DIAGNOSIS SUPPORT DEVICE, DIAGNOSIS SUPPORT METHOD, AND DIAGNOSIS SUPPORT PROGRAM

Abstract

To provide a diagnosis assistance device, a diagnosis assistance method and a diagnosis assistance program capable of reducing the burdens of medical care practitioners who handle medical care related documents of interpretation doctors and diagnosticians and prevent omission of information on important opinions and the like.SOLUTION: The diagnosis assistance device comprises: identification means for referring to storage means that stores prescribed negative-form contexts and prescribed character strings and identifying character strings from the prescribed character strings to the end of line or a punctuation as a unit sentence; extraction means which excludes unit sentences including the prescribed negative-form contexts among the unit sentences identified by the identification means, and extracts the prescribed character strings; and attention report creation means for creating an attention report in which a display form of the extracted prescribed character strings in a medical care related document is changed.SELECTED DRAWING: Figure 13

Description

[Technical field]

[0001] The present invention relates to a diagnostic support device, a diagnostic support method, and a diagnostic support program, and more particularly to a diagnostic support device, a diagnostic support method, and a diagnostic support program that prevent overlooking information in medical-related documents and support discovery of causes. [Background technology]

[0002] In a medical facility, a radiologist analyzes a plurality of medical images output from a modality that captures a patient, and creates a radiology report (image diagnosis report). A medical image showing a lesion is attached to the radiology report, and the name of a disease diagnosed from the attached medical image and a treatment method are described. When reporting the radiology report to a requesting doctor, it is very important to properly convey whether the disease is minor or serious. However, in recent years, there have been reported cases where information in the radiology report was overlooked, leading to an inappropriate diagnosis of a serious disease and causing serious problems in treatment, and there is a demand for a system to prevent such oversights. Therefore, a display device has been proposed that allows a user to grasp the position or characteristics of each piece of medical information (for example, the location of work performed on medical information in the past) from a bird's-eye view while maintaining the visibility of medical information (see, for example, Patent Document 1). In addition, an image reading report management device has been proposed that, with the aim of preventing clinicians from overlooking matters pointed out by image reading physicians when checking image reading reports, provides check boxes at positions corresponding to specific character strings in the image reading report and determines the clinician's checking status (see, for example, Patent Document 2). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2018-173902 A [Patent Document 2] JP 2019-204189 A Summary of the Invention [Problem to be solved by the invention]

[0004] Although the above-mentioned technology is expected to have the effect of making image interpretation reports easier to read, it has not been sufficient in terms of reducing the burden on image interpretation doctors and diagnosticians (requesting doctors) who perform many diagnoses. Image interpretation doctors, in particular, have to deal with different findings that require attention for each requesting department, which places a heavy burden on them. In addition, depending on the knowledge level and sense of the image interpretation doctor, there may be variations in the points that require attention. In addition, in terms of preventing information from being overlooked, if there are many check boxes, it may happen that the check boxes are checked out of habit. Therefore, the main object of the present invention is to provide a diagnosis support device, a diagnosis support method, and a diagnosis support program that can reduce the burden on medical professionals who handle medical-related documents, such as image interpretation doctors and diagnosticians, and prevent them from overlooking information such as important findings. [Means for solving the problem]

[0005] A diagnosis support device (10: corresponding reference symbol in the embodiments; the same applies below) according to the present invention includes: an identification means (S43, S45) for identifying a character string from a predetermined character string to an end of a line or a punctuation mark as a unit sentence by referring to a storage means (40) for storing a predetermined negative context and a predetermined character string in a medical-related document; an extraction means (S49, S51) for extracting the predetermined character string from the unit sentences identified by the identification means after excluding unit sentences including the predetermined negative context; and The medical information processing device further includes an attention report generating means (S53) for generating an attention report in which the display form of the extracted predetermined character string in the medical-related document is changed.

[0006] Preferably, a display format is associated with each of the predetermined character strings, and the attention report generating means converts the extracted predetermined character string into the associated display format (S53).

[0007] In one aspect, a warning indicator is associated with a portion of the specified character string, and the medical-related document includes an alert display means (S31 to S35) that displays an alert when the specified character string associated with the warning indicator is included.

[0008] Preferably, when an attention-calling comment corresponding to the attention-calling indicator is written in the medical-related document, the alert is not displayed (S33, S35).

[0009] Preferably, the predetermined negated context and the predetermined character string are determined for each medical department.

[0010] The diagnostic support method according to the present invention includes a storage step (40) of storing a predetermined negative context and a predetermined character string; A step of identifying a character string from the predetermined character string to the end of a line or a punctuation mark as a unit sentence in a medical document (S43, S45); an extraction step (S49, S51) of extracting the predetermined character string from the unit sentences identified by the identification step, after excluding unit sentences including the predetermined negative context; and The method further includes an attention report creating step (S53) of creating an attention report in which the display form of the extracted predetermined character string in the medical-related document is changed.

[0011] Preferably, the predetermined character string is partially associated with an attention-calling indicator, The method includes an alert display step (S31 to S35) of displaying an alert when the medical document contains a predetermined character string associated with the attention indicator.

[0012] Preferably, the predetermined negated context and the predetermined character string are determined for each medical department.

[0013] The diagnostic support program according to the present invention includes a storage step (40) of storing a predetermined negative context and a predetermined character string; A step of identifying a character string from the predetermined character string to the end of a line or a punctuation mark as a unit sentence in a medical document (S43, S45); an extraction step (S49, S51) of extracting the predetermined character string from the unit sentences identified by the identification step, after excluding unit sentences including the predetermined negative context; and The diagnostic support program is for executing an attention report creating step (S53) of creating an attention report in which the display form of the extracted predetermined character string in the medical-related document is changed.

[0014] Preferably, the predetermined character string is partially associated with an attention-calling indicator, The method includes an alert display step (S31 to S35) of displaying an alert when the medical document contains a predetermined character string associated with the attention indicator.

[0015] Preferably, the predetermined negated context and the predetermined character string are determined for each medical department. Effect of the Invention

[0016] According to the present invention, it is possible to provide a diagnostic support device, a diagnostic support method, and a diagnostic support program that can reduce the burden on medical professionals who handle medical documents, such as radiologists and diagnosticians, and prevent overlooking important information such as findings that differ depending on the requesting department. In particular, since character strings in negative sentences are not emphasized, only specific character strings written in positive sentences can be highlighted, effectively preventing oversight. As a result, it is possible to reduce the burden on radiologists and diagnosticians, and improve diagnostic support performance.

[0017] The above and other objects, features and advantages of the present invention will become more apparent from the following detailed description of the preferred embodiments with reference to the drawings. [Brief description of the drawings]

[0018] [Figure 1] FIG. 1 is a block diagram showing a configuration of a medical diagnosis support system applied to this embodiment. [Diagram 2] Fig. 2(A) is a diagram showing an example of the configuration of a table referenced as a predetermined character string. Fig. 2(B) is a diagram showing an example of the configuration of a table of a negative context database. Fig. 2(C) is a diagram showing an example of the configuration of a table of an important findings database. [Diagram 3] FIG. 2 is an illustrative diagram showing an example of the structure of a DICOM file created by a modality. [Figure 4] FIG. 13 is an illustrative view showing an example of a top screen of a diagnostic support screen displayed on a main monitor of the image diagnostic support device; [Diagram 5] 11 is an illustrative view showing an example of an image interpretation report screen of a diagnosis support screen displayed on a main monitor of the image diagnosis support device; FIG. [Figure 6] 1 is an illustrative view showing an example of a diagnostic support screen displayed on a sub-monitor of the image diagnostic support device; FIG. [Figure 7] FIG. 13 is an illustrative view showing another example of the image interpretation report screen of the diagnosis support screen displayed on the main monitor of the image diagnosis support device; [Figure 8] FIG. 13 is an illustrative view showing another example of the image interpretation report screen of the diagnosis support screen displayed on the main monitor of the image diagnosis support device; [Figure 9] 13 is an illustrative view showing an example in which a warning comment is additionally displayed on an image interpretation report screen of a diagnosis support screen displayed on a main monitor of the image diagnosis support device; FIG. [Figure 10] 13 is an illustrative view showing an example in which an input omission pop-up (attention alert) is displayed on an image interpretation report screen of a diagnosis support screen displayed on a main monitor of the image diagnosis support device; FIG. [Figure 11] FIG. 13 is an illustrative view showing another example of the top screen of the diagnostic support screen displayed on the main monitor of the image diagnostic support device; [Figure 12] FIG. 13 is an illustrative view showing an example of a report reference screen. [Figure 13] FIG. 13 is an illustrative view showing one example of an attention report display screen. [Figure 14] FIG. 4 is a flow chart showing a part of the operation of a CPU provided in the image diagnosis support device. [Figure 15] FIG. 11 is a flowchart showing another part of the operation of the CPU provided in the image diagnosis support device. [Figure 16] FIG. 11 is a flowchart showing another part of the operation of the CPU provided in the image diagnosis support device. [Figure 17] FIG. 11 is a flowchart showing still another part of the operation of the CPU provided in the image diagnosis support device. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0019] Referring to FIG. 1, the medical diagnosis support system of this embodiment is composed of an image diagnosis support device 10, a modality 20, a PACS 30, and a report database 40, all of which are connected to one another via an in-hospital LAN 50.

[0020] In the image diagnosis support device 10, a communication I / F 12cm, a CPU 12pr, a keyboard / mouse 12km, a DRAM 12mm, an HDD 12hd, a main monitor (first monitor) 12m1, and a sub-monitor (second monitor) 12m2 are connected to a bus BS1.

[0021] The sub-monitor 12m2 is attached to the main monitor 12m1. A radiologist (diagnostician) faces the main monitor 12m1 and the sub-monitor 12m2 and performs image diagnosis by operating the keyboard / mouse 12km.

[0022] The report database 40 is composed of, for example, a table referenced for each requesting department, a negative context database, and an important findings database. FIG. 2(A) shows an example of the configuration of a table referenced as a predetermined character string. This table is an important findings table in which important findings for each requesting department are registered as predetermined character strings. In this example, a table is configured for each requesting department, but a flag may be set in the important findings table for all departments to classify by requesting department. The report database 40 is not limited to the aspect of this embodiment, and may be constructed in the HDD 12hd.

[0023] According to Fig. 2(A), when the requesting department is the respiratory department, character strings such as "bleeding", "infarction", "malignant", "metastasis", "aneurysm", "dissection", "lung cancer", "lung cancer", "cancer", "cancer", "pulmonary embolism", "cardiac hypertrophy", "myocardial infarction", and "heart failure" are stored (registered) in the important findings table. Also, when the requesting department is the gastroenterological department, character strings such as "bleeding", "infarction", "malignant", "metastasis", "aneurysm", "dissection", "hepatocellular carcinoma", "hepatocellular carcinoma", "rapture", "pancreatic cancer", "pancreatic cancer", "pancreatic duct dilatation", "bile duct cancer", "bile duct dilatation", "kidney cancer", "kidney cancer", "ureter dilatation", "bladder cancer", "bladder cancer", "gastric cancer", "gastric cancer", "colon cancer", "colon cancer", and "appendicitis" are stored (registered) in the important findings table.

[0024] An example of the table configuration of the negative context database is shown in Figure 2(B). According to Figure 2(B), negative contexts such as "not recognized," "not recognized," "not available," "cannot be done," "cannot be done," "cannot be seen," and "cannot be seen" are stored (registered).

[0025] FIG. 2(C) shows an example of the table configuration of the important findings database. This table associates a display format with each of the predetermined character strings registered in the table of FIG. 2(A). According to FIG. 2(C), for the character string "metastasis", the color (character color displayed in the attention report) is red, the size (character font size) is 4, and "○" indicating that there is a corresponding attention indicator is stored (registered). For the character string "irregularly shaped", the color (character color displayed in the attention report) is black, the size (character font size) is 3, and there is no corresponding attention indicator is stored (registered). In this embodiment, for character strings registered in the table of FIG. 2(A) but not registered in the important findings database of FIG. 2(C) and other character strings, the color (character color displayed in the attention report) is black, and the size (character font size) is 1.

[0026] When creating an attention report (described later), the character string from the predetermined character string (important finding) to the end of the line or a punctuation mark in a medical document is identified as a unit sentence, and unit sentences including a predetermined negative context are excluded from the unit sentences, and the predetermined character string (important finding) is extracted. Then, the character color and size of only the extracted character string are changed according to the correspondence in FIG. 2(C). In this way, even if the word "important finding" is used, the character string is not highlighted in the part where the finding is negated, such as "no metastasis is found," so it is possible to prevent important findings that require attention from being overlooked.

[0027] The modality 20 is, for example, an MRI device that outputs a DICOM file containing multiple medical images showing cross sections of the patient's body axis. A technician who operates the modality 20 operates the modality 20 based on a request from the attending physician. In this way, a photographed image at a desired position is created as a medical image, and the created medical image is stored in a DICOM file. The DICOM file created in this way has the data structure shown in Fig. 3, and is stored in the PACS 30 via the hospital LAN 50.

[0028] 3, a DICOM file contains multiple medical images as well as additional information, which is made up of multiple items each indicating an examination attribute (examination date, patient name, patient age at the time of examination, accession number, etc.).

[0029] The CPU 12pr provided in the image diagnosis support device 10 executes the diagnosis support processing shown in Fig. 14 to Fig. 17 in order to support the image diagnosis by the image interpretation doctor by referring to the report database 40. Note that a program corresponding to this flow chart is stored in the HDD 12hd as a diagnosis support program.

[0030] With reference to Fig. 14, in step S1, the top screen is loaded into the DRAM 12m. The loaded top screen is read out by the main monitor 12m1 and displayed as shown in Fig. 4. According to Fig. 4, the top screen has a heading field IDX in which a plurality of headings each representing a plurality of examinations are listed. Also, in the top screen shown in Fig. 4, the image interpretation reports corresponding to all of the headings are also set to "pending".

[0031] In step S3, it is determined whether a heading selection operation (= an operation to select one of the multiple headings listed in the heading column IDX) has been performed using the keyboard / mouse 12km. In addition, in step S5, it is determined whether another operation has been performed using the keyboard / mouse 12km. If both the determination results of step S3 and step S5 are NO, the process returns to step S3; if the determination result of step S3 is YES, the process proceeds to step S7; if the determination result of step S5 is YES, the process proceeds to other processing.

[0032] In step S7, the image interpretation report screen corresponding to the heading selected by the heading selection operation is written to the DRAM 12 mm. The top screen on the DRAM 12 mm is updated by the image interpretation report screen.

[0033] The updated image interpretation report screen is read by the main monitor 12m1 and displayed as shown in Fig. 5. According to Fig. 5, the image interpretation report screen is provided with a request comment field (request text field) REQ, a findings field RMK, and a diagnosis field DGN. Among these, the character string "chest pain" in the request comment field REQ is written by the attending physician. In this embodiment, the findings field RMK and the diagnosis field DGN are collectively referred to as the "opinion entry field," and the findings written in the findings field RMK and the diagnostic comment written in the diagnosis field DGN are collectively referred to as the "opinion."

[0034] In step S9, the PACS 30 is accessed through the communication I / F 12cm, and a DICOM file corresponding to the accession number assigned to the selected heading is obtained from the PACS 30. In step S9, either a single medical image or multiple medical images stored in the obtained DICOM file are loaded onto the DRAM 12mm. The loaded medical image is read out by the sub-monitor 12m2 and displayed as shown in FIG.

[0035] In step S11, it is determined whether or not a finding input operation (an operation of designating a finding field RMK and inputting a desired character string) has been performed using the keyboard / mouse 12km. If the determination result is NO, the process proceeds directly to step S15.

[0036] On the other hand, if the determination result is YES, the process proceeds to step S13, where the character string acquired by the findings input operation is displayed in the findings field RMK in the manner shown in Fig. 7. According to Fig. 7, the following character string is displayed in the findings field RMK: "An irregular shadow was observed on the inside of the left lung, a post-treatment finding. Radiation pneumonitis is considered possible. No obvious recurrent mass was observed. No pleural effusion was observed. A tumor with a low CT value was observed in the liver, and metastasis is suspected." When display of the character string is complete, the process proceeds to step S15.

[0037] 15, in step S15, it is determined whether or not a diagnostic comment input operation (an operation of designating a diagnostic field DGN and inputting a desired character string) has been performed by the keyboard / mouse 12km. If the determined result is NO, the process proceeds to step S19.

[0038] On the other hand, if the determination result is YES, the process proceeds to step S17, where the character string acquired by the diagnostic comment input operation is displayed in the diagnosis field DGN as shown in Fig. 8. According to Fig. 8, the character string "Suspected post-treatment findings in chest, suspected liver metastasis" is displayed in the diagnosis field DGN. When the display of the character string is completed, the process proceeds to step S19.

[0039] In step S19, it is determined whether or not the "Caution Comment" button (shown by a thick circle in FIG. 8) displayed in the upper right corner of the diagnosis field DGN has been clicked by the keyboard / mouse 12km. If the determination result is NO, the process proceeds directly to step S27.

[0040] If the determination result of step S19 is YES, the process proceeds to step S21. In step S21, the attention calling comment field ATN is expanded in the DRAM 12m. The expanded attention calling comment field ATN is read out by the main monitor 12m1 and multiplexed (additionally displayed) on the image interpretation report screen as shown in FIG. 9. When the display process is completed, the process proceeds to step S23.

[0041] In step S23, it is determined whether or not an attention-calling comment input operation (an operation of designating an attention-calling comment field ATN and inputting a desired character string) has been performed using the keyboard / mouse 12km. If the determination result is NO, the process proceeds directly to step S27.

[0042] If the determination result is YES, the process proceeds to step S25, where the character string acquired by the attention comment input operation is displayed in the attention comment field ATN in the manner shown in Fig. 9. According to Fig. 9, the character string "Observations found in area other than requested" is displayed in the attention comment field ATN. The character string can be inputted by any character string using a keyboard or the like, or can be inputted by selecting a fixed phrase displayed by clicking a template button. When display of the character string is completed, the process proceeds to step S27.

[0043] 16, in step S27, it is determined whether or not the "Confirm" button (shown by a thick circle in FIG. 9) displayed in the upper right of the image interpretation report screen is clicked by the keyboard / mouse 12km. In addition, in step S29, it is determined whether or not another operation is performed by the keyboard / mouse 12km. If both the determination results of step S27 and step S29 are NO, the process returns to step S27, if the determination result of step S27 is YES, the process proceeds to step S31, and if the determination result of step S29 is YES, the process proceeds to other processing.

[0044] In step S31, the attention indicator (FIG. 2(C)) is referred to, and it is determined whether or not there is a character string registered as an attention indicator in the input data of the findings column RMK and the diagnosis column DGN. If the determination result is NO, the process proceeds directly to step S41.

[0045] If the decision result in the step S31 is YES, the process proceeds to a step S33. In the step S33, it is decided whether or not there is an input in the attention calling comment field ATN.

[0046] If the determination result in step S33 is YES (input present), the process proceeds directly to step S41. If the determination result in step S33 is NO (input absent), the process proceeds to step S35. In step S35, the attention alert ART is expanded in the DRAM 12m. The expanded attention alert ART is read out by the main monitor 12m1 and multiplexed (additionally displayed) on the radiology report screen as shown in FIG. 10. According to FIG. 10, the attention alert ART contains a finding of "metastasis." No attention comment has been entered. Are you sure? is this OK? is displayed. When the display process is completed, the process proceeds to step S37.

[0047] In step S37, it is determined whether the "Yes" button displayed on the attention alert ART has been clicked by the keyboard / mouse 12km. In step S39, it is determined whether the "No" button displayed on the attention alert ART has been clicked by the keyboard / mouse 12km. If both the determination results of step S37 and step S39 are NO, the process returns to step S37; if the determination result of step S37 is YES, the process proceeds to step S41; if the determination result of step S39 is YES, the process returns to step S21.

[0048] In step S41, a confirmation process is performed to confirm the input contents. After the confirmation process is performed, an attention report is created. After the confirmation process is performed in step S41, the process proceeds to step S43.

[0049] The attention report is created with reference to the report database 40. With reference to Fig. 17, in step S43, character strings (important findings) stored (registered) in the important findings table of Fig. 2(A) are extracted from the findings written in the findings column RMK and the diagnostic comments written in the diagnosis column DGN. In step S45, a character string from the extracted character string to the end of the line or a punctuation mark is specified as a unit sentence.

[0050] In step S47, the initial value of the variable n is set to "0", the final value of the variable n is set to "the number of detected unit sentences - 1", and the increment value is set to "1". In step S49, it is determined whether or not the nth unit sentence contains a negative context by referring to the negative context database in Fig. 2(B), and if the determination result is YES, the process proceeds to step S55, whereas if the determination result is NO, the process proceeds to step S51.

[0051] In step S51, a character string (important findings) contained in the n-th unit sentence is extracted, and in step S53, the display form of the character string extracted in step S51 is changed to the character color, font size, etc. described in the important findings database of FIG. 2(C), and the process proceeds to step S55.

[0052] In step S55, the variable n is incremented, and then the process returns to step S49. The processes in steps S49 to S55 are executed for the findings written in the findings column RMK and the diagnostic comments written in the diagnosis column DGN.

[0053] In the process of creating the attention report, the unit sentences identified in step S45 that contain a context stored (registered) in the negative context database are excluded (step S49, YES), and the display form, such as the character color and font size, of the character string (important findings) included in the unit sentences that remain after being excluded is changed. For example, if the character string (important findings) is "recurrence" and the statement "No obvious recurrent mass was found" is present in the findings column RMK, the character string "recurrence" is extracted in step S43, and the character string "No obvious recurrent mass was found" is identified as the unit sentence in step S45. This unit sentence contains the negative context "no obvious recurrent mass was found," so step S49 is YES, and the display form change process is not performed on the character string "recurrence."

[0054] When the processes of steps S49 to S55 are performed for all unit sentences of the findings written in the findings column RMK and the diagnostic comments written in the diagnosis column DGN, the process returns to step S1. As a result, the display on the main monitor 12m1 returns from the image interpretation report screen to the top screen (see FIG. 11). However, as shown by the bold circle in FIG. 11, the character string "Confirmed" is added to the heading corresponding to the image interpretation report that has been subjected to the confirmation process, instead of "Pending".

[0055] In this embodiment, the state shown in Fig. 10 is a display screen that appears as an alert when the character string "metastasis" with "○" registered therein indicating that there is a corresponding attention indicator in the important findings database shown in Fig. 2(C) is included in the opinion written in the findings column RMK and the diagnosis column DGN, but no attention comment is written as shown in Fig. 9. However, the present invention is not limited to this aspect, and the alert may be displayed when a predetermined character string corresponding to an attention indicator is included, regardless of the presence or absence of an attention comment.

[0056] When the attention report is created, it becomes possible to refer to the report. Fig. 12 is an illustrative view showing an example of a report reference screen. Fig. 13 is an illustrative view showing an example of an attention report display screen. When an attempt is made to open a report in which an attention comment has been input, as shown in Fig. 12, a character string of the attention comment "Findings in area other than requested" is displayed before the contents of the report are displayed. This character string is input in the attention comment field ATN by the comment input operation in step S23 (see Fig. 9).

[0057] In the state shown in FIG. 12, when the "Close" button is clicked using the keyboard / mouse 12km, the attention report shown in FIG. 13 is displayed.

[0058] In the example shown in FIG. 13, the character string "irregular" indicated by the symbol a, the character string "radiation pneumonia" indicated by the symbol b, the character string "metastasis" indicated by the symbol c, the character string "recurrence" indicated by the symbol d, and the character string "pleural effusion" indicated by the symbol e are extracted as important findings. Character strings from these character strings to the end of the line or a punctuation mark are identified as unit sentences. At this time, the unit sentence from the character string "recurrence" indicated by the symbol d contains "not recognized" registered in the negative context database of FIG. 2(B). Also, the unit sentence from the character string "pleural effusion" indicated by the symbol e contains "not recognized" registered in the negative context database of FIG. 2(B). After excluding these unit sentences, the extracted character strings (important findings) are the character string "irregular" indicated by the symbol a, the character string "radiation pneumonia" indicated by the symbol b, and the character string "metastasis" indicated by the symbol c. Based on the important findings database in Figure 2(C), an attention report is created and displayed in which the character string "irregularly shaped" indicated by symbol a is colored black and has a size (font size) of 3, the character string "radiation pneumonia" indicated by symbol b is colored red and has a size (font size) of 3, and the character string "metastasis" indicated by symbol c is colored red and has a size (font size) of 4.

[0059] As described above, for negative sentences, character strings are not highlighted, so that abnormal parts can be highlighted and they can be prevented from being overlooked.

[0060] In the present embodiment, an example in which the character color and font size are specified as the display format has been described, but the present invention is not limited to this, and for example, the type of font may be changed, or effects such as blinking characters may be added. Also, the settings may be changeable depending on the manner in which the attention report is displayed. For example, it is conceivable to change the character color pattern depending on the background color of the screen display.

[0061] It is preferable to have a database for each medical department, because when findings related to diseases in other departments that are not the department in question are found (when a character string in another department is hit), the degree of emphasis can be increased to prevent oversight.

[0062] As can be seen from the above description, the image diagnosis support device 10 is a device that supports diagnosis based on a single or multiple medical images, and the following processing is executed by the CPU 12pr constituting the device.

[0063] First, at least one of the medical images is displayed on the sub-monitor 12m2 facing the image interpreter (S9). The image interpreter's opinion (findings and / or diagnostic comments) on the requested comment is acquired through the keyboard / mouse 12km and displayed on the image interpretation report screen on the main monitor 12m1 (S11 to S17).

[0064] Thereafter, a warning comment for the opinion (findings and / or diagnostic comment) is acquired via the keyboard / mouse 12km and displayed in a warning comment field ATN that is multiplexed (additionally displayed) on the image interpretation report screen (S19 to S25).

[0065] If the character string associated with the attention indicator is present in the opinion (findings and / or diagnostic comment) but the input of the attention comment is not permitted, the attention alert ART is displayed (S27-S35). A display is displayed to the radiologist to confirm whether or not to input an attention comment before the radiology report input confirmation process (S27-S41), thereby reducing concerns that a diagnosis will be made by overlooking a medical image showing a lesion.

[0066] The doctor's opinion (findings and / or diagnostic comments) on the requested comment is displayed by creating an attention report with a modified display format with reference to the report database 40 (S43 to S55).

[0067] According to the present invention, the color, type, and size of the font of the normal text of the image reading report are automatically converted by recognizing the context and the words that should be noted, and an expression that calls attention is realized, and it is possible to support the appropriate transmission of the report. In addition, since the important findings differ for each requesting department, it is also preferable to create a database of important findings and the color and size for displaying the important findings on the report for each requesting department and adapt them. Furthermore, an index is set that can distinguish findings that require attention among each important finding, and if the image reading doctor has not input a warning comment even though there is a finding that requires attention, it is possible to display a pop-up to the image reading doctor to check whether or not the warning comment has been forgotten. If a diagnosis is delayed due to overlooking an important finding, insufficient confirmation of the image diagnosis result, or simply forgetting to add a warning comment, the delay in diagnosis may affect the treatment result. In the present invention, the degree of warning can be displayed in different forms depending on the importance of the finding.

[0068] In the above, an image interpretation report has been described as an example of a medical document, but the present invention is not limited to this and can be applied to various documents. For example, the present invention can be applied to medical records, medication records, prescriptions, etc. In medical records, character strings related to examination items and medication can be stored as predetermined character strings. Also, in medication records and prescriptions, a database can be constructed so that drugs are displayed in different colors according to their medicinal effects. [Explanation of symbols]

[0069] 10. Diagnostic imaging device 12pr...CPU 12km ... Keyboard / Mouse 12hd...HDD 12m1 ...Main monitor 12m2 …Sub-monitor 40 … Reporting database

Claims

1. an identifying means for identifying a character string from a predetermined character string to an end of a line or a punctuation mark as a unit sentence in a medical document by referring to a storage means for storing a predetermined negative context and a predetermined character string; an extracting means for extracting the predetermined character string from the unit sentences identified by the identifying means after excluding unit sentences including the predetermined negative context; and a diagnostic support device comprising an attention report creating means for creating an attention report in which a display form of the extracted predetermined character string in the medical-related document is changed;

2. A display format is associated with each of the predetermined character strings, 2. The diagnostic support device according to claim 1, wherein said attention report generating means converts said extracted predetermined character string into said associated display format.

3. The predetermined character string is partially associated with an attention indicator, 3. The diagnostic support device according to claim 1, further comprising an alert display means for displaying an alert when the medical document contains a predetermined character string associated with the attention indicator.

4. The diagnosis support device according to claim 3 , wherein the alert is not displayed when an attention-attracting comment corresponding to the attention-attracting indicator is written in the medical-related document.

5. The diagnosis support device according to claim 1 , wherein the predetermined negative context and the predetermined character string are determined for each medical department.

6. A diagnostic support device having a storage means for storing a predetermined negative context and a predetermined character string, a step of identifying a character string from the predetermined character string to an end of a line or a punctuation mark as a unit sentence in a medical-related document; an extraction step of extracting the predetermined character string from the unit sentences identified by the identification step, after excluding unit sentences including the predetermined negative context; and The diagnostic support method includes a step of creating an attention report in which a display form of the extracted predetermined character string in the medical-related document is changed.

7. The predetermined character string is partially associated with an attention indicator, The diagnostic support method according to claim 6 , further comprising an alert display step of displaying an alert when the medical document contains a predetermined character string associated with the attention indicator.

8. 8. The method of claim 6, wherein the predetermined negative context and the predetermined character string are determined for each medical department.

9. a computer having storage means for storing a predetermined negation context and a predetermined character string, a step of identifying a character string from the predetermined character string to an end of a line or a punctuation mark as a unit sentence in a medical-related document; an extraction step of extracting the predetermined character string from the unit sentences identified by the identification step, after excluding unit sentences including the predetermined negative context; and a diagnostic support program for causing a user to execute an attention report creating step of creating an attention report in which the display form of the extracted predetermined character string in the medical-related document is changed;

10. The predetermined character string is partially associated with an attention indicator, 10. The diagnostic support program according to claim 9, further comprising an alert display step of displaying an alert when the medical document contains a predetermined character string associated with the attention indicator.

11. 11. The diagnostic support program according to claim 9, wherein the predetermined negative context and the predetermined character string are determined for each medical department.

Images