Method and system for comparing past images and current images

Abstract

To provide an image analysis apparatus, an operation method and a computer program for comparing past images and current images.SOLUTION: An image analysis apparatus includes a memory and a processor that executes instructions stored in the memory. The processor analyzes a target image of a patient using an artificial intelligence model to obtain an analysis result including lesion information for a plurality of types of comparison-target lesions, determines a past image captured prior to the target image as a reference image, compares and analyzes the analysis result of the reference image with the analysis result of the target image to obtain a comparative analysis result including degrees of lesion change for the plurality of types of lesions by associating lesions detected at corresponding positions in the reference image and the target image to determine the degrees of lesion change, and displays the comparative analysis result on a viewer executed on a user terminal.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present disclosure relates to artificial intelligence-based medical image analysis technology. [Background technology]

[0002] In the past, computer-aided detection (CAD) devices detected lesions from medical images based on rules or from candidate regions set in medical images. In recent years, as artificial intelligence (AI) technology has been actively introduced into the medical field, research is being conducted on AI-based medical image analysis technology, such as the Lunit INSIGHT solution, which uses AI to analyze medical images and visually presents the analysis results.

[0003] Users can check abnormal lesions detected through video analysis and perform tasks such as reading and diagnosis. However, for patients who require follow-up observation, users have to manually search for the patient's past videos, open the past videos, and visually compare the current video with the past video to check for changes in the lesion, which is inconvenient. Summary of the Invention [Problem to be solved by the invention]

[0004] The present disclosure provides a method and system for comparing past and current video.

[0005] The present disclosure provides a method and system for providing a comparative analysis result with past videos as a result of analyzing a target video. [Means for solving the problem]

[0006] According to one embodiment, the image analysis device includes a memory and a processor that executes instructions stored in the memory. The processor analyzes a target image of a patient using an artificial intelligence model to obtain an analysis result including lesion information, determines a previous image of the patient taken before the target image as a reference image, and compares and analyzes the reference image and the target image to obtain a comparative analysis result including a degree of change in the lesion.

[0007] The processor can determine a reference image from among the patient's past images that meets the criteria.

[0008] The processor can extract lesion information for at least one comparison lesion from the analysis results of the reference image and the analysis results of the target image, determine the degree of change of each comparison lesion over time based on the extracted lesion information, and generate a comparative analysis result including the degree of change of each comparison lesion.

[0009] The processor can determine the degree of change for each comparison lesion as either no change, lesion disappeared, lesion appeared, lesion decreased, lesion increased, or no lesion exists.

[0010] The processor can determine that there is a lesion change if there is a change equal to or greater than a threshold for each comparison lesion.

[0011] The processor can determine lesion changes using thresholds set for each comparison lesion.

[0012] The processor is an image analysis device that selects a plurality of past images of the patient that were taken before the target image as a plurality of reference images, and obtains a plurality of comparative analysis results including the degree of change in the lesion between the images by comparing and analyzing temporally adjacent images between the plurality of reference images and the target image.

[0013] The processor can generate the analysis results performed for the target image in a specified data format and store the results in the image storage device.

[0014] The processor can generate comparative analysis results in a DICOM standard Secondary Capture.

[0015] The processor can generate an augmented secondary capture that includes analysis and comparison analysis of the target image.

[0016] The processor can generate an additional secondary capture that compares the analysis results of the reference image with the analysis results of the target image.

[0017] An operating method of the image analysis device according to one embodiment includes analyzing a target image of a patient using an artificial intelligence model to obtain an analysis result including lesion information, determining a previous image of the patient taken before the target image as a reference image, and comparing and analyzing the reference image and the target image to obtain a comparative analysis result including a degree of lesion change.

[0018] Obtaining the comparative analysis results may include extracting lesion information of at least one comparative lesion from the analysis results of the reference image and the analysis results of the target image, determining the degree of change of each comparative lesion over time based on the extracted lesion information, and generating comparative analysis results including the degree of change of each comparative lesion.

[0019] The degree of change can be determined by determining the degree of change for each comparison lesion as either no change, lesion disappeared, lesion appeared, lesion decreased, lesion increased, or no lesion exists.

[0020] The degree of change can be determined by using a threshold value set for each comparison target lesion, and if there is a change equal to or greater than the threshold value set for that comparison target lesion, it can be determined that there is a change in the lesion.

[0021] The method of operation may further include generating results of the analysis performed for the target image in a specified data format.

[0022] The data format may include a DICOM standard secondary capture. Generating in the specified data format may generate an augmented secondary capture in which comparative analysis results are added to the analysis results of the target image, and / or an additional secondary capture that shows a comparison between the analysis results of the reference image and the analysis results of the target image.

[0023] According to one embodiment, a computer program stored in a computer-readable recording medium includes instructions to cause a processor to execute the program to display a worklist including an image list for image reading work in conjunction with an image storage device, and when a target image of a patient is selected from the worklist, to display an analysis result including a comparative analysis result of the target image with past images of the patient taken before the target image.

[0024] The computer program may include an instruction to display the results of the comparative analysis with the past image on the worklist, and the results of the comparative analysis may include a degree of change in the lesion obtained by comparing and analyzing the current image to be read and the past image taken before the current image among the images of the target patient of the current image.

[0025] The computer program may include instructions to display an augmented secondary capture that adds comparative analysis results to the analysis results of the target image, and / or display an augmented secondary capture that compares the analysis results of the past image with the analysis results of the target image. [Effects of the Invention]

[0026] According to one embodiment, the analysis result for the target image is a comparative analysis result with a past image, so that the user can quickly know the changes over time of the lesion detected from the target image without having to check the past image separately.

[0027] According to the embodiment, by providing the results of comparison analysis with past images in a viewer, work list, or analysis report, the accuracy of image interpretation can be improved, and the efficiency of image interpretation work can be increased.

[0028] According to one embodiment, the augmented auxiliary image or additional auxiliary image visually distinguishes and highlights lesions or lesion changes that require attention, thereby improving the accuracy of image interpretation and increasing the efficiency of image interpretation work.

[0029] According to one embodiment, the priority of work in the work list can be determined based on the results of comparison and analysis with past images, thereby improving the efficiency of image reading work. [Brief explanation of the drawings]

[0030] [Figure 1] 1 is a configuration diagram of a medical imaging system according to an embodiment. [Figure 2] 1 is an illustration of a graphical indicator showing lesion change according to one embodiment. [Figure 3] 10 is an example of a screen that provides a comparison analysis result with past video according to an embodiment. [Figure 4] 10 is an example of a screen that provides a comparison analysis result with past video according to an embodiment. [Figure 5] 10 is a diagram illustrating an order in which a comparison analysis result is output in a viewer according to an embodiment; [Figure 6] 10 is an example of a screen providing an augmented auxiliary video according to one embodiment. [Figure 7] 10 is an example of a screen providing an augmented auxiliary video according to one embodiment. [Figure 8]10 is an example of a screen providing an augmented auxiliary video according to one embodiment. [Figure 9] 10 is an example of a screen that provides additional auxiliary video according to an embodiment. [Figure 10] 10 is an example of a screen that provides additional auxiliary video according to an embodiment. [Figure 11] 1 is an illustration of an analysis report generated by one embodiment. [Figure 12] 1 is an illustration of an analysis report generated by one embodiment. [Figure 13] 1 is an illustration of a worklist generated according to one embodiment. [Figure 14] 1 is a flowchart of a video analysis method according to an embodiment. [Figure 15] 10 is a flowchart of a video analysis method according to another embodiment. [Figure 16] 1 is a flowchart of a method for providing analysis results according to an embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0031] Hereinafter, with reference to the accompanying drawings, embodiments of the present disclosure will be described in detail so that those skilled in the art can easily carry out the present disclosure. However, the present disclosure may be embodied in various different forms and is not limited to the embodiments described herein. In order to clearly explain the present disclosure in the drawings, parts that are not relevant to the description are omitted, and similar parts are designated by similar reference numerals throughout the specification.

[0032] In the description, when a part "includes" a certain element, it does not mean that it excludes other elements, but that it may further include other elements, unless otherwise specified. Furthermore, terms such as "unit," "machine," and "module" used in the specification refer to a unit that processes at least one function or operation, and this can be realized by hardware, software, or a combination of hardware and software.

[0033] An apparatus or terminal of the present disclosure is a computing device configured and coupled to perform the operations of the present disclosure by executing instructions from at least one processor. A computer program containing instructions written to cause a processor to perform the operations of the present disclosure can be stored on a non-transitory computer-readable storage medium. The computer program can also be downloaded over a network and / or sold as a product.

[0034] The medical images disclosed herein may be images of various parts of the body taken using various modalities, such as X-ray, MRI (magnetic resonance imaging), ultrasound, CT (computed tomography), Digital MMG (mammography), and DBT (digital breast tomosynthesis).

[0035] A user of the present disclosure may be a medical professional such as, but not limited to, a doctor, nurse, clinical pathologist, sonographer, or medical imaging specialist.

[0036] The artificial intelligence model (AI model) of the present disclosure is a machine learning model that learns at least one task and can be implemented as a computer program executed by a processor. The task learned by the AI ​​model can refer to a problem to be solved or a task to be performed through machine learning. The AI ​​model can be implemented as a computer program executed on a computing device, downloaded via a network, and / or sold as a product. The AI ​​model can also interface with various devices via a network.

[0037] FIG. 1 is a block diagram of a medical imaging system according to one embodiment, and FIG. 2 is an example of a graphical indicator showing the degree of change of a lesion according to one embodiment.

[0038] Referring to FIG. 1, a medical imaging system 1 may include at least one user terminal 100, an image storage device 200, and an image analysis device 300.

[0039] The user terminal 100 includes hardware and software that installs a program executed by a processor and provides a computing environment and a network environment for performing the operations of the present disclosure. The user terminal 100 can be implemented in various types, such as a computing device in a workstation or a mobile device. The user terminal 100 can include a viewer (simply referred to as "viewer") 110 that interfaces with the image storage device 200 and displays medical image-related data stored in the image storage device 200. The viewer 110 can be installed and executed in a computing device in a workstation, for example, and can be connected to the image storage device 200 to display medical image-related data stored in the image storage device 200. The viewer 110 is a computer program stored in a computer-readable medium and includes instructions that can be executed by a processor. The processor of the user terminal 100 executes the instructions to perform the operations described in the present disclosure.

[0040] The viewer 110 can display the analysis results of the videos stored in the video storage device 200. The viewer 110 can provide a worklist configured in a table format that lists and displays a list of videos to be read by the user along with key information. The viewer 110 can include a PACS (Picture Archiving and Communication System) viewer. Here, the viewer 110 is a program designed to display the analysis results of the videos stored in the video storage device 200 and can support the video reading task related to the worklist, but it is not necessarily limited to a viewer for reading tasks.

[0041] The image archiving device 200 can store and manage captured medical images. The image archiving device 200 can also store and manage analysis results for the medical images. The image archiving device 200 can include a PACS database. The image archiving device 200 can store data in a specified data format. For example, the image archiving device 200 can store medical images captured by a medical imaging device and analysis results for the medical images according to the Digital Imaging and Communications in Medicine (DICOM) standard, and can communicate with the user terminal 100 to provide data for image reading. The image archiving device 200 and the viewer 110 can be configured as a PACS system, where the image archiving device 200 can be a PACS server / DB and the viewer 110 can be a PACS viewer.

[0042] In this disclosure, the DICOM standard utilized for medical image storage will be described as an example, but the medical image standard does not need to be limited to DICOM.

[0043] The image storage device 200 can obtain medical image analysis results from the image analyzer 300. The medical image analysis results can include various medical predictions, including lesion information. The medical image analysis results can be provided to assist the user in interpreting the image, and can also be provided as auxiliary images that display lesion information on the image. For example, the auxiliary image can be a DICOM secondary capture (SC) image (simply referred to as SC). The SC image is a separate image from the original medical image, generated by displaying lesion information on the original medical image, and can be displayed in a PACS viewer. The medical image analysis results can also be provided as a text-based report. For example, the report may be a DICOM Basic Text SR (Structured Report). However, the format of the medical image analysis results is not limited to this and may include results in various DICOM formats.

[0044] The image storage device 200 can obtain the comparative analysis results of the target image and the past image (comparison analysis results with the past image) from the image analysis device 300. The comparative analysis results with the past image can include the degree of change in the lesion obtained by comparing the analysis results of the target image and the analysis results of the past image. The comparative analysis results can also be provided to assist the user in interpreting the image, and can be provided in various ways. For example, the comparative analysis results can be provided together with an auxiliary image (SC) of the target image, and such an auxiliary image including the comparative analysis results can be called an augmented auxiliary image (Augmented SC). Alternatively, the comparative analysis results can be provided as an auxiliary image separate from the auxiliary image (SC) of the target image, and such a separately provided auxiliary image can be called an additional auxiliary image (Additional SC). Augmented auxiliary images and additional auxiliary images will be described in detail below.

[0045] The medical images stored in the image storage device 200 may include images acquired by medical imaging devices of various modalities. The medical images may be X-ray images, magnetic resonance imaging (MRI) images, ultrasound images, computed tomography (CT) images, digital mammography (MMG) images, digital breast tomosynthesis (DBT) images, etc. In the following description, chest X-ray images are used as an example of medical images, but the medical images are not limited thereto, and the present disclosure may be applied to various types of medical images.

[0046] The video analysis device 300 can analyze a requested medical image (target image) using an artificial intelligence (AI) model and store the analysis results in the image storage device 200. The video analysis device 300 can be equipped with an AI model specialized for each type of medical image and can select an AI model depending on the type of input image to perform analysis such as lesion detection appropriate for the input image. The AI ​​model is generated to perform medical inference from the input medical image, and the model structure, training data configuration, training method, and medical inference target can be variously designed.

[0047] In addition, the video analysis device 300 can compare and analyze the image requested for analysis (target image) with past images and store the results of the comparison and analysis with the past image in the image storage device 200. The video analysis device 300 can extract at least one past image related to the target image for the comparison and analysis and compare and analyze the target image with the past image. The comparison and analysis target can be images taken by the patient at a time lag, and can be at least one past image to be compared with the current image. Here, the image requested for analysis can be referred to as the target image or the current image, and a past image of the patient taken before this can be referred to as the reference image. Although one past image is mainly described as the reference image in the following description, the reference image may be multiple past images.

[0048] When the video analysis device 300 receives a request to analyze a target image of a patient, it can analyze the target image and obtain analysis results including lesion information. When the video analysis device 300 receives a request to analyze or compare the target image, it can identify past images of the patient taken before the target image and perform a comparative analysis of the past images with the target image to obtain comparative analysis results, such as the degree of change in the lesion. For example, the video analysis device 300 can search for previously taken images based on the patient ID of the target image in the image storage device 200 and perform a comparative analysis with the past images. Information about past images to be used for the comparative analysis can also be included in the analysis request so that the video analysis device 300 does not need to search for past images. While the video analysis device 300 may be described as determining past images, the past images to be used as a comparison reference can be specified by a user input and / or the image storage device 200 can inform the video analysis device 300 of past images selected based on criteria from among similar images of the same patient.

[0049] The past video used as the comparison reference may be determined in various ways. For example, the video analysis device 300 may determine the most recent video from among the past videos of the patient stored in the video storage device 200 as the reference video. The video analysis device 300 may search for past videos of the patient taken within a certain period (e.g., the last n, the last n months, the last n years, etc.) based on the capture date of the target video, and determine the most recent video or a video that meets certain conditions as the reference past video. Here, the conditions may be set to select videos taken a certain period (e.g., three months) before the capture date of the target video to detect significant changes, or to select videos that have undergone AI analysis or reading, or various other conditions to determine the past video used for comparison analysis. Meanwhile, videos captured by a video device are automatically stored in the video storage device 200. However, if an image (e.g., an X-ray image) is not captured accurately and is re-captured immediately after capture, duplicate or inaccurate images may be accumulated in the video storage device 200. Therefore, to prevent a video whose shooting time is the same as that of the target video from being determined as a past video, the video analysis device 300 may exclude videos shot consecutively before the target video from the reference video. The consecutively shot videos are, for example, videos shot at a time difference of minutes from the target video, and various exclusion criteria may be set.

[0050] The video analysis device 300 may perform a comparative analysis in various ways. For example, the video analysis device 300 may analyze both past and current images of a patient, detect lesions in each of the two images, and detect the degree of change in the lesion. Alternatively, if the video analysis device 300 has already analyzed past images, it may extract lesion information from the analysis results of the past images and compare this with the lesion information detected in the current image to detect the degree of change in the lesion. For convenience of explanation, the comparative analysis with past images may be described as a comparative analysis of past and current images, which may include utilizing the results of an analysis of past images that has already been performed.

[0051] The time point at which the video analysis device 300 performs a comparative analysis with a past video can be set in various ways. For example, when the video analysis device 300 receives a request to analyze a target video, it can perform a target video analysis and a comparative analysis with a past video, and provide the comparative analysis result along with the analysis result of the target video. Alternatively, when the video analysis device 300 receives a request to compare and analyze a past video, it can perform a comparative analysis with the past video, and provide the comparative analysis result with the past video. The request to analyze the target video or the request to compare and analyze with a past video can be transferred from the video storage device 200 or the user terminal 100, or can be automatically generated by the video analysis device 300 upon detecting the storage of the target video.

[0052] The following explanation will be given using a chest X-ray image as an example.

[0053] The image analysis device 300 can analyze chest X-ray images to detect lesions from the chest X-ray images. Lesions that can be detected in chest X-ray images include nodules, pneumothorax, pleural effusion, consolidation, cardiomegaly, atelectasis, pulmonary edema, calcific degeneration, pulmonary fibrosis, mediastinal dilation, pulmonary tuberculosis, and fractures, as shown in Table 1. In addition, the image analysis device 300 can analyze chest X-ray images to obtain major medical indicators, including an abnormality score. For example, the image analysis device 300 can obtain an abnormality score and a tuberculosis (TB) analysis score (TB) from the input image. It is possible to infer the following: the analysis score, the probability of cardiac hypertrophy (cardiomegaly), etc. Of course, the detectable lesions and medical indicators may change depending on the images analyzed by the image analyzer 300.

[0054] [Table 1] The lesions to be compared with the previous image, i.e., the comparison lesions, can be set to all lesions detectable in the image. Alternatively, the comparison lesions can be set to some of the lesions detectable in the image. The comparison lesions can be changed and can be set differently depending on the medical institution or medical staff. For example, the lesions that can be compared in a chest X-ray image can be set as shown in Table 2, but this can be changed. If the comparison lesions can be set differently depending on the medical staff, the image analysis device 300 can analyze all the change levels of lesions that the user can select and display only the change levels of the lesions selected by the user on the viewer 110.

[0055] [Table 2] The image analysis device 300 compares changes in lesions detected between past and current images to obtain a comparison analysis result. The image analysis device 300 can determine that there is a change (increase or decrease) in the lesion if there is a change (increase or decrease) greater than a threshold. The image analysis device 300 can determine that there is no change in the lesion if there is a change less than the threshold. The threshold can be set differently depending on the type of lesion. There are various methods for comparing changes in lesions, and the determination can be made based on a change in the area occupied by the lesion. The lesion change may be determined by, but is not limited to, the ratio of the lesion area in the current image to the lesion area in the past image (e.g., 1.2 times, 0.8 times), or by comparing the area ratio of an abnormal area (e.g., left pulmonary nodule) to a reference area (e.g., left lung) calculated from each of the past and current images, or by comparing the abnormality score ratio of an abnormal area (e.g., left pulmonary nodule) to an abnormality score for a reference area (e.g., left lung) calculated from each of the past and current images. The image analysis device 300 may determine the degree of lesion change as shown in Table 3.

[0056] [Table 3] When a lesion is present in both the past and current images but its size does not change over time, the comparative analysis result of the lesion is determined to be no change. When a lesion was detected in the past image but not in the current image, the comparative analysis result of the lesion is stored as disappeared. When a lesion was not detected in the past image but is detected in the current image, the comparative analysis result of the lesion is determined to be appeared. When the lesion area in the current image is decreased from the past image, the comparative analysis result of the lesion is determined to be decreased. When the lesion area in the current image is increased from the past image, the comparative analysis result of the lesion is determined to be increased. In this case, the image analysis device 300 can calculate the area ratio of the lesion area (e.g., the nodule area in the left lung) to the reference area (e.g., the left lung) and compare the area ratios to determine whether the lesion area has increased or decreased. Alternatively, the image analysis device 300 may calculate the ratio of abnormal scores for a reference region (e.g., the left lung) to the abnormal score for a lesion region (e.g., a nodule region in the left lung), and compare the score ratios to determine whether the lesion region is increased or decreased. If no lesion is detected in either the past image or the current image, the comparative analysis result for the lesion is determined to be no lesion (No existence).

[0057] In another embodiment, the image analysis device 300 can compare and analyze a plurality of past images and a present image. The number (N) of medical images used for the comparison and analysis and the image selection method can be predetermined by user settings, and / or adaptively determined during the comparison and analysis.

[0058] When N images are selected from the patient's images, the image analysis device 300 can generate a comparative analysis result by comparing and analyzing the two images and determining the degree of change in the lesion. The image analysis device 300 can obtain N-1 comparative analysis results by comparing two temporally adjacent images. The N-1 comparative analysis results can be output as auxiliary images (SC) including the degree of change in the lesion. The image analysis device 300 can then combine the N-1 comparative analysis results to generate an overall comparative analysis result. The overall comparative analysis result can be expressed as, for example, a graph or table of change rate or time (photograph date) as information showing the progression of lesion change. The overall comparative analysis result can be provided as a separate report or interface.

[0059] The video analysis device 300 can adaptively select past images. According to one embodiment, the video analysis device 300 can determine that there is no need to review the image before the previous past image (past image 1) if, as a result of comparing the current image with the immediately preceding past image, a lesion disappears, appears, or there is no change in area. If the lesion increases and / or decreases, the video analysis device 300 can search for the earliest past image (past image n) in which the lesion first appeared by referring to the analysis results and reading report of the past images, and compare and analyze images from the earliest past image to the current image to analyze changes in the lesion between adjacent images and analyze the progression of changes in the lesion (e.g., change rate, graph or table of change over time). The video analysis device 300 can select and compare and analyze at least a portion of the images from the earliest past image to the current image based on user selection or selection criteria (e.g., a shooting interval of three months or more).

[0060] According to another embodiment, if a comparison with the immediately preceding past image (past image 1) indicates an increase and / or decrease in the lesion, the video analysis device 300 may sequentially analyze a certain number of past images. For example, if configured to analyze up to three past images, the video analysis device 300 may search for the image before past image 1 (past image 2). If the analysis results of past image 2 and past image 1 also indicate an increase / decrease in the lesion, the video analysis device 300 may search for the image before past image 2 (past image 3) and compare and analyze past image 3 and past image 2. As a result, the video analysis device 300 may compare and analyze images from past image 3 to the current image to analyze changes in the lesion between adjacent images and analyze the progression of the change in the lesion (such as the rate of change, a graph or table of change over time, etc.). If a lesion appears and / or no change in the lesion is detected as a result of the analysis of past image 2 and past image 1, the video analysis device 300 may not further search for the image before past image 2 (past image 3) and may use past image 2 and past image 1 as reference images.

[0061] The analysis results for the target image analyzed by the image analyzer 300 can be stored in the image storage device 200 and displayed on the user terminal 100. The analysis results can include AI analysis results for the target image and comparative analysis results between the target image and past images. If the image is a DICOM image, the image metadata can be stored in a public tag and a private tag. Information about the medical image is recorded in the public tag according to the file structure defined by the DICOM standard. Tags can be freely used by medical device companies when adding information not included in public tags to DICOM images, and analysis results can be recorded in private tags. Private tags record AI analysis results including lesion information and comparative analysis results including lesion change levels, and can also include whether the current-past image comparison function is enabled.

[0062] The viewer 110 executed in the user terminal 100 can display the analysis results of the target image and the comparative analysis results of the target image and past images. The analysis results of the target image can be provided as a basic auxiliary image (SC). The comparative analysis results with past images can be provided together with the basic auxiliary image (SC), and the basic auxiliary image (SC) that further includes the comparative analysis results can be called an augmented auxiliary image (Augmented SC). The comparative analysis results with past images can be provided as an auxiliary image separate from the basic auxiliary image (SC), and an auxiliary image provided in addition to the basic auxiliary image (SC) can be called an additional auxiliary image (Additional SC).

[0063] The viewer 110 can display various information included in the comparative analysis results, and for this purpose, the comparative analysis results can be saved in the DICOM format, which is a data format that can be displayed by the viewer 110.

[0064] The viewer 110 can display the shooting dates and times of past and current footage.

[0065] The viewer 110 may display the degree of change for each comparison target lesion based on the comparison analysis results. The viewer 110 may display the location of a lesion that has changed among the comparison target lesions. The viewer 110 may display a lesion in which a change requiring careful interpretation (e.g., Appeared, Increased, etc.) has appeared so as to be distinguishable from other lesions. For example, the viewer 110 may visually display the lesion or the degree of change in the lesion differently and / or add a highlight mark. When the medical image is a chest X-ray image, the viewer 110 may display the degree of change in the lesion separately for the left lung and the right lung. The viewer 110 may provide a threshold value used to determine the degree of change in the lesion.

[0066] 2, the viewer 110 can display the lesion change degree included in the comparison analysis result as a graphical indicator such as an icon. A user can intuitively and quickly recognize the lesion change degree through the graphical indicator designated for each change degree.

[0067] This comparative analysis function can be used as follows:

[0068] For example, assume that an abnormal lesion is detected as a result of analyzing a patient's chest X-ray image, and the patient undergoes lung surgery. The doctor can then instruct the hospital system to take another chest X-ray image of the patient to monitor the progress. When the radiologist takes the patient's chest X-ray image, the image is transmitted from the X-ray imaging device to the image storage device 200. The image analysis device 300 compares and analyzes the chest X-ray image taken after the procedure with the chest X-ray image taken before the procedure, obtains a comparative analysis result including the degree of change in the lesion, and stores the comparative analysis result in the image storage device 200. The doctor can check the change in the lesion before and after the procedure using the current-past image comparison function of the image analysis device 300.

[0069] For example, suppose that an abnormal lesion is detected as a result of analyzing a patient's chest X-ray image, and the doctor diagnoses that follow-up observation is necessary. When the patient undergoes X-ray imaging after a certain period of time, the image is transmitted from the X-ray device to the image storage device 200. The image analysis device 300 compares and analyzes the previously taken chest X-ray image with the currently taken chest X-ray image, obtains a comparative analysis result including the degree of change in the lesion, and stores the comparative analysis result in the image storage device 200. The doctor can check the change in the lesion over a certain period of time through the current-past image comparison function of the image analysis device 300, which is linked to the image storage device 200.

[0070] 3 and 4 are examples of screens that provide comparative analysis results with past video according to an embodiment.

[0071] 3, the viewer 110 executed on the user terminal 100 can provide a screen related to the target image reading operation in conjunction with the image storage device 200, and can also provide the results of a current-prior comparison function on the screen. The current image vs. prior image comparison function can be selected by the user or provided as a default. When the current image vs. prior image comparison function is activated in the image analysis device 300, the viewer 110 can display the results of the comparison analysis with the prior image on the screen, and can also provide an augmented supplemental image (ASC) that includes the results of the comparison analysis in addition to the analysis results of the target image.

[0072] The augmented auxiliary image screen 400 displayed by the viewer 110 may be composed of an image area 410 and an analysis information area 420. The image area 410 may display a basic auxiliary image (SC) including the analysis results of the target image. The basic auxiliary image (SC) may be an image including the analysis results of the target image (e.g., lesion scores such as Ptx 88% and Csn 94%, an outline of the lesion area, a heat map, etc.). Lesion change information may be additionally displayed on the basic auxiliary image (SC). The lesion score may indicate the confidence level of the presence of a lesion as a score / probability.

[0073] The analysis information area 420 may be configured with an area 421 displaying the analysis results of the target image and an area 422 displaying the results of a comparison analysis with a past image (e.g., the degree of change in a lesion). Area 421 may display medical indices obtained by analyzing the target image using an AI model, such as an abnormality score, a pulmonary tuberculosis analysis score, and a cardiomegaly probability. Area 422 may display the degree of change in a comparison target lesion (e.g., Ptx, PEf, Csn). In a case where an object is divided into left and right, such as a chest X-ray image, the degree of change in a lesion in the right lung (422-R) and the degree of change in a lesion in the left lung (422-L) may be displayed separately. In this case, the degree of change in a comparison target lesion (e.g., Ptx, PEf, Csn) may be displayed using a graphical indicator 423 such as an icon. The text describing the degree of change (e.g., No change, Disappeared) can be displayed and / or omitted depending on the size of the analysis information area 420. Even without a text description such as No change, the user can intuitively and quickly recognize the degree of change in the lesion through a graphical indicator such as an icon.

[0074] Augmented auxiliary image (Augmented SC) is a form of providing comparative analysis results to the analysis results of a target image, but the user needs to check the capture time of the past image used for the comparative analysis to determine the rate of change, etc. For this purpose, the augmented auxiliary image screen 400 can provide the capture time of the past image used for the comparative analysis. The augmented auxiliary image screen 400 can also provide information explaining the time difference between the target image and the past image (e.g., a comparison with an image of the patient from 8 weeks ago).

[0075] Referring to FIG. 4, when the comparison function between the current image and the past image is activated in the image analysis device 300, the viewer 110 can display the comparison analysis results with the past image on the screen, and can provide the comparison analysis results through additional auxiliary images (Additional SC).

[0076] The additional auxiliary image screen 500 displayed by the viewer 110 may be composed of an image area 510 and an analysis information area 520. An auxiliary image (SC) 511 including the analysis results of the past image and an auxiliary image (SC) 512 including the analysis results of the target image may be displayed together in the image area 510 so that the user can simultaneously check the past image and the current target image. The arrangement of the past image and the target image may vary. The auxiliary images 511 and 512 of the past image and the target image may be images including the analysis results (lesion information) of the corresponding images. Lesion change information may be additionally displayed in the auxiliary image (SC) of the target image.

[0077] The viewer 110 can provide information about the past video and the target video (such as the shooting date and time), and can provide information to show the time difference between the target video and the past video (for example, a comparison with a video from eight weeks ago).

[0078] The analysis information area 520 displays the results of the comparison analysis with the previous image (the degree of change in the lesion). The UI for displaying the degree of change in the comparison lesion (e.g., Ptx, PEf, Csn) in the analysis information area 520 can be designed in various ways. For example, the lesion name 521 and its degree of change can be displayed in a table format. When an object is divided into left and right, such as a chest X-ray image, the degree of change in the lesion in the right lung (522-R) and the degree of change in the lesion in the left lung (522-L) can be separated. In this case, the degree of change in the comparison lesion (e.g., Ptx, PEf, Csn) can be displayed using a graphical indicator such as an icon. The user can intuitively and quickly recognize the degree of change in the lesion through the graphical indicator such as an icon. Meanwhile, if there is space to enter text describing the degree of change (e.g., No change, Disappeared, etc.), the text description can be displayed together with the graphical indicator.

[0079] This additional auxiliary image (Additional SC) provides the analysis results of the current image of the person being analyzed and the past image of the person being compared on one screen, so the user does not need to check the patient's past image on a separate screen and can easily compare the lesions detected in the two images on the additional auxiliary image screen 500.

[0080] FIG. 5 is a diagram illustrating an order in which a comparison analysis result is output in a viewer according to an embodiment.

[0081] 5, the viewer 110 can sequentially provide images for reading a target image in conjunction with the image storage device 200. While conventional viewers provide a captured image 10 and a supplementary image (SC) 20 including an analysis result of the image, the viewer 110 of the present disclosure can also provide a comparative analysis result with a past image.

[0082] When set to provide the comparative analysis results through the augmented auxiliary image (Augmented SC), the viewer 110 can sequentially display the captured image 10 of the target image and the augmented auxiliary image (Augmented SC) 400. The augmented auxiliary image (Augmented SC) 400 can include the analysis results of the target image and the comparative analysis results.

[0083] When configured to provide comparative analysis results through Augmented SC, the viewer 110 can sequentially display the captured image 10 of the target image, the basic SC 20 containing the analysis results of the target image, and the Additional SC 500.

[0084] The output options in which the viewer 110 presents the comparative analysis results can be fixed and / or user selectable.

[0085] Each of Figures 6 to 8 is an example of a screen providing an augmented auxiliary video according to one embodiment.

[0086] 6, the augmented auxiliary image screen 400A displayed on the viewer 110 may be configured with an image area 410A and an analysis information area 420A, and may further include an area 430A for displaying past image information used for comparison and analysis. The layout and size of the augmented auxiliary image screen 400A may be designed in various ways.

[0087] An auxiliary image (SC) including the analysis results of the target image may be displayed in the image area 410A. The auxiliary image (SC) displays the analysis results of the target image (e.g., lesion scores such as Ptx 88% and Csn 94%, lesion area contours, heat maps, etc.), and may additionally display lesion change information 411, 412, 413, and 414 of comparison lesions (e.g., Csn and PEf in the left lung, Ptx and Csn in the right lung) among the lesions detected in the target image. The lesion change information 411, 412, 413, and 414 indicates the degree of lesion change (Increased, Appeared, No change, Decreased) based on the results of comparison analysis with past images, and may be displayed in text and / or as a change degree icon.

[0088] The analysis information area 420A can display the analysis results of the target image (Abnormality Score, TB analysis score, etc.) and the comparison analysis results with the past image (degree of change of lesion). At this time, the degree of change of the comparison target lesion (e.g., Ptx, PEf, Csn) can be displayed using a graphical indicator such as an icon, and text explaining the degree of change can be omitted or displayed.

[0089] Area 430A may display past image information used for the comparative analysis. The past image information may include the shooting time of the past image used for the comparative analysis or the time difference between the target image and the past image.

[0090] The augmented auxiliary video screen 400A can identify lesions that have changes (e.g., Appeared, Increased, etc.) that require further user attention and highlight them so that they can be visually distinguished. For example, if a lesion PEf appears in the left lung, the newly appeared lesion PEf, its lesion change information 412, or its change degree icon can be highlighted by displaying it in a different color, size, pattern, etc., and / or adding a highlight mark.

[0091] 7, the augmented auxiliary image screen 400B displayed on the viewer 110 may include an image area 410B and an analysis information area 420B, and may further include an area 430B for displaying past image information used for comparison and analysis. The layout and size of the augmented auxiliary image screen 400B may be designed in various ways.

[0092] The image area 410B may display a supplementary image (SC) including the analysis result of the target image. The supplementary image (SC) displays the analysis result of the target image, and may additionally display lesion change information of a comparison lesion among the lesions detected in the target image, as shown in FIG. 6.

[0093] The analysis information area 420B may display the analysis results of the target image (Abnormality Score, TB analysis score, etc.) and the comparative analysis results with the past image (degree of change of lesion). At this time, the degree of change of the comparison target lesion (e.g., Ptx, PEf, Csn) may be displayed using a graphical indicator such as an icon, and text explaining the degree of change may be omitted or displayed.

[0094] On the other hand, the comparison lesions displayed on the augmented auxiliary image screen 400B may differ depending on the user settings. For example, if the user sets Ptx and Csn to be displayed but not Ndl and PEf, the analysis information area 420B may only display the Ptx and Csn change rates of the lesions that are set to be displayed. In addition, lesion change information displayed on the auxiliary image (SC) may only be provided for the comparison lesions that are set to be displayed.

[0095] 8, the augmented auxiliary image screen 400C displayed by the viewer 110 may be composed of an image area 410C and an analysis information area 420C, and may further include a detailed analysis table 440C. The layout and area size of the augmented auxiliary image screen 400C may be designed in various ways.

[0096] The image area 410C may display a supplementary image (SC) including the analysis results of the target image (current image). The supplementary image (SC) displays the analysis results of the target image and may additionally display lesion change information of a comparison lesion among the lesions detected in the target image, as shown in FIG. 6.

[0097] The analysis information area 420C may display the analysis results of the target image (Abnormality Score, TB analysis score, etc.) and the comparative analysis results with the past image (degree of change of lesions). At this time, the degree of change of the comparison target lesion (e.g., Ptx, PEf, Csn) may be displayed using a graphical indicator such as an icon, and the text explaining the degree of change may be omitted or displayed.

[0098] The detailed analysis table 440C may include a lesion name 441C, a lesion-specific threshold 442C, a lesion score 443C, and a lesion location 444C, which may be variously modified.

[0099] 9 and 10 are each an example of a screen providing additional auxiliary video according to one embodiment.

[0100] 9, the additional auxiliary video screen 500A displayed on the viewer 110 may be configured with an image area 510A and an analysis information area 520A, and may display the shooting time of the past image and the target image. The layout and size of the additional auxiliary video screen 500A may be designed in various ways.

[0101] In the image area 510A, an auxiliary image (SC) 511A including the analysis result of the past image and an auxiliary image (SC) 512A including the analysis result of the target image can be displayed together. The auxiliary images 511A and 512A of the past image and the target image display the analysis results (lesion information) of the images, and the auxiliary image 512A of the target image can additionally display lesion change information of a comparison lesion among the detected lesions. The lesion change information can be displayed in various forms.

[0102] The analysis information area 520A displays the results of the comparison analysis with the past image (the degree of change in the lesion). The UI for displaying the degree of change in the comparison target lesion (e.g., Ptx, PEf, Csn) in the analysis information area 520A can be designed in various ways. For example, the lesion name 521A and its degree of change can be displayed in a table format. When an object is divided into left and right, such as a chest X-ray image, the degree of change in the lesion in the right lung (522A-R) and the degree of change in the lesion in the left lung (522A-L) can be separated. In this case, the degree of change in the comparison target lesion (e.g., Ptx, PEf, Csn) can be displayed using a graphical indicator such as an icon, and text explaining the degree of change can be displayed or omitted.

[0103] The additional auxiliary video screen 500A can highlight and visually distinguish lesions that have undergone changes requiring highlighting, such as lesion appearance (Appeared) or lesion area increase (Increased). For example, when a lesion PEf appears in the left lung, the additional auxiliary video screen 500A can display change information (Appeared or Appeared icon) for the lesion PEf in the auxiliary video 512A of the target video. In this case, since the newly appeared lesion PEf is a lesion that requires highlighting, it can be highlighted by adding a visual change (such as a change in color, size, or pattern) to the text (PEf or Appeared) or change degree icon displayed in the video, and / or adding a highlight mark 513A.

[0104] Furthermore, if there is a change that requires highlighting (e.g., Appeared, Increased, etc.), the additional auxiliary video screen 500A can highlight it in the analysis information area 520A so that it is visually distinguished from other change degrees. For example, in the lesion change degree for the left lung (522A-L), the change information for the lesion PEf (Appeared or the Appeared icon) can be displayed in a color that stands out.

[0105] 10, the additional auxiliary video screen 500B displayed on the viewer 110 may be configured with an image area 510B and an analysis information area 520B, and may display the shooting time of the past image and the target image. The layout and size of the additional auxiliary video screen 500B may be designed in various ways.

[0106] In the image area 510B, a supplementary image (SC) 511B including the analysis result of the past image and a supplementary image (SC) 512B including the analysis result of the target image can be displayed together. The auxiliary images 511B and 512B of the past image and the target image display the analysis results (lesion information) of the images, but the auxiliary image 512B of the target image can additionally display lesion change information of a comparison lesion among the detected lesions.

[0107] In the analysis information area 520B, the results of the comparison analysis with the past video (degree of change in the lesion) are displayed. The additional auxiliary image screen 500B can display a comparison target lesion selected by the user in the analysis information area 520B. For example, if the user sets Ptx and Csn to be displayed but not Ndl and PEf, only the change rates of Ptx and Csn of the set lesion can be displayed in the analysis information area 520B. In addition, lesion change information displayed in the auxiliary image 512B of the target image can only be provided for the comparison target lesion set to be displayed.

[0108] 11 and 12 are each examples of analysis reports generated by one embodiment.

[0109] 11 and 12, the analysis result of the target image by the image analysis device 300 can be generated as an analysis report. The analysis report can further include a comparative analysis result with a past image along with information on lesions detected in the target image.

[0110] The analysis report may be, for example, a structured report created according to the DICOM standard, which may display the comparative analysis results of comparison lesions A, B, C, and D using phrases such as "A has appeared in the left (or right or both) lung..., B has not changed..., C has increased..., D has disappeared...".

[0111] For example, analysis report 600A describes lesions detected in the target image, and if the result of the comparative analysis with the past image shows that the pneumothorax in the right lung has not changed compared to the past image, analysis report 600A may include a corresponding explanation (Pneumothorax has not changed in the right lung) 610. Also, if the pleural effusion in the left lung of the target image has not changed compared to the past image, analysis report 600A may include a corresponding explanation (Pleural effusion has not changed in the left lung) 611.

[0112] For example, the analysis report 600B describes the lesions detected in the target image. If consolidation that was not detected in the previous image appears in the left and right lungs as a result of the comparison analysis with the previous image, the explanation for this (consolidation has appeared in both lungs.) 612. Also, if a pneumothorax that was not detected in the previous image is detected in the right lung in the target image, the analysis report 600B may include a description that a pneumothorax has appeared in the right lung. In addition, if pleural effusion that was not detected in the previous image is detected in the left or right lung in the target image, the analysis report 600B may include a description that pleural effusion has appeared in both lungs. 614.

[0113] Therefore, the analysis report can provide the analysis result that a lesion exists as well as the change in the lesion over time. Therefore, the user can know whether the lesion is a newly appeared lesion, a lesion that has not changed, a lesion that has decreased in size, or a lesion that has increased in size through the analysis report of the target image without having to look at past images and their analysis reports. In particular, the analysis report provides information on lesions that were previously present but have disappeared and were not detected, so the user can know the lesions that have disappeared and were not detected through the analysis report of the target image.

[0114] FIG. 13 is an example of a worklist generated according to one embodiment.

[0115] 13, the viewer 110 executed on the user terminal 100 can provide a worklist 700 in conjunction with the image storage device 200. The worklist 700 displays a list of images to be read by the user in a table format along with key information. The worklist does not necessarily have to be included in the viewer 110 and can be installed as a separate program. The information displayed in the worklist can be provided by the viewer 110 or the image storage device 200, but for convenience of explanation, it can be described as being provided by the viewer 110.

[0116] The viewer 110 can display the analysis results of the target image analyzed by the image analysis device 300 in a designated column of the worklist 700 in conjunction with the image storage device 200. The analysis results can include AI analysis results for the target image and comparison analysis results between the target image and past images. In this case, the viewer 110 can display the comparison analysis results in a designated column 710 of the worklist 700. The viewer 110 can display the comparison analysis results included in the DICOM Private tag in the worklist 700. In this case, the viewer 110 can display in the worklist 700 whether the automatic comparison analysis function with past images is operating based on the Private tag of the DICOM image.

[0117] There are various ways to display the comparative analysis results in the worklist, such as color chips, text, icons, flagging, etc. For example, the viewer 110 can distinguish the comparative analysis results included in the private tag by color chips and display them in a specified column 710. The color chips for the comparative analysis results can be set by the user, or the viewer 110 can display color chips set according to the priority or importance of the comparative analysis results.

[0118] A representative change degree (e.g., Appeared or icon) can be displayed in a designated column 710 of the worklist. Because the comparative analysis results include multiple lesion change degrees, the lesion change degree with the highest importance (e.g., Appeared, Increased, etc.) can be determined as the representative change degree, and the representative change degree can be displayed in the worklist. In addition, because the criticality of each lesion is different, the change degree that represents the comparative analysis results of the image can be determined taking into account the importance of the lesion and the importance of the lesion change degree.

[0119] The work priority of the worklist can be determined based on the comparative analysis results generated by the image analysis device 300. For example, a user can check the comparative analysis results performed on the image to be read through the worklist 700 and improve the efficiency of the reading work by arranging the work order according to the importance of the comparative analysis results. Alternatively, the viewer 110 can provide a worklist by setting a high work priority for an image in which a change requiring careful reading (e.g., Appeared, Increased, etc.) has occurred. For example, if the comparative analysis results show no change, the lesion has disappeared, or the lesion has decreased (positive change), the reading priority of the image can be set low. On the other hand, if the comparative analysis results show a new lesion and / or an increase in lesions (negative change), the reading priority of the image can be set high.

[0120] FIG. 14 is a flowchart of a video analysis method according to an embodiment.

[0121] 14, when a patient's image (target image) is acquired, the image analysis device 300 analyzes the target image using an AI model and acquires an analysis result including lesion information (S110). The analysis result may include lesion information including a lesion score, a lesion location, and major medical indicators including an abnormality score.

[0122] The video analysis device 300 determines a previous video of the patient captured before the target video as a reference video for comparison (S120). The video analysis device 300 may search for previously captured videos in the video storage device 200 based on the patient identifier (Patient ID) of the target video and select a previous video that meets the criteria. The previous video to be used as the comparison reference may be determined in various ways. For example, the video analysis device 300 may determine the latest video of the patient stored in the video storage device 200 as the reference video, a previous video captured a certain time interval after the target video as the reference video, or a video that has undergone AI analysis or reading as the reference video. Here, the time point at which the video analysis device 300 performs the comparison analysis with the previous video may be set in various ways. For example, the video analysis device 300 may perform the comparison analysis when it receives a request for analysis of the target video, or may perform the comparison analysis when it receives a separate request for comparison analysis.

[0123] The video analysis device 300 compares and analyzes the past video and the target video to obtain a comparison analysis result including a change degree of the lesion (S130). The video analysis device 300 can extract lesion information of at least one comparison target lesion from the analysis results of the past video and the target video. The video analysis device 300 can determine the change degree of the comparison target lesion over time and generate a comparison analysis result including the change degree of the comparison target lesion. The video analysis device 300 can match lesions detected at corresponding positions in the past video and the target video to determine the change degree, and can determine that a lesion that exists only in the past video or the target video has disappeared and / or appeared. The video analysis device 300 can determine that a lesion change has occurred if the comparison result with the past video shows a change in the comparison target lesion that is greater than or equal to a threshold, and the threshold can be set differently depending on the type of lesion. A lesion change can be determined based on a change in the area occupied by the lesion or a change in the abnormality score for the lesion, but is not limited thereto. The degree of lesion change can be analyzed as no change, lesion disappeared, lesion appeared, lesion decreased, or lesion increased, as shown in Table 3. Meanwhile, the video analysis device 300 can analyze the past video using an AI model for comparative analysis of the past video and the target video, obtain analysis results including lesion information of the past video, and then compare the analysis results with the analysis results of the target video. Alternatively, if there are AI analysis results for the identified past video, i.e., if the video analysis device 300 has already analyzed the past video, the video analysis device 300 can immediately compare the analysis results of the past video and the target video without having to re-analyze the past video.

[0124] The image analyzer 300 generates the analysis results for the target image in a specified data format (e.g., DICOM format) and stores them in the image storage device 200 (S140). For example, analysis results including lesion information for the target image can be stored in a secondary capture format conforming to the DICOM standard, which can be called a basic SC. Comparative analysis results with past images can also be stored in a secondary capture format conforming to the DICOM standard, or in an augmented SC in which the comparative analysis results are added to the analysis results of the target image, or in an additional SC that compares and displays the analysis results of the past image and the analysis results of the target image. The analysis results for the target image can be included in the private tag of the DICOM image. The analysis results for the target image can be compiled in the secondary capture format of the target image and displayed sequentially in the viewer 110. The analysis results for the target image, particularly the comparative analysis results, can be displayed in a worklist. Furthermore, the analysis results for the target image, particularly the degree of lesion change, can be displayed in a written analysis report.

[0125] FIG. 15 is a flowchart of a video analysis method according to another embodiment.

[0126] Referring to FIG. 15, the image analysis device 300 analyzes an image of a patient (target image) using an AI model and obtains an analysis result including lesion information (S210). The analysis result includes lesion information including a lesion score, a lesion location, and an abnormality score (Abnormality Score). The image analyzer 300 can automatically generate analysis results when new images are acquired, and can provide analysis results for the image of a patient when the patient ID is selected in the PACS worklist or viewer.

[0127] The image analysis device 300 selects a plurality of previous images taken before the target image from among the patient images for comparative analysis (S220). The number (N) of medical images to be used for comparative analysis and the image selection method can be predetermined by user settings or adaptively determined during the comparative analysis.

[0128] The image analysis device 300 obtains a comparative analysis result including the degree of lesion change between the images by comparing and analyzing temporally adjacent images between multiple past images and the target image (S230). The degree of lesion change can be analyzed as no change, lesion disappeared, lesion appeared, lesion decreased, or lesion increased, as shown in Table 3.

[0129] The video analysis device 300 extracts information indicating the progression of changes by lesion from the results of the comparison and analysis of multiple past videos and the target video (S240). The information indicating the progression of changes by lesion can be expressed as a graph or table of change speed, change by time (photographing date), etc.

[0130] The image analyzer 300 generates analysis results for the target image in a specified data format (e.g., DICOM format) and stores them in the image storage device 200 (S250). For example, analysis results including lesion information for the target image can be stored as a secondary capture in accordance with the DICOM standard, and multiple comparative analysis results can also be stored as secondary capture in accordance with the DICOM standard. Each comparative analysis result can be stored as an additional SC that shows both the two compared images, and comparative analysis results for a previous image compared to the target image can be stored as an augmented SC. Analysis results for the target image can be included in the private tag of the DICOM image. Analysis results for the target image can be compiled in the secondary capture of the DICOM image in the viewer 110 and displayed sequentially. Analysis results for the target image, particularly comparative analysis results, can be displayed in a worklist. Analysis results for the target image, particularly the degree of lesion change, can also be displayed in text format in an analysis report.

[0131] FIG. 16 is a flowchart of a method for providing analysis results according to an embodiment.

[0132] Referring to FIG. 16, the viewer 110 displays a worklist including a list of videos for a video reading operation in conjunction with the video storage device 200 (S310). The viewer 110 displays the analysis results of each video analyzed by the video analysis device 300 in a designated column of the worklist. The analysis results may include AI analysis results for the video and comparative analysis results. The viewer 110 may display the comparative analysis results in the worklist in various ways (e.g., color chips, text, flagging, icons, etc.). For example, the viewer 110 may classify the comparative analysis results included in the private tag of the video using color chips and display them in the worklist. The viewer 110 may display the degree of change (e.g., Appeared, Increased, etc.) representing the comparative analysis results of the video in the worklist. The viewer 110 may sort and display the video lists in the worklist according to the priority determined by the comparative analysis results.

[0133] When a target image is selected from the work list, the viewer 110 displays analysis results including comparative analysis results between the target image and past images (S320). The viewer 110 can call up and display analysis results saved in a specified data format (e.g., DICOM format). When set to provide comparative analysis results through augmented auxiliary images (ASC), the viewer 110 can sequentially display the captured image of the target image, and the augmented auxiliary images (ASC) including the analysis results of the target image and the comparative analysis results. When set to provide comparative analysis results through augmented auxiliary images (ASC), the viewer 110 can sequentially display the captured image of the target image, the basic auxiliary images (SC) including the analysis results of the target image, and the augmented auxiliary images (ASC) including the comparison results between the past images and the target image.

[0134] The viewer 110 is embodied as a computer program stored on a computer-readable recording medium and includes instructions that are executable by a processor. The computer program may include instructions that cause the processor to, in conjunction with the image storage device 200, display a worklist including a list of images for image reading operations, and, when a target image is selected from the worklist, display analysis results including comparative analysis results between the target image and past images. The computer program may include instructions that cause the worklist to display the comparative analysis results with past images. The computer program may include instructions to display an augmented secondary capture in which the comparative analysis results are added to the analysis results of the target image, and / or to display an additional secondary capture that compares the analysis results of the past images with the analysis results of the target image.

[0135] Here, the user does not necessarily need to check the analysis results, including the comparative analysis results of the target image and the past image, through a worklist, and this is merely an example for explanation. For example, the user (doctor) can check the analysis results, including the comparative analysis results of the target image and the past image, through a viewer that displays the patient's medical information.

[0136] The terminal or device 100, 200, or 300 constituting the medical imaging system 1 of the present disclosure may include one or more processors, a memory for loading a computer program executed by the processor, a storage device for storing the computer program and various data, and a communication interface. The terminal or device 100, 200, or 300 may further include various other components. The processor may be any of various types of processors that process instructions included in a computer program, such as at least one of a central processing unit (CPU), a microprocessor unit (MPU), a microcontroller unit (MCU), a graphic processing unit (GPU), or any other type of processor well known in the art of the present disclosure. The memory stores various data, instructions, and / or information. The memory may be configured to store instructions written to perform the operations of the present disclosure so that they can be processed by the processor. The memory may be, for example, a read-only memory (ROM), a random access memory (RAM), etc. The storage device may non-temporarily store the computer program and various data. The storage device may be configured to include a non-volatile memory such as a read-only memory (ROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a flash memory, a hard disk, a removable disk, or any other form of computer-readable recording medium well known in the art to which the present disclosure pertains. The communication interface may be a wired / wireless communication module supporting wired / wireless communication. The computer program includes instructions to be executed by the processor and is stored in a non-transitory computer-readable storage medium, and the instructions cause the processor to perform the operations of the present disclosure.

[0137] As described above, the embodiments of the present disclosure can be realized not only through devices and methods, but also through a program that realizes functions corresponding to the configurations of the embodiments of the present disclosure or a recording medium on which the program is recorded.

[0138] Although the embodiments of the present disclosure have been described in detail above, the scope of the present disclosure is not limited thereto, and various modifications and improvements made by those skilled in the art using the basic concept of the present disclosure as defined in the appended claims also fall within the scope of the present disclosure.

Claims

1. memory, and a processor for executing instructions stored in the memory; The processor: Analyze the target patient video using an artificial intelligence model and obtain analysis results including lesion information for multiple types of comparison lesions. A past image captured before the target image is determined as a reference image; obtaining a comparative analysis result including lesion change degrees for the plurality of types of lesions by comparing and analyzing the analysis result of the reference image and the analysis result of the target image, and determining the lesion change degrees by matching lesions detected at corresponding positions in the reference image and the target image; The video analysis device displays the comparative analysis results in a viewer executed on a user terminal.

2. The screen displayed by the viewer is It consists of a video area and an analytical information area. an auxiliary image including an analysis result of the target image is displayed in the image area; The video analysis device according to claim 1 , wherein the analysis information area displays lesion change levels for the plurality of types of lesions together with identifiers of the corresponding lesions.

3. The image analysis device according to claim 2 , wherein the identifiers and the lesion change degrees are displayed in a table format.

4. A graphical indicator is assigned for each lesion change degree; The image analysis device according to claim 2 , wherein the lesion change degree is displayed together with an identifier of the lesion by a designated graphical indicator.

5. The image analysis device of claim 2, wherein the image area displays an auxiliary image displaying at least one of medical indices, a contour of a lesion area, or a heat map obtained by analyzing the target image using the artificial intelligence model.

6. The image analysis device of claim 5, wherein the medical index includes at least one of an abnormality score, a TB analysis score, or a probability of cardiac hypertrophy.

7. 2. The image analysis device of claim 1, wherein the lesion change degree is determined as one of no change, lesion disappearance, lesion appearance, lesion decrease, lesion increase, or no existence.

8. determining a representative change degree among the lesion change degrees of the lesions included in the comparative analysis results; The video analysis device of claim 1 , wherein the representative change degree is displayed in a worklist.

9. The processor: The video analysis device according to claim 1 , wherein the viewer determines whether to provide the comparative analysis result based on a user's selection.

10. The processor: generating an analysis report using the analysis results of the target video; The image analysis device of claim 1 , wherein the analysis report includes information about a lesion detected from the target image and a result of a comparison analysis with the reference image.

11. The processor:

2. The image analysis device of claim 1, wherein a plurality of past images taken before the target image are selected as a plurality of reference images from among the patient's images, and a plurality of comparative analysis results including a degree of change in the lesion between the images are obtained by comparatively analyzing temporally adjacent images of the plurality of reference images and the target image.

12. The processor:

2. The video analysis device according to claim 1, wherein the analysis result performed for the target video is generated in a designated data format and stored in a video storage device.

13. The processor:

13. The image analysis device according to claim 12, wherein the comparative analysis result is generated by a secondary capture of the DICOM standard.

14. The video analysis device operates as follows: analyzing the target image of the patient using the artificial intelligence model and obtaining an analysis result including lesion information for a plurality of types of lesions; determining a previous image captured before the target image as a reference image; obtaining an analysis result of analyzing the reference video using the artificial intelligence model; comparing and analyzing the analysis result of the reference image with the analysis result of the target image to obtain a comparative analysis result including lesion change degrees for the plurality of types of lesions; and displaying the comparison and analysis results in a viewer executed on a user terminal; The step of obtaining the comparative analysis result includes: The method includes determining the degree of change of the lesion by matching the lesions detected at corresponding positions in the reference image and the target image.

15. The screen displayed by the viewer is It consists of a video area and an analytical information area. an auxiliary image including an analysis result of the target image is displayed in the image area; The operating method according to claim 14 , wherein the analysis information area displays lesion change levels for the plurality of types of lesions together with identifiers of the corresponding lesions.

16. A graphical indicator is assigned for each lesion change degree; 16. The method of claim 15, wherein the lesion change rate is displayed along with an identifier of the lesion in a designated graphical indicator.

17. The method of claim 14, wherein the degree of change in the lesion is determined as any one of no change, disappearance of the lesion, appearance of the lesion, decrease of the lesion, increase of the lesion, or absence of the lesion.

18. A computer program stored on a computer-readable recording medium, The method further comprises: a command for causing a processor to execute the command to display on a screen an image analysis result including a comparative analysis result of the target image and a past image that was taken before the target image and determined as a reference image; The comparative analysis results are as follows: The analysis result of the reference image and the analysis result of the target image are compared to obtain lesion change degrees for a plurality of types of lesions, A graphical indicator is assigned for each lesion change degree; The screen is It consists of a video area and an analytical information area. an auxiliary image including an analysis result of the target image is displayed in the image area; A computer program, wherein the analysis information area displays the degree of lesion change for the plurality of types of lesions using designated graphical indicators together with identifiers of the corresponding lesions.

19. 19. The computer program according to claim 18, wherein the degree of change in the lesion is determined as any one of no change, disappearance of the lesion, appearance of the lesion, decrease in the lesion, increase in the lesion, or absence of the lesion.

Images