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

Abstract

This document preparation assistance device is provided with at least one processor. The processor performs a process of generating a text describing the class of a disease regarding at least one feature portion included in an image, and incorporating, into the text, a description relating to a relevant portion that is relevant to the class of the disease described in the text.

Description

[Technical Field]

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

[0002] The following technologies are known as technologies related to document creation support devices that create text that can be applied to documents such as radiology reports based on medical images. For example, Japanese Patent Application Laid-Open No. 2017-29411 describes a medical document creation device that identifies attribute information related to attribute information acquired in response to user operations, collects finding information including the identified attribute information, and displays the collected finding information side by side on a display unit.

[0003] Japanese Patent Publication No. 2020-181288 describes a medical information processing device that includes a reception unit that receives the selection of a target area or target disease, an extraction unit that extracts a past first event corresponding to the selected target area or target disease and a past second event corresponding to an area or disease related to the target area or target disease, and a display control unit that maps and displays the first event and the second event on a schema. Summary of the Invention [Problem to be solved by the invention]

[0004] It is expected that an interpretation report created based on a medical image will include a description of a disease found in the medical image. Depending on the classification of the disease, it may be preferable to note that another disease may occur concomitantly at a site other than the site of onset of the disease. For example, if a pulmonary nodule is found in the medical image, it is preferable to note that pleural effusion may also occur concomitantly. In this case, it is preferable that the interpretation report includes not only a description of the pulmonary nodule but also a description of the pleural effusion.

[0005] The disclosed technology has been developed in consideration of the above points, and aims to include in the text, in automatic generation of text based on an image, descriptions of parts other than the onset part of the main disease described in the text. [Means for solving the problem]

[0006] A document creation support device according to the disclosed technology includes at least one processor that generates text describing a disease classification for at least one characteristic portion included in an image, and includes in the text a description of a relevant portion related to the disease classification described in the text.

[0007] The processor may include a description of a relevant portion in the text when the classification of a disease described in the text is a specific classification. The processor may include a description of a relevant portion in the text when the classification of a disease described in the text is malignant. The processor may accept designation of a characteristic portion and include a description of a relevant portion related to the classification of a disease corresponding to the designated characteristic portion in the text.

[0008] The document creation support method according to the disclosed technology generates text describing a disease classification for at least one characteristic part contained in an image, and at least one processor provided in an information processing device executes a process of including in the text a description of relevant parts related to the disease classification described in the text.

[0009] The program related to the disclosed technology is a program for causing at least one processor provided in an information processing device to execute a process of generating text describing a disease classification for at least one characteristic part contained in an image and including in the text a description of relevant parts related to the disease classification described in the text. [Effects of the Invention]

[0010] According to the disclosed technology, in the automatic generation of text based on an image, it is possible to include in the text a description of a part other than the onset part of the main disease described in the text. [Brief explanation of the drawings]

[0011] [Figure 1] 1 is a diagram illustrating a schematic configuration of a medical information system according to an embodiment of the disclosed technology. [Figure 2] FIG. 1 is a diagram illustrating an example of a hardware configuration of a document creation support device according to an embodiment of the disclosed technology. [Figure 3] 1 is a functional block diagram illustrating an example of a functional configuration of a document creation support device according to an embodiment of the disclosed technology. [Figure 4] 1 is a diagram illustrating functions of a document creation support device according to an embodiment of the disclosed technology; [Figure 5] FIG. 10 is a diagram illustrating an example of a related part table according to an embodiment of the disclosed technique. [Figure 6] FIG. 1 is a diagram illustrating an example of a schematic configuration of a recurrent neural network that constitutes a text generation unit according to an embodiment of the disclosed technology. [Figure 7] 10A and 10B are diagrams illustrating an example of a display mode of information displayed on a display screen according to an embodiment of the disclosed technology. [Figure 8] 10 is a flowchart illustrating an example of the flow of a document creation support process according to an embodiment of the disclosed technique. [Figure 9] 1 is a functional block diagram illustrating an example of a functional configuration of a document creation support device according to an embodiment of the disclosed technology. DETAILED DESCRIPTION OF THE INVENTION

[0012] Hereinafter, embodiments of the disclosed technology will be described with reference to the drawings. In each drawing, substantially the same or equivalent components or parts are designated by the same reference numerals.

[0013] [First embodiment] 1 is a diagram showing a schematic configuration of a medical information system 1 to which a document creation support device according to an embodiment of the disclosed technology is applied. The medical information system 1 is a system for capturing images of a subject's examination target region, 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.

[0014] The medical information system 1 is composed of multiple imaging devices 2, multiple interpretation workstations (WS) 3 which are interpretation terminals, department workstations (WS) 4, an image server 5, an image database 6, an interpretation report server 7, and an interpretation report database 8, all connected in a state where they can communicate with each other via a wired or wireless network 9.

[0015] 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 recorded on a recording medium such as a DVD (Digital Versatile Disc) or a CD-ROM (Compact Disc Read Only Memory) and distributed, and then installed on the computer from the recording medium. Alternatively, the application program is stored in a storage device of a server computer connected to the network 9 or in network storage in an externally accessible state, and is downloaded to the computer upon request and installed.

[0016] The imaging device 2 is a device that generates a medical image representing a diagnostic target part of a subject by capturing an image of the diagnostic target part. The imaging device 2 may be, for example, a plain X-ray imaging device, a CT device, an MRI 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.

[0017] The department WS4 is a computer used by doctors in the department to perform detailed observations of medical images, 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 department WS4 executes software programs for each process, such as creating patient medical records (electronic medical records), requesting the image server 5 to view images, displaying medical images received from the image server 5, 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.

[0018] 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 an image database 6 that includes storage. The image database 6 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) that is connected to the network 9. 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 database 6.

[0019] The image database 6 stores image data of 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 for identifying each medical image, a patient ID (identification) for identifying the patient who is the subject, an examination ID for identifying the examination details, a unique ID (UID) assigned to each medical image, 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 such as the patient's name, age, and gender, the examination site (imaging site), imaging information (imaging protocol, imaging sequence, imaging technique, imaging conditions, use of contrast agent, etc.), and a series number or acquisition number when multiple medical images are acquired in a single examination. Furthermore, upon receiving a viewing request from the image interpretation WS 3 via the network 9, the image server 5 searches for medical images registered in the image database 6 and transmits the searched medical images to the image interpretation WS 3 that made the request.

[0020] A software program that provides a general-purpose computer with the functions of a database management system 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 database 8 for the image interpretation report.

[0021] The radiological report database 8 stores radiological reports that include 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.

[0022] 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 by connecting 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.

[0023] The image interpretation WS3 executes software programs for various processes, such as requests to the image server 5 for viewing medical images, various image processing of medical images received from the image server 5, display of medical images, analysis of medical images, highlighting of medical images based on the analysis results, creation of image interpretation reports based on the analysis results, support for creation of image interpretation reports, requests to the image interpretation report server 7 for registration and viewing of image interpretation reports, and display of image interpretation reports received from the image interpretation report server 7. The image interpretation WS3 incorporates a document creation support device 10 (described below). Since processes other than those performed by the document creation support device 10 are performed by well-known software programs, 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 those 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 incorporated in the image interpretation WS3 will be described in detail below.

[0024] FIG. 2 is a diagram illustrating an example of the hardware configuration of the document creation support device 10. The document creation support device 10 includes a CPU (Central Processing Unit) 101, a memory 102, a storage unit 103, a display unit 104 including a display device such as a liquid crystal display, an input unit 105 including input devices such as a keyboard and a mouse, and an external I / F (Interface) 106. The input unit 105 may include a microphone for receiving voice input. The CPU 101, the memory 102, the storage unit 103, the display unit 104, the input unit 105, and the external I / F 106 are connected to a bus 107. The document creation support device 10 is connected to the network 9 of the medical information system 1 via the external I / F 106. The CPU 101 is an example of a processor in the disclosed technology.

[0025] The storage unit 103 is realized by a non-volatile storage medium such as a hard disk drive (HDD), a solid state drive (SSD), or a flash memory. The storage unit 103 stores a document creation support program 108 and a related part table 30 (described later). The document creation support program 108 is recorded on a recording medium such as a DVD or a CD-ROM and distributed, and is installed in the document creation support device 10 from the recording medium. Alternatively, the document creation support program 108 is stored in a storage device of a server computer connected to a network or in network storage in an externally accessible state, and is downloaded to and installed in the document creation support device 10 upon request. The CPU 101 reads the document creation support program 108 from the storage unit 103, expands it in the memory 102, and executes the expanded document creation support program 108.

[0026] 3 is a functional block diagram showing an example of the functional configuration of the document creation support device 10. The document creation support device 10 has an image acquisition unit 11, a characteristic part extraction unit 12, a characteristic part analysis unit 13, a related part analysis unit 14, a text generation unit 15, and a display control unit 16. The document creation support device 10 functions as the image acquisition unit 11, the characteristic part extraction unit 12, the characteristic part analysis unit 13, the related part analysis unit 14, the text generation unit 15, and the display control unit 16 when the CPU 101 executes the document creation support program 108.

[0027] The image acquisition unit 11 acquires medical images to be diagnosed (hereinafter referred to as diagnostic target images). The diagnostic target images are stored in the image database 6, and are transmitted from the image database 6 to the document creation support device 10 in response to a request from the document creation support device 10 (image interpretation workstation 3), and are stored in the storage unit 103. The image acquisition unit 11 acquires the diagnostic target images stored in the storage unit 103. The image acquisition unit 11 may also acquire the diagnostic target images stored in the image database 6 directly from the image database 6. In the following, an example will be described in which the diagnostic target images are chest CT images.

[0028] The feature portion extraction unit 12 extracts, as feature portions, shadows that are suspected to be diseased, such as nodules or tumors (hereinafter referred to as abnormal shadows), from the diagnostic target image acquired by the image acquisition unit 11. The feature portion extraction unit 12 may extract abnormal shadows using a trained model trained by machine learning such as deep learning. The trained model is trained by machine learning using, for example, multiple combinations of medical images that include abnormal shadows and information that identifies the areas in the images where the abnormal shadows exist, as training data. Completed study The extraction model takes a medical image as input and outputs the results of identifying an abnormal shadow area in the medical image. Figure 4 shows an example in which an abnormal shadow 210 is extracted from a diagnostic image 200.

[0029] The feature part analysis unit 13 analyzes the abnormal shadow extracted from the image to be diagnosed, and identifies the classification of the disease corresponding to the abnormal shadow. The classification of the disease includes, for example, the name of the disease and the diagnosis, such as nodule, hemangioma, cyst, lymph node enlargement, pleural effusion, hamartoma, etc., and also includes the classification of whether the disease is benign or malignant (cancer). The feature part analysis unit 13 may identify the classification of the disease using a trained model trained by machine learning, such as deep learning. The trained model is trained by machine learning using training data in which the classification of the disease corresponding to the abnormal shadow is assigned as a correct answer label to a medical image containing the abnormal shadow. Completed study The model takes a medical image as input and outputs a classification of a disease corresponding to an abnormal shadow contained in the medical image.

[0030] The characteristic part analysis unit 13 also analyzes the abnormal shadow extracted by the characteristic part extraction unit 12 to identify the characteristics of the abnormal shadow for each of a plurality of predetermined characteristic items. Examples of characteristic items identified for an abnormal shadow include the position, size, presence or absence of spicules, presence or absence of irregular margins, whether the abnormal shadow is solid or not, whether the abnormal shadow is partially solid or not, and presence or absence of pleural indentation.

[0031] The feature portion analysis unit 13 may identify the characteristics of an abnormal shadow using a trained model trained by machine learning such as deep learning. The trained model is trained by machine learning using, for example, a plurality of combinations of medical images including an abnormal shadow and characteristic labels indicating the characteristics of the abnormal shadow as training data. Completed study The model takes a medical image as input and outputs an attribute score derived for each attribute item in the abnormal shadow contained in the medical image. The attribute score indicates the prominence of the attribute for the attribute item. The attribute score takes a value between 0 and 1, for example, and the larger the attribute score value, the more prominent the attribute.

[0032] For example, when the attribute score for "presence or absence of spicules," which is one of the attribute items of an abnormal shadow, is 0.5 or more, the characteristic part analysis unit 13 determines that the attribute of the "presence or absence of spicules" of the abnormal shadow is "spicules present (positive)," and when the attribute score for "presence or absence of spicules" is less than 0.5, the characteristic part analysis unit 13 determines that the attribute of the "presence or absence of spicules" of the abnormal shadow is "spicules absent (negative)." Note that the threshold value of 0.5 used for attribute determination is merely an example, and an appropriate value is set for each attribute item.

[0033] In FIG. 4, the disease classification corresponding to the abnormal shadow 210 extracted from the diagnostic image 200 is identified as "nodule," and the characteristics of the abnormal shadow 210 are identified as "left upper lobe," "3 cm in size," "solid+," "spicules+," and "marginal Adjustment The examples shown are those in which " " was identified. The "+" mark next to the identified characteristic indicates that the characteristic is positive.

[0034] The related part analysis unit 14 identifies related parts related to the disease classification identified by the characteristic part analysis unit 13 and performs a judgment on predetermined judgment items for the identified related parts. A related part is a part in the diagnostic target image where another disease classification (e.g., pleural effusion) that is expected to occur together with the disease classification (e.g., nodule) corresponding to the abnormal shadow (characteristic part) may occur. When identifying related parts, the related part analysis unit 14 refers to a related part table 30 stored in the storage unit 103. The related part table 30 records related parts related to each disease classification in association with the classification. The related part table 30 may be created based on knowledge obtained from past cases.

[0035] FIG. 5 is an example of the related part table 30. The related part table 30 is stored in the storage unit 103. For example, a "nodule," which is one of the disease classifications, is expected to develop together with "pleural effusion" and "lymphadenopathy." Therefore, in the related part table 30, the "space between the visceral pleura and the parietal pleura," where "pleural effusion" can develop, is associated with the "nodule" as a first related part, and the "lymph node," where "lymphadenopathy" can develop, is associated with the "nodule" as a second related part. Furthermore, in the related part table 30, "presence or absence of pleural effusion" is associated as a determination item for the first related part, and "presence or absence of lymphadenopathy" is associated as a determination item for the second related part.

[0036] When the disease classification of an abnormal shadow identified by the characteristic part analysis unit 13 is "nodule," the relevant part analysis unit 14 identifies "between the visceral pleura and parietal pleura" as a first relevant part based on the relevant part table 30 and determines "the presence or absence of pleural effusion" for the first relevant part. Furthermore, the relevant part analysis unit 14 identifies "lymph node" as a second relevant part based on the relevant part table 30 and determines "the presence or absence of lymphadenopathy" for the second relevant part. Figure 4 shows an example in which "pleural effusion -" is derived as the determination result for the first relevant part, and "lymphadenopathy -" is derived as the determination result for the second relevant part. The "-" notation in the derived determination result indicates a negative finding. When determining the relevant parts, the relevant part analysis unit 14 may use an image different from the diagnostic target image used to extract and analyze the abnormal shadow. For example, the determination of the related parts may be performed using a chest CT image of a slice different from the slice where the abnormal shadow was extracted and analyzed. Depending on the disease classification, there may be no related parts to be associated. For example, for "atelectasis," there are no other diseases that are expected to occur together with atelectasis, so the related part column associated with "atelectasis" in the related part table 30 shown in FIG. 5 is left blank.

[0037] The text generation unit 15 generates text describing the disease classification identified by the characteristic portion analysis unit 13 for the abnormal shadow extracted by the characteristic portion extraction unit 12. The text may include a description of the properties of the abnormal shadow identified by the characteristic portion analysis unit 13. The text generation unit 15 also includes a description of a relevant portion related to the disease classification described in the text. The text generation unit 15 generates the description of the relevant portion based on the determination result for the relevant portion derived by the relevant portion analysis unit 14.

[0038] To explain the processing by the text generator 15, the following case will be considered as an example. As shown in FIG. 4, the characteristic part analyzer 13 identifies "nodule" as the classification of the disease corresponding to the abnormal shadow 210 extracted from the diagnostic target image 200, and identifies "left upper lobe," "3 cm in size," "solid+," "spicules+," and "marginal insufficiency" as the properties of the abnormal shadow 210. Adjustment Assume that the relevant portion analysis unit 14 has identified "+" as the first relevant portion related to the "nodule" and determined that "no pleural effusion" exists for "between the visceral pleura and parietal pleura" and "no lymph node enlargement" as the second relevant portion related to the "nodule." In this case, the text generation unit 15 generates, as an example, text such as "A 3-cm solid nodule is observed in the left upper lobe. It is accompanied by spicules and has irregular margins. No pleural effusion is observed. No lymph node enlargement is observed." In other words, the text generation unit 15 generates text that includes the description "nodule" as a description related to the classification of the disease corresponding to the abnormal shadow, and the descriptions "no pleural effusion is observed" and "no lymph node enlargement is observed" as descriptions related to the relevant portion related to the "nodule."

[0039] The text generation unit 15 includes a recurrent neural network that has been trained to generate text from input words. FIG. 6 is a diagram showing a schematic configuration of a recurrent neural network. As shown in FIG. 6, the recurrent neural network 20 includes an encoder 21 and a decoder 22. The encoder 21 receives input of characters corresponding to the disease classification and characteristics of the abnormal shadow (characteristic portion) identified by the characteristic portion analysis unit 13, as well as the determination result of the related portion derived by the related portion analysis unit 14. FIG. 6 illustrates an example in which the following are input to the encoder 21: "left upper lobe," "3 cm in size," "solid+," "nodule," "spicule+," "irregular margin+," "pleural effusion-," and "lymphadenopathy-." The decoder 22 is trained to convert words input to the encoder 21 into sentences, and generates the following text from the above input words: "A 3 cm solid nodule is observed in the left upper lobe. It is accompanied by spicules and has irregular margins. No pleural effusion is observed. No lymph node enlargement is observed." In Figure 6, "EOS" indicates the end of the sentence.

[0040] The display control unit 16 controls the display unit 104 to display the text generated by the text generation unit 15. FIG. 7 is a diagram showing an example of a display mode of information displayed on the display screen 300 of the display unit 104 under the control of the display control unit 16. As shown in FIG. 7, text 400 generated by the text generation unit 15 is displayed on the display screen 300. Also, a diagnostic target image 200 including an abnormal shadow 210 used to generate the text 400 is displayed on the display screen 300. A mark 220 indicating the position of the abnormal shadow 210 may be added to the diagnostic target image 200. Also, a label (icon) 230 indicating the classification and characteristics of the disease identified for the abnormal shadow 210 and the derived determination results for related parts is displayed on the display screen 300.

[0041] The operation of the document creation support device 10 will be described below. FIG. 8 is a flowchart showing an example of the flow of document creation support processing carried out by the CPU 101 executing the document creation support program 108. The document creation support program 108 is executed, for example, when a command to start execution is input by the user via the input unit 105. It is assumed that the diagnostic target image is downloaded from the image server 5 to the document creation support device 10 (image interpretation workstation 3) and stored in the storage unit 103.

[0042] In step ST11, the image acquisition unit 11 acquires the diagnostic object image stored in the storage unit 103. In step ST12, the feature portion extraction unit 12 extracts the diagnostic object image stored in step ST13. T An abnormal shadow is extracted as a characteristic part from the diagnostic target image acquired in step ST11. In step ST13, the characteristic part analysis unit 13 analyzes the abnormal shadow extracted from the diagnostic target image and identifies the classification and nature of the disease corresponding to the abnormal shadow.

[0043] Step S T In step ST14, the related part analysis unit 14 identifies related parts related to the disease classification identified in step ST13 based on the related part table 30. In step ST15, the related part analysis unit 14 analyzes the related parts identified in step ST14 and makes a judgment on predetermined judgment items for the related parts. The related part analysis unit 14 identifies the judgment items based on the related part table 30.

[0044] In step ST16, the text generator 15 generates text including a description of the classification and characteristics of the disease corresponding to the abnormal shadow identified in step ST13, and a description of the determination result for the relevant portion derived in step ST15.

[0045] In step ST17, the display control unit 16 controls the display of the text generated in step ST16 on the display screen of the display unit 104. The user can use the text displayed on the display unit 104 as part or all of a document (radiology report) that the user creates. The user can also add or modify the text displayed on the display unit 104.

[0046] As described above, according to the document creation support device 10 of the embodiment of the disclosed technology, text generated based on a diagnostic image includes not only a description of the classification of the disease corresponding to the abnormal shadow, but also a description of the relevant portion related to the classification of the disease. In other words, in the automatic generation of text based on an image, it is possible to include a description of a portion other than the onset portion of the main disease described in the text. This makes it possible to effectively support the user in creating documents (radiology reports).

[0047] As shown in FIG. 5 , text describing a disease classification to which no related portion is associated in the related portion table 30 does not include a description regarding the related portion. That is, when the disease classification described in the text is a specific classification, the text generator 15 includes a description regarding the related portion in the text. Furthermore, when the disease classification described in the text is malignant (cancer), the text generator 15 may include a description regarding the related portion in the text. In other words, when the disease classification described in the text is benign, the text may not include a description regarding the related portion. Furthermore, although the present embodiment has exemplified a case in which a description regarding the characteristics of an abnormal shadow is included in the text, the text may not include a description regarding the characteristics of an abnormal shadow.

[0048] [Second embodiment] 9 is a functional block diagram showing an example of the functional configuration of a document creation support device 10 according to a second embodiment of the disclosed technology. The document creation support device 10 according to this embodiment differs from the document creation support device 10 according to the first embodiment (see FIG. 3) in that it has a designation receiving unit 17 instead of the characteristic part extraction unit 12.

[0049] The designation receiving unit 17 receives designation of an abnormal shadow (characteristic portion) included in the diagnostic target image. The abnormal shadow can be designated, for example, by the user clicking or dragging a partial area in the diagnostic target image displayed on the display screen of the display unit 104 using an input device such as a mouse.

[0050] The characteristic part analysis unit 13 analyzes the abnormal shadow related to the designation received by the designation receiving unit 17, and identifies the classification and characteristics of the disease corresponding to the abnormal shadow. The related part analysis unit 14 identifies related parts related to the disease classification identified by the characteristic part analysis unit 13, and makes a judgment on predetermined judgment items for the identified related parts.

[0051] The text generation unit 15 generates text including a description of the classification and characteristics of the disease corresponding to the abnormal shadow related to the designation accepted by the designation acceptance unit 17, and a description of the determination result for the related part identified by the related part analysis unit 14. The display control unit 16 controls the display unit 104 to display the multiple texts generated by the text generation unit 15.

[0052] According to the document creation support device of the second embodiment of the disclosed technology, text is generated for the abnormal shadow (characteristic part) specified by the user, thereby making it possible to effectively support the user in creating a document (radiology report).

[0053] sentence CalligraphyThe image generation support device may generate and display text as follows. For example, before receiving a user's designation of an abnormal shadow (characteristic portion), a plurality of texts may be generated in advance for each of a plurality of abnormal shadows (characteristic portions). After that, when the user designates an abnormal shadow (characteristic portion), the device may select text related to the designated abnormal shadow (characteristic portion) from the plurality of texts generated in advance, and control the display unit 104 to display the selected text. The displayed text includes a description of the relevant portion.

[0054] The following various processors can be used as the hardware structure of the processing unit that executes various processes of the functional units of the document creation support device 10 according to the first and second embodiments. 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 execute specific processes, such as a programmable logic device (PLD) that 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).

[0055] 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.

[0056] 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.

[0057] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements.

[0058] The disclosure of Japanese Patent Application No. 2021-007429, filed on January 20, 2021, is incorporated herein by reference in its 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 having at least one processor, the processor: generating text describing a disease classification for at least one feature included in the image; identifying the relevant part based on a relevant part table in which relevant parts related to each disease category described in the text are recorded in association with each other; making a judgment on predetermined judgment items for the identified relevant portion; The text includes a description of the determination result for the relevant portion. Document creation support device.

2. The processor includes a description of the relevant portion in the text when the classification of the disease described in the text is a specific classification.

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

3. The processor includes a description of the relevant portion in the text if the classification of the disease described in the text is malignant.

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

4. The processor: Accepting designation of the characteristic portion; The text includes a description of relevant parts related to the classification of diseases corresponding to the specified characteristic parts. The document creation support device according to any one of claims 1 to 3.

5. generating text describing a disease classification for at least one feature included in the image; identifying the relevant part based on a relevant part table in which relevant parts related to each disease category described in the text are recorded in association with each other; making a judgment on predetermined judgment items for the identified relevant portion; The text includes a description of the determination result for the relevant portion. A document creation support method in which processing is executed by at least one processor included in an information processing device.

6. generating text describing a disease classification for at least one feature included in the image; identifying the relevant part based on a relevant part table in which relevant parts related to each disease category described in the text are recorded in association with each other; making a judgment on predetermined judgment items for the identified relevant portion; The text includes a description of the determination result for the relevant portion. A program for causing at least one processor included in an information processing device to execute a process.

Images