JP7368592B2 - Document creation support device, method and program - Google Patents

Description

The present disclosure relates to a document creation support device, method, and program that support the creation of documents such as image interpretation reports.

In recent years, advances in medical equipment such as CT (Computed Tomography) devices and MRI (Magnetic Resonance Imaging) devices have made it possible to perform image diagnosis using higher quality, high resolution medical images. In particular, image diagnosis using CT images, MRI images, etc. allows the identification and analysis of lesion areas with high accuracy, making it possible to implement appropriate treatment.

In addition, medical images are analyzed by CAD (Computer-Aided Diagnosis) using a learning model that has been machine learned using deep learning etc., and the shape, density, and position of structures of interest such as abnormal shadow candidates included in the medical images are analyzed. It is also carried out to determine properties such as size and size, and obtain these as analysis results. The analysis results obtained by CAD are stored in a database in association with examination information such as patient name, gender, age, and the modality by which the medical image was obtained. The medical image and analysis results are transmitted to a terminal of an interpreting doctor who interprets the medical image. The image interpreting doctor refers to the transmitted medical image and analysis results on his/her own terminal, interprets the medical image, and creates an image interpretation report.

On the other hand, as the performance of the CT apparatus and MRI apparatus described above increases, the number of medical images to be interpreted is also increasing. However, since the number of image interpreting doctors has not kept up with the number of medical images, it is desired to reduce the burden of image interpretation work on image interpreting doctors. For this reason, various methods have been proposed to support the creation of medical documents such as image interpretation reports. For example, in Japanese Patent Application Laid-open No. 2019-153250, an image interpretation report is created based on information representing the properties of the structure of interest (hereinafter referred to as property information) included in the analysis results of keywords and medical images input by an image interpretation doctor. Various methods have been proposed to automatically generate sentences for writing in documents. The method described in Japanese Patent Application Laid-open No. 2019-153250 uses a learning model that has undergone machine learning such as a recurrent neural network that has been trained to generate sentences from characters representing input property information. , a medical text (hereinafter referred to as a medical text) is generated. By automatically generating medical texts as in the method described in Japanese Unexamined Patent Publication No. 2019-153250, it is possible to reduce the burden on an image interpreting doctor when creating a medical document such as an image interpretation report.

By the way, when creating an image interpretation report, it is necessary to write necessary items in accordance with diagnostic guidelines according to the target disease. Clinical practice guidelines are the latest information on the basis and procedures of medical care such as disease prevention, diagnosis, treatment, and prognosis prediction, provided by experts in an easy-to-understand manner, with the aim of assisting appropriate diagnosis and treatment in medical settings. This is a set of guidelines. For this reason, we maintain a diagnostic guideline database that links information expected to be obtained from medical examinations with information used for disease diagnosis, and accept input of information actually obtained during medical examinations. A method has been proposed for extracting and displaying information used for disease diagnosis from a diagnostic guideline database based on information related to medical examinations (see Japanese Patent Laid-Open No. 2005-110944).

Diagnostic guidelines vary widely for each disease and are constantly revised. Therefore, it is a burden for image interpreting doctors to memorize all the diagnostic guidelines, and they may write an image interpretation report while referring to the latest version of the diagnostic guidelines. However, the task of creating an interpretation report while comparing the diagnostic guidelines and the interpretation report places a heavy burden on the interpretation doctor.

The present disclosure has been made in view of the above circumstances, and aims to reduce the burden on an operator who creates an interpretation report by referring to a diagnostic guideline.

A document creation support device according to the present disclosure includes at least one processor,
The processor identifies, in the image interpretation report representing the image interpretation result, a corresponding portion corresponding to an item included in the diagnostic guideline for the disease described in the image interpretation report,
The image interpretation report and the diagnostic guideline are configured to be displayed on the display by associating corresponding parts in the image interpretation report with items in the diagnostic guideline.

Note that in the document creation support device according to the present disclosure, the processor may be configured to save the results of the association.

Further, in the document creation support device according to the present disclosure, the processor derives analysis results corresponding to the items of the diagnostic guideline by analyzing the medical image, generates an interpretation report based on the analysis results,
The analysis result may be used to identify a portion of the image interpretation report that corresponds to the item of the diagnostic guideline.

Further, in the document creation support device according to the present disclosure, the processor may be configured to identify and display items in the diagnostic guideline that are not included in the interpretation report.

Further, in the document creation support device according to the present disclosure, the diagnostic guideline includes information on the disease stage,
The processor may be configured to identify diagnostic guideline stage information in the interpretation report.

Furthermore, in the document creation support device according to the present disclosure, the disease stage information may be stage information based on TNM classification.

The document creation support method according to the present disclosure identifies, in an interpretation report representing an image interpretation result, a corresponding portion corresponding to an item included in a diagnostic guideline for a disease described in the interpretation report,
Corresponding parts in the image interpretation report and items in the diagnostic guideline are associated with each other, and the image interpretation report and the diagnostic guideline are displayed on the display.

Note that the document support creation method according to the present disclosure may be provided as a program for causing a computer to execute it.

According to the present disclosure, it is possible to reduce the burden on the operator who creates an interpretation report with reference to the diagnostic guidelines.

A diagram showing a schematic configuration of a medical information system to which a document creation support device according to an embodiment of the present disclosure is applied. A diagram showing a schematic configuration of a document creation support device according to the present embodiment Functional configuration diagram of the document creation support device according to this embodiment Diagram for explaining an example of property information Diagram showing the schematic configuration of a recurrent neural network Diagram showing an input medical image and an interpretation report generated from the medical image Diagram showing diagnostic guidelines for lung cancer Diagram showing diagnostic guidelines for lung cancer Diagram showing the display screen of the interpretation report and diagnostic guidelines Diagram showing the display screen of the interpretation report and diagnostic guidelines Diagram showing the display screen of the interpretation report and diagnostic guidelines Flowchart showing processing performed in this embodiment Diagram showing other examples of display screens for interpretation reports and diagnostic guidelines Diagram showing other examples of display screens for interpretation reports and diagnostic guidelines

Embodiments of the present disclosure will be described below with reference to the drawings. First, the configuration of a medical information system 1 to which a document creation support device according to this embodiment is applied will be described. FIG. 1 is a diagram showing a schematic configuration of a medical information system 1. As shown in FIG. The medical information system 1 shown in FIG. 1 is based on an examination order from a doctor in a medical department using a known ordering system, photographs the part of the subject to be examined, stores the medical images acquired by the photograph, and sends them to an interpreting doctor. This is a system for interpreting medical images, creating an interpretation report, viewing the interpretation report by a doctor in the requesting medical department, and making detailed observations of the medical image to be interpreted.

As shown in FIG. 1, the medical information system 1 includes a plurality of imaging devices 2, a plurality of image interpretation WSs (WorkStations) 3 as image interpretation terminals, a medical treatment WS 4, an image server 5, and an image database (hereinafter referred to as image DB (DataBase)). A report server 7 and a report database (hereinafter referred to as report DB) 8 are connected to each other via a wired or wireless network 10 so as to be able to communicate with each other.

Each device is a computer installed with an application program for functioning as a component of the medical information system 1. Application programs are recorded and distributed on recording media such as DVDs (Digital Versatile Discs) and CD-ROMs (Compact Disc Read Only Memory), and are installed on computers from the recording media. Alternatively, it is stored in a storage device of a server computer connected to the network 10 or in a network storage in a state that can be accessed from the outside, and is downloaded and installed in a computer in response to a request.

The imaging device 2 is a device (modality) that generates a medical image representing a region to be diagnosed by photographing a region of a subject to be diagnosed. Specifically, they include a simple X-ray imaging device, a CT device, an MRI device, and a PET (Positron Emission Tomography) device. The medical images generated by the imaging device 2 are transmitted to the image server 5 and stored in the image DB 6.

The image interpretation WS3 is a computer used by, for example, an image interpreter in a radiology department to interpret medical images and create an interpretation report, and includes the document creation support device 20 according to the present embodiment. The image interpretation WS 3 requests the image server 5 to view medical images, performs various image processing on the medical images received from the image server 5, displays the medical images, and accepts input of comments regarding the medical images. In addition, the image interpretation WS 3 performs analysis processing on medical images and input findings, supports the creation of image interpretation reports based on the analysis results, requests registration and viewing of image interpretation reports to the report server 7, and interprets images received from the report server 7. The report is displayed. These processes are performed by the image interpretation WS 3 executing software programs for each process.

The medical treatment WS4 is a computer used by doctors in the medical department to observe images in detail, view interpretation reports, create electronic medical records, etc., and includes a processing device, a display device such as a display, and an input device such as a keyboard and mouse. Consisted of. The medical treatment WS 4 requests the image server 5 to view an image, displays the image received from the image server 5, requests the report server 7 to view an interpretation report, and displays the interpretation report received from the report server 7. These processes are performed by the medical care WS 4 executing software programs for each process.

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 includes a storage in which an image DB 6 is configured. This storage may be a hard disk device connected to the image server 5 by a data bus, or a disk device connected to a NAS (Network Attached Storage) and a SAN (Storage Area Network) connected to the network 10. It may be. Further, upon receiving a medical image registration request from the imaging device 2, the image server 5 formats the medical image into a database format and registers it in the image DB 6. In this embodiment, it is assumed that diagnostic guidelines according to diseases are also stored in the image server 5, but the present invention is not limited to this.

Image data and supplementary information of medical images acquired by the imaging device 2 are registered in the image DB 6. Additional information includes, for example, an image ID (identification) for identifying individual medical images, a patient ID for identifying a subject, an examination ID for identifying an examination, and a unique ID (identification) assigned to each medical image. UID (unique identification), examination date and time when the medical image was generated, type of imaging device used in the examination to obtain the medical image, patient information such as patient name, age, and gender, examination site (imaging This information includes information such as imaging information (imaging protocol, imaging sequence, imaging method, imaging conditions, use of contrast agent, etc.), series number or collection number if multiple medical images are acquired in one examination. .

Further, when the image server 5 receives a viewing request from the image interpretation WS 3 and the medical treatment WS 4 via the network 10, it searches for medical images registered in the image DB 6 and transfers the searched medical images to the requesting image interpretation WS 3 and the treatment WS 4. Send to WS4.

The report server 7 incorporates a software program that provides the functions of a database management system to a general-purpose computer. When the report server 7 receives a request for registration of an image interpretation report from the image interpretation WS 3, the report server 7 formats the image interpretation report into a database format and registers it in the report DB 8.

In the report DB 8, an image interpretation report including at least a finding prepared by an image interpreting doctor using the image interpretation WS3 is registered. The interpretation report includes, for example, a medical image to be interpreted, an image ID for identifying the medical image, an interpretation doctor ID for identifying the interpretation doctor who performed the interpretation, a lesion name, lesion position information, and a medical image including a specific region. It may include information such as information for access and property information.

Further, when the report server 7 receives a request to view an interpretation report from the interpretation WS 3 and the medical treatment WS 4 via the network 10, it searches for the interpretation reports registered in the report DB 8, and transfers the searched interpretation report to the interpretation report of the request source. Send to WS3 and medical treatment WS4.

In this embodiment, the medical image is a three-dimensional CT image consisting of a plurality of tomographic images, with the lung as the diagnosis target, and by interpreting the CT image in the image interpretation WS3, abnormal shadows included in the lung can be detected. An interpretation report shall be prepared. Note that the medical image is not limited to a CT image, and any medical image such as an MRI image and a simple two-dimensional image acquired by a simple X-ray imaging device can be used.

The network 10 is a wired or wireless local area network that connects various devices within the hospital. When the image reading WS 3 is installed in another hospital or clinic, the network 10 may be configured such that the local area networks of each hospital are connected to each other via the Internet or a dedicated line.

Next, a document creation support device according to this embodiment will be explained. FIG. 2 explains the hardware configuration of the document creation support device according to this embodiment. As shown in FIG. 2, the document creation support device 20 includes a CPU (Central Processing Unit) 11, a nonvolatile storage 13, and a memory 16 as a temporary storage area. Further, the document creation support device 20 includes a display 14 such as a liquid crystal display, an input device 15 such as a keyboard and a mouse, and a network I/F (InterFace) 17 connected to the network 10. The CPU 11, storage 13, display 14, input device 15, memory 16, and network I/F 17 are connected to the bus 18. Note that the CPU 11 is an example of a processor in the present disclosure.

The storage 13 is realized by an HDD (Hard Disk Drive), an SSD (Solid State Drive), a flash memory, or the like. A document creation support program 12 is stored in the storage 13 as a storage medium. The CPU 11 reads the document creation support program from the storage 13, expands it into the memory 16, and executes the expanded document creation support program 12.

Next, the functional configuration of the document creation support device according to this embodiment will be explained. FIG. 3 is a diagram showing the functional configuration of the document creation support device according to this embodiment. As shown in FIG. 3, the document creation support device 20 includes an acquisition section 21, a text generation section 22, a specification section 23, a display control section 24, a storage control section 25, and a communication section 26. When the CPU 11 executes the document creation support program, the CPU 11 functions as an acquisition section 21 , a text generation section 22 , a specification section 23 , a display control section 24 , a storage control section 25 , and a communication section 26 .

The acquisition unit 21 acquires a medical image for creating an interpretation report from the image server 5 in response to an instruction from the input device 15 by an operator who is an interpretation doctor. Diagnostic guidelines regarding lung cancer, which is the target disease, are also acquired from the image server 5. The acquired medical images and diagnostic guidelines are stored in the storage 13.

The text generation unit 22 derives an analysis result by analyzing the medical image, and generates an interpretation report based on the analysis result. For this purpose, the text generation unit 22 identifies abnormal shadow candidates in the medical image, and determines the properties of the identified abnormal shadow candidates for each of a plurality of predetermined property items. Examples of characteristic items identified for abnormal shadows include the location of the abnormal shadow, the size of the abnormal shadow, the shape of the border (clear and irregular), the type of absorption value (solid and ground glass), the presence or absence of spicules, and whether it is a mass. Examples include whether it is a nodule, the presence or absence of pleural contact, the presence or absence of pleural invagination, the presence or absence of pleural invasion, the presence or absence of a cavity, and the presence or absence of calcification.

In the present embodiment, the text generation unit 22 has a learning model that has been subjected to machine learning to determine the characteristics of abnormal shadow candidates from medical images. The learning model uses training data to determine, for example, whether each pixel (voxel) in a medical image represents an abnormal shadow candidate, and if it is an abnormal shadow candidate, to determine its characteristics. It consists of a convolutional neural network (CNN) that has undergone deep learning.

The learning model is learned, for example, by machine learning using multiple combinations of medical images including abnormal shadows and property labels representing the properties of the abnormal shadows as training data. The learning model receives a medical image as input, and outputs a property score derived for each property item in an abnormal shadow included in the input medical image. The property score is a score indicating the salience of the property for each property item. The property score takes a value of, for example, 0 or more and 1 or less, and the larger the value of the property score, the more remarkable the property is.

For example, if the property score for "presence or absence of spicules", which is one of the property items of an abnormal shadow, is 0.5 or higher, the property for "presence or absence of spicules" of the abnormal shadow is "with spicules (positive)". If it is specified that there is, and the property score for "presence or absence of spicules" is, for example, less than 0.5, it is specified that the property for the presence or absence of spicules in the abnormal shadow is "no spicules (negative)". Note that the threshold value of 0.5 used for property determination is merely an example, and is set to an appropriate value for each property item.

Note that as a learning model for analyzing medical images, in addition to a convolutional neural network, any learning model such as a support vector machine (SVM) can be used. Further, a learning model for detecting abnormal shadow candidates from medical images and a learning model for detecting property information of abnormal shadow candidates may be constructed separately.

FIG. 4 is a diagram for explaining an example of property information derived by the text generation unit 22. As shown in FIG. 4, in the property information 30 derived by the text generation unit 22, the properties for each property item are "left lung subpleura", "4.2 cm", "irregular", "solid", ``spiculae'', ``mass'', ``pleural contact'', ``pleural invagination'', ``no pleural invasion'', ``no cavity'', and ``no calcification''. In FIG. 4, + is assigned when "present" and - is assigned when absent.

Further, the sentence generation unit 22 generates a finding sentence using the derived property information. In this embodiment, therefore, the sentence generation unit 22 is composed of a learning model trained to generate sentences from input property information. As such a learning model, for example, a recurrent neural network can be used. FIG. 5 is a diagram showing a schematic configuration of a recurrent neural network. As shown in FIG. 5, the recurrent neural network 40 includes an encoder 41 and a decoder 42. The property information derived by the text generation unit 22 is input to the encoder 41 . For example, the encoder 41 receives the property information of "left lung subpleura", "4.2 cm", "spicula +", and "mass". The decoder 42 is trained to convert character information into sentences, and generates sentences from input property information. Specifically, from the above-mentioned information on the properties of "subpleural in the left lung," "4.2 cm," "spicula+," and "mass," we found that "a mass with a diameter of 4.2 cm with a spicula was observed under the pleura in the left lung." Generates a medical sentence that says, Note that in FIG. 5, "EOS" indicates the end of a sentence (End Of Sentence).

In this way, in order to output findings based on the input of property information, the recurrent neural network 40 trains the encoder 41 and decoder 42 using a large amount of training data consisting of combinations of property information and findings. It will be constructed. Note that the generated text shown in FIG. 5 represents findings regarding pulmonary nodules, and is generated by learning a learning model using the property information of pulmonary nodules as input.

Here, by preparing a learning model for deriving property information and a learning model for generating finding statements that the text generation unit 22 has, not only for pulmonary nodules but also for lymph node enlargement, intrapulmonary metastasis, etc. It becomes possible to generate findings regarding pulmonary nodules, lymph node enlargement, intrapulmonary metastasis, and the like. The text generation unit 22 uses these learning models to generate an interpretation report including at least one finding sentence.

FIG. 6 is a diagram showing an interpretation report including an input medical image and a finding statement generated from the medical image. As shown in Figure 6, regarding the input medical image G0, "A solid nodule with a diameter of 17 mm is observed in the upper lobe of the right lung S2, with spiculae at the margin and pleural invagination. Interpretation report 35 is generated saying, "Bronchial lucency is observed. No lymph node enlargement is observed. There is no intrapulmonary metastasis."

Here, the diagnostic guidelines will be explained. As mentioned above, clinical practice guidelines provide experts with the latest information on the basis and procedures for medical care such as disease prevention, diagnosis, treatment, and prognosis prediction, with the aim of assisting appropriate diagnosis and treatment in medical settings. This is a guideline that has been compiled in an easy-to-understand manner. In this embodiment, the acquisition unit 21 acquires diagnostic guidelines for lung cancer and stores them in the storage 13. FIGS. 7 and 8 are diagrams showing diagnostic guidelines for lung cancer. Note that FIG. 7 shows the disease stages based on the TNM classification of lung cancer, and FIG. 8 shows the T factor, N factor, and M factor shown in the disease stages.

As shown in FIG. 7, the stages of lung cancer are classified into stage 0, stage I (IA, IB), stage II (IIA, IIB), stage III (IIIA, IIIB), and stage IV. Note that period 0 is not shown. As shown in FIG. 7, for each stage, the T factor representing cancer size and invasion, the N factor representing metastasis to lymph nodes, and the M factor representing distant metastasis are shown.

Further, as shown in FIG. 8, each factor is classified and defined into multiple stages. For example, factor T is classified into four stages, T1 to T4, depending on the size of cancer and the state of invasion. Note that T1 and T2 are classified more finely as T1a, T1b, T2a, and T2b, respectively. Further, the N factor is classified into three levels, N1 to N3. Note that N0 indicates no lymph node metastasis. Furthermore, the M factor is classified into two levels: M0 when there is no metastasis and M1 when there is metastasis. Note that M1 is classified more finely as M1a and M1b, respectively.

The specifying unit 23 specifies, in the image interpretation report, a corresponding portion corresponding to an item included in the diagnostic guideline for the disease described in the image interpretation report. For this purpose, the specifying unit 23 includes a learning model 23A that is subjected to machine learning so as to specify, as a corresponding portion, a portion corresponding to an item included in the diagnostic guideline in an input sentence. In this embodiment, when an image interpretation report is input, the learning model 23A uses deep learning using training data to identify words and phrases related to items included in the diagnostic guidelines as corresponding parts in the input image interpretation report. It consists of a convolutional neural network (CNN).

The teacher data for learning the learning model 23A consists of words included in the diagnostic guideline items and sentences using the words included in the diagnostic guideline items. Here, as shown in Figure 8, the items in the diagnostic guidelines include T1a for T factor: ``The maximum diameter of the tumor is 2 cm or less'', N0 for N factor: ``No regional lymph node metastasis'', and M factor for M0. Includes “no distant metastasis.” Examples of training data include the words "diameter," "lymph node," "no metastasis," and "no distant metastasis," which are included in the diagnostic guideline items, as well as "nodules with a diameter of 15 mm. Lymph node metastasis. An example of this is the following sentence: "No metastasis found in the lungs." The learning model 23A is constructed by learning a neural network using a large amount of such training data. Thereby, when the image interpretation report is input, the learning model 23A outputs corresponding portions corresponding to items included in the diagnostic guidelines for the disease described in the image interpretation report. Further, upon specifying the corresponding portion in the image interpretation report, the specifying unit 23 specifies an item corresponding to the corresponding portion in the diagnostic guideline.

Note that as the learning model 23A, in addition to the convolutional neural network, any learning model such as a support vector machine and a recurrent neural network can be used.

Further, the specifying unit 23 is not limited to specifying the corresponding portion using the learning model 23A. The corresponding portion may be identified by searching the image interpretation report using the size of the mass and items included in the diagnostic guideline as keywords.

The display control unit 24 displays the image interpretation report and the diagnostic guideline on the display 14 by associating the corresponding portions of the image interpretation report with the items in the diagnostic guideline. FIG. 9 is a diagram showing a display screen of an image interpretation report and a diagnostic guideline. As shown in FIG. 9, the display screen 50 has an image display area 51, an interpretation report display area 52, and a diagnostic guideline display area 53. Below the interpretation report display area 52, a switching button 54, a correction button 55, and a confirmation button 56 are displayed.

The image display area 51 displays a tomographic image S0 included in the medical image G0 for which an interpretation report is to be generated. In the image interpretation report display area 52, the image interpretation report generated by the text generation section 22 is displayed. In the image interpretation report, the corresponding portions identified by the identifying unit 23 are highlighted. As shown in Figures 9 to 11, the three corresponding parts in the interpretation report, ``Diameter 17 mm,'' ``No lymph node enlargement,'' and ``No intrapulmonary metastasis.'' are surrounded by frames. This is highlighted by: Note that these three corresponding portions are highlighted in different ways. In Figures 9 to 11, ``Diameter 17 mm'' is a solid line frame, ``No lymph node enlargement is observed.'' is a broken line frame, and ``No intrapulmonary metastasis.'' is a dot-dashed line frame. There is. Note that instead of using different line types for the frames, the frames may have different colors. Furthermore, instead of providing a frame, the characters may be highlighted or the color of the characters may be changed.

Further, in the diagnostic guideline display area 53, diagnostic guidelines 60A to 60C are displayed. Since the diagnostic guidelines 60A to 60C have a wide variety of contents, by selecting the switching button 54, the contents of the diagnostic guidelines displayed in the diagnostic guideline display area 53 can be changed. Specifically, FIG. 9 displays a diagnostic guideline 60A for T factor and N factor. Further, in FIG. 10, a diagnostic guideline 60B regarding the M factor is displayed. Further, in FIG. 11, a diagnostic guideline 60C regarding the disease stage is displayed. Note that instead of displaying the diagnostic guidelines by switching them, the entire diagnostic guideline may be displayed so as to be referenceable by scrolling.

Here, in the diagnostic guideline 60A shown in FIG. 9, the item T1a corresponding to "diameter 17 mm" in the image interpretation report is highlighted. In FIG. 9, the item T1a is highlighted by being surrounded by a solid line frame 61 similar to the corresponding portion of "diameter 17 mm" in the interpretation report. Furthermore, in the diagnostic guideline 60A shown in FIG. 9, the item N0 corresponding to "no lymph node enlargement observed" in the image interpretation report is also highlighted. In FIG. 9, the item N0 is highlighted by being surrounded by a broken line frame 62 similar to the corresponding portion of "Lymph node enlargement not observed" in the image interpretation report.

Furthermore, in the diagnostic guideline 60B shown in FIG. 10, the item M0 corresponding to "No intrapulmonary metastasis" in the image interpretation report is highlighted. In FIG. 11, the item M0 is highlighted by being surrounded by a dashed-dotted frame 63 similar to the corresponding portion of "There is no intrapulmonary metastasis" in the image interpretation report.

In addition, in the diagnostic guideline 60C shown in Figure 11, the three corresponding parts in the interpretation report: "diameter 17 mm," "no lymph node enlargement," and "no intrapulmonary metastasis." The disease stage derived from the item corresponding to the corresponding part is highlighted. In FIG. 11, stage IA is highlighted. Note that in FIG. 11, the highlighted display is represented by surrounding it with a solid line frame 64.

Note that the highlighting of items in the diagnostic guidelines is not limited to providing frames. Instead of providing a frame, the text may be highlighted or the text color may be changed.

The operator can use the display screen 50 to compare and confirm the interpretation report and the diagnostic guidelines. Further, if necessary, by selecting the correction button 55, the interpretation report displayed in the interpretation report display area 52 can be corrected by inputting from the input device 15. When the confirmation or correction of the image interpretation report is completed, the operator selects the OK button 56.

Note that, when the image interpretation report is corrected, the specifying unit 23 specifies again a corresponding portion corresponding to the item included in the diagnostic guideline in the corrected image interpretation report. In this case, if the corresponding portion is added or deleted, items in the diagnostic guideline will also be added or deleted accordingly.

When the operator selects the confirm button 56, the storage control unit 25 displays the interpretation report with the corresponding portions highlighted, the tomographic image S0 included in the medical image G0 referred to when generating the interpretation report, and the items highlighted. The resulting diagnostic guidelines are also stored in the storage 13.

The communication unit 26 transmits the interpretation report with the corresponding portions highlighted, the tomographic image S0 included in the medical image G0 referred to when generating the interpretation report, and the diagnostic guideline with the items highlighted, together with the network I/O. It is transferred to the report server 7 via F17. The report server 7 also saves an interpretation report with corresponding parts highlighted, the medical image G0 referred to when generating the interpretation report, and a diagnostic guideline with highlighted items.

Next, the processing performed in this embodiment will be explained. FIG. 12 is a flowchart showing the processing performed in the first embodiment. It is assumed that the medical image G0 to be interpreted and the diagnostic guidelines are acquired from the image server 5 by the acquisition unit 21 and stored in the storage 13. The process starts when the interpretation doctor gives an instruction to create an interpretation report, and the text generation unit 22 derives an analysis result by analyzing the medical image G0, and generates an interpretation report based on the analysis result ( Step ST1). Next, the specifying unit 23 specifies, in the image interpretation report, a corresponding portion corresponding to an item included in the diagnostic guideline for the disease described in the image interpretation report (step ST2).

Subsequently, the display control unit 24 displays the image interpretation report and the diagnostic guideline on the display 14 by associating the corresponding portions of the image interpretation report with the items of the diagnostic guideline (step ST3). In this state, the operator switches the diagnostic guidelines displayed in the diagnostic guideline display area 53 on the display screen 50, or modifies the interpretation report displayed in the text display area 51 if necessary.

Next, the storage control unit 25 starts monitoring whether or not the confirm button 56 is selected (step ST4), and if step ST4 is affirmed, the storage control unit 25 saves the image interpretation report with the corresponding portion highlighted. , the tomographic image S0 included in the medical image G0 referred to when generating the image interpretation report and the diagnostic guideline with highlighted items are stored together in the storage 13 (save image interpretation report, etc.; step ST5). Then, the communication unit 26 sends a report via the network I/F 17 together with the interpretation report with the corresponding parts highlighted, the tomographic image S0 referred to when generating the interpretation report, and the diagnostic guideline with the items highlighted. The information is transferred to the server 7 (transfer of image interpretation report, etc.; step ST6), and the process ends.

In this way, in this embodiment, in the image interpretation report, a corresponding portion corresponding to an item included in the diagnostic guideline for the disease described in the image interpretation report is specified, and the corresponding portion in the image interpretation report and the item in the diagnostic guideline are identified. The image interpretation report and diagnostic guidelines are displayed on the display 14 in association with the above. Therefore, it is possible to efficiently create an image interpretation report while comparing the diagnostic guideline and the image interpretation report. Therefore, according to the present embodiment, it is possible to reduce the burden on the operator who creates an interpretation report with reference to the diagnostic guidelines.

In addition, the interpretation report with corresponding parts highlighted, the tomographic image S0 included in the medical image G0 referred to when creating the interpretation report, and the diagnostic guideline with highlighted items are saved or transferred together. Therefore, the patient's attending physician can refer to the correspondence between the image interpretation report and the diagnostic guideline, and as a result, can efficiently diagnose.

Note that in the above embodiment, when displaying the image interpretation report and the diagnostic guideline, items that are not described in the image interpretation report may be specified and displayed in the diagnostic guideline. For example, as shown in Figure 13, the interpretation report states, ``A solid nodule with a diameter of 17 mm was observed in the upper lobe S2 of the right lung, with a spicule at the margin and an image of pleural invagination. "There is no intrapulmonary metastasis.", there is no information regarding lymph node metastasis in the interpretation report. In this case, "lymph node metastasis (N factor)" is highlighted in the diagnostic guideline 60A. Note that in FIG. 13, the highlighted display is indicated by surrounding it with a solid line frame 65. Thereby, the operator can easily recognize which items that should be written in accordance with the diagnostic guidelines are missing in the image interpretation report. Therefore, it is possible to create an interpretation report that complies with diagnostic guidelines.

Further, in the above embodiment, the text generation unit 22 analyzes the medical image G0 and generates the interpretation report, but the present invention is not limited to this. As shown in FIG. 14, the operator may input the interpretation report into the interpretation report display area 52 of the display screen 50 using the input device 15. In this case, the identification unit 23 may identify the corresponding portion corresponding to the diagnostic guideline item in the interpretation report every time a sentence of findings included in the interpretation report is written, and the identification unit 23 may identify the corresponding portion corresponding to the diagnostic guideline item in the interpretation report, and The corresponding portion may be specified from the above. Note that in this case, the text generation unit 22 shown in FIG. 3 is not required.

Further, in the above embodiment, the diagnostic guidelines are stored in the image server 5, but the present invention is not limited to this. A dedicated server for storing diagnostic guidelines may be provided in the medical information system 1, and the diagnostic guidelines may be acquired from this dedicated server.

Further, in the above embodiment, the image interpretation report is generated in the document creation support device 20, but the present invention is not limited to this. The acquisition unit 21 acquires the image interpretation report from the report server 7, and the identifying unit 23 identifies the corresponding part corresponding to the diagnostic guideline item in the acquired image interpretation report, and combines the acquired image interpretation report with the diagnostic guideline. It may also be displayed.

Further, in the embodiment described above, the technology of the present disclosure is applied when an interpretation report is created using a medical image in which the diagnosis target is the lungs, but the diagnosis target is not limited to the lungs. In addition to the lungs, any part of the human body such as the heart, liver, brain, and limbs can be targeted for diagnosis. In this case, a diagnostic guideline corresponding to the region to be diagnosed may be obtained, and a corresponding portion corresponding to an item of the diagnostic guideline in the image interpretation report may be specified.

Further, in each of the above embodiments, processing units (Processing Units) that execute various processes, such as the acquisition unit 21, the text generation unit 22, the identification unit 23, the display control unit 24, the storage control unit 25, and the communication unit 26, are used. As a hardware structure, the following various processors can be used. As mentioned above, the various processors mentioned above include the CPU, which is a general-purpose processor that executes software (programs) and functions as various processing units, as well as circuits such as FPGA (Field Programmable Gate Array) after manufacturing. A programmable logic device (PLD), which is a processor whose configuration can be changed, and a dedicated electrical device, which is a processor with a circuit configuration specifically designed to execute a specific process, such as an ASIC (Application Specific Integrated Circuit) Includes circuits, etc.

One processing unit may be composed of one of these various types of processors, or a combination of two or more processors of the same type or different types (for example, a combination of multiple FPGAs or a combination of a CPU and an FPGA). ). Further, the plurality of processing units may be configured with one processor.

As an example of configuring a plurality of processing units with one processor, firstly, as typified by computers such as a client and a server, one processor is configured with a combination of one or more CPUs and software, There is a form in which this processor functions as a plurality of processing units. Second, there are processors that use a single IC (Integrated Circuit) chip to implement the functions of an entire system including multiple processing units, as typified by System On Chip (SoC). be. In this way, various processing units are configured using one or more of the various processors described above as a hardware structure.

Furthermore, as the hardware structure of these various processors, more specifically, an electric circuit (Circuitry) that is a combination of circuit elements such as semiconductor elements can be used.

1 Medical information system 2 Imaging device 3 Interpretation WS
4 Clinical department WS
5 Image server 6 Image DB
7 Report server 8 Report DB
10 Network 11 CPU
12 Document creation support program 13 Storage 14 Display 15 Input device 16 Memory 17 Network I/F
18 Bus 20 Document creation support device 21 Acquisition unit 22 Text generation unit 23 Specification unit 24 Display control unit 25 Storage control unit 26 Communication unit 30 Property information 35 Interpretation report 40 Recurrent neural network 41 Encoder 42 Decoder 50 Display screen 51 Image display area 52 Interpretation report display area 53 Diagnostic guideline display area 54 Switch button 55 Edit button 56 Confirm button 60A-60C Diagnostic guideline 61-65 Frame

Claims (8)

comprising at least one processor;
The processor includes:
In an image interpretation report representing an image interpretation result, identifying a corresponding portion corresponding to an item included in a diagnostic guideline for the disease described in the image interpretation report,
A document creation support device configured to display the image interpretation report and the diagnostic guideline on a display by associating the corresponding portions of the image interpretation report with items in the diagnostic guideline. The document creation support device according to claim 1, wherein the processor is configured to save the results of the association. The processor derives an analysis result corresponding to the item of the diagnostic guideline by analyzing the medical image, and generates the image interpretation report based on the analysis result,
The document creation support device according to claim 1 or 2, wherein the document creation support device is configured to use the analysis result to specify a portion of the image interpretation report that corresponds to an item of the diagnostic guideline. The document creation support device according to any one of claims 1 to 3, wherein the processor is configured to identify and display, in the diagnostic guideline, items that are not in the image interpretation report. The diagnostic guidelines include stage information;
The document creation support device according to any one of claims 1 to 4, wherein the processor is configured to specify stage information of the diagnostic guideline in the image interpretation report. 6. The document creation support device according to claim 5, wherein the disease stage information is stage information based on TNM classification. In an image interpretation report representing an image interpretation result, identifying a corresponding portion corresponding to an item included in a diagnostic guideline for the disease described in the image interpretation report,
A document creation support method in which a computer displays the image interpretation report and the diagnostic guideline on a display by associating the corresponding portions of the image interpretation report with items in the diagnostic guideline. a step of identifying, in an image interpretation report representing an image interpretation result, a corresponding portion corresponding to an item included in a diagnostic guideline for a disease described in the image interpretation report;
A document creation support program that causes a computer to execute a procedure of associating the corresponding portions of the image interpretation report with items in the diagnostic guidelines and displaying the image interpretation report and the diagnostic guidelines on a display.