Pulmonary artery embolism guiding method and system based on chest CT (Computed Tomography) plain-scan image

Abstract

The invention provides a pulmonary artery embolism guiding method and system based on a chest CT plain-scan image, and the method comprises the steps: obtaining the chest CT plain-scan image of a patient, and generating continuous pulmonary artery image data through an image motion compensation strategy; shape distribution information and blood density distribution information of all blood vessels of the pulmonary artery are captured through an image recognition model so as to recognize the blood vessel abnormal range and the blood vessel abnormal degree of all embolism blood vessels, and the pulmonary artery embolism probability of the patient is obtained based on the blood vessel abnormal range and the blood vessel abnormal degree of all the embolism blood vessels. And generating a pulmonary artery embolism guidance report of the patient. By adopting the scheme, the accuracy of guiding the medical staff to identify the pulmonary artery embolism of the patient can be improved.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence and intelligent medical technology, and in particular to a pulmonary embolism guidance method and system based on chest CT plain scan images. Background Art

[0002] Pulmonary embolism is a condition characterized by pulmonary embolism (PE), characterized by blood clots or other obstructions that block the lungs' blood vessels. The most common form of this condition is acute PE (also known as acute PE). Prompt and efficient detection of pulmonary embolism (PE) can significantly improve the accuracy of identifying, analyzing, and developing treatment strategies for PE. Therefore, improving the accuracy of detecting pulmonary embolism is a current research priority.

[0003] The traditional technical solution is to directly scan the lungs to detect whether there are blood clots or blockages in the pulmonary blood vessels. However, blood is fluid, and blood clots and blockages are difficult to accurately identify in a single blood vessel scan image. Even using an image recognition network, it is difficult to accurately locate them. Medical staff often need to combine a lot of work experience to conduct analysis to obtain a rough result, resulting in low accuracy in medical staff's identification of pulmonary embolism in patients. Summary of the Invention

[0004] The main purpose of the present invention is to provide a pulmonary embolism guidance method and system based on chest CT plain scan images, aiming to solve the problem of existing technology that due to the fluidity of blood, blood clots and blockages are difficult to accurately identify in the image of a single blood vessel scan. Even if an image recognition network is used, it is difficult to accurately locate them. Medical staff often need to combine a lot of work experience to analyze and obtain a rough result, which leads to low accuracy in identifying blockages in pulmonary blood vessels.

[0005] To achieve the above objectives, the present invention provides a pulmonary embolism guidance method based on chest CT plain scan images, the method comprising:

[0006] Obtaining a chest plain scan image of the patient, and generating continuous image data of the patient's pulmonary artery based on the chest plain scan image by using an image motion compensation strategy;

[0007] Based on the continuous pulmonary artery image data, the image recognition model is used to identify shape distribution information of each blood vessel of the patient's pulmonary artery and blood density distribution information of each blood vessel, and based on the shape distribution information of each blood vessel and the blood density distribution information of each blood vessel, the embolism image recognition strategy is used to identify the range of vascular abnormality and the degree of vascular abnormality of each embolized blood vessel;

[0008] Based on the range of vascular abnormalities of each of the embolic vessels and the degree of vascular abnormalities of each of the embolic vessels, the probability of pulmonary embolism in the patient is identified, and based on the range of vascular abnormalities of each of the embolic vessels, the degree of vascular abnormalities of each of the embolic vessels and the probability of pulmonary embolism in the patient, a pulmonary embolism guidance report is generated for the patient.

[0009] Optionally, the generating of the patient's pulmonary artery continuous image data based on the chest plain scan image by an image motion compensation strategy includes:

[0010] Based on the chest plain scan image, the actual chest plain scan image is generated by suppressing the hilar pulsation artifact strategy;

[0011] Identifying each lung image label contained in each sub-chest plain scan image in the actual chest plain scan image, and selecting a sub-chest plain scan image containing a target lung image label as a target sub-chest plain scan image; the target lung image label is a pulmonary artery image label;

[0012] The target sub-chest plain scan images are sorted according to the time sequence of each target sub-chest plain scan image to obtain the patient's chest plain scan image sequence, and the chest plain scan image sequence is subjected to continuous image supplementation generation processing through a continuous animation generation program to obtain the patient's pulmonary artery continuous image data.

[0013] Optionally, identifying shape distribution information of each blood vessel of the patient's pulmonary artery and blood density distribution information of each blood vessel by an image recognition model based on the pulmonary artery continuous image data includes:

[0014] Based on the pulmonary artery continuous image data, identifying the blood vessel continuous image data of each blood vessel in the pulmonary artery continuous image data by an image edge recognition algorithm;

[0015] For each blood vessel, based on the continuous blood vessel image data of the blood vessel, the image deformation recognition network of the image recognition model is used to identify the shape change information of each blood vessel portion, and the shape change information of each blood vessel portion is spliced ​​according to the connection relationship between the blood vessel portions to obtain the shape distribution information of the blood vessel;

[0016] Based on the continuous vascular image data of the blood vessel, the blood density change information of each vascular portion of the blood vessel is identified through the blood density recognition network of the image recognition model, and the blood density change information of each vascular portion is spliced ​​according to the connection relationship between the vascular portions to obtain the blood density distribution information of the blood vessel.

[0017] Optionally, the identifying the vascular abnormality range and degree of vascular abnormality of each embolic vessel through an embolic image recognition strategy based on the shape distribution information of each blood vessel and the blood density distribution information of each blood vessel includes:

[0018] Based on the shape distribution information of each of the blood vessels, identifying, by an image embolism recognition network, a shape change amplitude of each vascular portion of each blood vessel and a shape change speed of each vascular portion of each blood vessel; and based on the blood density distribution information of each of the blood vessels, identifying, by the image embolism recognition network, a blood density change degree of each vascular portion of each blood vessel and a blood density change speed of each vascular portion of each blood vessel;

[0019] identifying an embolic vessel portion in each blood vessel using an embolism evaluation network based on a shape change rate of each vessel portion of each blood vessel and a blood density change rate of each vessel portion of each blood vessel;

[0020] The blood vessels with embolized vascular parts are regarded as embolized vessels, and all embolized vascular parts in each embolized vessel are regarded as the vascular abnormality range of each embolized vessel;

[0021] For each embolic vessel, based on the shape change amplitude of each embolic vessel portion of the embolic vessel and the degree of blood density change of each embolic vessel portion of the embolic vessel, the embolism degree evaluation network is used to identify the sub-embolism degree of each embolic vessel portion, and the sub-embolism degree of all embolic vessel portions is used as the vascular abnormality degree of the embolic vessel.

[0022] Optionally, identifying the probability of pulmonary embolism in the patient based on the range of vascular abnormality and the degree of vascular abnormality of each embolic vessel includes:

[0023] Based on the vascular abnormality range of each embolic vessel and the vascular thrombosis degree of each embolic vessel, performing embolism marking processing on the pulmonary artery continuous image data to obtain a pulmonary artery embolism marking image;

[0024] identifying the patient's pulmonary embolism distribution information and degree distribution information based on the pulmonary embolism marking image, and extracting characteristic data of each pulmonary embolism based on the pulmonary embolism degree distribution information;

[0025] Based on each of the pulmonary embolism feature data, the probability of pulmonary embolism in the patient is identified.

[0026] Optionally, generating a pulmonary embolism guidance report for the patient based on the range of vascular abnormality of each embolic vessel, the degree of vascular abnormality of each embolic vessel, and the probability of pulmonary embolism of the patient includes:

[0027] identifying, based on the pulmonary embolism marking image, pulmonary embolism distribution characteristics and pulmonary embolism range characteristics of the patient, and generating, based on the pulmonary embolism distribution characteristics, pulmonary embolism range characteristics, and pulmonary embolism probability of the patient, pulmonary embolism guidance information for the patient using a pulmonary embolism guidance template;

[0028] The patient's pulmonary embolism guidance information and the pulmonary embolism marking image are used as the patient's pulmonary embolism guidance report.

[0029] In addition, to achieve the above-mentioned purpose, the present invention further provides a pulmonary embolism guidance system based on chest CT plain scan images, the pulmonary embolism guidance system based on chest CT plain scan images comprising:

[0030] An acquisition module is used to acquire a chest plain scan image of the patient and generate continuous image data of the patient's pulmonary artery based on the chest plain scan image by using an image motion compensation strategy;

[0031] an identification module configured to identify, based on the continuous pulmonary artery image data and using an image recognition model, shape distribution information of each blood vessel of the patient's pulmonary artery and blood density distribution information of each blood vessel, and to identify, based on the shape distribution information of each blood vessel and the blood density distribution information of each blood vessel and using an embolism image identification strategy, a range of vascular abnormality and a degree of vascular abnormality of each embolized blood vessel;

[0032] A generation module is used to identify the patient's probability of pulmonary embolism based on the vascular abnormality range of each embolic vessel and the degree of vascular abnormality of each embolic vessel, and to generate a pulmonary embolism guidance report for the patient based on the vascular abnormality range of each embolic vessel, the degree of vascular abnormality of each embolic vessel, and the patient's probability of pulmonary embolism.

[0033] Optionally, the acquisition module is specifically configured to:

[0034] Based on the chest plain scan image, the actual chest plain scan image is generated by suppressing the hilar pulsation artifact strategy;

[0035] Identifying each lung image label contained in each sub-chest plain scan image in the actual chest plain scan image, and selecting a sub-chest plain scan image containing a target lung image label as a target sub-chest plain scan image; the target lung image label is a pulmonary artery image label;

[0036] The target sub-chest plain scan images are sorted according to the time sequence of each target sub-chest plain scan image to obtain the patient's chest plain scan image sequence, and the chest plain scan image sequence is subjected to continuous image supplementation generation processing through a continuous animation generation program to obtain the patient's pulmonary artery continuous image data.

[0037] Optionally, the identification module is specifically configured to:

[0038] Based on the pulmonary artery continuous image data, identifying the blood vessel continuous image data of each blood vessel in the pulmonary artery continuous image data by an image edge recognition algorithm;

[0039] For each blood vessel, based on the continuous blood vessel image data of the blood vessel, the image deformation recognition network of the image recognition model is used to identify the shape change information of each blood vessel portion, and the shape change information of each blood vessel portion is spliced ​​according to the connection relationship between the blood vessel portions to obtain the shape distribution information of the blood vessel;

[0040] Based on the continuous vascular image data of the blood vessel, the blood density change information of each vascular portion of the blood vessel is identified through the blood density recognition network of the image recognition model, and the blood density change information of each vascular portion is spliced ​​according to the connection relationship between the vascular portions to obtain the blood density distribution information of the blood vessel.

[0041] Optionally, the identification module is specifically configured to:

[0042] Based on the shape distribution information of each of the blood vessels, identifying, by an image embolism recognition network, a shape change amplitude of each vascular portion of each blood vessel and a shape change speed of each vascular portion of each blood vessel; and based on the blood density distribution information of each of the blood vessels, identifying, by the image embolism recognition network, a blood density change degree of each vascular portion of each blood vessel and a blood density change speed of each vascular portion of each blood vessel;

[0043] identifying an embolic vessel portion in each blood vessel using an embolism evaluation network based on a shape change rate of each vessel portion of each blood vessel and a blood density change rate of each vessel portion of each blood vessel;

[0044] The blood vessels with embolized vascular parts are regarded as embolized vessels, and all embolized vascular parts in each embolized vessel are regarded as the vascular abnormality range of each embolized vessel;

[0045] For each embolic vessel, based on the shape change amplitude of each embolic vessel portion of the embolic vessel and the degree of blood density change of each embolic vessel portion of the embolic vessel, the embolism degree evaluation network is used to identify the sub-embolism degree of each embolic vessel portion, and the sub-embolism degree of all embolic vessel portions is used as the vascular abnormality degree of the embolic vessel.

[0046] Optionally, the generating module is specifically configured to:

[0047] Based on the vascular abnormality range of each embolic vessel and the vascular thrombosis degree of each embolic vessel, performing embolism marking processing on the pulmonary artery continuous image data to obtain a pulmonary artery embolism marking image;

[0048] identifying the patient's pulmonary embolism distribution information and degree distribution information based on the pulmonary embolism marking image, and extracting characteristic data of each pulmonary embolism based on the pulmonary embolism degree distribution information;

[0049] Based on each of the pulmonary embolism feature data, the probability of pulmonary embolism in the patient is identified.

[0050] Optionally, the generating module is specifically configured to:

[0051] identifying, based on the pulmonary embolism marking image, pulmonary embolism distribution characteristics and pulmonary embolism range characteristics of the patient, and generating, based on the pulmonary embolism distribution characteristics, pulmonary embolism range characteristics, and pulmonary embolism probability of the patient, pulmonary embolism guidance information for the patient using a pulmonary embolism guidance template;

[0052] The patient's pulmonary embolism guidance information and the pulmonary embolism marking image are used as the patient's pulmonary embolism guidance report.

[0053] In a third aspect, the present application provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of any one of the methods described in the first aspect when executing the computer program.

[0054] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of any one of the methods in the first aspect.

[0055] In a fifth aspect, the present application provides a computer program product, wherein the computer program product comprises 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.

[0056] The present invention provides a pulmonary embolism guidance method and system based on chest CT plain scan images. The method includes: obtaining a chest plain scan image of a patient, and generating continuous pulmonary artery image data of the patient based on the chest plain scan image through an image motion compensation strategy; based on the continuous pulmonary artery image data, identifying the shape distribution information of each blood vessel of the patient's pulmonary artery and the blood density distribution information of each blood vessel through an image recognition model, and based on the shape distribution information of each blood vessel and the blood density distribution information of each blood vessel, identifying the vascular abnormality range of each embolic vessel and the degree of vascular abnormality of each embolic vessel through an embolism image recognition strategy; based on the vascular abnormality range of each embolic vessel and the degree of vascular abnormality of each embolic vessel, identifying the pulmonary embolism probability of the patient, and generating a pulmonary embolism guidance report for the patient based on the vascular abnormality range of each embolic vessel, the degree of vascular abnormality of each embolic vessel, and the pulmonary embolism probability of the patient. This solution generates continuous image data of the patient's pulmonary artery through chest plain scan images collected at different time points and an image motion compensation strategy. This not only avoids the problem that blood clots and blockages are difficult to accurately identify in a single blood vessel scan image, but can also identify vascular change information in the patient's pulmonary artery through continuous image data, thereby effectively and accurately identifying changes in blood density and shape of the pulmonary artery. This solution then uses the identification results to analyze the vascular abnormality range of each embolic vessel in each blood vessel, as well as the degree of vascular abnormality of each embolic vessel, to comprehensively evaluate the patient's pulmonary embolism probability and generate a pulmonary embolism guidance report for the patient. This can not only accurately locate and identify the vascular abnormality range and degree of vascular thrombosis of the patient's different embolic vessels, but also guide medical staff to conduct a comprehensive analysis of the patient's pulmonary embolism condition, thereby comprehensively improving the accuracy of guiding medical staff in identifying pulmonary embolism in the patient. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] In order to more clearly illustrate the solutions in this application, a brief introduction will be given below to the drawings required for use in the description of the embodiments of this application. Obviously, the drawings described below are some embodiments of this application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0058] Figure 1 This is a flow chart of a pulmonary embolism guidance method based on chest CT plain scan images provided by an embodiment of the present invention;

[0059] Figure 2 2 is a schematic structural diagram of a pulmonary embolism guidance system based on chest CT plain scan images provided by an embodiment of the present invention;

[0060] Figure 3 This is a diagram of the internal structure of a computer device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0061] The pulmonary embolism guidance method based on chest CT plain scan images provided in an embodiment of the present invention is applied to a pulmonary embolism guidance system based on chest CT plain scan images. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly 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.

[0062] References herein to "embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute an independent or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0063] 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.

[0064] The pulmonary embolism guidance method based on chest CT plain scan images provided in the embodiments of the present application can be applied to a pulmonary embolism guidance application environment based on chest CT plain scan images. The method can be applied to a terminal, a server, or a system including a terminal and a server, and implemented through interaction between the terminal and the server. The terminal can be, but is not limited to, various personal computers, laptop computers, and the like. Among them, the terminal generates continuous image data of the patient's pulmonary artery through the chest plain scan images collected at different time points and the image motion compensation strategy. It not only avoids the problem that blood clots and blockages are difficult to accurately identify in the image of a single blood vessel scan, but can also identify the vascular change information in the patient's pulmonary artery through continuous image data, thereby effectively and accurately identifying the blood density changes and shape changes in the pulmonary artery. Then, this solution uses the identification results to analyze the vascular abnormality range of each embolic vessel in each blood vessel and the degree of vascular abnormality of each embolic vessel, thereby comprehensively evaluating the patient's pulmonary embolism probability and generating a pulmonary embolism guidance report for the patient. It can not only accurately locate and identify the vascular abnormality range and degree of vascular thrombosis of the patient's different embolic vessels, but also guide medical staff to conduct a comprehensive analysis of the patient's pulmonary embolism situation, thereby comprehensively improving the accuracy of guiding medical staff in identifying the patient's pulmonary embolism.

[0065] In one embodiment, Figure 1 As shown, a pulmonary embolism guidance method based on chest CT plain scan images is provided. The method is applied to a terminal as an example, and includes the following steps:

[0066] Step S101 : obtaining a chest plain scan image of a patient, and generating continuous image data of the patient's pulmonary artery based on the chest plain scan image by using an image motion compensation strategy.

[0067] In this embodiment, the terminal uses a CT plain scan strategy to perform plain scan processing on the patient's chest area to obtain a plain scan image of the patient's chest. The plain scan image includes sub-plain scan images corresponding to each frame, each sub-plain scan image being a plain scan image of the patient acquired at different times during the plain scan of the chest. The terminal then performs image motion compensation on the plain scan images at each time point and then performs continuous image generation processing to obtain continuous image data of the patient's pulmonary artery. The specific generation process will be described in detail later. The image motion compensation method is a motion compensation method corresponding to the technology for suppressing hilar pulsation artifacts.

[0068] In step S102, based on the continuous pulmonary artery image data, the shape distribution information of each blood vessel of the patient's pulmonary artery and the blood density distribution information of each blood vessel are identified through an image recognition model. Based on the shape distribution information of each blood vessel and the blood density distribution information of each blood vessel, the embolism image recognition strategy is used to identify the range of vascular abnormality and the degree of vascular abnormality of each embolized blood vessel.

[0069] In this embodiment, the terminal uses an image recognition model based on continuous pulmonary artery image data to identify the shape distribution information and blood density distribution information of each vessel in the patient's pulmonary artery. Based on this information, the terminal uses an embolism image recognition strategy to identify the range and degree of vascular abnormality in each embolic vessel. The image recognition model includes an image deformation recognition network for vessel shape recognition and a blood density recognition network for vessel blood density recognition. Both the image deformation recognition network and the blood density recognition network are convolutional neural networks based on an attention mechanism, trained using different sample data. The embolism image recognition strategy includes an image embolism recognition network, an embolism assessment network, and an embolism degree assessment network. The image embolism recognition network is a convolutional neural network based on deep learning, while the embolism assessment network and the embolism degree assessment network are neural networks trained using different training data and based on different evaluation indicators for embolism assessment and embolism degree assessment. The specific recognition process will be described in detail later.

[0070] Step S103, based on the range of vascular abnormalities of each embolic vessel and the degree of vascular abnormalities of each embolic vessel, the probability of pulmonary embolism of the patient is identified, and based on the range of vascular abnormalities of each embolic vessel, the degree of vascular abnormalities of each embolic vessel and the probability of pulmonary embolism of the patient, a pulmonary embolism guidance report is generated for the patient.

[0071] In this embodiment, the terminal identifies the patient's probability of pulmonary embolism based on the range and degree of vascular abnormality of each embolic vessel. Based on this, a pulmonary embolism guidance report is generated for the patient. The pulmonary embolism guidance report includes the patient's pulmonary embolism guidance information and a pulmonary embolism marking image. The pulmonary embolism marking image identifies the embolic areas and the corresponding embolism degree for each embolic area. The specific marking process will be described in detail later.

[0072] Based on the above scheme, by using the image motion compensation strategy for chest plain scan images collected at different time points, continuous image data of the patient's pulmonary artery is generated. This not only avoids the problem that blood clots and blockages are difficult to accurately identify in a single blood vessel scan image, but also can identify the vascular change information in the patient's pulmonary artery through continuous image data, thereby effectively and accurately identifying the blood density changes and shape changes in the pulmonary artery. Then, this scheme uses the identification results to analyze the vascular abnormality range of each embolic vessel in each blood vessel, as well as the degree of vascular abnormality of each embolic vessel, to comprehensively evaluate the patient's pulmonary embolism probability and generate a pulmonary embolism guidance report for the patient. It can not only accurately locate and identify the vascular abnormality range and degree of vascular thrombosis of the patient's different embolic vessels, but also guide medical staff to conduct a comprehensive analysis of the patient's pulmonary embolism condition, thereby comprehensively improving the accuracy of guiding medical staff in identifying the patient's pulmonary embolism.

[0073] Optionally, based on the chest plain scan image, continuous image data of the patient's pulmonary artery is generated through an image motion compensation strategy, including: based on the chest plain scan image, an actual chest plain scan image is generated through a strategy of suppressing hilar pulsation artifacts; identifying each lung image label contained in each sub-chest plain scan image in the actual chest plain scan image, and screening the sub-chest plain scan image containing the target lung image label as the target sub-chest plain scan image; the target lung image label is the pulmonary artery image label; sorting each target sub-chest plain scan image according to the time sequence of each target sub-chest plain scan image to obtain the patient's chest plain scan image sequence, and performing continuous image supplementation generation processing on the chest plain scan image sequence through a continuous animation generation program to obtain the patient's pulmonary artery continuous image data.

[0074] In this embodiment, the terminal generates an actual chest plain scan image at a time point based on the chest plain scan image by suppressing the hilar pulsation artifact strategy. Then, the terminal adds a lung image label to each sub-chest plain scan image in the actual chest plain scan image through the image recognition network. The lung image label includes a pulmonary artery label and a non-pulmonary artery label. Specifically, the terminal identifies the pulmonary artery image in each sub-chest plain scan image through the image recognition network, and adds a pulmonary artery label to the sub-chest plain scan image if a pulmonary artery image exists; and adds a non-pulmonary artery label to the sub-chest plain scan image if no pulmonary artery image exists. The lung image label can also be set by manual label addition by the staff. Then, the terminal screens the sub-chest plain scan image containing the pulmonary artery label as the target sub-chest plain scan image. The image recognition network is a convolutional neural network based on the attention mechanism.

[0075] The terminal sorts the sub-chest plain scan images according to the time sequence of each target sub-chest plain scan image to obtain a chest plain scan image sequence of the patient, and performs continuous image supplementation and generation processing on the chest plain scan image sequence using a continuous animation generation program to obtain continuous image data of the patient's pulmonary artery. The continuous animation generation program can perform image supplementation using an image continuous image generation program in a MATLAB program, and the supplemented continuous image data of the pulmonary artery is an image sequence obtained by arranging multiple continuous and smooth images.

[0076] Based on the above scheme, by suppressing the hilar pulsation artifact strategy, it is possible to restore true, pulsation-artifact-free plain scan images, thereby improving the sensitivity and reliability of pulmonary embolism detection. Finally, continuous pulmonary artery image data is regenerated, which improves the accuracy of identifying changes in embolism shape and blood density in each blood vessel.

[0077] Optionally, based on the continuous pulmonary artery imaging data, an image recognition model is used to identify the shape distribution information of each blood vessel of the patient's pulmonary artery and the blood density distribution information of each blood vessel, including: based on the continuous pulmonary artery imaging data, an image edge recognition algorithm is used to identify the continuous vascular imaging data of each blood vessel in the continuous pulmonary artery imaging data; for each blood vessel, based on the continuous vascular imaging data of the blood vessel, an image deformation recognition network of an image recognition model is used to identify the shape change information of each vascular part of the blood vessel, and according to the connection relationship between the vascular parts, the shape change information of each vascular part is spliced ​​to obtain the shape distribution information of the blood vessel; based on the continuous vascular imaging data of the blood vessel, an image density recognition network of an image recognition model is used to identify the blood density change information of each vascular part of the blood vessel, and according to the connection relationship between the vascular parts, the blood density change information of each vascular part is spliced ​​to obtain the blood density distribution information of the blood vessel.

[0078] In this embodiment, the terminal uses an image edge recognition algorithm based on the continuous pulmonary artery image data to identify continuous vascular image data of each blood vessel in the continuous pulmonary artery image data. The continuous vascular image data of each blood vessel is continuous image data of all portions of the blood vessel within the image area.

[0079] For each blood vessel, the terminal uses the image deformation recognition network of the image recognition model based on the continuous image data of the vessel to identify the shape change information of each vessel segment. Based on the connection relationship between the vessel segments, the terminal then splices the shape change information of each vessel segment to obtain the vessel shape distribution information. Each vessel segment is obtained by dividing the vessel into intervals of preset lengths, which can be, but is not limited to, 1 cm, 5 cm, 10 cm, etc.

[0080] The terminal identifies the blood density change information of each vascular part of the blood vessel based on the continuous vascular image data of the blood vessel through the blood density recognition network of the image recognition model, and splices the blood density change information of each vascular part according to the connection relationship between the vascular parts to obtain the blood density distribution information of the blood vessel.

[0081] Based on the above solution, by refining the shape changes of each blood vessel part and identifying the changes in blood density for each blood vessel, the comprehensiveness and accuracy of the recognition of the overall shape change distribution of the blood vessel and the blood density change distribution are improved.

[0082] Optionally, based on the shape distribution information of each blood vessel and the blood density distribution information of each blood vessel, an embolism image recognition strategy is used to identify the vascular abnormality range of each embolized blood vessel and the degree of vascular abnormality of each embolized blood vessel, including: based on the shape distribution information of each blood vessel, using an image embolism recognition network, identifying the shape change amplitude of each blood vessel portion of each blood vessel and the shape change speed of each blood vessel portion of each blood vessel, and based on the blood density distribution information of each blood vessel, using an image embolism recognition network, identifying the blood density change degree of each blood vessel portion of each blood vessel and the blood density change speed of each blood vessel portion of each blood vessel; based on the shape distribution information of each blood vessel, using an image embolism recognition network, identifying the shape change amplitude of each blood vessel portion of each blood vessel and the shape change speed of each blood vessel portion of each blood vessel; The shape change rate of each embolic vessel part and the blood density change rate of each vascular part of each blood vessel are used to identify the embolic vessel part in each blood vessel through the embolism evaluation network; the blood vessel with the embolic vessel part is regarded as the embolic vessel, and all the embolic vessel parts in each embolic vessel are regarded as the vascular abnormality range of each embolic vessel; for each embolic vessel, based on the shape change amplitude of each embolic vessel part of the embolic vessel and the degree of blood density change of each embolic vessel part of the embolic vessel, the sub-embolism degree of each embolic vessel part is identified through the embolism degree evaluation network, and the sub-embolism degree of all the embolic vessel parts is regarded as the vascular abnormality degree of the embolic vessel.

[0083] In this embodiment, based on the shape distribution information of each blood vessel, the terminal uses an image embolism recognition network to identify the shape change amplitude and shape change speed of each vessel portion of each blood vessel. Furthermore, based on the blood density distribution information of each blood vessel, the terminal uses an image embolism recognition network to identify the blood density change degree and blood density change speed of each vessel portion of each blood vessel. The shape change speed is the value of the shape increase, diameter increase, or width change per unit time period. This unit time period can be, but is not limited to, 1 day, 5 days, 1 week, 10 days, etc.

[0084] The terminal uses an embolism assessment network to identify embolic vessel portions within each blood vessel based on the shape change rate and blood density change rate of each vessel portion. The embolism assessment network includes embolism assessment values ​​corresponding to different shape change rate ranges and blood density change rate ranges. When the embolism assessment value exceeds an embolism assessment threshold, the vessel portion is considered embolic.

[0085] The terminal regards the blood vessel with the embolized vascular portion as the embolized vessel, and regards all the embolized vascular portions in each embolized vessel as the vascular abnormality range of each embolized vessel.

[0086] For each embolic vessel, the terminal uses an embolism degree assessment network to identify sub-embolism degrees for each embolic vessel segment based on the shape change amplitude and blood density change degree of each embolic vessel segment. These sub-embolism degrees for all embolic vessel segments are then used as the vascular abnormality degree of the embolic vessel. The embolism degree assessment network includes a correspondence / conversion algorithm between different embolism degrees and shape change amplitude and blood density change ranges. Using the trained embolism degree assessment network, the terminal identifies the vascular abnormality degree corresponding to the shape change amplitude and blood density change degree of each embolic vessel segment.

[0087] Based on the above scheme, the embolism range of the embolic blood vessels and the degree of vascular abnormality are totaled and analyzed by using different information such as different shape change speeds, blood density change speeds, shape change amplitudes, and blood density change degrees, thereby improving the accuracy and comprehensiveness of identifying the embolism range of the embolic blood vessels and the degree of vascular abnormality.

[0088] Optionally, based on the range of vascular abnormalities of each embolic vessel and the degree of vascular abnormalities of each embolic vessel, the probability of pulmonary embolism in the patient is identified, including: based on the range of vascular abnormalities of each embolic vessel and the degree of vascular embolism of each embolic vessel, performing embolism marking processing in the continuous imaging data of the pulmonary artery to obtain a pulmonary embolism marking image; based on the pulmonary embolism marking image, identifying the distribution information and degree distribution information of the patient's pulmonary embolism, and based on the pulmonary embolism degree distribution information, extracting characteristic data of each pulmonary embolism; based on the characteristic data of each pulmonary embolism, identifying the probability of pulmonary embolism in the patient.

[0089] In this embodiment, the terminal performs embolism marking processing on the pulmonary artery continuous image data based on the vascular abnormality range and the vascular thrombosis degree of each embolic vessel to obtain a pulmonary artery embolism marking image.

[0090] Then, based on the pulmonary embolism marker image, the terminal identifies the patient's pulmonary embolism distribution information and degree distribution information, and based on the pulmonary embolism degree distribution information, extracts the characteristic data of each pulmonary embolism. The pulmonary embolism characteristic data includes characteristic data of each pulmonary embolism type, and the pulmonary embolism type includes the range ratio value type of each pulmonary embolism degree, the ratio value type of embolized vessels, the ratio value type of embolized vessels within the embolism range, etc. Finally, based on each pulmonary embolism characteristic data, the terminal queries the patient's pulmonary embolism probability in the embolism database. The embolism database stores the correspondence between different pulmonary embolism probability values ​​and the characteristic data range of each pulmonary embolism type. The terminal identifies the patient's pulmonary embolism probability through the above correspondence.

[0091] Based on the above scheme, after marking the distribution of embolic blood vessels, the characteristic data of each pulmonary embolism type is identified, thereby identifying the patient's pulmonary embolism probability, thereby improving the accuracy and comprehensiveness of the identification of the patient's pulmonary embolism probability.

[0092] Optionally, a pulmonary embolism guidance report for the patient is generated based on the range of vascular abnormalities of each embolic vessel, the degree of vascular abnormalities of each embolic vessel, and the patient's pulmonary embolism probability, including: identifying the patient's pulmonary embolism distribution characteristics and the patient's pulmonary embolism range characteristics based on the pulmonary embolism marking image, and generating the patient's pulmonary embolism guidance information through a pulmonary embolism guidance template based on the patient's pulmonary embolism distribution characteristics, the patient's pulmonary embolism range characteristics, and the patient's pulmonary embolism probability; and using the patient's pulmonary embolism guidance information and the pulmonary embolism marking image as the patient's pulmonary embolism guidance report.

[0093] In this embodiment, the terminal identifies the patient's pulmonary embolism distribution characteristics and the patient's pulmonary embolism range characteristics based on the pulmonary embolism marking image, and based on the patient's pulmonary embolism distribution characteristics, the patient's pulmonary embolism range characteristics, and the patient's pulmonary embolism probability, generates the patient's pulmonary embolism guidance information through the pulmonary embolism guidance template. The pulmonary embolism guidance template includes filling positions for pulmonary embolism range characteristics and pulmonary embolism probability. The terminal directly fills the above data into the pulmonary embolism guidance template to obtain the patient's pulmonary embolism guidance information. The pulmonary embolism guidance template is manually designed by the staff and is suitable for use as a report template for guiding medical staff on pulmonary embolism conditions. Finally, the terminal fills the pulmonary embolism marking image into the pulmonary embolism image display area in the patient's pulmonary embolism guidance information to obtain the patient's pulmonary embolism guidance report.

[0094] Based on the above solution, a pulmonary embolism guidance report for the patient is generated from the pulmonary embolism image and the pulmonary embolism guidance template, thereby improving the accuracy and efficiency of guidance for medical staff.

[0095] It should be understood that, although the various steps in the flowcharts involved in the various embodiments described above are displayed in sequence according to the instructions of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowcharts involved in the various embodiments described above can include multiple steps or multiple stages, and these steps or stages are not necessarily executed and completed 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 portion of steps or stages in other steps.

[0096] Based on the same inventive concept, the embodiments of the present application also provide a pulmonary embolism guidance system based on chest CT plain scan images for implementing the above-mentioned pulmonary embolism guidance method based on chest CT plain scan images. The implementation solution provided by this system is similar to the implementation solution described in the above-mentioned method. Therefore, the specific limitations of one or more embodiments of the pulmonary embolism guidance system based on chest CT plain scan images provided below can be referred to the limitations of the pulmonary embolism guidance method based on chest CT plain scan images above, and will not be repeated here.

[0097] Further references Figure 2 , as a response to the above Figure 1 To implement the method shown, the present application provides an embodiment of a pulmonary embolism guidance system 200 based on chest CT plain scan images. The pulmonary embolism guidance system based on chest CT plain scan images includes an acquisition module 210, an identification module 220, and a generation module 230, wherein:

[0098] An acquisition module 210 is configured to acquire a chest plain scan image of the patient and generate continuous image data of the patient's pulmonary artery based on the chest plain scan image using an image motion compensation strategy;

[0099] an identification module 220 for identifying, based on the continuous pulmonary artery image data and using an image recognition model, shape distribution information of each blood vessel of the patient's pulmonary artery and blood density distribution information of each blood vessel, and identifying, based on the shape distribution information of each blood vessel and the blood density distribution information of each blood vessel, a range of vascular abnormality and a degree of vascular abnormality of each embolic vessel using an embolism image recognition strategy;

[0100] The generation module 230 is used to identify the probability of pulmonary embolism in the patient based on the range of vascular abnormalities of each embolic vessel and the degree of vascular abnormalities of each embolic vessel, and to generate a pulmonary embolism guidance report for the patient based on the range of vascular abnormalities of each embolic vessel, the degree of vascular abnormalities of each embolic vessel, and the probability of pulmonary embolism in the patient.

[0101] Optionally, the acquisition module 210 is specifically configured to:

[0102] Based on the chest plain scan image, the actual chest plain scan image is generated by suppressing the hilar pulsation artifact strategy;

[0103] Identifying each lung image label contained in each sub-chest plain scan image in the actual chest plain scan image, and selecting a sub-chest plain scan image containing a target lung image label as a target sub-chest plain scan image; the target lung image label is a pulmonary artery image label;

[0104] The target sub-chest plain scan images are sorted according to the time sequence of each target sub-chest plain scan image to obtain the patient's chest plain scan image sequence, and the chest plain scan image sequence is subjected to continuous image supplementation generation processing through a continuous animation generation program to obtain the patient's pulmonary artery continuous image data.

[0105] Optionally, the identification module 220 is specifically configured to:

[0106] Based on the pulmonary artery continuous image data, identifying the blood vessel continuous image data of each blood vessel in the pulmonary artery continuous image data by an image edge recognition algorithm;

[0107] For each blood vessel, based on the continuous blood vessel image data of the blood vessel, the image deformation recognition network of the image recognition model is used to identify the shape change information of each blood vessel portion, and the shape change information of each blood vessel portion is spliced ​​according to the connection relationship between the blood vessel portions to obtain the shape distribution information of the blood vessel;

[0108] Based on the continuous vascular image data of the blood vessel, the blood density change information of each vascular portion of the blood vessel is identified through the blood density recognition network of the image recognition model, and the blood density change information of each vascular portion is spliced ​​according to the connection relationship between the vascular portions to obtain the blood density distribution information of the blood vessel.

[0109] Optionally, the identification module 220 is specifically configured to:

[0110] Based on the shape distribution information of each of the blood vessels, identifying, by an image embolism recognition network, a shape change amplitude of each vascular portion of each blood vessel and a shape change speed of each vascular portion of each blood vessel; and based on the blood density distribution information of each of the blood vessels, identifying, by the image embolism recognition network, a blood density change degree of each vascular portion of each blood vessel and a blood density change speed of each vascular portion of each blood vessel;

[0111] identifying an embolic vessel portion in each blood vessel using an embolism evaluation network based on a shape change rate of each vessel portion of each blood vessel and a blood density change rate of each vessel portion of each blood vessel;

[0112] The blood vessels with embolized vascular parts are regarded as embolized vessels, and all embolized vascular parts in each embolized vessel are regarded as the vascular abnormality range of each embolized vessel;

[0113] For each embolic vessel, based on the shape change amplitude of each embolic vessel portion of the embolic vessel and the degree of blood density change of each embolic vessel portion of the embolic vessel, the embolism degree evaluation network is used to identify the sub-embolism degree of each embolic vessel portion, and the sub-embolism degree of all embolic vessel portions is used as the vascular abnormality degree of the embolic vessel.

[0114] Optionally, the generating module 230 is specifically configured to:

[0115] Based on the vascular abnormality range of each embolic vessel and the vascular thrombosis degree of each embolic vessel, performing embolism marking processing on the pulmonary artery continuous image data to obtain a pulmonary artery embolism marking image;

[0116] identifying the patient's pulmonary embolism distribution information and degree distribution information based on the pulmonary embolism marking image, and extracting characteristic data of each pulmonary embolism based on the pulmonary embolism degree distribution information;

[0117] Based on each of the pulmonary embolism feature data, the probability of pulmonary embolism in the patient is identified.

[0118] Optionally, the generating module 230 is specifically configured to:

[0119] identifying, based on the pulmonary embolism marking image, pulmonary embolism distribution characteristics and pulmonary embolism range characteristics of the patient, and generating, based on the pulmonary embolism distribution characteristics, pulmonary embolism range characteristics, and pulmonary embolism probability of the patient, pulmonary embolism guidance information for the patient using a pulmonary embolism guidance template;

[0120] The patient's pulmonary embolism guidance information and the pulmonary embolism marking image are used as the patient's pulmonary embolism guidance report.

[0121] Each module in the aforementioned chest CT plain scan-based pulmonary embolism guidance system can be implemented in whole or in part through software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in the computer device in the form of software, so that the processor can call and execute the corresponding operations of each module.

[0122] 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 via a system bus. 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, a pulmonary embolism guidance method based on chest CT plain scan images 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 covering the display screen, or a button, trackball or touchpad provided on the computer device housing, or an external keyboard, touchpad or mouse.

[0123] Those skilled in the art will understand that Figure 3 The 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 shown in the figure, or combine certain components, or have a different component arrangement.

[0124] In one embodiment, a computer device is provided, comprising 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.

[0125] 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.

[0126] In one embodiment, a computer program product is provided, comprising a computer program, which implements the steps of any one of the methods of the first aspect when executed by a processor.

[0127] It should be noted that the patient information (including but not limited to patient device information, patient 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 patient or fully authorized by all parties.

[0128] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiment methods can be implemented 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 memory, database or other media used in the embodiments provided in this application may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory may include random access memory (RAM) or external cache memory, etc. By way of 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 the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processor involved in the various embodiments provided herein may be, but are not limited to, a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic unit, a data processing logic unit based on quantum computing, and the like.

[0129] The technical features of the above embodiments can be combined arbitrarily. 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.

[0130] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present application. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present application, and these modifications and improvements fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. A pulmonary embolism guidance method based on chest CT plain scan images, characterized in that: The method comprises: Obtaining a chest plain scan image of the patient, and generating continuous image data of the patient's pulmonary artery based on the chest plain scan image by using an image motion compensation strategy; Based on the continuous pulmonary artery image data, the image recognition model is used to identify shape distribution information of each blood vessel of the patient's pulmonary artery and blood density distribution information of each blood vessel, and based on the shape distribution information of each blood vessel and the blood density distribution information of each blood vessel, the embolism image recognition strategy is used to identify the range of vascular abnormality and the degree of vascular abnormality of each embolized blood vessel; Based on the range of vascular abnormalities of each of the embolic vessels and the degree of vascular abnormalities of each of the embolic vessels, the probability of pulmonary embolism in the patient is identified, and based on the range of vascular abnormalities of each of the embolic vessels, the degree of vascular abnormalities of each of the embolic vessels and the probability of pulmonary embolism in the patient, a pulmonary embolism guidance report is generated for the patient.

2. The method according to claim 1, characterized in that The method of generating continuous pulmonary artery image data of the patient based on chest plain scan images by image motion compensation strategy includes: Based on the chest plain scan image, the actual chest plain scan image is generated by suppressing the hilar pulsation artifact strategy; Identifying each lung image label contained in each sub-chest plain scan image in the actual chest plain scan image, and selecting a sub-chest plain scan image containing a target lung image label as a target sub-chest plain scan image; the target lung image label is a pulmonary artery image label; The target sub-chest plain scan images are sorted according to the time sequence of each target sub-chest plain scan image to obtain the patient's chest plain scan image sequence, and the chest plain scan image sequence is subjected to continuous image supplementation generation processing through a continuous animation generation program to obtain the patient's pulmonary artery continuous image data.

3. The method according to claim 1, characterized in that The identifying, based on the pulmonary artery continuous image data, shape distribution information of each blood vessel of the patient's pulmonary artery and blood density distribution information of each blood vessel by an image recognition model includes: Based on the pulmonary artery continuous image data, identifying the blood vessel continuous image data of each blood vessel in the pulmonary artery continuous image data by an image edge recognition algorithm; For each blood vessel, based on the continuous blood vessel image data of the blood vessel, the image deformation recognition network of the image recognition model is used to identify the shape change information of each blood vessel portion, and the shape change information of each blood vessel portion is spliced ​​according to the connection relationship between the blood vessel portions to obtain the shape distribution information of the blood vessel; Based on the continuous vascular image data of the blood vessel, the blood density change information of each vascular portion of the blood vessel is identified through the blood density recognition network of the image recognition model, and the blood density change information of each vascular portion is spliced ​​according to the connection relationship between the vascular portions to obtain the blood density distribution information of the blood vessel.

4. The method according to claim 1, wherein The method of identifying the abnormal range and degree of abnormality of each embolic vessel by using an embolic image recognition strategy based on the shape distribution information of each blood vessel and the blood density distribution information of each blood vessel includes: Based on the shape distribution information of each of the blood vessels, identifying, by an image embolism recognition network, a shape change amplitude of each vascular portion of each blood vessel and a shape change speed of each vascular portion of each blood vessel; and based on the blood density distribution information of each of the blood vessels, identifying, by the image embolism recognition network, a blood density change degree of each vascular portion of each blood vessel and a blood density change speed of each vascular portion of each blood vessel; identifying an embolic vessel portion in each blood vessel using an embolism evaluation network based on a shape change rate of each vessel portion of each blood vessel and a blood density change rate of each vessel portion of each blood vessel; The blood vessels with embolized vascular parts are regarded as embolized vessels, and all embolized vascular parts in each embolized vessel are regarded as the vascular abnormality range of each embolized vessel; For each embolic vessel, based on the shape change amplitude of each embolic vessel portion of the embolic vessel and the degree of blood density change of each embolic vessel portion of the embolic vessel, the embolism degree evaluation network is used to identify the sub-embolism degree of each embolic vessel portion, and the sub-embolism degree of all embolic vessel portions is used as the vascular abnormality degree of the embolic vessel.

5. The method according to claim 1, wherein The identifying the probability of pulmonary embolism in the patient based on the range of vascular abnormality and the degree of vascular abnormality of each embolic vessel includes: Based on the vascular abnormality range of each embolic vessel and the vascular thrombosis degree of each embolic vessel, performing embolism marking processing on the pulmonary artery continuous image data to obtain a pulmonary artery embolism marking image; identifying the patient's pulmonary embolism distribution information and degree distribution information based on the pulmonary embolism marking image, and extracting characteristic data of each pulmonary embolism based on the pulmonary embolism degree distribution information; Based on each of the pulmonary embolism feature data, the probability of pulmonary embolism in the patient is identified.

6. The method according to claim 5, characterized in that Generating a pulmonary embolism guidance report for the patient based on the range of vascular abnormality of each embolic vessel, the degree of vascular abnormality of each embolic vessel, and the probability of pulmonary embolism of the patient includes: identifying, based on the pulmonary embolism marking image, pulmonary embolism distribution characteristics and pulmonary embolism range characteristics of the patient, and generating, based on the pulmonary embolism distribution characteristics, pulmonary embolism range characteristics, and pulmonary embolism probability of the patient, pulmonary embolism guidance information for the patient using a pulmonary embolism guidance template; The patient's pulmonary embolism guidance information and the pulmonary embolism marking image are used as the patient's pulmonary embolism guidance report.

7. A pulmonary embolism guidance system based on chest CT plain scan images, characterized in that: The system comprises: An acquisition module is used to acquire a chest plain scan image of the patient and generate continuous image data of the patient's pulmonary artery based on the chest plain scan image by using an image motion compensation strategy; an identification module configured to identify, based on the continuous pulmonary artery image data and using an image recognition model, shape distribution information of each blood vessel of the patient's pulmonary artery and blood density distribution information of each blood vessel, and to identify, based on the shape distribution information of each blood vessel and the blood density distribution information of each blood vessel and using an embolism image identification strategy, a range of vascular abnormality and a degree of vascular abnormality of each embolized blood vessel; A generation module is used to identify the patient's probability of pulmonary embolism based on the vascular abnormality range of each embolic vessel and the degree of vascular abnormality of each embolic vessel, and to generate a pulmonary embolism guidance report for the patient based on the vascular abnormality range of each embolic vessel, the degree of vascular abnormality of each embolic vessel, and the patient's probability of pulmonary embolism.

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