostic target image.

[0071] In the above embodiment, the document creation support device 10 may present the evaluation value derived by the derivation unit 46 to the user and accept the evaluation value modified by the user. In this case, the generation unit 48 generates text using the evaluation value modified by the user.

[0072] 12, the display control unit 50 controls the display of the evaluation value derived by the derivation unit 46 on the display 23. When the user modifies the evaluation value and then performs an operation to confirm the evaluation value, the generation unit 48 generates text using the evaluation value that reflects the user's modification.

[0073] As an example, as shown in FIG. 13, when the display control unit 50 controls the display of the text generated by the generation unit 48 on the display 23, the display control unit 50 may also control the display of the evaluation value derived by the derivation unit 46 together with the text.

[0074] Furthermore, in the above embodiment, the following various processors can be used as the hardware structure of processing units that perform various processes, such as the acquisition unit 40, extraction unit 42, analysis unit 44, derivation unit 46, generation unit 48, and display control unit 50. 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), 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).

[0075] 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.

[0076] 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 the 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.

[0077] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements.

[0078] In the above embodiment, the document creation support program 30 is pre-stored (installed) in the storage unit 22, but the present invention is not limited to this. The document creation support program 30 may be provided in a form recorded on a recording medium such as a CD-ROM (Compact Disc Read Only Memory), a DVD-ROM (Digital Versatile Disc Read Only Memory), or a USB (Universal Serial Bus) memory. The document creation support program 30 may also be downloaded from an external device via a network.

[0079] The disclosures of Japanese Patent Application No. 2021-073618, filed on April 23, 2021, and Japanese Patent Application No. 2021-208522, filed on December 22, 2021, are incorporated herein by reference in their entirety. In addition, 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 was specifically and individually indicated to be incorporated by reference.

Claims

1. A document creation support device including at least one processor, The processor: obtaining information representing a plurality of regions of interest contained in a medical image; deriving an evaluation index for each of the plurality of regions of interest as a target of the medical document; generating a text including a description of at least one of the plurality of regions of interest based on the evaluation index; Document creation support device.

2. The processor: determining, from among the plurality of regions of interest, a region of interest to be included in the text in accordance with the evaluation index; 2. The document creation support device according to claim 1.

3. The processor: and determining whether or not to include features in the text for the region of interest to be included in the text in accordance with the evaluation index.

2. The document creation support device according to claim 1.

4. The processor: A description order of the regions of interest to be included in the text is determined according to the evaluation index.

4. The document creation support device according to claim 1.

5. The processor: The amount of description of the text is determined according to the evaluation index for the region of interest to be included in the text.

2. The document creation support device according to claim 1.

6. The evaluation index is an evaluation value, The processor: A text including a description of the region of interest in descending order of the region of interest having the highest evaluation value is generated, the text having a predetermined upper limit of the number of characters.

2. The document creation support device according to claim 1.

7. The processor: Generate the text in sentence form 2. The document creation support device according to claim 1.

8. The processor: Generate the text in bulleted or tabular format 2. The document creation support device according to claim 1.

9. The processor: Deriving the evaluation index according to the type of the region of interest.

2. The document creation support device according to claim 1.

10. The processor: The evaluation index is derived depending on whether or not there is a change from the same region of interest detected in a previous examination.

2. The document creation support device according to claim 1.

11. The evaluation index is an evaluation value, The processor: The evaluation value of a region of interest that has changed from the same region of interest detected in a previous inspection is set higher than the evaluation value of a region of interest that has not changed. The document creation support device according to claim 10.

12. The processor: The evaluation index is derived depending on whether the same region of interest was detected in a previous examination.

2. The document creation support device according to claim 1.

13. The region of interest is a region including an abnormal shadow.

2. The document creation support device according to claim 1.

14. The evaluation index is an evaluation value, The processor: When displaying the text, a description of a region of interest for which the evaluation value is higher than when detected in a past inspection is displayed in a manner that makes it distinguishable from descriptions of other regions of interest.

2. The document creation support device according to claim 1.

15. The processor: A display mode of a description relating to the region of interest included in the text is changed according to the evaluation index.

2. The document creation support device according to claim 1.

16. The processor: Controlling the display of the derived evaluation index; Accepting modifications to the evaluation index; Generate the text based on the evaluation index that reflects the received corrections.

2. The document creation support device according to claim 1.

17. obtaining information representing a plurality of regions of interest contained in a medical image; deriving an evaluation index for each of the plurality of regions of interest as a target of the medical document; generating a text including a description of at least one of the plurality of regions of interest based on the evaluation index; A document creation support method in which processing is executed by a processor provided in a document creation support device.

18. obtaining information representing a plurality of regions of interest contained in a medical image; deriving an evaluation index for each of the plurality of regions of interest as a target of the medical document; generating a text including a description of at least one of the plurality of regions of interest based on the evaluation index; A document creation support program for causing a processor included in the document creation support device to execute processing.

Images