Assistant identification method and system for aortic dissection

Abstract

The invention provides an aortic dissection auxiliary identification method and system, and the method comprises the steps: obtaining the thoracic cavity plain-scan images of the aorta of a user through CT equipment, and recognizing the cross section contour image of the aorta in each thoracic cavity plain-scan image through an image edge recognition algorithm; identifying edge structure information of each cross section contour image, and extracting image features of each cross section contour image; and for each cross section contour image, identifying each abnormal image region and abnormal information thereof in the cross section contour image, and based on the abnormal information of each abnormal image region, identifying an abnormal type and an abnormal degree of the cross section contour image, so that the aortic dissection is analyzed through an aortic dissection analysis strategy. And predicting the aortic dissection probability and the prediction reason of the user to obtain aortic dissection auxiliary identification information of the user. By adopting the scheme, the auxiliary recognition efficiency of the aortic dissection during emergency treatment can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of image recognition and data analysis, and in particular to an auxiliary recognition method and system for aortic dissection. Background Art

[0002] Aortic dissection (AD) refers to a pathological change in which high-speed, high-pressure blood flow in the aorta enters the aortic media from the tear in the intima, causing the media to separate and expand along the long axis of the aorta, thereby causing the true and false lumens of the aorta. This disease has an acute onset, rapid progression, and a high mortality rate, so how to detect aortic dissection is the current research focus.

[0003] The traditional method of detecting aortic dissection is to obtain a scan of the user's torso through CT enhanced imaging scanning, thereby assisting doctors in identifying whether the user has aortic dissection. However, due to the rapid onset and rapid progression of aortic dissection, some patients have atypical symptoms and are difficult to distinguish from other diseases, resulting in clinical physicians failing to prescribe CT enhanced examinations in the first place. Some patients are not suitable for CT enhanced examinations due to various factors. In the emergency department, they often only have CT plain scan images with a contrast far lower than that of CT enhanced images, resulting in low efficiency in the auxiliary identification of aortic dissection in the emergency department. Summary of the invention

[0004] The main purpose of the present invention is to provide an auxiliary identification method for aortic dissection, aiming to solve the problem that the prior art cannot efficiently assist doctors in identifying the user's aortic dissection condition in emergency due to the shortage of equipment and personnel resources for CT enhanced imaging, resulting in low efficiency of auxiliary identification of aortic dissection in emergency.

[0005] To achieve the above object, the present invention provides an auxiliary identification method for aortic dissection, the method comprising:

[0006] Obtaining a chest plain scan image of the user's aorta, and identifying a cross-sectional contour image of the aorta in each of the chest plain scan images by using an image edge recognition algorithm;

[0007] Identify the edge structure information of each cross-sectional contour image, and extract each image feature of each cross-sectional contour image;

[0008] For each cross-sectional contour image, based on each image feature in the cross-sectional contour image and edge structure information of the cross-sectional contour image, using an aorta abnormality recognition model, each abnormal image region in the cross-sectional contour image and abnormality information of each abnormal image region are identified, and based on the abnormality information of each abnormal image region, the abnormality type of the cross-sectional contour image and the abnormality degree of the cross-sectional contour image are identified;

[0009] Based on the abnormality type of each of the cross-sectional contour images and the degree of abnormality of each of the cross-sectional contour images, the aortic dissection probability of the user and the predicted cause of the aortic dissection probability are predicted through the aortic dissection analysis strategy, and the user's aortic dissection probability and the predicted cause of the aortic dissection probability are used as auxiliary identification information of the user's aortic dissection.

[0010] Optionally, identifying edge structure information of each cross-sectional contour image includes:

[0011] Based on the aorta position corresponding to each cross-sectional contour image, identifying the sample structure position range of each aorta structure contained in the cross-sectional contour image, and for each cross-sectional contour image, based on each edge contour line in the cross-sectional contour image, identifying the image content contained in each edge contour line;

[0012] Based on the sample structure position range of each aortic structure and the content position range corresponding to the image content contained in each edge contour line, the aortic structure corresponding to each image content is identified;

[0013] Based on each image content, each adjacent edge contour line is identified, and for each pair of adjacent edge contour lines, each sub-edge spacing information between the adjacent edge contour lines is identified, and each sub-edge spacing information between each pair of adjacent edge contour lines and the aortic structure corresponding to the image content contained in each pair of adjacent edge contour lines are used as edge structure information of the cross-sectional contour image.

[0014] Optionally, the extracting of each image feature of each cross-sectional contour image includes:

[0015] For each cross-sectional contour image, extracting initial image features of the cross-sectional contour image through an image feature extraction network, and identifying a feature type of each initial image feature;

[0016] Add a type identifier corresponding to the feature type of each initial image feature to each initial image feature, and establish a corresponding relationship between each initial image feature and the image content represented by each initial image feature;

[0017] The initial image features including the type identification and the corresponding relationship are used as the image features of the cross-sectional contour image.

[0018] Optionally, based on each image feature in the cross-sectional contour image and edge structure information of the cross-sectional contour image, identifying each abnormal image region in the cross-sectional contour image and abnormal information of each abnormal image region through an aorta abnormality recognition model includes:

[0019] Based on the feature type of each image feature in the cross-sectional profile image, query the database for the conventional feature corresponding to each image feature and the feature image corresponding to each conventional feature, and based on the feature image corresponding to each conventional feature and the image content of the image feature corresponding to each conventional feature, identify the similarity between each image feature and the conventional feature corresponding to each image feature through a similarity recognition network;

[0020] Screening the image contents corresponding to the abnormal image features below the similarity threshold as the abnormal image regions, and inputting each abnormal image region, the abnormal image features of each abnormal image region, the edge structure information between each abnormal image region, and the feature type of each abnormal image feature into the aorta abnormality recognition model to identify each image sign of each abnormal image region;

[0021] All image signs of each abnormal image region are used as abnormal information of each abnormal image region.

[0022] Optionally, the identifying the abnormal type of the cross-sectional contour image and the abnormal degree of the cross-sectional contour image based on the abnormal information of each abnormal image region includes:

[0023] For each abnormal image region, based on each image sign of the abnormal image region, querying the sub-abnormal type of each image sign and the sub-abnormal degree of each image sign in the image sign database;

[0024] The sub-abnormality types of all image signs are used as the abnormality types of the cross-sectional contour image, and the sub-abnormality degrees of all image signs are used as the abnormality degrees of the cross-sectional contour image.

[0025] Optionally, the predicting of the probability of aortic dissection of the user and the predicted cause of the probability of aortic dissection based on the abnormal type of each of the cross-sectional contour images and the degree of abnormality of each of the cross-sectional contour images through an aortic dissection analysis strategy includes:

[0026] The aortic dissection analysis strategy is divided into sub-analysis strategies for each abnormality type, and for each cross-sectional contour image, based on the sub-abnormality degree of each sub-abnormality type of the cross-sectional contour image, the sub-aortic dissection probability of each sub-abnormality type is analyzed by the sub-analysis strategy of each abnormality type;

[0027] Obtaining the aortic dissection weight value of each abnormality type, and based on the aortic dissection weight value of each abnormality type, performing weighted calculation on the sub-aortic dissection probability of each sub-abnormality type to obtain the first aortic dissection probability of each sub-abnormality type;

[0028] Sorting the first aortic dissection probability of each sub-abnormality type from large to small to obtain a sub-abnormality type sequence of the cross-sectional contour image, and screening a preset number of sub-abnormality degrees of the sub-abnormality types according to the sub-abnormality type sequence from front to back as the sub-prediction reasons of the cross-sectional contour image;

[0029] Summing up all first aortic dissection probabilities to obtain a second aortic dissection probability of the cross-sectional contour image, and averaging the second aortic dissection probabilities of all cross-sectional contour images to obtain the aortic dissection probability of the user;

[0030] The sub-prediction reasons of all cross-sectional contour images are used as the prediction reasons of the aortic dissection probability.

[0031] In addition, to achieve the above-mentioned purpose, the present invention also provides an auxiliary identification system for aortic dissection, the auxiliary identification system for aortic dissection comprising:

[0032] An acquisition module, used to acquire a chest plain scan image of the user's aorta, and identify a cross-sectional contour image of the aorta in each of the chest plain scan images by using an image edge recognition algorithm;

[0033] An extraction module, used for identifying edge structure information of each cross-sectional profile image and extracting various image features of each cross-sectional profile image;

[0034] an identification module for identifying, for each cross-sectional contour image, each abnormal image region in the cross-sectional contour image and abnormality information of each abnormal image region based on each image feature in the cross-sectional contour image and edge structure information of the cross-sectional contour image, and identifying, based on the abnormality information of each abnormal image region, an abnormality type of the cross-sectional contour image and an abnormality degree of the cross-sectional contour image;

[0035] The analysis module is used to predict the user's aortic dissection probability and the predicted cause of the aortic dissection probability based on the abnormality type of each of the cross-sectional contour images and the abnormality degree of each of the cross-sectional contour images through an aortic dissection analysis strategy, and use the user's aortic dissection probability and the predicted cause of the aortic dissection probability as auxiliary identification information of the user's aortic dissection.

[0036] Optionally, the extraction module is specifically used to:

[0037] Based on the aorta position corresponding to each cross-sectional contour image, identifying the sample structure position range of each aorta structure contained in the cross-sectional contour image, and for each cross-sectional contour image, based on each edge contour line in the cross-sectional contour image, identifying the image content contained in each edge contour line;

[0038] Based on the sample structure position range of each aortic structure and the content position range corresponding to the image content contained in each edge contour line, the aortic structure corresponding to each image content is identified;

[0039] Based on each image content, each adjacent edge contour line is identified, and for each pair of adjacent edge contour lines, each sub-edge spacing information between the adjacent edge contour lines is identified, and each sub-edge spacing information between each pair of adjacent edge contour lines and the aortic structure corresponding to the image content contained in each pair of adjacent edge contour lines are used as edge structure information of the cross-sectional contour image.

[0040] Optionally, the extraction module is specifically used to:

[0041] For each cross-sectional contour image, extracting initial image features of the cross-sectional contour image through an image feature extraction network, and identifying a feature type of each initial image feature;

[0042] Add a type identifier corresponding to the feature type of each initial image feature to each initial image feature, and establish a corresponding relationship between each initial image feature and the image content represented by each initial image feature;

[0043] The initial image features including the type identification and the corresponding relationship are used as the image features of the cross-sectional contour image.

[0044] Optionally, the identification module is specifically used to:

[0045] Based on the feature type of each image feature in the cross-sectional profile image, query the database for the conventional feature corresponding to each image feature and the feature image corresponding to each conventional feature, and based on the feature image corresponding to each conventional feature and the image content of the image feature corresponding to each conventional feature, identify the similarity between each image feature and the conventional feature corresponding to each image feature through a similarity recognition network;

[0046] Screening the image contents corresponding to the abnormal image features below the similarity threshold as the abnormal image regions, and inputting each abnormal image region, the abnormal image features of each abnormal image region, the edge structure information between each abnormal image region, and the feature type of each abnormal image feature into the aorta abnormality recognition model to identify each image sign of each abnormal image region;

[0047] All image signs of each abnormal image region are used as abnormal information of each abnormal image region.

[0048] Optionally, the identification module is specifically used to:

[0049] For each abnormal image region, based on each image sign of the abnormal image region, querying the sub-abnormal type of each image sign and the sub-abnormal degree of each image sign in the image sign database;

[0050] The sub-abnormality types of all image signs are used as the abnormality types of the cross-sectional contour image, and the sub-abnormality degrees of all image signs are used as the abnormality degrees of the cross-sectional contour image.

[0051] Optionally, the analysis module is specifically used to:

[0052] The aortic dissection analysis strategy is divided into sub-analysis strategies for each abnormality type, and for each cross-sectional contour image, based on the sub-abnormality degree of each sub-abnormality type of the cross-sectional contour image, the sub-aortic dissection probability of each sub-abnormality type is analyzed by the sub-analysis strategy of each abnormality type;

[0053] Obtaining the aortic dissection weight value of each abnormality type, and based on the aortic dissection weight value of each abnormality type, performing weighted calculation on the sub-aortic dissection probability of each sub-abnormality type to obtain the first aortic dissection probability of each sub-abnormality type;

[0054] Sorting the first aortic dissection probability of each sub-abnormality type from large to small to obtain a sub-abnormality type sequence of the cross-sectional contour image, and screening a preset number of sub-abnormality degrees of the sub-abnormality types according to the sub-abnormality type sequence from front to back as the sub-prediction reasons of the cross-sectional contour image;

[0055] Summing up all first aortic dissection probabilities to obtain a second aortic dissection probability of the cross-sectional contour image, and averaging the second aortic dissection probabilities of all cross-sectional contour images to obtain the aortic dissection probability of the user;

[0056] The sub-prediction reasons of all cross-sectional contour images are used as the prediction reasons of the aortic dissection probability.

[0057] In a third aspect, the present application provides a computer device, wherein the computer device comprises a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of any one of the methods in the first aspect are implemented.

[0058] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the steps of any one of the methods in the first aspect are implemented.

[0059] In a fifth aspect, the present application provides a computer program product. The computer program product includes a computer program, and when the computer program is executed by a processor, the steps of any one of the methods in the first aspect are implemented.

[0060] The present invention provides an auxiliary identification method and system for aortic dissection, the method comprising: obtaining a chest plain scan image of a user's aorta, and identifying the cross-sectional contour image of the aorta in each of the chest plain scan images through an image edge recognition algorithm; identifying the edge structure information of each cross-sectional contour image, and extracting each image feature of each cross-sectional contour image; for each cross-sectional contour image, based on each image feature in the cross-sectional contour image and the edge structure information of the cross-sectional contour image, identifying each abnormality in the cross-sectional contour image through an aortic abnormality recognition model. The method comprises the steps of: identifying an abnormal type of the cross-sectional contour image and an abnormality degree of the cross-sectional contour image based on the abnormal type of each cross-sectional contour image and the abnormality degree of each cross-sectional contour image, predicting the probability of aortic dissection of the user and the predicted cause of the probability of aortic dissection through an aortic dissection analysis strategy, and using the probability of aortic dissection of the user and the predicted cause of the probability of aortic dissection as auxiliary identification information of aortic dissection of the user. This solution uses instant and efficient ordinary plain scanning equipment to perform plain scanning of various aorta positions in the user's chest to obtain a chest plain scanning image, and then performs image feature extraction and edge recognition on each cross-sectional contour image to identify various image features and edge structure information of the cross-sectional contour image. Then, the aortic abnormality recognition model is used to identify various abnormal image areas in the cross-sectional contour image and the abnormal information of each abnormal image area. While avoiding the defect that CT enhanced imaging scanning resources are not available to ordinary patients, the traditional plain scanning method and the aortic abnormality recognition model are used to identify the abnormal information of the abnormal image area in the user's cross-sectional contour image, thereby improving the recognition efficiency and recognition accuracy of the abnormal information. Secondly, this solution uses the abnormal information of the abnormal image area in each cross-sectional contour image to identify the cross-sectional contour image. The type and degree of abnormality are then used to predict the user's aortic dissection probability and the predicted cause of the aortic dissection probability through an aortic dissection analysis strategy, thereby comprehensively analyzing the user's aortic dissection probability and predicted cause through multiple images, all-round, and multi-angle analysis to assist in generating the user's aortic dissection auxiliary identification information, thereby avoiding the problem of misjudgment of aortic dissection due to omissions and recognition errors when doctors manually review chest plain scan images, so that ordinary plain scan images are used instead of CT enhanced imaging scans to improve the recognition efficiency of aortic dissection, and then through the abnormal type of cross-sectional contour images of multiple aortic chest plain scan images, as well as the abnormal degree of cross-sectional contour images, through the aortic dissection analysis strategy, the user's aortic dissection probability and predicted cause are predicted, thereby improving the comprehensiveness and accuracy of auxiliary identification of aortic dissection.Thereby comprehensively improving the auxiliary identification efficiency of aortic dissection in emergency. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] In order to more clearly illustrate the scheme in the present application, a brief introduction is given below to the drawings required for use in the description of the embodiments of the present application. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0062] Figure 1 is a flow chart of an auxiliary identification method for aortic dissection provided by an embodiment of the present invention;

[0063] Figure 2 is a schematic structural diagram of an auxiliary identification system for aortic dissection provided by an embodiment of the present invention;

[0064] Figure 3 An internal structure diagram of a computer device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0065] The auxiliary identification method of aortic dissection provided by an embodiment of the present invention is applied to the auxiliary identification system of aortic dissection. Unless otherwise defined, all technical and scientific terms used in this article have the same meaning as those generally understood by technicians in the technical field of this application; the terms used in the specification of the application herein are only for the purpose of describing specific embodiments and are not intended to limit this application; the terms "including" and "having" in the specification and claims of this application and the above-mentioned drawings and any variations thereof are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of this application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0066] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0067] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0068] The auxiliary identification method of aortic dissection provided in the embodiment of the present application can be applied to the application environment of auxiliary identification of aortic dissection. The method can be applied to a terminal, a server, or a system including a terminal and a server, and is implemented through the interaction between the terminal and the server. The terminal can be, but is not limited to, various personal computers, etc. The terminal uses an instant and efficient ordinary plain scanning device to perform a plain scan of each aorta position in the chest of the user to obtain a chest plain scan image, and then performs image feature extraction and edge recognition on each cross-sectional contour image to identify each image feature and edge structure information of the cross-sectional contour image. Then, the aortic abnormality recognition model is used to identify each abnormal image area in the cross-sectional contour image and the abnormal information of each abnormal image area. While avoiding the defect that CT enhanced image scanning resources cannot be obtained for ordinary patients, the abnormal information of the abnormal image area in the cross-sectional contour image of the user is identified through the traditional plain scanning method and the aortic abnormality recognition model, thereby improving the recognition efficiency and recognition accuracy of the abnormal information. Secondly, this solution further identifies the cross-sectional contour image through the abnormal information of the abnormal image area in each cross-sectional contour image. The abnormal type and degree of abnormality of the user are then predicted through the aortic dissection analysis strategy to predict the probability of aortic dissection of the user and the predicted cause of the aortic dissection probability, thereby comprehensively analyzing the probability of aortic dissection and the predicted cause of the user through multiple images, all-round and multi-angle, to assist in generating the user's aortic dissection auxiliary identification information, thereby avoiding the problem of misjudgment of aortic dissection caused by omissions and recognition errors when doctors manually review chest plain scan images, so that the recognition efficiency of aortic dissection is improved by replacing CT enhanced imaging scans with ordinary plain scan images, and then through the abnormal type of cross-sectional contour images of chest plain scan images of multiple aortas and the abnormal degree of cross-sectional contour images, through the aortic dissection analysis strategy, the probability of aortic dissection of the user and the predicted cause are predicted, thereby improving the comprehensiveness and accuracy of auxiliary identification of aortic dissection. Thereby comprehensively improving the auxiliary identification efficiency of aortic dissection in emergency.

[0069] In one embodiment, Figure 1 As shown, an auxiliary identification method for aortic dissection is provided, and the method is applied to a terminal as an example for explanation, including the following steps:

[0070] Step S101 : obtaining chest plain scan images of the user's aorta, and identifying the cross-sectional contour images of the aorta in each chest plain scan image by using an image edge recognition algorithm.

[0071] In this embodiment, the terminal performs plain scan processing at different positions of the user's chest range through a CT plain scan device to obtain different chest plain scan images of the user. Then, the terminal responds to the image recognition information upload operation of the staff to obtain the aorta position corresponding to each chest plain scan image. After that, the terminal uses an image edge recognition algorithm to identify the cross-sectional contour image of the aorta in each chest plain scan image, wherein the cross-sectional contour image of the aorta includes the cross-sectional contour image of the aorta and the aortic branches. The specific recognition process will be described in detail later.

[0072] Step S102: identifying edge structure information of each cross-sectional contour image, and extracting image features of each cross-sectional contour image.

[0073] In this embodiment, the terminal identifies the edge structure information of each cross-sectional contour image, wherein the cross-sectional contour image includes multiple aortic structure parts, so the edge structure information is the edge spacing information of each aortic structure part, and the edge spacing information includes the farthest edge spacing and the closest edge spacing of two aortic structures. Then the terminal extracts each image feature of each cross-sectional contour image, wherein the image feature includes the image feature corresponding to each aortic structure.

[0074] Step S103, for each cross-sectional contour image, based on each image feature in the cross-sectional contour image and the edge structure information of the cross-sectional contour image, the aorta abnormality recognition model is used to identify each abnormal image area in the cross-sectional contour image and the abnormal information of each abnormal image area, and based on the abnormal information of each abnormal image area, the abnormal type of the cross-sectional contour image and the degree of abnormality of the cross-sectional contour image are identified.

[0075] In this embodiment, the terminal identifies each abnormal image area in the cross-sectional contour image and the abnormal information of each abnormal image area through the aorta abnormality recognition model based on each image feature in the cross-sectional contour image and the edge structure information of the cross-sectional contour image. Among them, the abnormal image area is the image content corresponding to the image feature with abnormality, and the image area corresponding to the image content is the abnormal area. The method of identifying the image feature with abnormality will be described in detail later. The abnormal information of each abnormal image area is the image sign information of the abnormal image area, and the image sign information includes but is not limited to signs such as calcification inward migration, linear high density in the aorta cavity, high density in the aorta, uneven density in the aorta cavity, widening of the aorta and widening of branch vessels, irregular aortic morphology, peripheral exudation, pericardial effusion, pleural effusion, and high density shadow in the dorsal lung field. Based on the abnormal information of each abnormal image area, the terminal identifies the abnormal type of the cross-sectional contour image and the abnormal degree of the cross-sectional contour image. Among them, the abnormal type is the sign type corresponding to each sign. For example, the inward shift of calcification corresponds to the inward shift type of calcification, the linear high density in the aorta corresponds to the linear high density type, the high density in the aorta corresponds to the high density type of the aorta, the uneven density in the aorta corresponds to the uneven density type, the widening of the aorta and the widening of the branch vessels correspond to the widening type of the vessels, the irregular aorta morphology corresponds to the irregular morphology type, etc. The degree of abnormality is identified according to the degree corresponding to the obtained signs, and different abnormal types correspond to different degrees of abnormality. For example, the degree of abnormality corresponding to the high density type of the aorta includes different degrees of abnormality corresponding to different high density ranges, and the degree of abnormality corresponding to the inward shift type of calcification includes the degree of abnormality corresponding to the calcification moving inward from the outer contour edge of the aorta ring ≥3mm, and the degree of abnormality corresponding to the calcification moving inward from the outer contour edge of the aorta ring <3mm, etc.

[0076] Step S104, based on the abnormality type of each cross-sectional contour image and the abnormality degree of each cross-sectional contour image, predict the user's aortic dissection probability and the predicted cause of the aortic dissection probability through the aortic dissection analysis strategy, and use the user's aortic dissection probability and the predicted cause of the aortic dissection probability as the user's aortic dissection auxiliary identification information.

[0077] In this embodiment, the terminal predicts the user's aortic dissection probability and the predicted cause of the aortic dissection probability based on the abnormal type of each cross-sectional contour image and the abnormal degree of each cross-sectional contour image through the aortic dissection analysis strategy, and uses the user's aortic dissection probability and the predicted cause of the aortic dissection probability as the user's aortic dissection auxiliary identification information. Among them, different abnormal types in the aortic dissection analysis strategy correspond to different sub-analysis strategies, and the terminal predicts each aortic dissection probability based on the probability value corresponding to the degree range to which the different degrees of each abnormal type belong. The corresponding relationship between each degree range and the aortic dissection probability value is the sub-analysis strategy corresponding to the different abnormal types. The specific recognition process will be described in detail later. The predicted reason for each aortic dissection probability is the degree of abnormality corresponding to the abnormal type with a preset number of larger probability values. Based on the above scheme, the various aortic positions in the user's chest are scanned through instant and efficient ordinary plain scanning equipment to obtain a chest plain scanning image, and then each cross-sectional contour image is subjected to image feature extraction and edge recognition to identify the various image features of the cross-sectional contour image and the edge structure information. Then, the aortic abnormality recognition model is used to identify the various abnormal image areas in the cross-sectional contour image and the abnormal information of each abnormal image area. While avoiding the defect that CT enhanced image scanning resources are unavailable to ordinary patients, the traditional plain scanning method and the aortic abnormality recognition model are used to identify the abnormal information of the abnormal image area in the user's cross-sectional contour image, thereby improving the recognition efficiency and recognition accuracy of the abnormal information. Secondly, this scheme further uses each cross-sectional contour image to extract image features and edge recognition to identify the abnormal image areas in the user's cross-sectional contour image. The abnormal information of the abnormal image area in the contour image is used to identify the abnormal type and degree of the cross-sectional contour image, and then the probability of aortic dissection of the user and the predicted cause of the aortic dissection probability are predicted through the aortic dissection analysis strategy, so that the probability of aortic dissection and the predicted cause of the aortic dissection of the user are comprehensively analyzed through multiple images, all-round and multi-angles to assist in generating the auxiliary identification information of the aortic dissection of the user, thereby avoiding the problem of misjudgment of aortic dissection caused by omissions and recognition errors when doctors manually review chest plain scan images, so that the recognition efficiency of aortic dissection is improved by replacing CT enhanced imaging scans with ordinary plain scan images, and then the abnormal type of the cross-sectional contour image of the chest plain scan images of multiple aortas and the abnormal degree of the cross-sectional contour image are predicted through the aortic dissection analysis strategy, so as to improve the comprehensiveness and accuracy of auxiliary identification of aortic dissection. Thereby, the auxiliary identification efficiency of aortic dissection in emergency is comprehensively improved.

[0078] Optionally, edge structure information of each cross-sectional contour image is identified, including: based on the aorta position corresponding to each cross-sectional contour image, identifying the sample structure position range of each aorta structure contained in the cross-sectional contour image, and for each cross-sectional contour image, based on each edge contour line in the cross-sectional contour image, identifying the image content contained in each edge contour line; based on the sample structure position range of each aorta structure and the content position range corresponding to the image content contained in each edge contour line, identifying the aorta structure corresponding to each image content; based on each image content, identifying each adjacent edge contour line, and for each pair of adjacent edge contour lines, identifying each sub-edge spacing information between adjacent edge contour lines, and using each sub-edge spacing information between each pair of adjacent edge contour lines and the aorta structure corresponding to the image content contained in each pair of adjacent edge contour lines as the edge structure information of the cross-sectional contour image.

[0079] In this embodiment, the terminal identifies the image content contained in each edge contour line for each cross-sectional contour image based on each edge contour line in the cross-sectional contour image. Based on the sample structure position range of each aortic structure and the content position range corresponding to the image content contained in each edge contour line, the aortic structure corresponding to each image content is identified.

[0080] Based on the aortic position corresponding to each cross-sectional contour image, the terminal queries the database for the structural range of each aortic structure in each aortic position and the adjacent relationship between each aortic structure. Then, the terminal locates the sample structural position range of each aortic structure in the cross-sectional contour image of each aortic position. The positioning method is that the terminal identifies each edge contour range of each cross-sectional contour image, and then identifies the overlap (i.e., the percentage of the area of ​​the overlap range to the area of ​​the structure range) of each structure range with the edge contour range (i.e., the range of the image content contained in the edge contour line), and then the terminal uses the aortic structure described in the structural range corresponding to the maximum overlap as the aortic structure of the edge contour range.

[0081] Then, the terminal identifies each adjacent edge contour line based on each image content, and for each pair of adjacent edge contour lines, identifies each sub-edge spacing information between the adjacent edge contour lines, and uses the each sub-edge spacing information between each pair of adjacent edge contour lines and the aortic structure corresponding to the image content contained in each pair of adjacent edge contour lines as the edge structure information of the cross-sectional contour image.

[0082] Based on the above scheme, the aortic structure of each edge contour range is identified by means of structural range overlap, and then the sub-edge spacing information between adjacent edge contour lines is identified based on the spacing information between the edge contour lines, thereby improving the accuracy of identifying the aortic structure corresponding to each image content and the edge structure information of each cross-sectional contour image.

[0083] Optionally, extracting each image feature of each cross-sectional contour image, including: for each cross-sectional contour image, extracting the initial image features of the cross-sectional contour image through an image feature extraction network, and identifying the feature type of each initial image feature; adding a type identifier corresponding to the feature type of each initial image feature to each initial image feature, and establishing a corresponding relationship between each initial image feature and the image content represented by each initial image feature; using the initial image features including the type identifier and the corresponding relationship as the image features of the cross-sectional contour image.

[0084] In this embodiment, the terminal extracts the initial image features of the cross-sectional contour image through the image feature extraction network for each cross-sectional contour image, and identifies the feature type of each initial image feature. The image feature extraction network is a convolutional neural network (CNN) based on a self-attention mechanism, which adds a type identifier corresponding to the feature type of each initial image feature in each initial image feature. The feature type is the structural type of the aorta structure to which the image feature belongs. The type identifier can be a text identifier, a symbol identifier, a color identifier, etc.

[0085] The terminal establishes a corresponding relationship between each initial image feature and the image content represented by each initial image feature. Finally, the terminal uses the initial image features including the type identification and the corresponding relationship as each image feature of the cross-sectional profile image.

[0086] Based on the above scheme, the structural characteristics of each aortic structure are identified by extracting image features, thereby improving the comprehensiveness and accuracy of the recognition of the aortic structure.

[0087] Optionally, based on each image feature in the cross-sectional contour image and the edge structure information of the cross-sectional contour image, each abnormal image region in the cross-sectional contour image and the abnormal information of each abnormal image region are identified through an aortic abnormality recognition model, including: based on the feature type of each image feature in the cross-sectional contour image, querying the conventional feature corresponding to each image feature and the feature image corresponding to each conventional feature in the database, and based on the feature image corresponding to each conventional feature and the image content of the image feature corresponding to each conventional feature, identifying the similarity between each image feature and the conventional feature corresponding to each image feature through a similarity recognition network; screening the image content corresponding to the abnormal image features below the similarity threshold as the abnormal image region, and inputting each abnormal image region, the abnormal image feature of each abnormal image region, the edge structure information between each abnormal image region, and the feature type of each abnormal image feature into the aortic abnormality recognition model to identify each image sign of each abnormal image region; and taking all image signs of each abnormal image region as the abnormal information of each abnormal image region.

[0088] In this embodiment, based on the feature type of each image feature in the cross-sectional profile image, the terminal queries the conventional features corresponding to each image feature and the feature image corresponding to each conventional feature in the database, and based on the feature image corresponding to each conventional feature and the image content of the image feature corresponding to each conventional feature, identifies the similarity between each image feature and the conventional feature corresponding to each image feature through a similarity recognition network. The similarity between the image feature and the conventional feature includes the cosine similarity between the two features (calculated by the cosine similarity algorithm) and the image similarity between the feature image and the image content identified by the image similarity recognition network. Then, the terminal calculates the average of the two similarities to obtain the similarity between each image feature and the conventional feature corresponding to each image feature.

[0089] Then, the terminal selects the image content corresponding to the abnormal image features below the similarity threshold preset in the terminal as the abnormal image area, and inputs each abnormal image area, the abnormal image features of each abnormal image area, the edge structure information between each abnormal image area, and the feature type of each abnormal image feature into the aortic abnormality recognition model to identify each image sign of each abnormal image area. Among them, the aortic abnormality recognition model is a classifier based on a reinforcement learning neural network. Finally, the terminal uses all the image signs of each abnormal image area as the abnormal information of each abnormal image area.

[0090] Based on the above scheme, through the dual similarity recognition of feature similarity and image similarity, whether there is an abnormality in each aortic structure of Patin is improved in accuracy and comprehensiveness of recognition. Then, through the aortic abnormality recognition network, the image signs of each abnormal image area are identified, avoiding the error rate and abnormality of manual recognition. The accuracy of identifying the image signs of each abnormal image area is improved.

[0091] Optionally, based on the abnormal information of each abnormal image area, the abnormal type of the cross-sectional contour image and the abnormality degree of the cross-sectional contour image are identified, including: for each abnormal image area, based on each image sign of the abnormal image area, querying the sub-abnormality type of each image sign and the sub-abnormality degree of each image sign in an image sign database; using the sub-abnormality types of all image signs as the abnormality types of the cross-sectional contour image, and using the sub-abnormality degrees of all image signs as the abnormality degrees of the cross-sectional contour image.

[0092] In this embodiment, for each abnormal image area, the terminal queries the sub-abnormal type of each image sign and the sub-abnormal degree of each image sign in the image sign database based on each image sign of the abnormal image area. The image sign database includes multiple sub-abnormal degrees corresponding to each abnormal type, the corresponding relationship between each abnormal type and the image sign, and the corresponding relationship between each sub-abnormal degree and the abnormal sign. The terminal queries the above corresponding relationship to identify the sub-abnormal type and sub-abnormal degree of the image sign, thereby improving the accuracy and efficiency of recognition.

[0093] Finally, the terminal uses the sub-abnormality types of all image signs as the abnormality types of the cross-sectional contour image, and uses the sub-abnormality degrees of all image signs as the abnormality degrees of the cross-sectional contour image.

[0094] Based on the above scheme, by identifying the sub-abnormality type of each image sign and the sub-abnormality degree of each image sign, the abnormality type and abnormality degree of the cross-sectional contour image are determined, thereby improving the comprehensiveness of the identification.

[0095] Optionally, based on the abnormality type of each cross-sectional contour image and the abnormality degree of each cross-sectional contour image, the user's aortic dissection probability and the predicted reason for the aortic dissection probability are predicted through an aortic dissection analysis strategy, including: splitting the aortic dissection analysis strategy into sub-analysis strategies for each abnormality type, and for each cross-sectional contour image, based on the sub-abnormality degree of each sub-abnormality type of the cross-sectional contour image, analyzing the sub-aortic dissection probability of each sub-abnormality type through the sub-analysis strategy of each abnormality type; obtaining the aortic dissection weight value of each abnormality type, and performing weighted calculation on the sub-aortic dissection probability of each sub-abnormality type based on the aortic dissection weight value of each abnormality type, Obtain the first aortic dissection probability of each sub-abnormality type; sort the first aortic dissection probability of each sub-abnormality type from large to small to obtain a sub-abnormality type sequence of the cross-sectional contour image, and screen a preset number of sub-abnormality degrees of the sub-abnormality type in the order of the sub-abnormality type sequence from front to back as the sub-prediction causes of the cross-sectional contour image; sum all the first aortic dissection probabilities to obtain the second aortic dissection probability of the cross-sectional contour image, and average the second aortic dissection probabilities of all cross-sectional contour images to obtain the user's aortic dissection probability; use the sub-prediction causes of all cross-sectional contour images as the prediction causes of the aortic dissection probability.

[0096] In this embodiment, the terminal splits the aortic dissection analysis strategy into sub-analysis strategies for each abnormality type, and for each cross-sectional contour image, based on the sub-abnormality degree of each sub-abnormality type of the cross-sectional contour image, analyzes the sub-aortic dissection probability of each sub-abnormality type through the sub-analysis strategy of each abnormality type. As described above, the sub-analysis strategy of each abnormality type includes the aortic dissection probability corresponding to each abnormality degree, and then, based on the corresponding relationship, the terminal identifies the sub-aortic dissection probability corresponding to the sub-abnormality degree of each abnormality type.

[0097] The terminal obtains the aortic dissection weight value of each abnormal type, and based on the aortic dissection weight value of each abnormal type, performs weighted calculation on the probability of sub-aortic dissection of each sub-abnormal type to obtain the first aortic dissection probability of each sub-abnormal type. Among them, the aortic dissection weight value represents the influence probability of each abnormal type of the aorta causing aortic dissection, for example, the dissection weight value of the calcification inward migration type, the linear high density type, and the aortic high density area type is high, and the dissection weight value of other abnormal types is low.

[0098] The terminal sorts the first aortic dissection probability of each sub-abnormality type from large to small to obtain a sub-abnormality type sequence of the cross-sectional contour image, and screens a preset number of sub-abnormality degrees of the sub-abnormality types according to the sub-abnormality type sequence from front to back as the sub-prediction causes of the cross-sectional contour image.

[0099] Finally, the terminal sums up all the first aortic dissection probabilities to obtain the second aortic dissection probability of the cross-sectional contour image, and averages the second aortic dissection probabilities of all cross-sectional contour images to obtain the user's aortic dissection probability. The terminal uses the sub-prediction reasons of all cross-sectional contour images as the prediction reasons of the aortic dissection probability.

[0100] Based on the above scheme, probability distribution is performed through the aortic dissection weight value to ensure attention to the sub-abnormality degree of the abnormal type corresponding to the main sign, thereby improving the accuracy of the judgment of the probability of aortic dissection.

[0101] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0102] Based on the same inventive concept, the embodiment of the present application also provides an auxiliary identification system for aortic dissection for implementing the auxiliary identification method for aortic dissection involved above. The implementation scheme for solving the problem provided by the system is similar to the implementation scheme recorded in the above method, so the specific limitations in the embodiments of one or more auxiliary identification systems for aortic dissection provided below can refer to the limitations of the auxiliary identification method for aortic dissection above, and will not be repeated here.

[0103] Further references Figure 2 , as a response to the above Figure 1 The present application provides an embodiment of an auxiliary identification system 200 for aortic dissection, wherein the auxiliary identification system for aortic dissection comprises an acquisition module 210, an identification module 220, an identification module 230 and an analysis module 240, wherein:

[0104] The acquisition module 210 is used to acquire a chest plain scan image of the user's aorta, and identify a cross-sectional contour image of the aorta in each of the chest plain scan images by using an image edge recognition algorithm;

[0105] An extraction module 220, used to identify edge structure information of each cross-sectional contour image and extract various image features of each cross-sectional contour image;

[0106] The recognition module 230 is used for, for each cross-sectional contour image, based on each image feature in the cross-sectional contour image and the edge structure information of the cross-sectional contour image, identifying each abnormal image region in the cross-sectional contour image and the abnormality information of each abnormal image region through the aorta abnormality recognition model, and based on the abnormality information of each abnormal image region, identifying the abnormality type of the cross-sectional contour image and the abnormality degree of the cross-sectional contour image;

[0107] The analysis module 240 is used to predict the user's aortic dissection probability and the predicted cause of the aortic dissection probability based on the abnormality type of each of the cross-sectional contour images and the abnormality degree of each of the cross-sectional contour images through an aortic dissection analysis strategy, and use the user's aortic dissection probability and the predicted cause of the aortic dissection probability as auxiliary identification information of the user's aortic dissection.

[0108] Optionally, the extraction module 220 is specifically used to:

[0109] Based on the aorta position corresponding to each cross-sectional contour image, identifying the sample structure position range of each aorta structure contained in the cross-sectional contour image, and for each cross-sectional contour image, based on each edge contour line in the cross-sectional contour image, identifying the image content contained in each edge contour line;

[0110] Based on the sample structure position range of each aortic structure and the content position range corresponding to the image content contained in each edge contour line, the aortic structure corresponding to each image content is identified;

[0111] Based on each image content, each adjacent edge contour line is identified, and for each pair of adjacent edge contour lines, each sub-edge spacing information between the adjacent edge contour lines is identified, and each sub-edge spacing information between each pair of adjacent edge contour lines and the aortic structure corresponding to the image content contained in each pair of adjacent edge contour lines are used as edge structure information of the cross-sectional contour image.

[0112] Optionally, the extraction module 220 is specifically used to:

[0113] For each cross-sectional contour image, extracting initial image features of the cross-sectional contour image through an image feature extraction network, and identifying a feature type of each initial image feature;

[0114] Add a type identifier corresponding to the feature type of each initial image feature to each initial image feature, and establish a corresponding relationship between each initial image feature and the image content represented by each initial image feature;

[0115] The initial image features including the type identification and the corresponding relationship are used as the image features of the cross-sectional contour image.

[0116] Optionally, the identification module 230 is specifically configured to:

[0117] Based on the feature type of each image feature in the cross-sectional profile image, query the database for the conventional feature corresponding to each image feature and the feature image corresponding to each conventional feature, and based on the feature image corresponding to each conventional feature and the image content of the image feature corresponding to each conventional feature, identify the similarity between each image feature and the conventional feature corresponding to each image feature through a similarity recognition network;

[0118] Screening the image contents corresponding to the abnormal image features below the similarity threshold as the abnormal image regions, and inputting each abnormal image region, the abnormal image features of each abnormal image region, the edge structure information between each abnormal image region, and the feature type of each abnormal image feature into the aorta abnormality recognition model to identify each image sign of each abnormal image region;

[0119] All image signs of each abnormal image region are used as abnormal information of each abnormal image region.

[0120] Optionally, the identification module 230 is specifically configured to:

[0121] For each abnormal image region, based on each image sign of the abnormal image region, querying the sub-abnormal type of each image sign and the sub-abnormal degree of each image sign in the image sign database;

[0122] The sub-abnormality types of all image signs are used as the abnormality types of the cross-sectional contour image, and the sub-abnormality degrees of all image signs are used as the abnormality degrees of the cross-sectional contour image.

[0123] Optionally, the analysis module 240 is specifically used for:

[0124] The aortic dissection analysis strategy is divided into sub-analysis strategies for each abnormality type, and for each cross-sectional contour image, based on the sub-abnormality degree of each sub-abnormality type of the cross-sectional contour image, the sub-aortic dissection probability of each sub-abnormality type is analyzed by the sub-analysis strategy of each abnormality type;

[0125] Obtaining the aortic dissection weight value of each abnormality type, and based on the aortic dissection weight value of each abnormality type, performing weighted calculation on the sub-aortic dissection probability of each sub-abnormality type to obtain the first aortic dissection probability of each sub-abnormality type;

[0126] Sorting the first aortic dissection probability of each sub-abnormality type from large to small to obtain a sub-abnormality type sequence of the cross-sectional contour image, and screening a preset number of sub-abnormality degrees of the sub-abnormality types according to the sub-abnormality type sequence from front to back as the sub-prediction reasons of the cross-sectional contour image;

[0127] Summing up all first aortic dissection probabilities to obtain a second aortic dissection probability of the cross-sectional contour image, and averaging the second aortic dissection probabilities of all cross-sectional contour images to obtain the aortic dissection probability of the user;

[0128] The sub-prediction reasons of all cross-sectional contour images are used as the prediction reasons of the probability of aortic dissection. Each module in the auxiliary identification system of aortic dissection can be implemented in whole or in part by software, hardware and a combination thereof. Each of the above modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.

[0129] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Figure 3 As shown. The computer device includes a processor, a memory, a communication interface, a display screen and an input system connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, an auxiliary identification method for aortic dissection is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input system of the computer device can be a touch layer covered on the display screen, or a button, trackball or touchpad set on the computer device housing, or an external keyboard, touchpad or mouse, etc.

[0130] Those skilled in the art will understand that Figure 3The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0131] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the steps of any one of the methods in the first aspect are implemented.

[0132] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of any one of the methods in the first aspect are implemented.

[0133] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the steps of any one of the methods in the first aspect.

[0134] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0135] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0136] The technical features of the above embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0137] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be construed as limiting the scope of the present application. It should be noted that, for a person of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. An auxiliary identification method for aortic dissection, characterized in that: The method comprises: Obtaining a chest plain scan image of the user's aorta, and identifying a cross-sectional contour image of the aorta in each of the chest plain scan images by using an image edge recognition algorithm; Identify the edge structure information of each cross-sectional contour image, and extract each image feature of each cross-sectional contour image; For each cross-sectional contour image, based on each image feature in the cross-sectional contour image and edge structure information of the cross-sectional contour image, using an aorta abnormality recognition model, each abnormal image region in the cross-sectional contour image and abnormality information of each abnormal image region are identified, and based on the abnormality information of each abnormal image region, the abnormality type of the cross-sectional contour image and the abnormality degree of the cross-sectional contour image are identified; Based on the abnormality type of each of the cross-sectional contour images and the degree of abnormality of each of the cross-sectional contour images, the aortic dissection probability of the user and the predicted cause of the aortic dissection probability are predicted through the aortic dissection analysis strategy, and the user's aortic dissection probability and the predicted cause of the aortic dissection probability are used as auxiliary identification information of the user's aortic dissection.

2. The method according to claim 1, characterized in that The step of identifying edge structure information of each cross-sectional contour image comprises: Based on the aorta position corresponding to each cross-sectional contour image, identifying the sample structure position range of each aorta structure contained in the cross-sectional contour image, and for each cross-sectional contour image, based on each edge contour line in the cross-sectional contour image, identifying the image content contained in each edge contour line; Based on the sample structure position range of each aortic structure and the content position range corresponding to the image content contained in each edge contour line, the aortic structure corresponding to each image content is identified; Based on each image content, each adjacent edge contour line is identified, and for each pair of adjacent edge contour lines, each sub-edge spacing information between the adjacent edge contour lines is identified, and each sub-edge spacing information between each pair of adjacent edge contour lines and the aortic structure corresponding to the image content contained in each pair of adjacent edge contour lines are used as edge structure information of the cross-sectional contour image.

3. The method according to claim 2, characterized in that The step of extracting each image feature of each cross-sectional contour image comprises: For each cross-sectional contour image, extracting initial image features of the cross-sectional contour image through an image feature extraction network, and identifying a feature type of each initial image feature; Add a type identifier corresponding to the feature type of each initial image feature to each initial image feature, and establish a corresponding relationship between each initial image feature and the image content represented by each initial image feature; The initial image features including the type identification and the corresponding relationship are used as the image features of the cross-sectional contour image.

4. The method according to claim 3, characterized in that: The method of identifying each abnormal image region in the cross-sectional contour image and abnormal information of each abnormal image region by using an aorta abnormality recognition model based on each image feature in the cross-sectional contour image and edge structure information of the cross-sectional contour image includes: Based on the feature type of each image feature in the cross-sectional profile image, query the database for the conventional feature corresponding to each image feature and the feature image corresponding to each conventional feature, and based on the feature image corresponding to each conventional feature and the image content of the image feature corresponding to each conventional feature, identify the similarity between each image feature and the conventional feature corresponding to each image feature through a similarity recognition network; Screening the image contents corresponding to the abnormal image features below the similarity threshold as the abnormal image regions, and inputting each abnormal image region, the abnormal image features of each abnormal image region, the edge structure information between each abnormal image region, and the feature type of each abnormal image feature into the aorta abnormality recognition model to identify each image sign of each abnormal image region; All image signs of each abnormal image region are used as abnormal information of each abnormal image region.

5. The method according to claim 4, characterized in that The identifying the abnormal type of the cross-sectional contour image and the abnormal degree of the cross-sectional contour image based on the abnormal information of each abnormal image region includes: For each abnormal image region, based on each image sign of the abnormal image region, querying the sub-abnormal type of each image sign and the sub-abnormal degree of each image sign in the image sign database; The sub-abnormality types of all image signs are used as the abnormality types of the cross-sectional contour image, and the sub-abnormality degrees of all image signs are used as the abnormality degrees of the cross-sectional contour image.

6. The method according to claim 5, characterized in that The method of predicting the probability of aortic dissection of the user and the predicted reason of the probability of aortic dissection based on the abnormal type of each of the cross-sectional contour images and the abnormal degree of each of the cross-sectional contour images through an aortic dissection analysis strategy includes: The aortic dissection analysis strategy is divided into sub-analysis strategies for each abnormality type, and for each cross-sectional contour image, based on the sub-abnormality degree of each sub-abnormality type of the cross-sectional contour image, the sub-aortic dissection probability of each sub-abnormality type is analyzed by the sub-analysis strategy of each abnormality type; Obtaining the aortic dissection weight value of each abnormality type, and based on the aortic dissection weight value of each abnormality type, performing weighted calculation on the sub-aortic dissection probability of each sub-abnormality type to obtain the first aortic dissection probability of each sub-abnormality type; Sorting the first aortic dissection probability of each sub-abnormality type from large to small to obtain a sub-abnormality type sequence of the cross-sectional contour image, and screening a preset number of sub-abnormality degrees of the sub-abnormality types according to the sub-abnormality type sequence from front to back as the sub-prediction reasons of the cross-sectional contour image; Summing up all first aortic dissection probabilities to obtain a second aortic dissection probability of the cross-sectional contour image, and averaging the second aortic dissection probabilities of all cross-sectional contour images to obtain the aortic dissection probability of the user; The sub-prediction reasons of all cross-sectional contour images are used as the prediction reasons of the aortic dissection probability.

7. An auxiliary identification system for aortic dissection, characterized in that: The system comprises: An acquisition module, used to acquire a chest plain scan image of the user's aorta, and identify a cross-sectional contour image of the aorta in each of the chest plain scan images by using an image edge recognition algorithm; An extraction module, used for identifying edge structure information of each cross-sectional profile image and extracting various image features of each cross-sectional profile image; an identification module for identifying, for each cross-sectional contour image, each abnormal image region in the cross-sectional contour image and abnormality information of each abnormal image region based on each image feature in the cross-sectional contour image and edge structure information of the cross-sectional contour image, and identifying, based on the abnormality information of each abnormal image region, an abnormality type of the cross-sectional contour image and an abnormality degree of the cross-sectional contour image; The analysis module is used to predict the user's aortic dissection probability and the predicted cause of the aortic dissection probability based on the abnormality type of each of the cross-sectional contour images and the abnormality degree of each of the cross-sectional contour images through an aortic dissection analysis strategy, and use the user's aortic dissection probability and the predicted cause of the aortic dissection probability as auxiliary identification information of the user's aortic dissection.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images