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

Abstract

This invention provides a picture interpretation management device, program, and picture interpretation management method that can realize a desired workflow in picture interpretation. [Solution] The image interpretation management device includes a first acquisition unit for acquiring automatically generated findings, a second acquisition unit for acquiring first image interpretation findings created by the user, a third acquisition unit for acquiring second image interpretation findings created by the user, a comparison unit for comparing the automatically generated findings with at least one of the first and second image interpretation findings, a presentation unit for presenting the comparison results between the automatically generated findings and the image interpretation findings to the user based on a series of workflows, and a setting unit for pre-setting a series of workflows. The setting unit allows setting at least one workflow as a series of workflows, which includes a workflow for acquiring the second image interpretation findings after comparing the automatically generated findings with the first image interpretation findings, and a workflow for acquiring the second image interpretation findings after acquiring the first image interpretation findings and comparing the automatically generated findings with the second image interpretation findings.

Description

Technical Field

[0001] The present invention relates to a radiology management device, a program, and a radiology management method.

Background Art

[0002] In recent years, with the development of AI (Artificial Intelligence) technology, attempts have been made to introduce AI-based analysis in the medical field to support the analysis and diagnosis of medical information such as image diagnosis, which has conventionally been performed by doctors, using AI. In the clinical field of medicine, it is required to perform examinations and diagnoses appropriately and quickly, streamline and optimize diagnoses, and reduce the burden on doctors. The introduction of AI analysis is expected to contribute to the streamlining and optimization of such diagnoses.

[0003] For example, Patent Document 1 discloses an apparatus including an acquisition unit that acquires an automatically generated finding generated by analyzing examination data (medical information) using AI and a reading finding input from an operation unit with respect to the examination data, and an evaluation unit that acquires change information input by a user with respect to the reading finding after presenting the automatically generated finding to the user and evaluates either the automatically generated finding or the reading finding based on the change information.

Prior Art Documents

Patent Documents

[0004] [[ID=三十]] Japanese Patent Application Laid-Open No. 2017-010577

Summary of the Invention

[0006] Furthermore, in secondary image interpretation, there is a need for efficient interpretation by having the secondary radiologist prioritize the review of images that are likely to have been overlooked by the primary radiologist. However, conventional methods have the problem that they cannot compare the findings of the primary radiologist with those of the automated system before secondary interpretation, and therefore cannot adopt a workflow that prioritizes the interpretation of images that are likely to be overlooked.

[0007] Thus, the workflow required for image interpretation and other procedures varies depending on the medical facility. Developing and manufacturing separate devices (image interpretation management devices, analysis devices) to achieve the desired workflow in this regard is costly and time-consuming.

[0008] The present invention has been made in view of the problems of the prior art described above, and aims to provide a picture interpretation management device, program, and picture interpretation management method that can realize a desired workflow in picture interpretation. [Means for solving the problem]

[0009] To solve the above problems, the invention described in claim 1 is a picture interpretation management device, A first acquisition unit that acquires automatically generated findings obtained by computer processing of medical information, A second acquisition unit that acquires a first image interpretation finding created by the user based on the aforementioned medical information, A third acquisition unit that acquires a second set of readings created by the user based on the aforementioned medical information, A comparison unit that compares the automatically generated findings with at least one of the first and second interpretation findings, Based on a series of workflows, a presentation unit presents to the user the results of comparing the automatically generated findings with at least one of the image interpretation findings. A setting unit that allows the aforementioned series of workflows to be pre-configured based on user operations, Equipped with, The aforementioned setting unit, as part of the series of workflows, A workflow to obtain the second interpretation findings after comparing the automatically generated findings with the first interpretation findings, A workflow in which, after obtaining the first image interpretation findings, the second image interpretation findings are obtained and the automatically generated findings are compared with the second image interpretation findings, It is characterized by allowing the configuration of at least one workflow. Furthermore, the invention described in claim 3 is another aspect of the image interpretation management device, It includes a setting unit that allows pre-configuration of a series of image interpretation workflows until the diagnosis of medical information is finalized. The setting unit is, The system is characterized by the ability to set up a workflow in which a diagnostic result is determined based on a comparison between the first findings obtained by a first radiologist interpreting the medical information and the automatically generated findings obtained by computer processing the medical information.

[0010] Furthermore, the invention described in claim 6 is a program, On the computer, A first acquisition function that acquires automatically generated findings obtained by computer processing of medical information, A second acquisition function that acquires a first image interpretation finding created by the user based on the aforementioned medical information, A third acquisition function that acquires a second set of imaging findings created by the user based on the aforementioned medical information, A comparison function that compares the automatically generated findings with at least one of the first and second interpretation findings, A presentation function that presents the comparison result between the automatically generated findings and the at least one radiological finding to the user based on a series of workflows, A setting function that enables the pre - setting of the series of workflows based on user operations, is realized, The setting function uses, as the series of workflows, A workflow that acquires the second radiological finding after comparing the automatically generated finding with the first radiological finding, A workflow that acquires the second radiological finding after acquiring the first radiological finding and then compares the automatically generated finding with the second radiological finding, characterized in that at least one of the workflows can be set. Further, the invention according to claim 7 is another aspect of the program, A computer is caused to realize a setting function that enables the pre - setting of a series of radiological workflows until the diagnosis result of medical information is determined, The setting function can set a workflow for determining a diagnosis result based on the result of comparing the first radiological finding obtained by a first radiologist reading the medical information with the automatically generated finding obtained by computer - processing the medical information.

[0011] Further, the invention according to claim 10 is a radiology management method in which each step is executed by a computer, A first acquisition step of acquiring an automatically generated finding obtained by computer - processing medical information, A second acquisition step of acquiring a first radiological finding created by a user based on the medical information, A third acquisition step of acquiring a second radiological finding created by a user based on the medical information, A comparison step of comparing the automatically generated finding with at least one of the first radiological finding and the second radiological finding, A presentation step of presenting the comparison result between the automatically generated finding and the at least one radiological finding to the user based on a series of workflows, A setting step that enables the presetting of the series of workflows based on user operations; causing a computer to perform; The setting step includes, as the series of workflows, a workflow for obtaining the second reading finding after comparing the automatically generated finding with the first reading finding; a workflow for obtaining the second reading finding after obtaining the first reading finding and comparing the automatically generated finding with the second reading finding; and is characterized in that at least one of the workflows can be set.

Advantages of the Invention

[0012] According to the present invention, a desired workflow can be realized in reading.

Brief Description of the Drawings

[0013] [Figure 1] It is an overall configuration diagram of a medical image system in this embodiment. [Figure 2] It is a main part block diagram showing a functional configuration of an embodiment of an analysis device as a reading management device according to the present invention. [Figure 3] It is a diagram showing an example of a work list display screen. [Figure 4] It is a diagram showing an example of a workflow setting screen. [Figure 5] It is an explanatory diagram schematically showing the content of the "first workflow" set on the workflow setting screen shown in FIG. 4. [Figure 6] It is a diagram showing an example of a workflow setting screen. [Figure 7] It is an explanatory diagram schematically showing the content of the "second workflow" set on the workflow setting screen shown in FIG. 6. [Figure 8] It is a diagram showing an example of a workflow setting screen. [Figure 9] It is an explanatory diagram schematically showing the content of the "third workflow" set on the workflow setting screen shown in FIG. 8. [Modes for carrying out the invention]

[0014] The following describes one embodiment of the image interpretation management device, image interpretation management method, and program according to the present invention. However, the scope of the invention is not limited to the illustrated example.

[0015] [Configuration of the medical imaging system] The image interpretation management device in this embodiment performs, for example, analysis of medical images, which are medical information, within a medical image system, and the "analysis device" referred to below functions as the "image interpretation management device." Figure 1 shows the system configuration of the medical imaging system 100.

[0016] As shown in Figure 1, the medical imaging system 100 includes modality 1, console 2, analysis device 3, image interpretation terminal 4, image server 5, etc., which are connected via a communication network N such as a LAN (Local Area Network), WAN (Wide Area Network), or the Internet. Each device constituting the medical imaging system 100 conforms to the HL7 (Health Level Seven) or DICOM (Digital Image and Communications in Medicine) standards, and communication between each device is conducted in accordance with HL7 or DICOM. The number of modality 1, console 2, image interpretation terminal 4, etc., is not particularly limited.

[0017] Modality 1 is an image generation device such as an X-ray imaging device (DR, CR), an ultrasound diagnostic device (US), a CT scanner, or an MRI scanner. Based on examination order information transmitted from a RIS (Radiology Information System) or the like (not shown), it captures images of the patient's examination target area and generates medical images as medical information. The medical images generated in Modality 1 have supplementary information (patient information, examination information, image ID, etc.) written to the image file header in accordance with the DICOM standard. The medical images with this supplementary information are then transmitted to the analysis device 3 or the image interpretation terminal 4 via the console 2 or the like.

[0018] Console 2 is an imaging control device that controls imaging in Modality 1. Console 2 outputs imaging conditions and image reading conditions to Modality 1 and acquires image data of medical images captured in Modality 1. Console 2 is composed of a control unit, display unit, operation unit, communication unit, storage unit, etc. (not shown), and each unit is connected by a bus.

[0019] 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, for example, a medical image management device such as PACS (Picture Archiving and Communication System).

[0020] Figure 2 is a block diagram showing the functional configuration of the analysis device 3. As shown in Figure 2, the analysis device 3 is configured to include a control unit 31, a storage 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.

[0021] The data acquisition unit 33 is an acquisition unit that acquires various types of data from external devices (for example, the console 2 or the image interpretation terminal 4 described later). The data acquisition unit 33 is configured, for example, as a network interface, and is configured to receive data from an external device connected via a communication network N by wire or wireless connection. In this embodiment, the data acquisition unit 33 is configured as a network interface, but it can also be configured as a port into which a USB memory stick or SD card can be inserted.

[0022] In this embodiment, the data acquisition unit 33 acquires image data of medical images from, for example, the console 2. The data acquisition unit 33 also acquires information from the image interpretation terminal 4, such as diagnostic results related to medical images created by a user (e.g., a doctor) based on the medical images (information on the detection of lesions that can be read from the medical images), and image interpretation reports which are the interpretation results by a radiologist (e.g., a radiologist who performs primary and secondary interpretations).

[0023] Specifically, the data acquisition unit 33 functions as a "second acquisition unit" that acquires the "first interpretation findings" (results of the first interpretation) created by the user (e.g., the primary radiologist) based on medical information, and a "third acquisition unit" that acquires the "second interpretation findings" (results of the second interpretation) created by the user (e.g., the secondary radiologist) based on medical information. Furthermore, if supplementary information is added to the medical image, such as when a region of interest (ROI) is set by the user (e.g., the radiologist), the data acquisition unit 33 also acquires this supplementary information.

[0024] The "first reading findings" and "second reading findings" acquired by the data acquisition unit 33 include various types of information, such as information regarding the presence or absence of lesions (i.e., information indicating whether an abnormality was detected as "+ (abnormal finding present)" or "- (abnormal finding absent)"), the name of the lesion, and the location of the lesion. The specific content of the information included in the "first reading findings" and "second reading findings" is not limited to those exemplified here; it may include only a part of these, or it may include other types of information. The "first reading findings" and "second reading findings" acquired by the data acquisition unit 33 are sent to the control unit 31.

[0025] The data output unit 34 is an output unit that outputs information processed by the analysis device 3. The destination to which the data output unit 34 outputs various types of information is not particularly limited. For example, it may be the display unit 36 ​​of the analysis device 3, or it may be the image interpretation terminal 4 or image server 5 described later, or various external display devices not shown. As will be described later, in this embodiment, a "predetermined workflow" is set based on user operation, and the analysis device 3 outputs the processed information to the display unit 36, etc., so that various displays are shown based on the set "predetermined workflow". The data output unit 34 can be, for example, a network interface for communicating with the image interpretation terminal 4 or the image server 5, a connector for connecting to external devices (e.g., display devices not shown, printers, etc.), or ports for various media such as USB memory.

[0026] The operation unit 35 consists of a keyboard equipped with various keys, a pointing device such as a mouse, or a touch panel attached to the display unit 36. The operation unit 35 is capable of user input, and specifically outputs operation signals to the control unit 31 through key operations on the keyboard, mouse operations, or touch operations on the touch panel. In this embodiment, as will be described later, the user can customize their desired workflow (specific procedures in image interpretation, etc.), and the operation unit 35 receives user input and outputs an operation signal resulting from that input to the control unit 31.

[0027] The display unit 36 ​​is configured with a monitor such as an LCD (Liquid Crystal Display) and displays various screens according to the instructions of the display signals input from the control unit 31. Note that the monitor is not limited to one, and may be provided with multiple monitors. As will be described later, the display unit 36 ​​displays various information as appropriate based on the display data output from the control unit 31.

[0028] In this embodiment, as described above, the user can customize their desired workflow (specific procedures in image interpretation, etc.), and the display unit 36 ​​displays a workflow setting screen 361 for inputting and setting a "predetermined workflow" (see Figures 4, 6, and 8 as an example of the workflow setting screen 361). The user can set the order of image interpretation (primary interpretation and secondary interpretation), AI analysis matching process (comparison process), conditions for performing various processes, and specific processing details to be performed in each process, by operating the operation unit 35, etc., while viewing the screen, so that the desired flow is achieved. The display screen of the display unit 36 ​​may also have an integrated touch panel. In this case, the user can perform various inputs, such as rearranging the frames in the workflow setting screen 361 or rewriting the contents of each frame, by touch operation.

[0029] Furthermore, in this embodiment, the display unit 36 ​​functions as a presentation unit that presents to the user the comparison results between the "automatically generated findings" described later and at least one of the image interpretation findings (i.e., the "first image interpretation findings" and the "second image interpretation findings") based on a "predetermined workflow". Furthermore, the content displayed on the display unit 36 ​​is not limited to the comparison results between the "automatically generated findings" and the interpretation findings; various types of information and images can also be displayed. Furthermore, the display unit is not limited to the display unit 36; for example, it could be a terminal for image interpretation 4, an image server 5, or various external display devices.

[0030] Figure 3 shows an example of a worklist display screen 362 that includes the results of comparing the "automatically generated findings" displayed on the presentation unit (display unit 36, etc.) with the interpretation findings. The worklist display screen 362 is a screen that users, who are physicians (primary radiologists, secondary radiologists), refer to when interpreting radiographs (primary interpretation, secondary interpretation, confirmation interpretation, etc.). As shown in Figure 3, the worklist display screen 362 displays scheduled image interpretations associated with "Patient ID," "Patient Name," "Examination Type," etc. Furthermore, to make it easy for viewers to understand the current stage of each patient's examination on the list, the "Image Interpretation Status" and "Approval Status" are displayed.

[0031] Furthermore, the worklist display screen 362 displays the "automatically generated findings" (referred to as "AI judgment results" in Figure 3), which are the results of the AI ​​analysis described later; the interpretation findings by the user physician (primary radiologist, secondary radiologist, etc.) (i.e., "first interpretation findings" and "second interpretation findings"; referred to as "user judgment results" in Figure 3); and the results of comparing the "automatically generated findings" with the interpretation findings (at least one of "first interpretation findings" or "second interpretation findings"). In the example shown in Figure 3, a checkmark (✓) is displayed if there is a difference in the comparison results. In Figure 3, the portion of the worklist display screen 362 that presents the user with "automatically generated findings," "interpretation findings," and "comparison results" between "automatically generated findings" and "interpretation findings" (the portion displaying "AI judgment results," "user judgment results," and "comparison results (differences found)" in the figure) is enclosed in a dashed line as the findings presentation area 362a.

[0032] Referring to Figure 3, the contents displayed in the findings presentation field 362a within the worklist display screen 362 will be explained in detail. For example, in the illustrated example, in the case of patient A, AI analysis and primary interpretation by a primary radiologist are performed. The "automatically generated findings" obtained by the AI ​​analysis ("AI judgment result" in the figure) indicate "no lesion" (i.e., "no abnormality (-)"), and the "first interpretation findings" obtained from the primary interpretation ("user judgment result" in the figure) also indicate "no lesion" (i.e., "no abnormality (-)"). The result of comparing the two (comparison result) is "agreement" (i.e., no difference). In contrast, in the case of patient C, for example, both AI analysis and primary interpretation by a primary radiologist were performed. However, the "automatically generated findings" obtained by the AI ​​analysis ("AI judgment result" in the figure) determined "lesion: 1" (i.e., "abnormal (+)" indicating one lesion), while the "first interpretation findings" obtained from the primary interpretation ("user judgment result" in the figure) determined "no lesion" (i.e., "no abnormality (-)"). The result of comparing the two (comparison result) is "inconsistent" (i.e., there is a difference).

[0033] The control unit 31 includes a CPU (Central Processing Unit) and RAM (Random Access Memory). It is composed of the following components and comprehensively controls the operation of each part of the analysis device 3. Specifically, the CPU reads various processing programs stored in the program storage unit 321 of the memory unit 32, loads them into RAM, and executes various processes according to the program. In this embodiment, the control unit 31 works in cooperation with the program to realize various functions as follows.

[0034] 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 medical images acquired by the data acquisition unit 33 are subjected to lesion detection and analysis processing, and the detection and analysis results of one or more types of lesions are output as "first medical information." Here, the computer processing includes, for example, AI analysis using AI (Artificial Intelligence) which performs image diagnosis and image analysis, including lesion detection by CAD (Computer-Aided Diagnosis).

[0035] In this embodiment, the control unit 31, acting as the "first acquisition unit," is shown as an example of acquiring the detection result of the presence or absence of a lesion (i.e., the result that the detection of an abnormal area is "+ (abnormal finding present)" or "- (abnormal finding absent)") as the "automatically generated finding." However, the "automatically generated finding" is not limited to the detection result of the presence or absence of a lesion. 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 the "automatically generated finding" by computer processing the medical information (medical images) based on the learned correspondence between medical information (medical images) and medical information. In other words, a machine learning model created by training with a large amount of training data (for example, pairs of medical images showing lesions and correct labels (such as the lesion area in the medical image and the diagnostic name of the lesion (type of lesion))) is used to detect and analyze lesions from input medical images. When "automatically generated findings" are obtained in this manner, information such as the name and location of the lesion is also attached to the medical image data as supplementary information.

[0036] In this embodiment, the control unit 31 also functions as a comparison unit. The control unit 31, acting as a comparison unit, compares (matches) the "automatically generated findings" acquired by the "first acquisition unit" with at least one of the "first interpretation findings" and "second interpretation findings" acquired via the data acquisition unit 33. The control unit 31, acting as a comparison unit, compares information regarding the presence or absence of abnormal findings extracted from the "automatically generated findings" with information regarding the presence or absence of abnormal findings extracted from at least one of the image interpretation findings (i.e., the "first image interpretation findings" or the "second image interpretation findings"), and derives (calculates) the result of the comparison (comparison result). Specifically, the goal is to clarify the agreement and disagreement (differences) between the information from "automatically generated findings" and the information from the image interpretation findings.

[0037] For example, if the "automatically generated findings" resulting from the AI ​​analysis extract information indicating the detection of an abnormality (i.e., a "+" indicating the presence of an abnormality), and the interpretation findings (i.e., the "first interpretation findings" and the "second interpretation findings") also extract information indicating the detection of an abnormality (i.e., a "+" indicating the presence of an abnormality), then both the "automatically generated findings" by the AI ​​and the interpretation findings by the physician will be "+" (abnormality detected), and the control unit 31, acting as a comparison unit, will derive (calculate) a comparison result indicating that both results match as "+" (abnormality detected). In contrast, if, for example, the "automatically generated findings" resulting from the AI ​​analysis extract information indicating the presence of an abnormality (i.e., "+" indicating the presence of an abnormality), while the image interpretation findings (i.e., "first image interpretation findings" or "second image interpretation findings") extract information indicating the absence of an abnormality (i.e., "-" indicating no abnormality), the control unit 31, acting as a comparison unit, derives (calculates) a comparison result indicating that the "automatically generated findings" from the AI ​​analysis ("+" indicating an abnormality) and the image interpretation results by the physician ("-" indicating no abnormality) do not match (they differ).

[0038] In this embodiment, the information extracted from the "automatically generated findings" may include "+" information indicating the presence of abnormal findings and "-" information indicating the absence of abnormal findings. Furthermore, the information extracted from the radiographic findings (i.e., "first radiographic findings" and "second radiographic findings") can include both "+" information indicating the presence of abnormalities and "-" information indicating the absence of abnormalities. The information extracted from the "automatically generated findings" and the interpretation findings ("first interpretation findings" and "second interpretation findings") is not limited to the presence or absence of abnormal findings, but may also include the type, number, and location of abnormal findings. However, in the following embodiment, the explanation will be based on the premise that the control unit 31, acting as a comparison unit, performs a comparison (matching) process to determine the presence or absence of abnormal findings.

[0039] "Automatedly generated findings" are structured data obtained through computer processing (AI analysis). In contrast, interpretation findings ("first interpretation findings" and "second interpretation findings") are interpretation reports created by physicians and are not limited to structured data. For example, the presence or absence of abnormal findings may be expressed as "+" or "-", or as strings indicating presence or absence, such as "absent" or "not present", or "observed" or "not observed". Therefore, there may be variations in expression. For this reason, the control unit 31 may have a function to structure the reading findings and convert them into data consisting of strings, etc., that can be compared with the "automatically generated findings" (structured data), as a prerequisite for matching the "automatically generated findings" with the reading findings ("first reading findings" and "second reading findings"). In this case, for example, the storage unit 32 may store dictionary data, etc., that defines the correspondence between strings, etc., used to generate structured data, and the control unit 31 may refer to this to structure the reading findings.

[0040] Furthermore, if the control unit 31 broadly defines various expressions and terms in the reading findings, and associates expressions such as "+", "abnormality present", and "abnormality recognized" with the same meaning as "information indicating abnormality present (+)" extracted from the "automatically generated findings", and expressions such as "-", "abnormality absent", and "abnormality not recognized" with the same meaning as "information indicating no abnormality (-)" extracted from the "automatically generated findings", then even if there is a slight discrepancy in expression between the "automatically generated findings" and the reading findings, the comparison unit can determine whether they match or not. In this case, the matching (comparison) process between the "automatically generated findings" and the reading findings ("first reading findings" and "second reading findings") may be performed without structuring the reading findings.

[0041] In this embodiment, the control unit 31 also functions as a setting unit that enables the setting of a "predetermined workflow" based on user operations. In this embodiment, the control unit 31, acting as a setting unit, is capable of setting a predetermined workflow by associating the information of the "automatically generated findings" with the information of at least one of the image interpretation findings (i.e., the "first image interpretation findings" and the "second image interpretation findings").

[0042] For example, if information indicating the presence of an abnormal finding (+) is extracted from the "automatically generated findings," and information indicating the absence of an abnormal finding (-) is extracted from at least one of the image interpretation findings (i.e., "first image interpretation findings" or "second image interpretation findings"), the control unit 31, acting as a setting unit, can configure a "predetermined workflow" through user operation. The "prescribed workflow" referred to here includes the details of the procedure, such as the order in which each physician interprets the images, and what information the physicians refer to (or do not refer to) when creating their interpretation findings (i.e., "first interpretation findings" and "second interpretation findings"). The user can input their desired workflow by performing input operations from the operation unit 35 or by touching the settings screen, and the control unit 31, acting as a settings unit, accepts such user operations and sets a "predetermined workflow" based on them.

[0043] When the control unit 31, acting as a setting unit, sets a "predetermined workflow," it is possible to set whether or not to display the "automatically generated findings" or at least one of the interpretation findings (i.e., "first interpretation findings" or "second interpretation findings") by associating them with the information of the "automatically generated findings" (i.e., information indicating whether there are abnormal findings (+) or no abnormal findings (-)) and the information of at least one of the interpretation findings (i.e., information indicating whether there are abnormal findings (+) or no abnormal findings (-)). Specifically, the control unit 31 in this embodiment, acting as a setting unit, is capable of setting at least two workflows as "predetermined workflows," such as a workflow that compares "automatically generated findings" and "first interpretation findings" and then acquires "second interpretation findings" (hereinafter referred to as the "first workflow"), a workflow that acquires "first interpretation findings" and then acquires "second interpretation findings" and compares "automatically generated findings" and "second interpretation findings" (hereinafter referred to as the "second workflow"), and a workflow that compares "automatically generated findings," "first interpretation findings," and "second interpretation findings" (hereinafter referred to as the "third workflow"). Note that the specific content and types of "predetermined workflows" are not limited to those exemplified herein.

[0044] The storage unit 32 is composed of an HDD (Hard Disk Drive) and semiconductor memory, and includes a program storage unit 321 that stores programs for executing various processes, including the comparison processing of medical information such as medical images and the setting of workflows, which will be described later. The storage unit 32 also stores parameters, files, etc., necessary for executing the programs stored in the program storage unit 321. Furthermore, as mentioned above, when the control unit 31 processes unstructured data such as radiology reports created by the user (radiologist) to generate structured data that can be compared with "automatically generated findings," dictionary data (structured dictionary) used for the structuring process is also stored in the storage unit 32.

[0045] 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 reads medical images, which are medical information, from an image server 5 or the like and displays them for interpretation. Users (primary radiologists, secondary radiologists, etc.) interpret medical images on the image interpretation terminal 4 and create interpretation reports, etc., which are the radiologist's diagnostic results regarding the medical images.

[0046] 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 modality 1, along with patient information (patient ID, patient name, date of birth, age, gender, height, weight, etc.), examination information (examination ID, examination date and time, modality type, examination site, requesting department, examination purpose, etc.), image ID of the medical image, AI analysis results output from the control unit 31 of analysis device 3 (i.e., "automatically generated findings"), and the radiologist's interpretation findings (i.e., "first interpretation findings" and "second interpretation findings," etc.), such as the interpretation report created by the user (radiologist) on the interpretation terminal 4, and the matching results (comparison results) output from the control unit 31 of analysis device 3 (control unit 31 as a comparison unit).

[0047] [Regarding the image interpretation management method in this embodiment] In this embodiment, the image interpretation management method includes: a first acquisition step of acquiring "automatically generated findings" obtained by computer processing (AI analysis in this embodiment) of medical information; an acquisition step ("second acquisition step" and "third acquisition step") of image interpretation findings ("first image interpretation findings" and "second image interpretation findings") created by the user based on the medical information; a comparison step of comparing the "automatically generated findings" with the image interpretation findings (at least one of the "first image interpretation findings" and "second image interpretation findings"); a presentation step of presenting the comparison results of the "automatically generated findings" and the image interpretation findings (at least one of the "first image interpretation findings" and "second image interpretation findings") to the user based on a "predetermined workflow"; and a setting step of enabling the "predetermined workflow" to be set based on user operation.

[0048] In this embodiment, when interpreting medical information (medical images in this embodiment), in addition to interpretation by a radiologist, analysis is performed by computer processing (AI analysis), and the "automatically generated findings" resulting from the AI ​​analysis are compared with the interpretation findings by the radiologist ("first interpretation findings" and "second interpretation findings"). This enables quality assurance (QA) regarding the diagnostic accuracy of medical information (medical images).

[0049] Primary and secondary image interpretations are performed by different radiologists (primary and secondary interpreters). By switching between referring to the interpretation findings of the radiologists (primary and secondary interpreters) and referring to the analysis results (i.e., "automatically generated findings") generated by computer processing (AI analysis) during each interpretation, it is possible to create various variations in the image interpretation workflow.

[0050] The control unit 31, acting as a setting unit, pre-sets a "predetermined workflow" based on user operations to determine which workflow to apply during image interpretation. When image interpretation is performed, the pre-set "predetermined workflow" is applied. The "predetermined workflow" is set when, for example, the user performs an input operation from the workflow setting screen 361 as shown in Figures 4, 6, and 8, and the "Register" button is pressed. This operation sends an operation signal corresponding to the user's input to the control unit 31, and the control unit 31, upon receiving the operation signal, sets the "predetermined workflow" corresponding to the user's operation.

[0051] For example, if the priority is to perform image interpretation efficiently, as shown in Figure 4, the primary image interpretation is performed by a physician (primary radiologist), and the control unit 31 performs AI analysis. The AI ​​analysis result, "automatically generated findings," is compared with the primary radiologist's interpretation result, "first interpretation findings." If the AI ​​analysis yields a + (abnormal findings) and the primary interpretation yields a - (no abnormal findings), or if the AI ​​analysis yields a - (no abnormal findings) and the primary interpretation yields a - (no abnormal findings), the image is passed on to a secondary radiologist (secondary interpreter) for secondary interpretation. The secondary radiologist's (secondary interpreter's) worklist displays the result of comparing the "automatically generated findings" with the primary radiologist's interpretation result, "first interpretation findings." Then, a "prescribed workflow" is set up in which the secondary radiologist performs a secondary interpretation while referring to the matching results displayed in the worklist and the interpretation report by the primary radiologist, which is the "first interpretation finding," and the "second interpretation finding," which is the secondary radiologist's finding, is designated as the "definitive diagnostic information." The frames in Figure 4, which show the order of each image interpretation and AI analysis, can be rearranged by the user to achieve their desired order. Furthermore, the specific content and conditions of each "event," including what is displayed and processed at each stage, can also be modified as needed.

[0052] Figure 5 is a schematic diagram illustrating the flow of image interpretation when the flow shown in Figure 4 is set as the "predetermined workflow." The "predetermined workflow" shown in Figures 4 and 5 will be referred to as the "first workflow." As shown in Figure 5, in this case, the primary radiologist obtains the "first reading findings" through image interpretation, and then the computer processing (AI analysis) obtains the "automatically generated findings." After that, the control unit 31, acting as a comparison unit, performs a matching (comparison) process between the "first reading findings" and the "automatically generated findings." If the AI ​​analysis shows a + (abnormal findings) and the primary interpretation shows a - (no abnormal findings), or if the AI ​​analysis shows a - (no abnormal findings) and the primary interpretation also shows a - (no abnormal findings), the image will be sent for secondary interpretation by a secondary radiologist (secondary interpreter).

[0053] If the results of the AI ​​analysis differ from the findings of the primary radiologist, it is necessary to confirm and determine which findings are correct during the secondary interpretation. Furthermore, even if the AI ​​analysis results and the findings of the primary radiologist match, if the finding is "- (no abnormal findings)," it is advisable to check again during the secondary interpretation to ensure that no findings have been overlooked. In these cases, as shown in Figure 5, the secondary reading becomes the confirmatory reading, and the findings of the secondary radiologist, known as the "second reading findings," become the "definitive diagnostic information."

[0054] Furthermore, when interpreting images using this workflow, if there is a physician who performs a confirmation interpretation to verify each finding in addition to the primary and secondary radiologists, the confirmation radiologist may be responsible for the "secondary interpretation" shown in Figure 5. In this context, "definitive diagnostic information" refers to a diagnosis determined and confirmed by a physician (radiologist) based on medical images and the findings and analysis results obtained therefrom. The final diagnosis for a patient may be made by a clinician, for example, by comprehensively considering not only the judgment of the physician who prepared this "definitive diagnostic information," but also the test data and examination data obtained from various tests and examinations. In the following, "definitive diagnostic information" will have the same meaning as described above.

[0055] On the other hand, if the AI ​​analysis indicates a + (abnormal finding) and the primary image interpretation also indicates a + (abnormal finding), the matching finding, "+ (abnormal finding)," is treated as "definitive diagnostic information," and the interpretation of that medical information is terminated.

[0056] For example, if a more careful interpretation is desired, as shown in Figure 6, the primary radiologist performs the initial interpretation, and the secondary radiologist performs the secondary interpretation while referring to the "first interpretation findings" such as the interpretation report obtained from the primary interpretation, and obtains the "second interpretation findings." Separately, the control unit 31 obtains "automatically generated findings" as a result of AI analysis. The "automatically generated findings" as a result of the AI ​​analysis and the "second interpretation findings" as a result of the secondary radiologist's interpretation are then compared. If the AI ​​analysis yields a + (abnormal finding) and the secondary interpretation yields a - (no abnormal finding), or if the AI ​​analysis yields a - (no abnormal finding) and the secondary interpretation yields a - (no abnormal finding), the image is then sent for confirmation interpretation by a confirming radiologist (confirming radiologist), and the result of comparing the "automatically generated findings" and the "second interpretation findings" as a result of the secondary radiologist's interpretation is displayed in the confirming radiologist's (confirming radiologist's) worklist. Then, a "prescribed workflow" is set up in which the confirming radiologist performs a confirmation interpretation while referring to the matching results displayed in the worklist, the interpretation report by the primary radiologist ("first interpretation findings"), and the interpretation report by the secondary radiologist ("second interpretation findings"), and the confirming radiologist's findings are designated as "definitive diagnostic information."

[0057] As with the case shown in Figure 4, the order of the frames indicating the sequence of each image interpretation and AI analysis, the specific content of the "events," and the conditions can all be input by the user as appropriate. Furthermore, the confirming radiologist (confirming radiologist) may be a physician specializing in confirming interpretation, separate from the primary and secondary radiologists, or the secondary radiologist may also serve in this role.

[0058] Figure 7 is a schematic diagram illustrating the flow of image interpretation when the flow shown in Figure 6 is set as the "predetermined workflow." The "predetermined workflow" shown in Figures 6 and 7 will be referred to as the "second workflow." As shown in Figure 7, in this case, the primary radiologist obtains the "first interpretation findings" through their interpretation, and the secondary radiologist performs a second interpretation while referring to these "first interpretation findings" to obtain the "second interpretation findings." In addition, "automatically generated findings" are obtained through computer processing (AI analysis). Subsequently, the control unit 31, acting as a comparison unit, performs a matching (comparison) process between the "second interpretation findings" and the "automatically generated findings." As a result, if the AI ​​analysis shows a + (abnormal findings) and the primary image interpretation shows a - (no abnormal findings) If the result is positive (no abnormal findings) in both the AI ​​analysis and the initial reading, the image will be sent for confirmation reading by a confirming radiologist (confirming radiologist).

[0059] If the results of the AI ​​analysis differ from the findings of the secondary radiologist, it is necessary to confirm and determine which findings are correct during the re-interpretation. Furthermore, even if the AI ​​analysis results and the findings of the secondary radiologist match, if the finding is "- (no abnormal findings)," it is advisable to check again during the re-interpretation to ensure that nothing has been overlooked. In these cases, as shown in Figure 7, the findings of the confirming radiologist become the "definitive diagnostic information."

[0060] On the other hand, if the AI ​​analysis shows a + (abnormal finding) and the secondary reading also shows a + (abnormal finding), the matching finding, "+ (abnormal finding)," is treated as "definitive diagnostic information," and the reading of that medical information is terminated.

[0061] In the "first workflow," which is the "predetermined workflow" shown in Figures 4 and 5, the secondary radiologist performs a secondary interpretation as a confirmation interpretation, referring to the "first interpretation findings" by the primary radiologist, the "automatically generated findings" which are the results of AI analysis, and the results of comparing (matching) the two. Therefore, in secondary image interpretation, the focus should be on the differences between the "first interpretation findings" and the "automatically generated findings," and the main task should be checking for any oversights. This allows for efficient image interpretation and is expected to lead to a "definitive diagnosis" at an early stage. On the other hand, in the "first workflow," the secondary radiologist interprets the images after reviewing the "first interpretation findings" and "automatically generated findings" provided by the primary radiologist. This means that the secondary interpretation may be influenced by the "first interpretation findings" and "automatically generated findings," potentially leading to bias.

[0062] Furthermore, in the "predetermined workflow," or "second workflow," shown in Figures 6 and 7, the secondary interpretation does not refer to the "automatically generated findings," so the secondary interpretation is not influenced by the "automatically generated findings," but it is the same in that it refers to the "first interpretation findings" by the primary radiologist. For this reason, there remains a risk that the secondary interpretation may be influenced by the "first interpretation findings" and become biased.

[0063] In this regard, for example, as shown in Figure 8, if a "prescribed workflow" is set up in which primary image interpretation, secondary image interpretation, and AI analysis are performed in parallel, and the "automatically generated findings" resulting from the AI ​​analysis are compared with the "first interpretation findings" obtained from the primary image interpretation and the "second interpretation findings" obtained from the secondary image interpretation, and if either the "first interpretation findings" or the "second interpretation findings" matches the "automatically generated findings," then the matching findings are designated as "definitive diagnostic information," then although the interpretation efficiency is somewhat sacrificed because primary and secondary image interpretations are performed without any references, a more careful interpretation can be performed because primary and secondary interpretations are not influenced by other findings.

[0064] Figure 9 is a schematic diagram illustrating the flow of image interpretation when the flow shown in Figure 8 is set as the "predetermined workflow." The "predetermined workflow" shown in Figures 8 and 9 will be referred to as the "third workflow." As shown in Figure 9, in this case, the primary radiologist performs the initial interpretation and obtains the "first interpretation findings," and the secondary radiologist performs the secondary interpretation and obtains the "second interpretation findings." In addition, "automatically generated findings" are obtained through computer processing (AI analysis). Subsequently, the control unit 31, acting as a comparison unit, performs a matching (comparison) process between the "first interpretation findings," the "second interpretation findings," and the "automatically generated findings."

[0065] As a result, the AI ​​analysis yielded an "automatically generated finding" of + (abnormal findings present), and the primary reading If at least one of the shadow or secondary image interpretations yields a + (abnormal finding) result ("First Image Interpretation Finding" and "Second Image Interpretation Finding"), the "+ (abnormal finding)" result that matches the "Automatically Generated Finding" will be considered the "Definitive Diagnostic Information." Furthermore, if the AI ​​analysis yields an "automatically generated finding" of - (no abnormal findings), and at least one of the primary or secondary image interpretations yields an image interpretation finding of - (no abnormal findings) ("first image interpretation finding" or "second image interpretation finding"), the finding of - (no abnormal findings) that matches the "automatically generated finding" will be considered the "definitive diagnostic information." In other words, if there is a disagreement among multiple interpretations ("first interpretation" and "second interpretation") regarding the presence or absence of abnormalities, the one that matches the "automatically generated findings" (the result of the AI ​​analysis) will be adopted as correct, and the interpretation of the medical information will be terminated. For example, if the AI ​​analysis is highly reliable, adopting such a workflow can allow for early convergence of image interpretations and efficient image interpretation processing.

[0066] In contrast, if the AI ​​analysis yields an "automatically generated finding" of - (no abnormal findings), and both the primary and secondary image interpretations yield findings of - (no abnormal findings) ("first image interpretation findings" and "second image interpretation findings"), or if the AI ​​analysis yields an "automatically generated finding" of - (no abnormal findings), and both the primary and secondary image interpretations yield findings of + (abnormal findings) ("first image interpretation findings" and "second image interpretation findings"), the image will be sent for confirmation interpretation by a confirming radiologist (confirming radiologist).

[0067] If the AI ​​analysis results differ from the findings of either the primary or secondary radiologist, it is necessary to confirm and determine which of the two findings ("first interpretation findings" or "second interpretation findings") is correct during the final interpretation. Furthermore, even if the AI ​​analysis results match the findings of both the primary and secondary radiologists, if the finding is "-(no abnormal findings)," it is advisable to double-check during the final interpretation to ensure no findings have been overlooked. In these cases, as shown in Figure 9, the findings of the confirming radiologist become the "definitive diagnostic information."

[0068] The "first workflow," "second workflow," and "third workflow" exemplified above each have their own advantages and disadvantages, and their suitability depends on factors such as the proficiency level of the primary and secondary radiologists, the accuracy level of the AI ​​analysis, and the circumstances of the facility adopting the radiology management method. In this embodiment, however, the "predetermined workflow" adopted for radiology management can be set based on user operations. Therefore, the optimal workflow can be set according to the points that the user considers most important and the current circumstances of the facility.

[0069] Furthermore, the "predetermined workflows" that can be set in the control unit 31, which acts as a setting unit, are not limited to the "first workflow," "second workflow," and "third workflow" exemplified in this embodiment. For example, users can also configure various conditions on the workflow settings screen 361, such as what procedures should be followed when interpreting images (i.e., whether to allow or deny access to the interpretation report, whether to allow or deny access to the results of the comparison with the AI ​​analysis results, etc.) under what circumstances (i.e., patterns of combinations of AI analysis (+) or (-), "first interpretation findings" (+) or (-), "second interpretation findings" (+) or (-), etc.). For example, in "Workflow 1," "Workflow 2," and "Workflow 3," even if the AI ​​analysis results match the findings of the radiologist (primary and secondary radiologists), if the finding is "- (no abnormal findings)," the workflow is to send it for confirmation and check again. However, even if the finding is "- (no abnormal findings)," if the AI ​​analysis results match the findings of the radiologist (primary and secondary radiologists), it may be possible to set up a workflow as "prescribed workflow" that does not send it for confirmation and treats those findings as "definitive diagnostic information." .

[0070] 〔effect〕 As described above, the analysis device 3 as a reading management device according to this embodiment includes: a first acquisition unit that acquires "automatically generated findings" obtained by computer processing of medical information; a second acquisition unit that acquires "first reading findings" created by the user based on medical information; a third acquisition unit that acquires "second reading findings" created by the user based on medical information; a control unit 31 as a comparison unit that compares (matches) the "automatically generated findings" with at least one of the reading findings among the "first reading findings" and the "second reading findings"; a display unit 36 ​​as a presentation unit that presents the comparison result (matching result) of the "automatically generated findings" and at least one of the reading findings ("first reading findings" and "second reading findings") to the user based on a "predetermined workflow"; and a control unit 31 as a setting unit that enables the setting of a "predetermined workflow" based on user operation.

[0071] In this way, the results of computer processing (AI analysis) in image interpretation can be compared with the judgment of the user (physician, radiologist), and the comparison results (matching results) can be presented to the user. Therefore, image interpretation can be performed more carefully, leading to improvements in image interpretation accuracy and quality. In such cases, a "predetermined workflow" can be set according to the user's requirements, specifying the order in which image interpretation should be performed and what information should be provided to the user during the interpretation process. This allows for the creation of a more favorable workflow tailored to the facility environment, operational status, and differences in experience and preferences among users (physicians and radiologists).

[0072] In other words, since the desired image interpretation workflow differs from one medical facility to another, developing and manufacturing equipment to achieve each desired workflow would be costly and time-consuming. In this embodiment, in a diagnostic imaging method that aims to improve the quality of image interpretation by comparing the results of computer processing (AI analysis) with the judgment results of the user (physician, radiologist), the timing at which the radiologist (primary radiologist, secondary radiologist, etc.) displays the results of comparing the AI ​​analysis results with the physician's interpretation results can be changed according to the user's requests. Therefore, it is possible to customize the image interpretation workflow as needed, according to the user's needs, such as when they want to perform an efficient image interpretation by focusing on points of difference in findings while referring to other findings, or when they want to perform a careful interpretation without being influenced by other findings.

[0073] Furthermore, in this embodiment, the control unit 31, acting as a setting unit, is capable of setting a predetermined workflow by associating information from "automatically generated findings" (for example, information on the presence or absence of abnormalities) with information from at least one of the image interpretation findings ("first image interpretation findings" and "second image interpretation findings") (for example, information on the presence or absence of abnormalities). Therefore, depending on whether the "automatically generated findings," which are the result of computer processing (AI analysis), indicate the presence or absence of abnormal findings, the structure of the "predetermined workflow" in image interpretation (order, content, etc.) can be changed.

[0074] In other words, if the judgment regarding medical information (medical images) is that "abnormal findings are present," it is expected that clinicians and others who have seen the interpretation results will further carefully examine the medical information (medical images). However, if the judgment made by computer processing (AI analysis) is that "no abnormal findings are present," there is a risk that it will not be examined any further, and if there is an oversight in the AI ​​analysis, there is a risk that the final judgment will be incorrect. Therefore, if the AI ​​analysis indicates "no abnormal findings," a workflow can be established where further careful consideration is given, such as conducting a more thorough reconfirmation of the image.

[0075] Furthermore, in this embodiment, if information indicating abnormal findings is extracted from the "automatically generated findings" and information indicating no abnormal findings is extracted from at least one of the image interpretation findings ("first image interpretation findings" and "second image interpretation findings"), the control unit 31, acting as a setting unit, allows the user to set a "predetermined workflow". In other words, when the judgment (findings) regarding medical information (medical images) differs between "automatically generated findings" produced by computer processing (AI analysis) and findings interpreted by a radiologist ("first interpretation findings" and "second interpretation findings"), the system can be configured according to the user's preferences to decide which findings to adopt as correct, whether to perform further secondary interpretation or confirmation interpretation, etc. Therefore, the workflow for image interpretation can be customized according to the facility's situation, the reliability of the AI ​​analysis, the experience level of the radiologist, and other factors.

[0076] In this embodiment, the control unit 31, acting as a comparison unit, derives (calculates) a comparison result (matching result) by comparing information regarding the presence or absence of abnormal findings extracted from the "automatically generated findings" with information regarding the presence or absence of abnormal findings extracted from at least one of the image interpretation findings ("first image interpretation findings" and "second image interpretation findings"). Therefore, it is possible to clarify the agreement and discrepancies between the results of computer processing (AI analysis) and the interpretation by radiologists.

[0077] In this embodiment, the display unit 36, which acts as a presentation unit, presents the user with either an "automatically generated finding" or at least one of the image interpretation findings ("first image interpretation finding" or "second image interpretation finding") based on the comparison result (matching result) from the control unit 31, which acts as a comparison unit. Therefore, the results of computer processing (AI analysis) and radiologist interpretation, as well as the agreements and disagreements between them, can be made known to the user.

[0078] Furthermore, in this embodiment, the control unit 31, acting as a setting unit, can set whether or not to display the "automatically generated findings" or at least one of the interpretation findings ("first interpretation findings" or "second interpretation findings") by associating the information of the "automatically generated findings" (information on the presence or absence of abnormal findings) with the information of at least one of the interpretation findings ("first interpretation findings" or "second interpretation findings"). For example, if AI analysis indicates an abnormality, even if the radiologist is influenced by this judgment during their interpretation, they will likely perform a more cautious interpretation, making serious errors less likely. On the other hand, if AI analysis indicates no abnormalities, and the radiologist is shown this beforehand, they may perform an interpretation with a bias that assumes there are no abnormalities, potentially overlooking any actual abnormalities. Therefore, by adopting a workflow that changes the display depending on whether or not abnormal findings are detected, more careful image interpretation can be performed.

[0079] Furthermore, in this embodiment, the control unit 31, acting as a setting unit, can set at least two workflows from among those listed below: a workflow that compares the "automatically generated findings" and the "first interpretation findings" and then acquires the "second interpretation findings" (the "first workflow" in this embodiment); a workflow that acquires the "first interpretation findings" and then acquires the "second interpretation findings" and compares the "automatically generated findings" and the "second interpretation findings" (the "second workflow" in this embodiment); and a workflow that compares the "automatically generated findings," the "first interpretation findings," and the "second interpretation findings" (the "third workflow" in this embodiment). This allows users to adopt customized workflows for image interpretation, depending on the facility's situation, the reliability of the AI ​​analysis, and the radiologist's experience level.

[0080] Furthermore, this embodiment includes a first acquisition unit that acquires "automatically generated findings" obtained by computer processing (AI analysis) of medical information, a second acquisition unit that acquires interpretation findings created by a user (physician, radiologist) based on medical information, a control unit 31 as a comparison unit that compares the automatically generated findings and the interpretation findings, a display unit 36 ​​as a presentation unit that presents the comparison results between the "automatically generated findings" and the interpretation findings to the user based on a "predetermined workflow", and a control unit 31 as a setting unit that allows the "predetermined workflow" to be set based on user operation. In this way, even when only one reading is obtained by a radiologist in addition to the "automatically generated findings" generated by AI analysis, users can customize the workflow related to image interpretation, such as whether or not to allow the reference of the "automatically generated findings" during the interpretation process, according to the facility's situation, the reliability of the AI ​​analysis, and the radiologist's experience level.

[0081] [Variation] Although embodiments of the present invention have been described above, it goes without saying that the present invention is not limited to these embodiments, and various modifications are possible without departing from the spirit of the invention.

[0082] For example, in the above embodiment, the medical information to be analyzed by the analysis device 3 is described as a medical image, but the medical information is not limited to medical "images". Information obtained through various examinations of patients can be broadly included in medical information. For example, electrocardiogram waveform data, heart sound data, blood flow data, and results obtained from various examinations can also be included in medical information. Furthermore, when employing a diagnostic flow that involves AI analysis of this medical information and comparing the results of the AI ​​analysis with the physician's diagnosis, the present invention can be applied to construct a flow that is more suitable for the operational status of the facility.

[0083] Furthermore, in this embodiment, although the analysis device 3, image interpretation terminal 4, and image server 5 are shown as separate and independent devices in Figure 1, the analysis device 3 and image server 5, or the analysis device 3, image interpretation terminal 4, and image server 5, may be configured as a single device or a single system.

[0084] Furthermore, in this embodiment, we have illustrated a case where information regarding the presence or absence of abnormal findings is extracted from "automatically generated findings" and interpretation findings ("first interpretation findings" and "second interpretation findings") and compared (matched) with them. However, the information extracted from "automatically generated findings" and interpretation findings ("first interpretation findings" and "second interpretation findings") is not limited to information regarding the presence or absence of abnormal findings. For example, the control unit 31, acting as a comparison unit, may compare (match) information regarding at least one of the types, numbers, and locations of abnormal findings extracted from the "automatically generated findings" with information regarding at least one of the types, numbers, and locations of abnormal findings extracted from at least one of the image interpretation findings (i.e., the "first image interpretation findings" or the "second image interpretation findings"), and derive (calculate) a comparison result (matching result). In this case, in order to compare the two, the interpretation findings ("first interpretation findings" and "second interpretation findings") are structured, and a comparison (matching) is performed using the structured data.

[0085] It goes without saying that the present invention is not limited to the above embodiments or modifications, and can be modified as appropriate without departing from the spirit of the present invention. [Explanation of symbols]

[0086] 1 Modality 2 Console 3. Analysis device (image interpretation management device) 4. Terminal for image interpretation 5 Image Server 31 Control Unit 32 Storage section 33 Data Acquisition Unit 36 Display section 100 Medical Imaging Systems

Claims

1. A first acquisition unit that acquires automatically generated findings obtained by computer processing of medical information, A second acquisition unit that acquires a first image interpretation finding created by the user based on the aforementioned medical information, A third acquisition unit that acquires a second set of readings created by the user based on the aforementioned medical information, A comparison unit that compares the automatically generated findings with at least one of the first and second interpretation findings, Based on a series of workflows, a presentation unit presents to the user the results of comparing the automatically generated findings with at least one of the image interpretation findings. A setting unit that allows the aforementioned series of workflows to be pre-configured based on user operations, Equipped with, The aforementioned setting unit, as part of the series of workflows, A workflow to obtain the second interpretation findings after comparing the automatically generated findings with the first interpretation findings, A workflow in which, after obtaining the first image interpretation findings, the second image interpretation findings are obtained and the automatically generated findings are compared with the second image interpretation findings, Allows setting up at least one workflow. A picture interpretation management device characterized by the following features.

2. The setting unit is, A workflow for comparing the automatically generated findings with the first interpretation findings and the second interpretation findings, Make it possible to configure The image interpretation management device according to feature 1.

3. It includes a setting unit that allows pre-configuration of a series of image interpretation workflows until the diagnosis of medical information is finalized. The setting unit is, A workflow can be set up to confirm the diagnostic result based on a comparison between the first findings obtained by a first radiologist interpreting the medical information and the automatically generated findings obtained by computer processing the medical information. A picture interpretation management device characterized by the following features.

4. The workflow involves comparing the first findings obtained by the primary radiologist interpreting the medical information with automatically generated findings obtained by computer processing the medical information, and then having a user other than the first radiologist confirm the diagnosis. The image interpretation management device according to claim 3.

5. The workflow compares the first image interpretation findings with the automatically generated findings and confirms the matching findings as the diagnostic result. The image interpretation management device according to claim 3.

6. On the computer, A first acquisition function that acquires automatically generated findings obtained by computer processing of medical information, A second acquisition function that acquires a first image interpretation finding created by the user based on the aforementioned medical information, A third acquisition function that acquires a second set of imaging findings created by the user based on the aforementioned medical information, A comparison function that compares the automatically generated findings with at least one of the first and second interpretation findings, Based on a series of workflows, a presentation function presents to the user the results of comparing the automatically generated findings with at least one of the image interpretation findings, A setting function that allows the aforementioned series of workflows to be pre-configured based on user operations, To make it happen, The aforementioned setting function, as part of the aforementioned series of workflows, A workflow to obtain the second interpretation findings after comparing the automatically generated findings with the first interpretation findings, A workflow in which, after obtaining the first image interpretation findings, the second image interpretation findings are obtained and the automatically generated findings are compared with the second image interpretation findings, Allows setting up at least one workflow. A program characterized by the following features.

7. On the computer, This system implements a setting function that allows pre-configuration of the entire image interpretation workflow, from initial assessment to final confirmation of the medical diagnosis. The aforementioned setting function is A workflow can be set up to confirm the diagnostic result based on a comparison between the first findings obtained by a first radiologist interpreting the medical information and the automatically generated findings obtained by computer processing the medical information. A program characterized by the following features.

8. The workflow involves comparing the first findings obtained by the primary radiologist interpreting the medical information with automatically generated findings obtained by computer processing the medical information, and then having a user other than the first radiologist confirm the diagnosis. The program according to claim 7.

9. The workflow compares the first image interpretation findings with the automatically generated findings and confirms the matching findings as the diagnostic result. The program according to claim 7.

10. A first acquisition step involves obtaining automatically generated findings obtained by computer processing of medical information, A second acquisition step involves obtaining a first set of reading findings created by the user based on the aforementioned medical information, A third acquisition step involves obtaining a second set of readings created by the user based on the aforementioned medical information, A comparison step of comparing the automatically generated findings with at least one of the first and second interpretation findings, Based on a series of workflows, a presentation step is made to present to the user the results of comparing the automatically generated findings with at least one of the image interpretation findings, A setting process that allows the aforementioned series of workflows to be pre-configured based on user operations, Have the computer do it, The aforementioned setup process, as part of the aforementioned series of workflows, A workflow to obtain the second interpretation findings after comparing the automatically generated findings with the first interpretation findings, A workflow in which, after obtaining the first image interpretation findings, the second image interpretation findings are obtained and the automatically generated findings are compared with the second image interpretation findings, Allows setting up at least one workflow. A method for managing image interpretation, characterized by the features described herein.

Images