Image interpretation management device, program, and image interpretation management method

Abstract

To provide a radiogram interpretation management device, a program and a radiogram interpretation management method with which it is possible to realize desired highlighting display in radiogram interpretation.SOLUTION: An analysis device 3 as a radiogram interpretation device comprises: a first acquisition unit (control unit 31) for acquiring an automatically generated finding that is obtained by computer processing on medical information; a second acquisition unit (data acquisition unit 33) for acquiring a radiogram interpretation finding that is created by a user on the basis of medical information; and a setting unit (control unit 31) for allowing a combination for highlighting display among combinations of the results of automatically generated findings and the results of radiogram interpretation findings to be set by user operation.SELECTED DRAWING: Figure 2

Description

[Technical Field]

[0001] The present invention relates to an image interpretation management device, a program, and an image interpretation management method. [Background technology]

[0002] In recent years, with the development of AI (Artificial Intelligence) technology, AI analysis has been introduced into the medical field, and attempts are being made to use AI to assist in the analysis and diagnosis of medical information, such as image diagnosis, which was previously performed by doctors. In clinical settings, there is a need to perform tests and diagnoses appropriately and quickly, and to streamline and optimize diagnostics to reduce the burden on doctors. The introduction of AI analysis is expected to contribute to the efficiency and optimization of such diagnoses.

[0003] For example, Patent Document 1 discloses a device that compares analysis result information, in which medical information extracted from radiology report information created by a user is associated with items, with diagnostic support information, in which medical information obtained from medical test data is associated with items. The comparison detects differences for each item, and determines the importance of each detected difference. The device then changes the display mode of the detected differences according to the determined importance, and presents them together with the contents of the radiology report information. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Laid-Open No. 2009-86750 Summary of the Invention [Problem to be solved by the invention]

[0005] However, when combining the doctor's interpretation results with the AI's interpretation results (matching results), the matching results that each medical facility and each user wants to highlight will differ. For example, when checking the matching results by a secondary radiologist, there are cases where the secondary radiologist wants to check only when the doctor's (primary radiologist's) interpretation results and the AI's interpretation results differ, cases where the secondary radiologist wants to check only when there is a possibility that the primary radiologist has overlooked a lesion, and cases where the secondary radiologist wants to check only when there is a possibility that both the primary radiologist and the AI ​​have overlooked a lesion, and there is a need to highlight the matching results for each case that the secondary radiologist wants to check. The invention of Patent Document 1 does not realize the above-mentioned highlighting desired by each medical facility or each user, which differs depending on each medical facility or each user.

[0006] In this way, the emphasis display required when interpreting images varies depending on the medical facility, etc. In this regard, developing and manufacturing devices (image interpretation management devices, analysis devices) to realize the desired emphasis display would be costly and time-consuming.

[0007] The present invention has been made in consideration of the problems in the conventional technology described above, and aims to provide an image reading management device, program, and image reading management method that can realize desired highlighting during image reading. [Means for solving the problem]

[0008] In order to solve the above problem, the invention described in claim 1 is an image interpretation management device, First inspection a first acquisition unit that acquires automatically generated findings obtained by computer processing of medical information; a second acquisition unit that acquires image findings created by a user based on the medical information; a control unit that displays on a display unit a work list that displays a list of multiple examinations including the first examination; Highlighting conditions a setting unit that can be set by a user operation; Equipped with 、 the highlighting condition includes a first condition regarding a difference between the automatically generated findings and the image interpretation findings of the examination; the control unit causes the display unit to display the work list in a display format in which the examinations that satisfy the highlighting condition among the plurality of examinations are highlighted.It is characterized by:

[0009] Also, claims 14 The invention described in is a program, On the computer, First inspection a first acquisition function for acquiring automatically generated findings obtained by computer processing of medical information; a second acquisition function for acquiring image interpretation findings prepared by a user based on the medical information; a control function for displaying, on a display unit, a work list that displays a list of multiple examinations including the first examination; Highlighting conditions A setting function that can be set by user operation; To realize 、 the highlighting condition includes a first condition regarding a difference between the automatically generated findings and the image interpretation findings of the examination; The control function causes the display unit to display the work list in a display format in which the examinations that satisfy the highlighting conditions among the plurality of examinations are highlighted. It is characterized by the following.

[0010] Also, claims 26 The invention described in is a radiogram interpretation management method, First inspection a first acquisition step of acquiring automatically generated findings obtained by computer processing of medical information; a second acquisition step of acquiring image findings prepared by a user based on the medical information; a control step of displaying a work list on a display unit that displays a list of multiple examinations including the first examination; Highlighting conditions a setting step that allows setting by a user operation; Including fruit, the highlighting condition includes a first condition regarding a difference between the automatically generated findings and the image interpretation findings of the examination; In the control step, the work list is displayed on the display unit in a display format in which the examinations that satisfy the highlighting condition among the plurality of examinations are highlighted. It is characterized by: [Effects of the Invention]

[0011] According to the present invention, desired highlighting can be achieved during image interpretation. [Brief explanation of the drawings]

[0012] [Figure 1] 1 is a diagram illustrating the overall configuration of a medical image system according to an embodiment of the present invention. [Figure 2] 1 is a block diagram showing the functional configuration of an analysis device as an image interpretation management device according to an embodiment of the present invention; [Figure 3] 10 is a flowchart showing the flow of an image interpretation management method. [Figure 4] FIG. 1 is a diagram showing an example of a workflow for image interpretation. [Figure 5] FIG. 10 is a diagram showing an example of a work list display screen. [Figure 6] FIG. 10 is a diagram showing an example of a search condition tab in a search filter editing screen. [Figure 7] FIG. 10 is a diagram showing an example of a display item (examination) tab in the search filter editing screen. [Figure 8] FIG. 10 is a diagram showing an example of a design tab in a search filter editing screen. [Figure 9] FIG. 10 is a diagram showing an example of a condition setting screen. [Figure 10] FIG. 10 is a diagram showing an example of a condition setting screen. [Figure 11] FIG. 10 is a diagram showing an example of a condition setting screen. [Figure 12] FIG. 10 is a diagram showing an example of a work list display screen. [Figure 13] FIG. 10 is a diagram showing an example of a work list display screen. [Figure 14] FIG. 10 is a diagram showing an example of a work list display screen. [Figure 15] FIG. 1 is a diagram showing an example of a workflow for image interpretation. DETAILED DESCRIPTION OF THE INVENTION

[0013] Hereinafter, an embodiment of an image interpretation management device, a program, and an image interpretation management method according to the present invention will be described, but the scope of the invention is not limited to the illustrated examples.

[0014] [Configuration of medical imaging system] The image interpretation management device in this embodiment performs analysis of medical images, which are medical information, within a medical image system, for example, and the "analysis device" referred to below functions as the "image interpretation management device." FIG. 1 shows the system configuration of a medical image system 100.

[0015] As shown in Fig. 1, the medical image system 100 includes a modality 1, a console 2, an analysis device 3, an interpretation terminal 4, an image server 5, etc., which are connected via a communication network N such as a LAN (Local Area Network), a WAN (Wide Area Network), or the Internet. Each device constituting the medical image system 100 conforms to the HL7 (Health Level Seven) or DICOM (Digital Image and Communications in Medicine) standards, and communication between the devices is performed in accordance with HL7 or DICOM. Note that the number of modalities 1, consoles 2, interpretation terminals 4, etc. is not particularly limited.

[0016] The modality 1 is an image generating device such as an X-ray device (DR, CR), an ultrasound diagnostic device (US), a CT, or an MRI, and generates medical images as medical information by capturing an image of a patient's examination target area as a subject based on examination order information transmitted from a Radiology Information System (RIS) (not shown) or the like. In accordance with the DICOM standard, additional information (patient information, examination information, image ID, etc.) is written to the header of the image file of the medical image generated by the modality 1. The medical image thus annotated with additional information is transmitted to an analysis device 3 or an interpretation terminal 4 via a console 2 or the like.

[0017] The console 2 is an imaging control device that controls imaging in the modality 1. The console 2 outputs imaging conditions and image reading conditions to the modality 1 and acquires image data of medical images captured in the modality 1. The console 2 is configured with a control unit, display unit, operation unit, communication unit, memory unit, etc. (not shown), and each unit is connected by a bus.

[0018] The analysis device 3 is a device that performs various analyses on medical images, which are medical information, and is the image interpretation management device in this embodiment. The analysis device 3 is configured as a PC, a mobile terminal, or a dedicated device. In this embodiment, the analysis device 3 includes a medical image management device such as a PACS (Picture Archiving and Communication System).

[0019] FIG. 2 is a block diagram showing the functional configuration of the analysis device 3. As shown in FIG. As shown in Figure 2, the analysis device 3 is configured with a control unit 31, a memory unit 32, a data acquisition unit 33, a data output unit 34, an operation unit 35, a display unit 36, etc., and each unit is connected by a bus 37.

[0020] The data acquisition unit 33 acquires various data from an external device (for example, the console 2, the interpretation terminal 4, etc.). The data acquisition unit 33 is configured, for example, by a network interface or the like, and is configured to receive data from an external device connected by wire or wirelessly via the communication network N. In this embodiment, the data acquisition unit 33 is configured by a network interface or the like, but it can also be configured by a port into which a USB memory, an SD card, or the like can be inserted.

[0021] In this embodiment, the data acquisition unit 33 acquires image data of medical images, for example, from the console 2. The data acquisition unit 33 also acquires information from the interpretation terminal 4, such as a diagnosis result (detection result information of a lesion that can be read from a medical image) regarding the medical image created by a user (for example, a doctor, etc.) based on the medical image, which is medical information, and an interpretation report, which is an interpretation result by an image interpretation doctor (for example, an image interpretation doctor who performs primary interpretation or secondary interpretation, etc.).

[0022] Specifically, the data acquisition unit 33 functions as a "second acquisition unit" that acquires "image interpretation findings" (interpretation results) created by a user (e.g., a primary radiologist, a secondary radiologist, etc.) based on medical information. Note that if additional information is added, such as when a region of interest (ROI) is set in a medical image by a user such as a radiologist, the data acquisition unit 33 also acquires such additional information.

[0023] The "image findings" acquired by the data acquisition unit 33 include various information such as information regarding the presence or absence of a lesion (i.e., information indicating that the detection of an abnormality is "+ (abnormal findings present)" or "- (abnormal findings absent)"), the name of the lesion, the location of the lesion (i.e., the location of the detected lesion), etc. Note that the specific content of the information included in the "image findings" is not limited to those exemplified here, and may be a part of these, or may include information other than these. The “image findings” acquired by the data acquisition unit 33 are sent to the control unit 31 .

[0024] The data output unit 34 is an output unit that outputs information processed by the analysis device 3. There are no particular limitations on the destination to which the data output unit 34 outputs various pieces of information. For example, the information may be output to the display unit 36 ​​of the analysis device 3, the image interpretation terminal 4, the image server 5, various external display devices (not shown), etc. As will be described later, in this embodiment, a predetermined highlighting display is set based on user operation, and the information processed by the analysis device 3 is output to the display unit 36, etc. so that various displays are made based on the set predetermined highlighting display. Examples of the data output unit 34 include a network interface for communicating with the image interpretation terminal 4 and the image server 5, a connector for connecting to an external device (e.g., a display device, a printer, etc. not shown), and a port for various media such as a USB memory.

[0025] The operation unit 35 is composed of a keyboard with various keys, a pointing device such as a mouse, or a touch panel attached to the display unit 36. The operation unit 35 allows a user to input data, and specifically outputs operation signals input by key operations on the keyboard, mouse operations, or touch operations on the touch panel to the control unit 31. In this embodiment, the user can customize the desired highlighting, as will be described later, and the operation unit 35 accepts an input operation from the user and outputs an operation signal based on the input to the control unit 31.

[0026] The display unit 36 ​​is configured to include a monitor such as an LCD (Liquid Crystal Display), and displays various screens according to instructions of a display signal input from the control unit 31. The number of monitors is not limited to one, and multiple monitors may be provided. As will be described later, the display unit 36 ​​appropriately displays various information based on display data output from the control unit 31. Furthermore, the display unit 36 ​​performs highlighting based on a combination of highlighting set by the control unit 31 (setting unit), as will be described later. In addition, as described below, the display unit 36 ​​highlights the combination of the results of the "automatically generated findings" and the results of the "image findings" based on the combination to be highlighted set by the control unit 31 (setting unit) and the threshold value of the confidence level of the "automatically generated findings."

[0027] The control unit 31 is configured with a CPU (Central Processing Unit), RAM (Random Access Memory), etc., and comprehensively controls the operations of each unit of the analysis device 3. Specifically, the CPU reads out various processing programs stored in the program storage unit 321 of the storage unit 32, loads them into the RAM, and executes various processes in accordance with the programs. In this embodiment, the control unit 31 realizes various functions as follows in cooperation with the programs.

[0028] For example, the control unit 31 functions as a "first acquisition unit" that acquires "automatically generated findings" obtained by computer processing of medical information. Specifically, the computer performs lesion detection and analysis processing on the medical images acquired by the data acquisition unit 33, and outputs the detection and analysis results of one or more types of lesions. The computer processing used here is, for example, AI analysis using AI (Artificial Intelligence) that performs image diagnosis and image analysis, including lesion detection using CAD (Computer Aided Diagnosis).

[0029] In this embodiment, the control unit 31 as a "first acquisition unit" acquires, as an "automatically generated finding," a detection result of the presence or absence of a lesion (i.e., a result that the detection of an abnormality is "+ (abnormal finding present)" or "- (abnormal finding absent)") and a detection result of the location of the lesion (i.e., the detected location of the lesion), but the "automatically generated finding" is not limited to these. For example, the control unit 31 may also function as a learning unit (not shown) that learns the correspondence between medical information (medical images in this embodiment) and medical information (such as the name of the lesion), and obtain an "automatically generated finding" by computer processing the medical information (medical images) based on the learned correspondence between the medical information (medical images) and medical information. That is, for example, a machine learning model created by deep learning or other methods using a large amount of training data (pairs of medical images showing lesions and correct labels (diagnosis names of lesions in the medical images (types of lesions), etc.)) is used to detect and analyze lesions from input medical images. When the "automatically generated findings" are obtained in this manner, information such as the name of the lesion is also added to the image data of the medical image as additional information.

[0030] In this embodiment, when interpreting medical information (medical images in this embodiment), the control unit 31 compares the "automatically generated findings" that are the analysis results of the AI ​​with the "image interpretation findings" by the image interpreter. This allows quality assurance (hereinafter referred to as "QA") for the diagnostic accuracy of the medical information (medical images).

[0031] For example, if information that an abnormality has been detected (i.e., a "+" indicating that an abnormality has been found) is extracted from the "automatically generated findings" and information that an abnormality has been detected (i.e., a "+" indicating that an abnormality has been found) is also extracted from the "image findings," then both the "automatically generated findings" by the AI ​​and the image findings by the doctor will be "+" (abnormality has been found), and the control unit 31 will derive (calculate) a comparison result that the two results are consistent, "+" (abnormality has been found). In contrast to this, for example, if information that an abnormality has been detected (i.e., "+" indicating that an abnormality has been found) is extracted from the "automatically generated findings" and information that an abnormality has not been detected (i.e., "-" indicating that no abnormality has been found) is extracted from the "image findings," the control unit 31 will derive (calculate) a comparison result in which the "automatically generated findings" from the AI ​​analysis "+" (abnormality has been found) and the "image reading results" by the doctor "-" (no abnormality has been found) do not match (are different).

[0032] Furthermore, for example, if information is extracted from the "automatically generated findings" that an abnormality has been detected and the location of the lesion is "XX", and information is also extracted from the "image findings" that an abnormality has been detected and the location of the lesion is "XX", then both the "automatically generated findings" by the AI ​​and the image findings by the doctor will be information that an abnormality has been detected and the location of the lesion is "XX", and the control unit 31 will derive (calculate) a comparison result that the two results match. In contrast to this, for example, if information is extracted from the "automatically generated findings" that an abnormality has been detected and the location of the lesion is "XX," and information is extracted from the "image reading findings" that an abnormality has been detected and the location of the lesion is "YY," the control unit 31 will derive (calculate) a comparison result that the locations of the lesion do not match (are different) when comparing the "automatically generated findings" from the AI ​​analysis with the "image reading results" by the doctor.

[0033] In this embodiment, the information extracted from the "automatically generated findings" may be either "+" information indicating the presence of abnormal findings or "-" information indicating the absence of abnormal findings. Furthermore, if abnormal findings are present, information on the detected location of the lesion may be extracted. The information extracted from the "image findings" may be either "+" indicating the presence of abnormal findings or "-" indicating the absence of abnormal findings. If abnormal findings are present, information on the detected location of the lesion may be extracted. The information extracted from the "automatically generated findings" and "image interpretation findings" is not limited to the presence or absence of abnormal findings and the detected location of the lesion, but may include the type and number of abnormal findings, etc. However, in the following embodiment, the explanation is based on the assumption that the control unit 31 performs a comparison (matching) process on the presence or absence of abnormal findings and the detected location of the lesion.

[0034] Furthermore, "automatically generated findings" are structured data obtained through computer processing (AI analysis), whereas "image findings" are not limited to structured data, such as image interpretation reports prepared by doctors. For example, the presence or absence of abnormal findings may be expressed with "+" or "-", or may be expressed as a string indicating the presence or absence, such as "absence" or "absence" or "detection" or "not detection." Therefore, the control unit 31 may have a function to structure the "image findings" as data (structured data) consisting of character strings or the like that can be matched (compared) with the "automatically generated findings," as a prerequisite for matching the "automatically generated findings" with the "image findings." In this case, for example, dictionary data or the like that defines the correspondence between character strings and the like, used to generate structured data, is stored in the storage unit 32, and the control unit 31 structures the "image findings" by referring to this dictionary data.

[0035] Note that if the control unit 31 broadly defines various expressions and terms in the "image findings," for example, by associating expressions such as "+," "there is" an abnormality, and "there is found" an abnormality with the same meaning as "information indicating the presence of an abnormal finding (+)" extracted from the "automatically generated findings," and by associating expressions such as "-," "there is no" an abnormality, and "there is no found" an abnormality with the same meaning as "information indicating the absence of an abnormal finding (-)" extracted from the "automatically generated findings," then even if there is some discrepancy in the expressions between the "automatically generated findings" and the "image findings," it is possible to determine whether they match or mismatch. In this case, the "automatically generated findings" and the "image findings" can be matched (compared) without structuring the "image findings."

[0036] In addition, in this embodiment, the control unit 31 functions as a "setting unit" that enables a user to set, by operation, a combination of the "automatically generated findings" and the "image findings" to be highlighted. In this embodiment, the control unit 31 is capable of setting a predetermined emphasis display.

[0037] For example, the control unit 31 as a setting unit can be set by a user operation to highlight combinations of the results of the "automatically generated findings" and the results of the "image findings" where the result of the "automatically generated findings" is that a lesion has been detected (detection of an abnormal area is "+") and the result of the "image findings" is that a lesion has not been detected (detection of an abnormal area is "-"). Alternatively, the control unit 31 as a setting unit can be set by a user operation to highlight combinations of the results of the "automatically generated findings" and the results of the "image findings" where the result of the "automatically generated findings" is that no lesion is detected (detection of an abnormal area is "-") and the result of the "image findings" is that a lesion is detected (detection of an abnormal area is "+"). Alternatively, the control unit 31 as a setting unit can be set by a user operation to highlight combinations of the results of the "automatically generated findings" and the results of the "image findings" where the result of the "automatically generated findings" is no detection of a lesion (detection of an abnormal area is "-") and the result of the "image findings" is no detection of a lesion (detection of an abnormal area is "-"). Alternatively, the control unit 31 as a setting unit can be set by a user operation to highlight combinations of the results of the "automatically generated findings" and the results of the "image findings" where the result of the "automatically generated findings" indicates that a lesion has been detected (detection of an abnormal area is "+") and the result of the "image findings" indicates that a lesion has been detected (detection of an abnormal area is "+").

[0038] Furthermore, for example, the control unit 31 as a setting unit can be set by a user operation to highlight a combination of the results of the lesion detection position in the "automatically generated findings" and the results of the lesion detection position in the "image findings" in which a first area is detected as the lesion detection position in the "automatically generated findings" and a second area different from the first area is detected as the lesion detection position in the "image findings."

[0039] Furthermore, for example, the control unit 31 as a setting unit allows the user to set, by operation, the combination of the results of the "automatically generated findings" and the results of the "image findings" to be highlighted, and the threshold value for the confidence level of the "automatically generated findings." For example, suppose that a user operation sets, as a combination to be highlighted, a combination of the results of the "automatically generated findings" and the results of the "image findings" in which the results of the "automatically generated findings" include abnormal findings and the results of the "image findings" do not include abnormal findings. In this case, the threshold value for highlighting the combination is set to the threshold value of the confidence level of the "automatically generated findings." At this time, if the confidence level of the "automatically generated findings" is equal to or higher than a set threshold, the combination of the results of the "automatically generated findings" and the results of the "image findings" set as the combination to be highlighted is highlighted. On the other hand, if the confidence level of the "automatically generated findings" is equal to or lower than the set threshold, the combination of the results of the "automatically generated findings" and the results of the "image findings" set as the combination to be highlighted is not highlighted. The specific highlighting setting process will be described later.

[0040] In this embodiment, the control unit 31 also functions as a "display control unit" that performs highlighting based on the combination of highlighting set by the setting unit. In addition, the control unit 31 as a display control unit highlights the combination of the results of the "automatically generated findings" and the results of the "image findings" based on the combination to be highlighted set by the setting unit and the threshold value of the confidence level of the "automatically generated findings."

[0041] The storage unit 32 is configured with an HDD (Hard Disk Drive), a semiconductor memory, etc., and includes a program storage unit 321 that stores programs for executing various processes including a highlighting setting process described below. The storage unit 32 also stores parameters, files, etc. that are necessary for executing the programs stored in the program storage unit 321. As mentioned above, when the control unit 31 performs a process of structuring unstructured data such as an interpretation report created by a user (radiography physician) to generate structured data that can be compared with "automatically generated findings," dictionary data (structured dictionary) and the like used for the structuring process are also stored in the memory unit 32.

[0042] The image interpretation terminal 4 is a computer device that includes, for example, a control unit, an operation unit, a display unit, a storage unit, a communication unit, etc., and that reads out medical images, which are medical information, from the image server 5, etc., and displays them for image interpretation. A user (primary radiologist, secondary radiologist, etc.) interprets medical images on the radiological interpretation terminal 4 and creates an interpretation report or the like which is the diagnostic result of the radiological interpretation doctor regarding the medical images.

[0043] The image server 5 is, for example, a server that constitutes a PACS (Picture Archiving and Communication Systems), and stores in a database the medical images output from the modality 1 in association with patient information (patient ID, patient name, date of birth, age, sex, height, weight, etc.), examination information (examination ID, examination date and time, type of modality, examination area, requesting department, purpose of examination, etc.), image ID of the medical image, information on the AI ​​analysis results output from the control unit 31 of the analysis device 3 (i.e., automatically generated findings), an interpretation report created by the user (radiography doctor) on the interpretation terminal 4, the interpretation findings of the radiology doctor (i.e., interpretation findings, etc.), and matching results (comparison results) output from the control unit 31 of the analysis device 3.

[0044] [Image interpretation management method in this embodiment] As shown in Figure 3, the image reading management method in this embodiment includes a first acquisition step (step S1) of acquiring "automatically generated findings" obtained by computer processing of medical information (AI analysis in this embodiment), a second acquisition step (step S2) of acquiring "image reading findings" created by the user based on the medical information, a setting step (step S3) that allows the user to set the combination of the results of the "automatically generated findings" and the results of the "image reading findings" to be highlighted, and a highlighting step (step S4) that highlights the results set in the setting step. The setting step S3 may be performed before the first acquisition step S1 and the second acquisition step S2.

[0045] FIG. 4 shows an example of a workflow for image interpretation. In the example shown in FIG. 4, for example, a doctor (primary image interpreter) performs a primary image interpretation of medical information, and the control unit 31 performs an AI analysis. Then, the "automatically generated findings," which are the AI ​​analysis results, are compared with the "image interpretation findings," which are the image interpretation results of the primary image interpreter. The image is then passed to a secondary image interpretation by a secondary image interpreter (secondary image reader), and the comparison results between the "automatically generated findings" and the "image interpretation findings," which are the image interpretation results of the primary image interpreter, are displayed on the worklist of the secondary image interpreter (secondary image reader). The secondary image interpreter then performs a secondary image interpretation while referring to the comparison results displayed on the worklist and the image interpretation report by the primary image interpreter, which is the "image interpretation findings." After that, a diagnosis is confirmed.

[0046] (Worklist display setting process) The following describes the display setting process for the worklist described above (for example, for the secondary radiologist (secondary radiologist)). In this embodiment, the worklist displays a list of examination information (examination list) including the results of "automatically generated findings" (AI determination results) and the results of "image interpretation findings" (user determination results).

[0047] First, when a search filter edit 3611 is selected by an input operation by a user (e.g., a secondary radiologist) via the operation unit 35 on the work list display screen 361 shown in Figure 5 displayed on the display unit 36, the control unit 31 causes the display unit 36 ​​to display a search filter edit screen 362 shown in Figure 6.

[0048] In this embodiment, the user can specify desired search conditions for the examination information displayed on the work list display screen 361. The control unit 31 accepts designation of search conditions for examination information to be displayed on the work list display screen 361 in a search condition tab 3621 in the search filter edit screen 362 . 6, the search conditions can be specified as follows: examination type, region category name, request fee, requesting physician, interpretation classification, important findings, interpretation required, interpretation flow status, interpretation status, interpretation person in charge, approval status, approval person in charge, confirmation status, modality, current person in charge, wrong category classification (right), wrong category classification (left), wrong judgment classification, wrong category classification (left and right), matching result, and examination date. Note that the search conditions are not limited to these, and other items may also be used as search conditions. For example, when the examination type "plain X-ray radiography" is specified as a search condition, the control unit 31 extracts examination information whose examination type is "plain X-ray radiography" from the examination information stored in the image server 5. Then, the control unit 31 displays the extracted search information on the work list display screen 361. Furthermore, when the person in charge of image interpretation, "Radiologist A," is specified as a search condition, the control unit 31 extracts examination information for which the person in charge of image interpretation is "Radiologist A" from among the examination information stored in the image server 5. Then, the control unit 31 displays the extracted search information on the work list display screen 361.

[0049] In this embodiment, the user can specify the examination information items to be displayed on the work list display screen 361. The control unit 31 accepts designation of an item of examination information to be displayed on the work list display screen 361 in a display item (examination) tab 3622 in the search filter edit screen 362 shown in FIG. In the example shown in Fig. 7, the items of examination information to be displayed are examination ID, reception number, examination status, reservation status, department issued order, examination room, order date and time, order date, order time, reservation date and time, reservation date, reservation time, reservation date and time (displayed as undecided), reservation date (displayed as undecided), reservation time (displayed as undecided), reception date and time, reception date, reception time, examination start date and time, examination start date, examination start time, examination end date, examination end time, region group, image interpretation flow name, image interpretation flow progress, image interpretation flow status, name of step in charge of the user, step type, current It is possible to specify the current person in charge, person in charge of interpretation, approval status, person in charge of approval, approval date and time, return date and time, clinical diagnosis, special instructions, examination instruction comment (requesting physician), examination instruction comment (specialist), imaging method, supplementary comments, other details, examination comment, contact comment, required comment, free comment, optional comment, examination description, bookmark, print status, body part category name, reading required, examination type, reading status, patient ID, patient name, AI judgment result, user judgment result, difference [presence / absence], difference [location], and confidence level (of "automatically generated findings"). Note that the examination information items to be displayed are not limited to these, and other items may be used as examination information items to display. Then, the control unit 31 causes the work list display screen 361 to display the specified examination information items.

[0050] The difference [presence or absence] is the difference regarding the presence or absence of a lesion in the results of matching (comparison) between the "automatically generated findings" and the "image findings." Specifically, if the "automatically generated findings" indicate "no lesion" (i.e., "no abnormalities (-)") and the "image findings" also indicate "no lesion" (i.e., "no abnormalities (-)"), the result of comparing the two (comparison result) will be "match" (i.e., no difference). Furthermore, if the "automatically generated findings" indicate "lesion present" (i.e., "abnormality present (+)") and the "image findings" also indicate "lesion present" (i.e., "abnormality present (+)"), the result of comparing the two (comparison result) will be "match" (i.e., no difference). Furthermore, if the "automatically generated findings" indicate "lesion present" (i.e., "abnormality present (+)") and the "image findings" indicate "no lesion" (i.e., "no abnormality (-)"), the result of comparing the two (comparison result) will be "mismatch" (i.e., there is a difference). Furthermore, if the "automatically generated findings" indicate "no lesion" (i.e., "no abnormality (-)") and the "image findings" indicate "lesion present" (i.e., "abnormality present (+)"), the result of comparing the two (comparison result) will be "mismatch" (i.e., there is a difference).

[0051] The difference [position] is the difference in the detected position of the lesion in the matching result (comparison result) between the "automatically generated findings" and the "image findings." Specifically, if the "automatically generated findings" are "Lesion location: XX" and the "image findings" are also "Lesion location: XX," the result of comparing the two (comparison result) will be "match" (i.e., no difference). Furthermore, if the "automatically generated findings" are "Lesion location: XX" and the "image findings" are "Lesion location: YY," the result of comparing the two (comparison result) will be "mismatch" (i.e., there is a difference).

[0052] (Highlight setting process) In addition, in this embodiment, the user can set desired highlighting for the examination information displayed on the work list display screen 361. The control unit 31 accepts settings for highlighting the examination information to be displayed on the work list display screen 361 in the design tab 3623 in the search filter edit screen 362 shown in Fig. 8. This processing is a highlight setting processing. When the user presses the condition setting button 3624 in the design tab 3623 shown in FIG. 8 by inputting data via the operation unit 35, the control unit 31 causes the display unit 36 ​​to display a condition setting screen 3625 shown in FIG.

[0053] The control unit 31 accepts, on the condition setting screen 3625, condition settings for highlighting the examination information to be displayed on the work list display screen 361. Specifically, the control unit 31 receives a condition for highlighting in the condition item A and the condition state B shown in FIG. First, the control unit 31 accepts the condition items to be highlighted in the condition item A. In the example shown in Fig. 9, the condition items to be highlighted can be specified as interpretation status, age, sex, examination type, AI determination result (result of "automatically generated findings"), user determination result (result of "image interpretation findings"), admission / discharge (inpatient, outpatient, or outpatient during hospitalization), request fee, requesting physician, confirmation status, difference [position], interpretation person (radiography physician who performs image interpretation), and confidence level (confidence level of "automatically generated findings"). Note that the condition items to be highlighted are not limited to these, and other items may be highlighted as condition items.

[0054] Then, in condition state B, the control unit 31 accepts the condition state for highlighting. For example, in the example shown in Fig. 9, "User Determination Result" is specified in condition item A. In this case, in condition state B, the "User Determination Result" can be specified as "(Lesion) Present" or "(Lesion) Absent."

[0055] Then, the control unit 31 displays the conditions to be highlighted, which are specified in the condition item A and the condition state B, in the condition display C shown in FIG. In the example shown in FIG. 9, the conditions for highlighting are specified as "AI determination result: (lesion) present" and "user determination result: (lesion) absent."

[0056] Similarly, it is also possible to specify "AI determination result: (lesion) absent" and "user determination result: (lesion) present" as conditions for highlighting. Similarly, it is also possible to specify "AI determination result: (lesion) not present" and "user determination result: (lesion) not present" as conditions for highlighting. Similarly, it is also possible to specify "AI determination result: (lesion) present" and "user determination result: (lesion) present" as conditions for highlighting.

[0057] 10, "image interpreter" is specified in condition item A. In this case, in condition state B, "image interpreter" can be specified from "image interpreter A," "image interpreter B," or "image interpreter C." In the example shown in FIG. 10, in the condition display C, "user judgment result: (lesion) none" and "image interpretation person: image interpretation doctor A" are specified as conditions for highlighting.

[0058] In the example shown in FIG. 11, a "certainty level" (certainty level of "automatically generated findings") is specified in condition item A. In this case, a threshold value for the "certainty level" can be specified in condition state B. In the example shown in FIG. 11, the "certainty level" is specified as "50 or more," but the user can arbitrarily set the threshold value and whether it is above or below the threshold value via the operation unit 35. In the example shown in FIG. 11, in the condition display C, "AI determination result: (lesion) present" and "certainty level: 50 or more" are specified as conditions for highlighting.

[0059] Then, the control unit 31 accepts a designation of the highlighting mode in the display mode D shown in FIGS. For example, in the examples shown in FIGS. 9 to 11, font color, background color, bold text, and italic text can be specified as highlighting modes. Note that the highlighting modes are not limited to these and may be other modes, as long as they are display modes that allow a difference to be recognized compared to the display of non-highlighted examination information. A display mode that allows a difference to be recognized includes, for example, displaying in a mode different from non-highlighted examination information. Furthermore, highlighting includes displaying a predetermined combination of automatically generated findings and image interpretation findings in a way that allows a difference to be recognized compared to the display of other combinations. A display that allows a difference to be recognized includes, for example, displaying in a mode different from the display of other combinations. Specifically, in addition to the above, the highlighting mode may be the font of characters, blinking of characters, etc. Alternatively, an item for displaying a mark indicating that highlighting has been set may be added as an item of examination information displayed on the work list display screen 361, and a mark indicating highlighting may be added to the item column of the examination information for which highlighting has been set. Alternatively, the display order or position of the examination information for which highlighting has been set may be changed; specifically, for example, the examination information for which highlighting has been set may be displayed at the top of the work list. As described above, highlighting modes include color and character changes, blinking, and the like. Specifically, color changes include font color changes and background color changes. Character changes include changing characters to bold, italic, and changing the character font. Blinking includes blinking characters and blinking colors. Highlighting also includes adding an item for highlighting and marking that item. Highlighting also includes making a specific row or column stand out, and changing the display order, display position, and display priority of a specific row or column.

[0060] As described above, the highlighting conditions set on the condition setting screen 3625 are displayed in the field E in the design tab 3623 shown in FIG.

[0061] Next, FIG. 12 shows an example of a work list 3612 displayed on the work list display screen 361. 12, the examination information displayed in the work list 3612 is examination information when examination information with an examination type of "plain X-ray imaging" is specified as a search condition in the search condition tab 3621. In other words, the control unit 31 extracts examination information with an examination type of "plain X-ray imaging" from the examination information stored in the image server 5, and displays it in the work list 3612. Also, in the example shown in Figure 12, the items of examination information displayed in the worklist 3612 are the examination ID specified in the display item (examination) tab 3622, reading required, examination type, reading flow name, reading status, approval status, patient ID, patient name, AI judgment result, user judgment result, and difference [yes / no].

[0062] In the example shown in FIG. 12, the test information F and test information G are highlighted with a background color different from that of the other test information. For test information F, the AI ​​judgment result is "Lesion: 1 (lesion present)" and the user judgment result is "No lesion present." In other words, when "AI judgment result: (lesion) present" and "user judgment result: (lesion) absent" are specified as the conditions for highlighting on the condition setting screen 3625, the control unit 31 highlights the test information that meets the specified conditions as test information F. Furthermore, the AI ​​judgment result of test information G is "no lesion" and the user judgment result is "lesion: 1 (lesion present)." In other words, when "AI judgment result: (lesion) no" and "user judgment result: (lesion) present" are specified as the conditions for highlighting on the condition setting screen 3625, the control unit 31 highlights the test information that meets the specified conditions as test information G. In the example shown in FIG. 12, if there is a difference between the AI ​​judgment result and the user judgment result as a result of comparison, a check mark is displayed in the "Difference [Presence / absence]" column.

[0063] 13 shows an example of a work list 3612 in which different highlighting is set than in Fig. 12. The following mainly describes the parts that are different from the work list 3612 shown in Fig. 12. In the example shown in FIG. 13, the item of examination information displayed in the work list 3612 is designated as "difference [position] present."

[0064] In the example shown in FIG. 13, the test information H and test information I are highlighted with a background color different from that of the other test information. For test information H, the AI ​​judgment result is "Lesion: 1 (lesion present) (lesion detection location: XX)", and the user judgment result is "Lesion: 1 (lesion present) (lesion detection location: YY)", and "Difference [location]: present". Furthermore, for test information I, the AI ​​judgment result is "Lesion: 1 (lesion present) (lesion detection location: YY)", and the user judgment result is "Lesion: 1 (lesion present) (lesion detection location: XX)", and "Difference [location]: present". In other words, when "Difference [position]: Yes" is specified as the condition for highlighting on the condition setting screen 3625, the control unit 31 highlights the test information that meets the specified condition, such as test information H and test information I.

[0065] 14 shows an example of a worklist 3612 in which different highlighting is set than in Fig. 12 and Fig. 13. The following mainly describes the parts that are different from the worklist 3612 shown in Fig. 12. In the example shown in FIG. 14, the degree of certainty is designated as an item of the examination information displayed in the work list 3612.

[0066] In the example shown in FIG. 14, the test information J has a background color different from that of the other test information, and is highlighted. For test information J, the AI ​​judgment result is "lesion: 1 (lesion present)," the user judgment result is "lesion absent," and the confidence level is "60." In other words, when the conditions for highlighting are specified on the condition setting screen 3625 as "AI judgment result: (lesion) present," "user judgment result: (lesion) absent," and "confidence level: 50 or higher," the control unit 31 highlights test information that meets the specified conditions, as in test information J.

[0067] Also, in the example shown in Figure 14, if the conditions for highlighting are specified on the condition setting screen 3625 as ``AI judgment result: (lesion) present,'' ``user judgment result: (lesion) absent,'' and ``certainty level: 50 or less,'' the control unit 31 will highlight the examination information that meets the specified conditions, for example, examination condition K.

[0068] 〔effect〕 As described above, the analysis device 3 as an image interpretation management device in this embodiment includes a first acquisition unit (control unit 31) that acquires "automatically generated findings" obtained by computer processing of medical information, a second acquisition unit (data acquisition unit 33) that acquires "image interpretation findings" created by the user based on the medical information, and a setting unit (control unit 31) that enables the user to set, by operation, the combination of the results of the "automatically generated findings" and the results of the "image interpretation findings" to be highlighted. Therefore, even if the highlighting required for image interpretation differs depending on the medical facility, a predetermined highlighting can be set according to the user's request. This makes it possible to set more preferable highlighting depending on the facility environment, the facility's operational status, and the experience and preferences of users (doctors and image interpreters).

[0069] In this embodiment, the control unit 31 as a setting unit allows the user to set which combination of the results of the "automatically generated findings" and the results of the "image findings" to be highlighted. Therefore, a combination of predetermined "automatically generated findings" and "image interpretation findings" that the user (for example, a secondary image interpretation physician) wants to check can be highlighted.

[0070] In this embodiment, the result of the "automatically generated findings" includes the result of whether or not a lesion is detected in the "automatically generated findings," and the result of the "image findings" includes the result of whether or not a lesion is detected in the "image findings." Therefore, the combination of the result of whether or not a lesion is detected in a predetermined "automatically generated finding" and the result of whether or not a lesion is detected in an "image interpretation finding" that the user wants to check can be highlighted.

[0071] In this embodiment, the results of "automatically generated findings" include the results of the detected positions of lesions in "automatically generated findings," and the results of "image findings" include the results of the detected positions of lesions in "image findings." Therefore, it is possible to highlight the combination of the results of the lesion detection position in the predetermined "automatically generated findings" and the results of the lesion detection position in the "image findings" that the user wants to check. In other words, for example, it is possible to highlight a case where the results of the "automatically generated findings" and the "image findings" both indicate the presence of a lesion, but the positions of the detected lesions are different.

[0072] The analysis device 3 of this embodiment also includes a display unit 36 ​​that displays highlighting based on the combination of highlighting set by the setting unit. Therefore, the combination of the results of the "automatically generated findings" and the results of the "image findings" that corresponds to the combination to be highlighted set by the setting unit can be highlighted and presented to the user.

[0073] Furthermore, in this embodiment, the control unit 31 as a setting unit allows the user to set which combinations of the results of the "automatically generated findings" and the results of the "image findings" to be highlighted, and the threshold value of the confidence level of the "automatically generated findings", and is equipped with a display unit 36 ​​that highlights the combinations of the results of the "automatically generated findings" and the results of the "image findings" based on the combinations to be highlighted set by the setting unit and the threshold value of the confidence level of the "automatically generated findings". Therefore, if a user desires highlighting that takes into account the certainty of the "automatically generated findings," the combination of the results of the "automatically generated findings" and the results of the "image interpretation findings" that corresponds to the desired combination and certainty of highlighting can be highlighted and presented to the user.

[0074] Furthermore, in this embodiment, when the certainty of the "automatically generated findings" is equal to or greater than a threshold, the display unit 36 ​​highlights the combination of the results of the "automatically generated findings" and the results of the "image findings." Therefore, if a user wants to check only the results of "automatically generated findings" with a high degree of certainty (above a threshold), the combination of the results of "automatically generated findings" and "image findings" including the results of "automatically generated findings" with a high degree of certainty can be highlighted.

[0075] Furthermore, in this embodiment, when the certainty of the "automatically generated findings" is equal to or less than a threshold, the display unit 36 ​​highlights the combination of the results of the "automatically generated findings" and the results of the "image findings." For example, if the confidence level of the "automatically generated findings" is low (below a threshold) and the result of the "automatically generated findings" is no lesion, it is possible that the AI ​​analysis has missed a lesion. If the user wants to confirm that the AI ​​analysis has missed such a lesion, the system can highlight combinations of the results of the "automatically generated findings" and the results of the "image findings," including cases where the confidence level of the "automatically generated findings" is low and the result of the "automatically generated findings" is no lesion.

[0076] Furthermore, in this embodiment, the control unit 31 as a setting unit can be set by a user operation to highlight combinations of the results of the "automatically generated findings" and the results of the "image findings" where the result of the "automatically generated findings" indicates that a lesion has been detected and the result of the "image findings" indicates that a lesion has not been detected. Therefore, if the result of the "automatically generated findings" indicates the presence of a lesion and the result of the "image interpretation findings" indicates the absence of a lesion, there is a possibility that the radiologist interpreting the images may have overlooked the lesion, and this can be prevented from being overlooked.

[0077] Furthermore, in this embodiment, the control unit 31 as a setting unit can be set by a user operation to highlight combinations of the results of the "automatically generated findings" and the results of the "image findings" where the result of the "automatically generated findings" is that no lesion is detected and the result of the "image findings" is that a lesion is detected. Therefore, if the result of the "automatically generated findings" is no lesion and the result of the "image interpretation findings" is that a lesion is present, there is a possibility that the AI ​​analysis has overlooked the lesion, and this can be prevented from being overlooked.

[0078] Furthermore, in this embodiment, the control unit 31 as a setting unit can be set by a user operation to highlight combinations of the results of the "automatically generated findings" and the results of the "image findings" where the result of the "automatically generated findings" is no detection of a lesion and the result of the "image findings" is no detection of a lesion. Therefore, if the result of the "automatically generated findings" is no lesion and the result of the "image interpretation findings" is no lesion, there is a possibility that the radiologist who performs the AI ​​analysis and interpretation may have overlooked the lesion, and this can be prevented from being overlooked.

[0079] Furthermore, in this embodiment, the control unit 31 as a setting unit can be set by a user operation to highlight combinations of the results of the "automatically generated findings" and the results of the "image findings" where the result of the "automatically generated findings" indicates that a lesion has been detected and the result of the "image findings" indicates that a lesion has been detected. Therefore, for example, if the confidence level of the "automatically generated findings" is low (below a threshold), it is possible to confirm that the AI ​​analysis has incorrectly detected a lesion.

[0080] [Modification] Although the embodiments of the present invention have been described above, it goes without saying that the present invention is not limited to these embodiments and that various modifications are possible without departing from the spirit of the present invention.

[0081] For example, in the above embodiment, the medical information to be analyzed by the analysis device 3 is a medical image, but the medical information is not limited to a medical "image." Information obtained through various tests on patients may be broadly included in medical information, and for example, results obtained from various tests, such as electrocardiogram waveform data, heart sound data, and data related to blood flow, may also be included in medical information.

[0082] In this embodiment, in FIG. 1, the analysis device 3, the interpretation terminal 4, and the image server 5 are illustrated as separate and independent devices, but the analysis device 3 and the image server 5, or the analysis device 3, the interpretation terminal 4, and the image server 5 may be configured as a single device or a single system.

[0083] 4 is used as the workflow for image interpretation in this embodiment, but the present invention is not limited to this. The workflow for image interpretation may be a workflow as shown in FIG. In the example shown in Figure 15, primary interpretation, secondary interpretation, and AI analysis are performed in parallel, and the "automatically generated findings" that are the results of the AI ​​analysis are compared with the "image findings" from the primary interpretation obtained in the primary interpretation. The "automatically generated findings" are also compared with the "image findings" from the secondary interpretation obtained in the secondary interpretation. The final interpretation is then performed by referring to the results of the comparison of the two. In this case, the primary and secondary interpretations can be performed in parallel, so unlike the workflow shown in Figure 4, the secondary interpretation physician can begin interpretation without waiting for the results of the primary interpretation. Furthermore, even if the results of the primary and secondary readings differ, the diagnosis can be confirmed by comparing each with the results of the AI ​​analysis. As a result, the time required to make a diagnosis can be shortened. In addition, when primary reading, secondary reading, and AI analysis are performed in parallel, the "automatically generated findings," the "image findings" from the primary reading, and the "image findings" from the secondary reading can be compared to obtain matching results.

[0084] 9 to 11, in this embodiment, the control unit 31 accepts, on a condition setting screen 3625, condition settings for highlighting the examination information to be displayed on the work list display screen 361. That is, the control unit 31 as a setting unit allows the user to set, by operation, which combination of the results of the "automatically generated findings" and the results of the "image findings" to be highlighted. However, the method for setting the conditions for highlighting is not limited to the examples shown in FIGS. For example, the control unit 31 may accept, as a condition setting for highlighting, whether or not to highlight a combination of a predetermined "automatically generated finding" result and "image interpretation finding" result. In this case, the control unit 31 as a setting unit allows a user to set, by operation, which combination of the "automatically generated finding" result and the "image interpretation finding" result to be highlighted.

[0085] In addition, in this embodiment, the control unit 31 causes the display unit 36 ​​to highlight based on the combination of highlighting set by the setting unit, but this is not limited to this. The analysis device 3 may be configured without the display unit 36, in which case the control unit 31 causes the various display units of the interpretation terminal 4, the image server 5, and external devices (not shown) to highlight.

[0086] It goes without saying that the present invention is not limited to the above-described embodiments and modifications, and can be modified as appropriate without departing from the spirit of the present invention. [Explanation of symbols]

[0087] 1. Modality 2 Console 3. Analysis device (image reading management device) 4. Image reading terminal 5. Image Server 31 control unit (first acquisition unit, second acquisition unit, setting unit, display control unit) 32 Storage section 321 Program Memory Unit 33 Data Acquisition Section 34 Data output section 35 Control section 36 Display section 37 Bus 100 Medical Imaging Systems

Claims

1. A first acquisition unit that acquires automatically generated findings obtained by computer processing of medical information from a first examination; a second acquisition unit that acquires image findings created by a user based on the medical information; a control unit that displays on a display unit a work list that displays a list of multiple examinations including the first examination; a setting unit that allows highlighting conditions to be set by a user operation; Equipped with the highlighting condition includes a first condition regarding a difference between the automatically generated findings and the image findings of the examination; The image interpretation management device is characterized in that the control unit displays the work list on the display unit in a display format that highlights the examinations among the plurality of examinations that satisfy the highlighting conditions.

2. The image reading management device described in Claim 1, wherein the first condition includes a condition that there is no difference between the automatically generated findings and the image reading findings.

3. The image reading management device described in claim 1, wherein the highlighting conditions include a second condition relating to at least one of the image reading status of the examination, the image reading person for the examination, and the confirmation status of the examination.

4. 4. The image interpretation management device according to claim 1, wherein the results of the automatically generated findings include a result of whether or not a lesion has been detected in the automatically generated findings, and the results of the image interpretation findings include a result of whether or not a lesion has been detected in the image interpretation findings.

5. 5. The image interpretation management device according to claim 1, wherein the results of the automatically generated findings include results of the detected positions of the lesions in the automatically generated findings, and the results of the image interpretation findings include results of the detected positions of the lesions in the image interpretation findings.

6. An image reading management device described in any one of claims 1 to 5, which is provided with a display unit on which the work list is displayed.

7. the setting unit allows the highlighting condition and a condition related to a threshold value of a certainty of the automatically generated finding to be set by a user operation; 7. The image interpretation management device according to claim 1, wherein the control unit causes the display unit to display the work list in a display format that highlights examinations among the plurality of examinations that satisfy the highlighting conditions and the conditions related to the threshold for the certainty of the automatically generated findings, based on the highlighting conditions and the conditions related to the threshold for the certainty of the automatically generated findings.

8. The image interpretation management device according to claim 7 , wherein the control unit highlights an examination that satisfies the highlighting condition and in which the certainty of the automatically generated findings is equal to or greater than the threshold value.

9. The image interpretation management device according to claim 7 , wherein the control unit highlights an examination that satisfies the highlighting condition and in which the certainty of the automatically generated findings is equal to or less than the threshold value.

10. An image reading management device as described in any one of claims 1 to 9, wherein the first condition includes the result of the automatically generated findings being that a lesion is detected and the result of the image reading findings being that a lesion is not detected, and the result of the automatically generated findings and the result of the image reading findings being inconsistent.

11. An image reading management device as described in any one of claims 1 to 10, wherein the first condition includes a result of the automatically generated findings being that no lesion is detected and a result of the image reading findings being that a lesion is detected, and the result of the automatically generated findings and the result of the image reading findings are inconsistent.

12. An image reading management device as described in any one of claims 1 to 11, wherein the first condition includes the result of the automatically generated findings being no detection of a lesion and the result of the image reading findings being no detection of a lesion, and the result of the automatically generated findings and the result of the image reading findings being consistent.

13. An image reading management device as described in any one of claims 1 to 12, wherein the first condition includes the result of the automatically generated findings being that a lesion has been detected, and the result of the image reading findings being that a lesion has been detected, and the result of the automatically generated findings and the result of the image reading findings being consistent.

14. On the computer, a first acquisition function for acquiring automatically generated findings obtained by computer processing of the medical information of the first examination; a second acquisition function for acquiring image interpretation findings prepared by a user based on the medical information; a control function for displaying, on a display unit, a work list displaying a list of a plurality of examinations including the first examination; A setting function that allows the highlighting conditions to be set by user operation; To achieve this, the highlighting condition includes a first condition regarding a difference between the automatically generated findings and the image findings of the examination; The control function is a program that displays the work list on the display unit in a display format that highlights the examinations that satisfy the highlighting conditions among the plurality of examinations.

15. The program described in Claim 14, wherein the first condition includes a condition that there is no difference between the automatically generated findings and the image findings.

16. The program described in Claim 14, wherein the highlighting conditions include a second condition relating to at least one of the reading status of the examination, the person reading the examination, and the confirmation status of the examination.

17. The program according to any one of claims 14 to 16, wherein the results of the automatically generated findings include a result of whether or not a lesion has been detected in the automatically generated findings, and the results of the image findings include a result of whether or not a lesion has been detected in the image findings.

18. The program according to any one of claims 14 to 17, wherein the results of the automatically generated findings include results of the detected positions of the lesions in the automatically generated findings, and the results of the image findings include results of the detected positions of the lesions in the image findings.

19. The setting function allows the highlighting condition and a condition regarding a threshold of the confidence level of the automatically generated finding to be set by a user operation; 19. The program according to claim 14, wherein the control function causes the display unit to display the work list in a display format that highlights tests among the plurality of tests that satisfy the highlighting conditions and the conditions related to the threshold for the certainty of the automatically generated findings, based on the highlighting conditions and the conditions related to the threshold for the certainty of the automatically generated findings.

20. 20. The program according to claim 19, wherein the control function highlights an examination that satisfies the highlighting condition and in which the certainty of the automatically generated findings is equal to or greater than the threshold.

21. 20. The program according to claim 19, wherein the control function highlights an examination that satisfies the highlighting condition and in which the certainty of the automatically generated finding is equal to or less than the threshold.

22. A program described in any one of claims 14 to 21, wherein the first condition includes the result of the automatically generated findings being that a lesion is detected and the result of the image reading findings being that a lesion is not detected, and the result of the automatically generated findings and the result of the image reading findings being inconsistent.

23. A program described in any one of claims 14 to 22, wherein the first condition includes the result of the automatically generated findings being that no lesion is detected and the result of the image reading findings being that a lesion is detected, and the result of the automatically generated findings and the result of the image reading findings are inconsistent.

24. A program described in any one of claims 14 to 23, wherein the first condition includes the result of the automatically generated findings being no detection of a lesion and the result of the image reading findings being no detection of a lesion, and the result of the automatically generated findings and the result of the image reading findings being consistent.

25. A program described in any one of claims 14 to 24, wherein the first condition includes the result of the automatically generated findings being that a lesion has been detected, and the result of the image reading findings being that a lesion has been detected, and the result of the automatically generated findings and the result of the image reading findings being consistent.

26. A first acquisition step of acquiring automatically generated findings obtained by computer processing of medical information from a first examination; a second acquisition step of acquiring image findings prepared by a user based on the medical information; a control step of displaying a work list on a display unit that displays a list of multiple examinations including the first examination; a setting step for allowing the highlighting conditions to be set by a user operation; Including, the highlighting condition includes a first condition regarding a difference between the automatically generated findings and the image findings of the examination; An image interpretation management method, characterized in that in the control step, the work list is displayed on the display unit in a display format that highlights the examinations among the plurality of examinations that satisfy the highlighting conditions.

Images