Method and system for comparing past video and current video

Abstract

To provide a method and a system for comparing a previous image and a current image.SOLUTION: Disclosed is a device for analyzing an image, the device including: a memory; and a processor for executing instructions stored in the memory. The processor is configured to analyze a target image of a patient by using an artificial intelligence model to obtain an analysis result including lesion information, and determine a previous image taken prior to the target image as a reference image, among images of the patient, and perform a comparative analysis on the previous image and the target image to obtain a comparative analysis result including a degree of lesion change.SELECTED DRAWING: Figure 1

Description

Technical Field

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

Background Art

[0002] In the past, CAD (Computer Aided Detection) devices detected lesions from medical images as a rule based or detected lesions from candidate regions set from medical images. In recent years, as artificial intelligence (AI) technology has been actively introduced into the medical field, AI-based medical image analysis technologies, such as the Lunit INSIGHT solution, in which AI analyzes medical images and visually provides analysis results, have been studied.

[0003] Users can perform operations such as reading and diagnosis by confirming abnormal lesions detected by image analysis. However, in the case of patients who require follow-up observation, there is an inconvenience that the user has to manually search for the patient's past images, open the past images, and directly compare the current images with the past images to confirm changes in the lesions.

Summary of the Invention

Problems to be Solved by the Invention

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

[0005] The present disclosure provides a method and system for providing a comparative analysis result with a past image as an analysis result of a target image.

Means for Solving the Problems

[0006] A video analysis device according to an embodiment includes a memory and a processor that executes instructions stored in the memory. The processor analyzes a target video of a patient using an artificial intelligence model, obtains an analysis result including lesion information, determines a past video taken before the target video among the patient's videos as a reference video, and performs a comparative analysis of the reference video and the target video to obtain a comparative analysis result including the degree of lesion change.

[0007] The processor can determine a video that meets the conditions among the patient's past videos as the reference video.

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

[0009] The processor can determine the degree of change of each comparison target lesion as any one of no change, lesion disappearance, lesion appearance, lesion decrease, lesion increase, or no lesion existence.

[0010] For each comparison target lesion, if there is a change above the threshold value, the processor can determine that there is a lesion change.

[0011] The processor can determine the lesion change using the threshold value set for each comparison target lesion.

[0012] The processor selects a plurality of past videos taken before the target video among the patient's videos as a plurality of reference videos, and by performing a comparative analysis of videos that are temporally adjacent between the plurality of reference videos and the target video, it is a video analysis device that obtains a plurality of comparative analysis results including the degree of lesion change between the videos.

[0013] The processor can generate the analysis results for the target video in a specified data format and save them in the video storage device.

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

[0015] The processor can generate an enhanced secondary capture with the analysis results of the target video and the comparative analysis results added.

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

[0017] A method for operating a video analysis device according to an embodiment includes analyzing a target video of a patient using an artificial intelligence model to obtain an analysis result including lesion information, determining a past video taken before the target video among the patient's videos as a reference video, and performing a comparative analysis of the reference video and the target video to obtain a comparative analysis result including the degree of lesion change.

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

[0019] Determining the degree of change can be performed by determining the degree of change of each comparative target lesion as any one of No change, Disappeared, Appeared, Decreased, Increased, or No existence.

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

[0021] The operation method can further include generating the analysis result performed for the target video in a specified data format.

[0022] The data format can include secondary capture of the DICOM standard. Generating in the specified data format can generate an enhanced secondary capture with the comparison analysis result added to the analysis result of the target video, and / or generate an additional secondary capture that compares and shows the analysis result of the reference video and the analysis result of the target video.

[0023] A computer program stored in a computer-readable recording medium according to an embodiment causes a processor to be executed to display a worklist including a video directory for video reading work in conjunction with a video storage device, and when a target video of a patient is selected from the worklist, to display an analysis result including a comparison analysis result between a past video taken before the target video and the target video among the videos of the patient.

[0024] The computer program includes an instruction to display a comparison analysis result with a past video in the worklist, and the comparison analysis result can include the degree of lesion change obtained by comparing and analyzing a past video taken before the current video among the current video to be read and the videos of the target patient of the current video.

[0025] The computer program can include an instruction to display an enhanced secondary capture with the comparison analysis result added to the analysis result of the target video, and / or an additional secondary capture that compares and shows the analysis result of the past video and the analysis result of the target video.

Advantages of the Invention

[0026] According to one embodiment, as an analysis result for the target video, in order to provide a comparative analysis result with the past video, without the user separately checking the past video, the temporal change of the lesion detected from the target video can be quickly known.

[0027] According to the embodiment, by providing the comparative analysis result with the past video in a viewer, a work list, an analysis report, or the like, the accuracy of video reading can be improved and the efficiency of the video reading work can be increased.

[0028] According to one embodiment, by visually distinguishing and highlighting the lesions that require attention and the degree of lesion change with an enhanced auxiliary video or an additional auxiliary video, the accuracy of video reading can be improved and the efficiency of the video reading work can be increased.

[0029] According to one embodiment, based on the comparative analysis result with the past video, the work priority of the work list can be determined, and the efficiency of the video reading work can be increased.

Brief Description of Drawings

[0030]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Figure 13

Figure 14

Figure 15

Figure 16

Best Mode for Carrying Out 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 to which the present disclosure pertains can easily implement them. However, the present disclosure can be implemented in various different forms and is not limited to the embodiments described herein. And, in order to clearly explain the present disclosure in the drawings, parts not related to the explanation are omitted, and similar parts are denoted by similar reference numerals throughout the specification.

[0032] In the description, that a certain part "includes" a certain component means that, unless otherwise stated to the contrary, it does not exclude other components, but can further include other components. Also, terms such as "... section", "... machine", "module", etc. described in the specification mean units that process at least one function or operation, and these can be realized by hardware, software, or a combination of hardware and software.

[0033] The device or terminal of the present disclosure is a computing device configured and connected such that at least one processor can perform the operations of the present disclosure by executing instructions. A computer program includes instructions described such that the processor performs the operations of the present disclosure and can be stored in a non-transitory computer readable storage medium. The computer program can also be downloaded through a network and / or sold as a product.

[0034] The medical images of the present disclosure may be images of various parts taken in various modalities. For example, the modalities may be X-ray, MRI (magnetic resonance imaging), ultrasound, CT (computed tomography), Digital MMG (Mammography), DBT (Digital breast tomosynthesis), etc.

[0035] The users of the present disclosure include, but are not limited to, medical professionals such as doctors, nurses, clinical pathologists, sonographers, or medical image experts.

[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 realized as a computer program executed by a processor. The task that the artificial intelligence model learns can refer to the problem to be solved through machine learning or the operation to be executed through machine learning. The artificial intelligence model can be realized as a computer program executed on a computing device, downloaded through a network, and / or sold as a product. Also, the artificial intelligence model can interact with various devices through a network.

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

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

[0039] The user terminal 100 is composed of 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 realized in various types, such as, for example, an in-workstation computing device, a mobile device, etc. The user terminal 100 can include a viewer (simply referred to as the "viewer") 110 that, in conjunction with the video storage device 200, displays medical video-related data stored in the video storage device 200. The viewer 110 can be installed and executed, for example, on an in-workstation computing device, and is realized to be connected to the video storage device 200 and can display medical video-related data stored in the video storage device 200. The viewer 110 is a computer program stored in a computer-readable medium and includes instructions executed by a processor. By the processor of the user terminal 100 executing the instructions, the operations described in the present disclosure can be performed.

[0040] The viewer 110 can display the video analysis results stored in the video storage device 200. The viewer 110 is configured in a table format and can provide a worklist that lists and displays a video catalog to be read by the user together with the main information. The viewer 110 can include a PACS (Picture archiving and communication system) viewer. Here, the viewer 110 is a program made to be able to display the video analysis results stored in the video storage device 200 and can assist in the video reading operation related to the worklist, but does not necessarily have to be limited to a viewer for reading operations.

[0041] The image storage device 200 can store and manage the captured medical images. And the image storage device 200 can store and manage the analysis results for the medical images. The image storage device 200 can include a PACS database. The image storage device 200 can store data in a specified data format. For example, the image storage device 200 can store the medical images captured by medical imaging devices and the analysis results of the medical images according to the DICOM (Digital Imaging and Communications in Medicine) standard, and can communicate with the user terminal 100 to provide data for image reading. The image storage device 200 and the viewer 110 can be configured in a PACS system. The image storage 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 is taken as an example for description, but the medical image standard does not necessarily have to be limited to DICOM.

[0043] The image storage device 200 can obtain the analysis results of the medical images from the image analysis device 300. The analysis results of the medical images can include various medical predictions including lesion information. Such analysis results of the medical images can be provided for assisting the user in image reading, or can also be provided as an auxiliary image with lesion information displayed on the image. For example, the auxiliary image can be a DICOM SC (Secondary Capture) image (which can be simply called 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 on a PACS viewer. Also, the analysis results of the medical images can be provided as a report in a text-based reading form. For example, the report can be a DICOM Basic Text SR (Structured Report). However, the form of providing the analysis results of the medical images is not limited to this, and can include results in various forms of DICOM formats.

[0044] The video storage device 200 can obtain the comparison analysis result of the target video and the past video (the comparison analysis result with the past video) from the video analysis device 300. The comparison analysis result with the past video can include the degree of lesion change obtained by comparing the analysis result of the target video with the analysis result of the past video. The comparison analysis result can also be provided for assisting the user in reading the video, and there are various providing methods. For example, the comparison analysis result can be provided together with the auxiliary video (SC) of the target video, and the auxiliary video including the comparison analysis result in this way can be called an enhanced auxiliary video (Augmented SC). Alternatively, the comparison analysis result can be provided as a separate auxiliary video from the auxiliary video (SC) of the target video, and the auxiliary video provided separately in this way can be called an additional auxiliary video (Additional SC). The enhanced auxiliary video and the additional auxiliary video will be described in detail below.

[0045] The medical videos stored in the video storage device 200 can include videos acquired by medical video devices of various modalities. The medical videos can be X-ray videos, MRI (magnetic resonance imaging) videos, ultrasound videos, CT (computed tomography) videos, Digital MMG (Mammography) videos, DBT (Digital breast tomosynthesis) videos, etc. In the description, a chest X-ray video will be described as an example of the medical video, but the medical video does not have to be limited to this, and the present disclosure can be applied according to the type of the medical video.

[0046] The video analysis device 300 can use an artificial intelligence (AI) model to analyze the medically requested medical video (target video) and store the analysis result in the video storage device 200. The video analysis device 300 can be equipped with an AI model specialized for each type of medical video, select an AI model according to the type of the input video, and perform analysis such as lesion detection suitable for the input video. The AI model is generated to make medical inferences from the input medical video, and the model structure, training data configuration, training method, and medical inference target can be designed in various ways.

[0047] In addition, the video analysis device 300 can compare and analyze the analyzed video (target video) with past videos and store the comparison and analysis result with the past videos in the video storage device 200. For the comparison and analysis, the video analysis device 300 can extract at least one past video related to the target video and compare and analyze the target video with the past video. The comparison and analysis target can be a video taken by the patient with a time difference and can be at least one past video compared with the current video. Here, the analyzed video can be referred to as the target video or the current video, and the past video of the patient taken before this can be referred to as the reference video. In the description, mainly one past video is described as the reference video, but the reference video may be a plurality of past videos.

[0048] When receiving an analysis request for a patient's target video, the video analysis device 300 can analyze the target video and obtain an analysis result including lesion information. Also, when receiving an analysis request or a comparative analysis request for the target video, the video analysis device 300 can identify a past video of the patient taken before the target video by the video analysis device 300, perform a comparative analysis of the past video and the target video, and obtain a comparative analysis result such as the degree of lesion change. For example, the video analysis device 300 can search for a video taken previously based on the patient identifier (Patient ID) of the target video in the video storage device 200 and perform a comparative analysis with the past video. Also, information on the past video used for the comparative analysis can be included in the analysis request so that the video analysis device 300 does not need to search for the past video. In the description, it can be described that the video analysis device 300 determines the past video, but the past video serving as the comparison criterion can be specified by user input and / or the video storage device 200 can notify the video analysis device 300 of the past video selected based on a criterion from among videos of the same type of the same patient.

[0049] The past images used as comparison criteria can be determined in various ways. For example, the video analysis device 300 can determine the latest image among the past images of the patient stored in the video storage device 200 as the reference image. The video analysis device 300 can search for the past images of the patient taken within a certain period (e.g., the most recent n, the most recent n months, the most recent n years, etc.) based on the shooting date of the target image, and determine the latest image or the image that meets the conditions among the past images as the past image for comparison. Here, the conditions can be set, for example, to select the image taken a certain period (e.g., 3 months) before the shooting date of the target image in order to detect significant changes, or to select the image for which AI analysis or reading has been performed, or to determine the past images used for comparative analysis through various other conditions. On the other hand, the images taken by the imaging device are automatically stored in the video storage device 200. However, if the image (e.g., X-ray image) is not taken accurately and needs to be retaken immediately after shooting, duplicate or inaccurate images may be accumulated in the video storage device 200. Therefore, in order to prevent the image with a shooting time point that has no difference from the target image from being determined as the past image, the video analysis device 300 can exclude the images continuously taken before the target image from the reference image. The continuously taken images are, for example, the images taken with a time difference in minutes from the target image, and the exclusion criteria can be set in various ways.

[0050] The methods by which the video analysis device 300 performs comparative analysis are diverse. For example, the video analysis device 300 can analyze all the past images and current images of the patient to detect lesions in each of the two images and detect the degree of change of the lesions. Or, when the video analysis device 300 has already analyzed the past images, lesion information can be extracted from the analysis results of the past images and compared with the lesion information detected from the current image to detect the degree of lesion change. For the sake of convenience of explanation, during the comparative analysis with the past image, it can be explained that the past image and the current image are compared and analyzed, which can include making use of the analysis results of the past images that have already been performed.

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

[0052] Hereinafter, a chest X-ray image will be taken as an example for explanation.

[0053] The video analysis device 300 can analyze a chest X-ray image and detect lesions from the chest X-ray image. Lesions detectable in a chest X-ray image can include, as shown in Table 1, nodules, pneumothorax, pleural effusion, sclerosis, cardiomegaly, atelectasis, undulation, calcification, pulmonary fibrosis, mediastinal widening, pulmonary tuberculosis, fractures, etc. In addition, the video analysis device 300 can analyze a chest X-ray image and obtain main medical indicators such as an Abnormality Score. For example, the video analysis device 300 can infer an Abnormality Score, a Tuberculosis (TB) analysis score, a probability of cardiomegaly, etc. from the input video. Naturally, the detectable lesions and medical indicators may change depending on the video analyzed by the video analysis device 300.

[0054]

Table 1

[0055]

Table 2

[0056]

Table 3

[0057] As another example, the image analysis device 300 can perform comparative analysis on a plurality of past images and the current image. The number (N) of medical images used for comparative analysis and the image selection method can be determined in advance, such as by user settings, and / or can be adaptively determined during the process of comparative analysis.

[0058] When N images of a patient are selected, the image analysis device 300 can generate a comparative analysis result by comparatively analyzing two images to determine the degree of lesion change. 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 an auxiliary image (SC) including the degree of lesion change. Then, the image analysis device 300 can synthesize the N - 1 comparative analysis results to generate an overall comparative analysis result. The overall comparative analysis result can be expressed, for example, as information indicating the change trend of the lesion, such as a change speed, a change graph according to time (date of shooting), a table, etc. The overall comparative analysis result can be provided to a separate report or interface.

[0059] The image analysis device 300 can adaptively select past images. According to one embodiment, if, as a result of comparing the current image with the immediately previous past image (past image 1), the lesion disappears, appears, or there is no region change, the image analysis device 300 can determine that it is not necessary to check the image before the immediately previous past image. When the lesion increases and / or decreases, the image analysis device 300 refers to the analysis result and reading report of the past images, searches for the first past image (past image n) in which the lesion first appeared, comparatively analyzes the images from the first past image to the current image, analyzes the lesion change between adjacent images, and can also analyze the change trend (change speed, change graph over time, table, etc.) of the lesion. The image analysis device 300 can select and comparatively analyze at least a part of the images from the first past image to the current image according to user selection or selection criteria (for example, the shooting interval is 3 months or more).

[0060] According to another embodiment, when the comparison result with the immediately previous past video (past video 1) shows that the lesion has increased and / or decreased, the video analysis device 300 can sequentially analyze a certain number of past videos. For example, when it is set to analyze up to three past videos, the video analysis device 300 searches for the video before past video 1 (past video 2). If the analysis results of past video 2 and past video 1 also show an increase / decrease in the lesion, it searches for the video before past video 2 (past video 3) and can perform a comparative analysis of past video 3 and past video 2. As a result, the video analysis device 300 can perform a comparative analysis of the videos from past video 3 to the current video, analyze the lesion changes between adjacent videos, and also analyze the change trend of the lesion (change speed, change graph over time, table, etc.). If the analysis results of past video 2 and past video 1 show the appearance of a lesion and / or no lesion change, the video analysis device 300 does not search further for the video before past video 2 (past video 3) and can use past video 2 and past video 1 as reference videos.

[0061] The analysis result for the target video analyzed by the video analysis device 300 can be stored in the video storage device 200 and displayed on the user terminal 100. The analysis result can include the AI analysis result for the target video and the comparative analysis result between the target video and the past video. When the video is a DICOM video, the metadata of the video can be stored in the Public tag and the Private tag. Information about the medical video is recorded in the Public tag according to the file structure defined by the DICOM standard. Since the Private tag can be freely used when a medical device company wants to add information not included in the Public tag to the DICOM video, the analysis result can be recorded in the Private tag. The Private tag can record the AI analysis result including the lesion information and the comparative analysis result including the degree of lesion change, and can further include the operation status of the current-past video comparison function.

[0062] The viewer 110 executed on the user terminal 100 can display the analysis result of the target video and the comparative analysis result between the target video and past videos. The analysis result of the target video can be provided as a basic auxiliary video (SC). The comparative analysis result with past videos can be provided together with the basic auxiliary video (SC), and the basic auxiliary video (SC) further including the comparative analysis result can be called an enhanced auxiliary video (Augmented SC). The comparative analysis result with past videos can be provided as a separate auxiliary video from the basic auxiliary video (SC), and the auxiliary video additionally provided to the basic auxiliary video (SC) can be called an additional auxiliary video (Additional SC).

[0063] The viewer 110 can display various information included in the comparative analysis result. For this purpose, the comparative analysis result can be saved in the DICOM format, which is a data format displayable on the viewer 110.

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

[0065] Based on the comparative analysis result, the viewer 110 can display the degree of change for each lesion to be compared. The viewer 110 can display the lesion positions with changes among the lesions to be compared. The viewer 110 can display the lesions where changes that require attention in reading (such as Appeared, Increased, etc.) have occurred so as to be distinguishable from other lesions. For example, the viewer 110 can visually display the lesion or the degree of lesion change differently and / or add highlighting marks. When the medical video is a chest X-ray video, the viewer 110 can display the degree of lesion change by distinguishing each of the left lung and the right lung. The viewer 110 can provide the threshold value used for determining the degree of lesion change.

[0066] Referring to FIG. 2, the viewer 110 can display the degree of lesion change included in the comparative analysis result on a graphical indicator such as an icon. Through the graphical indicator specified for each degree of change, the user can intuitively and quickly recognize the degree of lesion change.

[0067] Such a comparative analysis function can be utilized as follows.

[0068] For example, assume that in the analysis result of a patient's chest X-ray image, a lesion with abnormal findings is detected and the patient undergoes lung surgery. Subsequently, the doctor can instruct the patient to take a chest X-ray image through the hospital system for follow-up confirmation. When the radiographer takes the patient's chest X-ray image, the image is transmitted from the X-ray imaging device to the image storage device 200. After the surgery, the image analysis device 300 compares and analyzes the taken chest X-ray image with the chest X-ray image taken before the surgery to obtain a comparative analysis result including the degree of lesion change, and saves the comparative analysis result in the image storage device 200. The doctor can confirm the lesion change before and after the surgery through the current-past image comparison function of the image analysis device 300.

[0069] For example, assume that in the analysis result of a patient's chest X-ray image, a lesion with abnormal findings is detected and the doctor diagnoses that follow-up observation is necessary. After a certain period, when the patient takes an X-ray, 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 to obtain a comparative analysis result including the degree of lesion change, and saves the comparative analysis result in the image storage device 200. The doctor can confirm the lesion change over a certain period through the current-past image comparison function of the image analysis device 300 linked to the image storage device 200.

[0070] Each of FIGS. 3 and 4 is an illustration of a screen providing a comparative analysis result with a past image according to an embodiment.

[0071] Referring to FIG. 3, the viewer 110 executed on the user terminal 100 can provide a screen related to the operation of reading a target video in conjunction with the video storage device 200, and provide the result of the Current-Prior comparison function on the screen. The comparison function between the current video and the past video may be selected by the user, or may be provided as a basic function. When the comparison function between the current video and the past video is activated in the video analysis device 300, the viewer 110 can display the comparison analysis result with the past video on the screen, but can provide an Augmented SC including the comparison analysis result in the analysis result of the target video.

[0072] The Augmented SC screen 400 displayed on the viewer 110 can be composed of a video area 410 and an analysis information area 420. In the video area 410, a basic SC including the analysis result of the target video can be displayed. The basic SC may be a video including the analysis result of the target video (for example, lesion scores such as Ptx88%, Csn94%, the contour of the lesion area, a heat map, etc.). Lesion change information can be additionally displayed in the basic SC. The lesion score may indicate the confidence level where the lesion exists as a score / probability.

[0073] The analysis information area 420 can be composed of an area 421 where the analysis result of the target video is displayed and an area 422 where the comparison analysis result (e.g., lesion change degree) with the past video is displayed. In the area 421, medical indicators obtained by analyzing the target video with an artificial intelligence model, such as an abnormality score, a tuberculosis analysis score, a cardiomegaly probability, etc., can be displayed. In the area 422, the change degree of the comparison target lesion (e.g., Ptx, PEf, Csn) can be displayed. When the left and right of the object are distinguished like in a chest X-ray image, the lesion change degree of the right lung (422-R) and the lesion change degree of the left lung (422-L) can be separately displayed. At this time, the change degree of the comparison target lesion (e.g., Ptx, PEf, Csn) can be displayed by a graphical indicator 423 such as an icon. The text explaining the change degree (No change, Disappeared, etc.) can be displayed according to the size of the analysis information area 420 and / or can be omitted. Even without a text explanation such as No change, the user can intuitively and quickly recognize the lesion change degree through a graphical indicator such as an icon.

[0074] The augmented supplementary video (Augmented SC) provides the comparison analysis result in the form of the analysis result of the target video. However, in order for the user to judge the change speed, etc., it is necessary to confirm the shooting time of the past video used for the comparison analysis. For this purpose, the augmented supplementary video screen 400 can provide the shooting time of the past video used for the comparison analysis. The augmented supplementary video screen 400 can provide information explaining the time difference between the target video and the past video (e.g., comparison with the video of the patient 8 weeks ago).

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

[0076] The additional type auxiliary video screen 500 displayed on the viewer 110 can be composed of a video area 510 and an analysis information area 520. So that the user can view the past video and the current target video simultaneously, an auxiliary video (SC) 511 including the analysis result of the past video and an auxiliary video (SC) 512 including the analysis result of the target video can be displayed together in the video area 510. The arrangements of the past video and the target video can be diverse. The auxiliary videos 511 and 512 of the past video and the target video can be videos including the analysis results (lesion information) of the corresponding videos. The lesion change information can be additionally displayed in the auxiliary video (SC) of the target video.

[0077] The viewer 110 can provide information (such as shooting date and time) of the past video and the target video. The viewer 110 can provide information (for example, comparison with a video eight weeks ago) so that the time difference between the target video and the past video can be known.

[0078] The comparison analysis result (lesion change degree) with the past video is displayed in the analysis information area 520. The UI for displaying the change degree of the comparison target lesion (for example, Ptx, PEf, Csn) in the analysis information area 520 can be designed in various ways. For example, the lesion name 521 and its change degree can be displayed in a table form. When the left and right of an object (such as a chest X-ray video) are distinguished, the lesion change degree of the right lung (522-R) and the lesion change degree of the left lung (522-L) can be separated. At this time, the change degree of the comparison target lesion (for example, Ptx, PEf, Csn) can be displayed by a graphical indicator such as an icon. The user can intuitively and quickly recognize the lesion change degree through a graphical indicator such as an icon. On the other hand, when there is a space for describing the text (No change, Disappeared, etc.) of the change degree, the text description can be displayed together with the graphical indicator.

[0079] Such an additional supplementary video (Additional SC) provides the analysis results of the current video of the person to be analyzed and the past video of the person to be compared on one screen, so that the user does not need to separately check the past video of the patient on another screen, and the lesions detected in the two videos of the additional supplementary video screen 500 can be easily compared.

[0080] FIG. 5 is a drawing for explaining the order in which the comparison analysis results are output by the viewer according to one embodiment.

[0081] Referring to FIG. 5, the viewer 110 can sequentially provide videos for the reading operation of the target video in conjunction with the video storage device 200. The conventional viewer provides the captured video 10 and the supplementary video (SC) 20 including the analysis result of the video, but the viewer 110 of the present disclosure can further provide the comparison analysis result with the past video.

[0082] When set to provide the comparison analysis result through the augmented supplementary video (Augmented SC), the viewer 110 can sequentially display the captured video 10 of the target video and the augmented supplementary video (Augmented SC) 400. The augmented supplementary video (Augmented SC) 400 can include the analysis result of the target video and the comparison analysis result.

[0083] When set to provide the comparison analysis result through the additional supplementary video (Augmented SC), the viewer 110 can sequentially display the captured video 10 of the target video, the basic supplementary video (SC) 20 including the analysis result of the target video, and the additional supplementary video (Additional SC) 500.

[0084] The output options for the viewer 110 to provide the comparison analysis result are fixed and / or can be selected by the user.

[0085] Each of FIGS. 6 to 8 is an illustration of a screen for providing an augmented supplementary video according to one embodiment.

[0086] Referring to FIG. 6, the enhanced auxiliary video screen 400A displayed on the viewer 110 can be composed of a video area 410A and an analysis information area 420A, and can further include an area 430A for displaying past video information used in the comparative analysis. The arrangement and area size of the enhanced auxiliary video screen 400A can be designed in various ways.

[0087] In the video area 410A, an auxiliary video (SC) including the analysis result of the target video can be displayed. The auxiliary video (SC) displays the analysis result of the target video (for example, lesion scores such as Ptx88%, Csn94%, the contour of the lesion area, heat map, etc.), and can additionally display the lesion change information 411, 412, 413, 414 of the comparison target lesions (for example, Csn and PEf in the left lung, Ptx and Csn in the right lung) among the lesions detected in the target video. The lesion change information 411, 412, 413, 414 indicates the degree of lesion change (Increased, Appeared, No change, Decreased) based on the comparative analysis result with the past video, and can be displayed in text and / or with a change degree icon.

[0088] In the analysis information area 420A, the analysis result of the target video (Abnormality Score, TB analysis score, etc.) and the comparative analysis result with the past video (degree of lesion change) can be displayed. At this time, the degree of change of the comparison target lesions (for example, Ptx, PEf, Csn) can be displayed with a graphical indicator such as an icon, and the text explaining the degree of change can be omitted or displayed.

[0089] In the area 430A, the past video information used in the comparative analysis can be displayed. The past video information can include the shooting time point of the past video used in the comparative analysis or the time difference between the target video and the past video.

[0090] The enhanced auxiliary video screen 400A can confirm lesions where changes that require further user attention (such as Appeared, Increased, etc.) have occurred and display them in a visually distinguishable and emphasized manner. For example, since a lesion PEf has appeared in the left lung, to emphasize the newly appeared lesion PEf, its lesion change information 412, or its change degree icon, different displays can be made in terms of color, size, pattern, etc., and / or an emphasis mark can be added.

[0091] Referring to FIG. 7, the enhanced auxiliary video screen 400B displayed on the viewer 110 can be composed of a video area 410B and an analysis information area 420B, and can further include an area 430B for displaying past video information used for comparative analysis. The layout and area size of the enhanced auxiliary video screen 400B can be designed in various ways.

[0092] An auxiliary video (SC) including the analysis result of the target video can be displayed in the video area 410B. The auxiliary video (SC) displays the analysis result of the target video and, as shown in FIG. 6, can additionally display the lesion change information of the comparison target lesion among the lesions detected in the target video.

[0093] In the analysis information area 420B, the analysis result of the target video (such as Abnormality Score, TB analysis score, etc.) and the comparative analysis result with the past video (lesion change degree) can be displayed. At this time, the change degree of the comparison target lesion (such as Ptx, PEf, Csn) can be displayed by a graphical indicator such as an icon, and the text explaining the change degree can be omitted or displayed.

[0094] On the one hand, depending on user settings, the comparison target lesions displayed on the enhanced auxiliary video screen 400B may be different. For example, when the user sets to display Ptx and Csn, and sets not to display Ndl and PEf, only the degrees of change of Ptx and Csn of the lesions set to be displayed may be displayed in the analysis information area 420B. Also, the lesion change information displayed on the auxiliary video (SC) can only be provided for the comparison target lesions set for display.

[0095] Referring to FIG. 8, the enhanced auxiliary video screen 400C displayed on the viewer 110 can be composed of a video area 410C and an analysis information area 420C, and can further include a detailed analysis table 440C. The layout and area size of the enhanced auxiliary video screen 400C can be designed in various ways.

[0096] An auxiliary video (SC) including the analysis result of the target video (current video) can be displayed in the video area 410C. The auxiliary video (SC) displays the analysis result of the target video and can additionally display the lesion change information of the comparison target lesions among the lesions detected in the target video as shown in FIG. 6.

[0097] In the analysis information area 420C, the analysis results of the target video (Abnormality Score, TB analysis score, etc.) and the comparative analysis results with past videos (lesion change degrees) can be displayed. At this time, the change degrees of the comparison target lesions (for example, Ptx, PEf, Csn) can be displayed by graphical indicators such as icons, and the text explaining the change degrees can be omitted or displayed.

[0098] The detailed analysis table 440C can include a lesion name 441C, a lesion-specific threshold 442C, a lesion score 443C, and a lesion position 444C, but this can be changed in various ways.

[0099] Each of FIGS. 9 and 10 is an illustration of a screen providing an additional type of auxiliary video according to an embodiment.

[0100] Referring to FIG. 9, the additional type auxiliary video screen 500A displayed on the viewer 110 can be composed of a video area 510A and an analysis information area 520A, and can display the shooting times of the past video and the target video. The arrangement and area size of the additional type auxiliary video screen 500A can be designed in various ways.

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

[0102] The comparison analysis result (lesion change degree) with the past video is displayed in the analysis information area 520A. The UI for displaying the change degree of the comparison target lesion (for example, Ptx, PEf, Csn) in the analysis information area 520A can be designed in various ways. For example, the lesion name 521A and its change degree can be displayed in a table form. When the left and right of the object (such as in a chest X-ray video) are distinguished, it can be separated into the lesion change degree (522A-R) of the right lung and the lesion change degree (522A-L) of the left lung. At this time, the change degree of the comparison target lesion (for example, Ptx, PEf, Csn) can be displayed by a graphical indicator such as an icon, and the text explaining the change degree can be omitted or displayed.

[0103] The additional auxiliary video screen 500A can visually distinguish and highlight changes that require emphasis, such as the appearance of a lesion (Appeared) or an increase in the lesion area (Increased). For example, since a lesion PEf has appeared in the left lung, the change information (Appeared or the icon of Appeared) can be displayed for the lesion PEf in the auxiliary video 512A of the target video. At this time, since the newly appeared lesion PEf is a lesion that requires emphasis, it can be emphasized by giving visual changes (such as changes in color, size, pattern, etc.) to the text (PEf and Appeared) or the change degree icon displayed in the video, and / or an emphasis mark 513A can be added.

[0104] Also, if there are changes that require emphasis (such as Appeared, Increased, etc.) in the additional auxiliary video screen 500A, it can be emphasized and displayed in the analysis information area 520A so as to be visually distinguished from other change degrees. For example, in the lesion change degree of the left lung (522A-L), the color of the change information (Appeared or the icon of Appeared) for the lesion PEf can be made prominent.

[0105] Referring to FIG. 10, the additional auxiliary video screen 500B displayed on the viewer 110 can be composed of a video area 510B and an analysis information area 520B, and the shooting times of the past video and the target video can be displayed. The arrangement and the size of the area of the additional auxiliary video screen 500B can be designed in various ways.

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

[0107] In the analysis information area 520B, the comparison analysis result (lesion change degree) with the past video is displayed. The additional type auxiliary video screen 500B can display the comparison target lesion selected according to the user setting in the analysis information area 520B. For example, when the user sets so that Ptx and Csn are displayed and Ndl and PEf are not displayed, only the change degrees of Ptx and Csn of the set lesions can be displayed in the analysis information area 520B. Also, the lesion change information displayed in the auxiliary video 512B of the target video can be provided only for the comparison target lesions set for display.

[0108] Each of FIGS. 11 and 12 is an illustration of an analysis report generated according to an embodiment.

[0109] Referring to FIGS. 11 and 12, the result of the analysis performed by the video analysis device 300 on the target video can be generated as an analysis report. The analysis report can further include the comparison analysis result with the past video together with the lesion information detected in the target video.

[0110] The analysis report can be, for example, a structured report created according to the DICOM standard. The analysis report can display the comparison analysis results of the comparison target lesions A, B, C, D in 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, the analysis report 600A describes the lesions detected in the target video. However, for the comparative analysis result with the past video, if the pneumothorax present in the right lung has not changed compared to the past video, it can include an explanation for this (Pneumothorax has not changed in the right lung.) 610. Also, if the pleural effusion present in the left lung of the target video has not changed compared to the past video, the analysis report 600A can include an explanation for this (Pleural effusion has not changed in the left lung.) 611.

[0112] For example, the analysis report 600B describes the lesions detected in the target video. However, for the comparative analysis result with the past video, if consolidation that was not detected in the past video appears in both the left and right lungs, it can include an explanation for this (Consolidation has appeared in both lungs.) 612. Also, if pneumothorax that was not detected in the past video is detected in the right lung of the target video, the analysis report 600B can include an explanation that pneumothorax has appeared in the right lung (Pneumothorax has appeared in the right lung.) 613. Also, if pleural effusion that was not detected in the past video is detected in both the left and right lungs of the target video, the analysis report 600B can include an explanation that pleural effusion has appeared in both lungs (Pleural effusion has appeared in both lungs.) 614.

[0113] Therefore, the analysis report can further provide the changes of the lesion over time together with the analysis result indicating the presence of the lesion. Therefore, without viewing the past videos and their analysis reports, the user can know, through the analysis report of the target video, whether the lesion is newly emerged, unchanged, reduced in size, or increased in size. In particular, since the analysis report provides lesion information that previously existed but disappeared and was not detected, the user can know, through the analysis report of the target video, the lesions that disappeared and were not detected.

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

[0115] Referring to FIG. 13, the viewer 110 executed on the user terminal 100 can provide a worklist 700 in conjunction with the video storage device 200. The worklist 700 lists and displays, in a table format, a video catalog that the user should read together with the main 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 video storage device 200, but for the sake of convenience of explanation, it can be described that the viewer 110 provides it.

[0116] The viewer 110 can display, in a specified column of the worklist 700, the analysis results analyzed by the video analysis device 300 for the target video in conjunction with the video storage device 200. The analysis results can include the AI analysis results for the target video and the comparative analysis results between the target video and the past videos. At this time, the viewer 110 can display the comparative analysis results in the specified column 710 of the worklist 700. The viewer 110 can display the comparative analysis results included in the DICOM Private tag in the worklist 700. At this time, the viewer 110 can display, in the worklist 700, the presence or absence of the operation of the automatic comparative analysis function with the past videos based on the Private tag of the DICOM video.

[0117] The methods of displaying the comparative analysis results in the work list are diverse, such as color chips, text, icons, flagging, etc. For example, the viewer 110 can display the comparative analysis results included in the private tag in the designated column 710 by classifying them with color chips. The color chips for the comparative analysis results can be set by the user, or the viewer 110 can display the color chips set according to the priority or importance of the comparative analysis results.

[0118] The representative degree of change (e.g., Appeared or icon) can be displayed in the designated column 710 of the work list. Since the comparative analysis results include the degrees of change of multiple lesions, the lesion change with a higher importance (e.g., Appeared, Increased, etc.) is determined as the representative degree of change, and the representative degree of change can be displayed in the work list. Also, since the risks of lesions are different for each lesion, the degree of change representing the comparative analysis results of the video can be determined by considering the importance of the lesions and the importance of the degrees of change of the lesions.

[0119] The work priority of the work list can be determined based on the comparative analysis results generated by the video analysis device 300. For example, the user can check the comparative analysis results performed on the video read through the work list 700, and by arranging the work order according to the importance of the comparative analysis results, the efficiency of the reading task can be improved. Or, the viewer 110 can provide the work list by setting a high work priority for the video in which a change (e.g., Appeared, Increased, etc.) that requires attention in reading occurs. For example, if the lesion change included in the comparative analysis results is a change where there is no change, the lesion disappears, or the lesion decreases (positive change), the reading priority of the video can be set low. On the other hand, if the lesion change included in the comparative analysis results is a change where a new lesion appears and / or the lesion increases (negative change), the reading priority of the video can be set high.

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

[0121] Referring to FIG. 14, when a video of a patient (target video) is acquired, the video analysis apparatus 300 analyzes the target video using an AI model and obtains an analysis result including lesion information (S110). The analysis result can include lesion information such as a lesion score and a lesion position, and main medical indicators including an Abnormality Score.

[0122] The video analysis apparatus 300 determines a past video taken before the target video among the videos of the patient as a reference video for comparison (S120). The video analysis apparatus 300 can search for videos taken previously in the video storage apparatus 200 based on the patient identifier (Patient ID) of the target video and select a past video that meets the conditions. The past video serving as the comparison reference can be determined in various ways. For example, the video analysis apparatus 300 can determine the latest video among the past videos of the patient stored in the video storage apparatus 200 as the reference video, or determine a past video taken at a certain time interval from the target video as the reference video, or determine a video on which AI analysis or reading has been performed as the reference video. Here, the timing at which the video analysis apparatus 300 performs comparative analysis with the past video can be set in various ways. For example, when receiving an analysis request for the target video, the video analysis apparatus 300 can proceed with the comparative analysis, or can separately receive a comparative analysis request and proceed with the comparative analysis.

[0123] The image analysis device 300 compares and analyzes a past image and a target image to obtain a comparative analysis result including the degree of lesion change (S130). The image analysis device 300 can extract lesion information of at least one comparative target lesion from the analysis result of the past image and the analysis result of the target image. The image analysis device 300 can determine the degree of change of the comparative target lesion over time and generate a comparative analysis result including the degree of change of the comparative target lesion. The image analysis device 300 determines the degree of change by associating the lesions detected at the corresponding positions in the past image and the target image. For lesions that exist only in the past image or the target image, it can be determined that the lesion has disappeared and / or appeared. If there is a change in the comparative result with the past image and the change of the comparative target lesion is equal to or greater than a threshold value, the image analysis device 300 can determine that there is a lesion change. The threshold value can be set differently according to the type of lesion. The lesion change can be determined based on the change in the area occupied by the lesion or the change in the abnormality score for the lesion, but it is not necessarily limited to this. The degree of lesion change can be analyzed as no change, disappeared, appeared, decreased, or increased, as shown in Table 3. On the other hand, the image analysis device 300 can use an AI model to analyze the past image for the comparative analysis of the past image and the target image, obtain an analysis result including the lesion information of the past image, and then compare it with the analysis result of the target image. Alternatively, if there is an AI analysis result for the identified past image, that is, if the image analysis device 300 has already analyzed the past image, the image analysis device 300 can directly compare the analysis results of the past image and the target image without having to re-perform the past image analysis.

[0124] The image analysis device 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). As an example of storing in the image storage device 200, the analysis results including the lesion information of the target image can be stored by secondary capture of the DICOM standard, which can be called the basic SC. The comparison analysis results with past images can also be stored by secondary capture of the DICOM standard, and can be stored in an enhanced SC with the comparison analysis results added to the analysis results of the target image, and can be stored in an additional SC that compares and shows 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 grouped in the secondary capture of the target image in the viewer 110 and can be sequentially displayed. The analysis results for the target image, especially the comparison analysis results, can be displayed in the worklist. Also, the analysis results for the target image, especially the degree of lesion change, can be displayed in the analysis report in text form.

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

[0126] Referring to FIG. 15, the image analysis device 300 analyzes a patient's image (target image) using an AI model and obtains analysis results including lesion information. The analysis results can include lesion information such as a lesion score and a lesion location, and major medical indicators including an Abnormality Score. The image analysis device 300 automatically generates analysis results when a new image is acquired, and can provide the analysis results for the image of the patient when the patient ID is selected in the PACS worklist or viewer.

[0127] For comparative analysis, the video analysis device 300 selects a plurality of past videos that were taken before the target video from among the patient's videos (S220). The number (N) of medical videos to be used for comparative analysis and the video selection method can be determined in advance by user settings or the like, or can be adaptively determined during the progress of the comparative analysis.

[0128] The video analysis device 300 obtains a comparative analysis result including the degree of lesion change between videos by comparatively analyzing videos that are temporally adjacent to each other among the plurality of past videos and the target video (S230). As shown in Table 3, the degree of lesion change can be analyzed as no change, disappeared, appeared, decreased, or increased.

[0129] The video analysis device 300 extracts information indicating the change transition for each lesion from the comparative analysis result of the plurality of past videos and the target video (S240). The information indicating the change transition for each lesion can be expressed by a change rate, a change graph based on time (recording date), a table, or the like.

[0130] The image analysis device 300 generates the analysis results obtained 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, the analysis results including the lesion information of the target image can be stored in accordance with the DICOM standard's secondary capture, and multiple comparative analysis results can also be stored in accordance with the DICOM standard's secondary capture. Each comparative analysis result can be stored in an additive SC that shows both of the compared images, and the comparative analysis results of the past images compared with the target image can also be stored in an enhanced SC. The analysis results obtained for the target image can be included in the Private tag of the DICOM image. The analysis results obtained for the target image can be grouped in the secondary capture of the DICOM image in the viewer 110 and can be sequentially displayed. The analysis results obtained for the target image, particularly the comparative analysis results, can be displayed in the worklist. Also, the analysis results obtained for the target image, particularly the degree of lesion change, can be displayed in the analysis report in text form.

[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 work list including a video directory for video reading operations 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 the designated column of the work list, and the analysis results can include AI analysis results for the video and comparative analysis results. The viewer 110 can display the comparative analysis results in the work list in various ways (such as color chips, text, flagging, icons, etc.). For example, the viewer 110 can classify the comparative analysis results included in the private tag of the video by color chips and display them in the work list. The viewer 110 can display the degree of change (such as Appeared, Increased, etc.) representing the comparative analysis results of the video in the work list. The viewer 110 can sort and display the video directories in the work list according to the priority determined by the comparative analysis results.

[0133] When a target video is selected from the work list, the viewer 110 displays the analysis results including the comparative analysis results between the target video and the past video (S320). The viewer 110 can call and display the analysis results saved in the designated data format (such as DICOM format). When set to provide the comparative analysis results through the Augmented SC, the viewer 110 can sequentially display the captured video of the target video and the Augmented SC including the analysis results and comparative analysis results of the target video. When set to provide the comparative analysis results through the Augmented SC, the viewer 110 can sequentially display the captured video of the target video, the basic SC including the analysis results of the target video, and the Augmented SC including the comparison results between the past video and the target video.

[0134] The viewer 110 is implemented by a computer program stored in a computer-readable recording medium and includes instructions executed by a processor. The computer program causes the processor to display a work list including a video directory for video reading operations in conjunction with the video storage device 200, and when a target video is selected from the work list, to display an analysis result including a comparison analysis result between the target video and a past video. The computer program can include instructions to cause the work list to display a comparison analysis result with a past video. The computer program can include instructions to display an enhanced secondary capture in which a comparison analysis result is added to the analysis result of the target video, and / or to display an additional secondary capture that compares and shows the analysis result of the past video and the analysis result of the target video.

[0135] Here, in order for the user to view the analysis result including the comparison analysis result between the target video and the past video, it is not necessarily required to view it through the work list, which is just one example for explanation. For example, the user (doctor) can view the analysis result including the comparison analysis result between the target video and the past video through a viewer showing the patient's medical information.

[0136] The medical video system 1 of the present disclosure, the constituent terminals or devices 100, 200, 300 can include one or more processors, a memory for loading a computer program executed by the processors, a storage device for storing the computer program and various data, and a communication interface. In addition, the terminals or devices 100, 200, 300 can further include various components. The processor can be various forms of processors that process instructions included in the computer program. For example, it can be configured to include at least one of a CPU (Central Processing Unit), an MPU (Micro Processor Unit), an MCU (Micro Controller Unit), a GPU (Graphic Processing Unit), or any form of processor well-known in the technical field of the present disclosure. The memory stores various data, instructions, and / or information. The memory can be realized to store instructions such that the instructions described to execute the operation of the present disclosure are processed by the processor. The memory can be, for example, a ROM (read only memory), a RAM (random access memory), etc. The storage device can non-temporarily store the computer program and various data. The storage device can be configured to include non-volatile memories such as ROM (Read Only Memory), EPROM (Erasable Programmable ROM), EEPROM (Electrically Erasable Programmable ROM), flash memory, a hard disk, a removable disk, or any form of computer-readable recording medium well-known in the technical field to which the present disclosure belongs. The communication interface can be a wired / wireless communication module that supports wired / wireless communication. The computer program includes instructions executed by the processor and is stored in a non-transitory computer readable storage medium, and the instructions cause the processor to execute the operation of the present disclosure.

[0137] As described above, the embodiments of the present disclosure are not only realized through devices and methods, but can also be realized 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] As described above, the embodiments of the present disclosure have been described in detail. However, the scope of the rights 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 defined in the appended claims also belong to the scope of the rights of the present disclosure.

Claims

1. A memory and a processor for executing instructions stored in the memory, wherein the processor analyzes a target video of a patient using an artificial intelligence model, obtains an analysis result including lesion information for a plurality of types of target lesions to be compared, determines a past video taken before the target video among the videos of the patient as a reference video, and performs a comparative analysis of the reference video and the target video to obtain a comparative analysis result including the degree of lesion change of the plurality of types of target lesions to be compared, wherein the degree of lesion change is determined as any one of no change, lesion disappearance, lesion appearance, lesion decrease, lesion increase, or no lesion, wherein a graphical indicator is specified for each degree of lesion change, and the degree of lesion change is displayed by the graphical indicator specified for the degree of lesion change corresponding to the plurality of types of target lesions to be compared, together with the identifiers of the plurality of types of target lesions to be compared, A video analysis device, wherein the degree of lesion change for at least one type of target lesion in which the lesion appearance or the lesion increase has occurred is emphasized and displayed so as to be visually distinguishable from other degrees of lesion change.

2. The video analysis device according to claim 1, wherein the processor determines a video that meets the conditions among the past videos of the patient as the reference video.

3. The video analysis device according to claim 1, wherein the processor extracts lesion information of at least one target lesion to be compared from the analysis result of the reference video and the analysis result of the target video, determines the degree of change of each target lesion to be compared over time based on the extracted lesion information, and generates the comparative analysis result including the degree of change of each target lesion to be compared.

4. The video analysis device according to claim 3, wherein the processor determines the degree of change of each target lesion to be compared as any one of no change, lesion disappearance, lesion appearance, lesion decrease, lesion increase, or no lesion.

5. The video analysis device according to claim 3, wherein the processor determines that there is a lesion change if there is a change greater than or equal to a threshold value for each target lesion to be compared.

6. The video analysis device according to claim 5, wherein the processor determines the lesion change using a threshold value set for each target lesion to be compared.

7. The processor selects, as a plurality of reference images, a plurality of past images captured before the target image among the images of the patient, and obtains a plurality of comparative analysis results including the degree of lesion change between the images by comparing and analyzing the images that are temporally adjacent to each other between the plurality of reference images and the target image. The image analysis apparatus according to claim 1.

8. The processor generates the result of the analysis performed for the target image in a specified data format and stores it in an image storage device. The image analysis apparatus according to claim 1.

9. The processor generates the comparative analysis result in a secondary capture in DICOM standard. The image analysis apparatus according to claim 8.

10. The processor generates an enhanced secondary capture in which the comparative analysis result is added to the analysis result of the target image. The image analysis apparatus according to claim 9.

11. The processor generates an additional secondary capture that compares and shows the analysis result of the reference image and the analysis result of the target image. The image analysis apparatus according to claim 9.

12. A method of operating an image analysis apparatus, including: analyzing 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 comparative target lesions; determining, as a reference image, a past image captured before the target image among the images of the patient; and comparing and analyzing the reference image and the target image to obtain a comparative analysis result including the degree of lesion change of the plurality of types of comparative target lesions. The degree of lesion change is determined as any one of no change, lesion disappearance, lesion appearance, lesion decrease, lesion increase, or no lesion existence. A graphical indicator is specified for each degree of lesion change, and the degree of lesion change is displayed by the graphical indicator specified for the degree of lesion change corresponding to the plurality of types of comparative target lesions, together with the lesion names of the plurality of types of comparative target lesions. A method of operation in which the degree of lesion change for at least one comparison target lesion in which the occurrence of the lesion or the increase in the lesion has occurred is emphasized and displayed so as to be visually distinguishable from other degrees of lesion change.

13. The obtaining of the comparative analysis result includes extracting lesion information of at least one comparison target lesion from the analysis result of the reference video and the analysis result of the target video, determining the degree of change of each comparison target lesion over time based on the extracted lesion information, and generating the comparative analysis result including the degree of change of each comparison target lesion. The method of operation according to claim 12.

14. The determining of the degree of change is to determine the degree of change of each comparison target lesion as any one of no change, disappearance of the lesion, appearance of the lesion, decrease of the lesion, increase of the lesion, or no lesion. The method of operation according to claim 13.

15. The determining of the degree of change is to use a threshold value set for each comparison target lesion and determine that there is a lesion change if there is a change equal to or greater than the threshold value set for the comparison target lesion. The method of operation according to claim 13.

16. The method of operation according to claim 12, further including generating the result of the analysis performed for the target video in a specified data format.

17. The data format includes secondary capture of the DICOM standard. The generating in the specified data format is to generate an enhanced secondary capture in which the comparative analysis result is added to the analysis result of the target video, and / or generate an additional secondary capture that compares and shows the analysis results of the reference video and the target video. The method of operation according to claim 16.

18. A computer program stored in a computer-readable storage medium, which causes a processor to be executed to display a work list including a video directory for video reading work in conjunction with a video storage device, and when a target video of a patient is selected from the work list, display an analysis result including a comparative analysis result of a past video taken before the target video and the target video among the videos of the patient. The comparative analysis result includes the degree of lesion change obtained by comparing and analyzing the current video to be read and a past video taken before the current video of the target patient of the current video. The degree of lesion change is determined as any one of no change (No change), lesion disappearance (Disappeared), lesion appearance (Appeared), lesion decrease (Decreased), lesion increase (Increased), or no lesion (No existence). A graphical indicator is specified for each degree of lesion change, and the degree of lesion change is displayed by the graphical indicator specified for the degree of lesion change corresponding to the plurality of types of target lesions to be compared, together with the lesion names of the plurality of types of target lesions to be compared. A computer program in which the degree of lesion change for at least one type of target lesion in which the lesion appearance or the lesion increase has occurred is emphasized and displayed so as to be visually distinguished from other degrees of lesion change.

19. The computer program according to claim 18, comprising an instruction to display an enhanced secondary capture in which the comparative analysis result is added to the analysis result of the target video, and / or to display an additional secondary capture that compares and shows the analysis result of the past video and the analysis result of the target video.

Images