170 results about "Vessel segmentation" patented technology

The invention discloses a three-dimensional blood vessel image segmentation method and system. Belongs to the technical field of medical image processing and particularly relates to the technical field of three-dimensional blood vessel image segmentation. The method solves the following problems existing in a blood vessel segmentation task in an existing method: small blood vessel features are difficult to accurately extract in a CTA image which is low in contrast and contains noise and artifacts; global context modeling is difficult to consider and local correlation is difficult to guarantee, so that long-distance dependent modeling is insufficient or a local structure is fractured; limited by a fixed geometrical shape of a traditional convolution kernel, the traditional convolution kernel is difficult to adapt to deformation characteristics of a complex topological structure of a blood vessel, resulting in discontinuous segmentation or fuzzy boundary of a branch region. Channel dynamic grouping and energy-driven attention generation are achieved through a grouping self-adaptive attention module, and self-adaptive modeling of a blood vessel complex branch structure and a geometrical shape is achieved through a multi-scale space structure aggregation module in combination with a strip-shaped deformable convolution and cross-scale guiding mechanism.

A system for hypertensive retinopathy (HTNR) detection includes a processor and a memory, including instructions stored thereon, which when executed by the processor, cause the system to: preprocess a retinal image using contrast enhancement, noise reduction and / or resolution normalization; segment a plurality of vessels from the preprocessed retinal image to generate a vessel segmentation map; detect a retinal marker, a vascular marker and / or an optic disc marker in the preprocessed retinal image using a first machine learning model; generate a severity score based on the detections; determine that the severity score exceeds a predefined threshold; and generate an output indicating a presence of HTNR based on the vessel segmentation map and the severity score using a second machine learning model.

The invention discloses a blood vessel OCT image training method, a blood vessel OCT image generating method and a blood vessel OCT image training device based on a DCN cross-modal fusion network and structure-blood flow coupling modeling. The method comprises the following steps: acquiring image data marked with a blood vessel segmentation result and a plaque position; acquiring the preprocessed OCT image data; registering the image data marked with the blood vessel segmentation result and the plaque position and the OCT image data so as to obtain registered image data; acquiring hemodynamic parameters; inputting the coronary artery CTA image, the image marked with the blood vessel segmentation result and the plaque position and hemodynamic parameters into a cross-modal fusion network based on deformable convolution so as to obtain CTA features of the cross-modal fusion network; and inputting the CTA features of the cross-modal fusion network into a trained OCT generation network so as to obtain a cross-section OCT image containing blood vessel wall and plaque information. The method can replace part of invasive OCT examination, assist doctors in assessing plaque vulnerability and guide interventional therapy.

The invention discloses a medical image optimization method and system based on vascular branch selective blurring. The method comprises the following steps: carrying out preprocessing and blood vessel enhancement on a three-dimensional angiography DICOM image; performing precise blood vessel segmentation by using an encoder-decoder network comprising a wide activation and residual cavity space pyramid module; identifying an interference branch which shields the target blood vessel structure at a specific working angle through blood vessel topology analysis; selective blurring repair is performed on the interference branches based on a Poisson equation and a bidirectional convolution LSTM to generate an optimized image which is visually unobstructed and keeps topological continuity. And a safety mechanism of virtual-real combined display and multi-angle plan planning is introduced, so that the reliability of surgical navigation is ensured. And finally, integrating the optimized 3D blood vessel model to a radiography system supporting real-time synchronization, and using the 3D blood vessel model as a road map. The clinical problem that the optimal working angle cannot be used due to blood vessel shielding can be effectively solved, and the precision and safety of an endovascular interventional operation are remarkably improved.

The embodiment of the invention provides a cross-domain generalization model training method, a blood vessel segmentation method, computing equipment, a computer readable storage medium and a computer program product. The cross-domain generalization model training method comprises the steps that source domain image data, label data corresponding to the source domain image data and target domain image data are acquired; respectively inputting the source domain image data and the target domain image data into a blood vessel segmentation model to obtain a source domain segmentation result and a target domain segmentation result; inputting the source domain segmentation result and the target domain segmentation result into a discriminator to generate a discrimination result; constructing a first loss function and a second loss function; and by taking minimization of the first loss function and simultaneous maximization and minimization of the second loss function as optimization objectives, iteratively adjusting network parameters of the blood vessel segmentation model and network parameters of the discriminator to obtain a trained generalized blood vessel segmentation model. According to the technical scheme provided by the embodiment of the invention, the blood vessel automatic segmentation precision and the cross-domain adaptive capacity are improved.

The invention provides a DSA-oriented X-ray coronary angiography image blood vessel segmentation method and system, and relates to the technical field of image processing and deep learning. The method comprises the following steps: firstly, acquiring a target segmentation image and a reference image based on X-ray coronary artery angiography video data, and forming a training sample by the reference image and the target segmentation image to construct a training data set; then constructing a segmentation network model; the segmentation network model comprises a main encoder, an auxiliary encoder, a plurality of up-sampling attention modules, a similarity attention module and a decoder; calculating a total loss function by using the segmentation mask of the target segmentation image, and optimizing the segmentation network model; and finally, inputting an X-ray coronary artery angiography image data set needing to be segmented into the trained segmentation network model to obtain a segmentation result. According to the method, an X-ray perspective image before radiography is compared with a target segmentation image, so that a neural network is helped to distinguish a foreground from a background, and blood vessels are accurately recognized.

The invention relates to the technical field of blood vessel image segmentation, and provides a fundus blood vessel image accurate segmentation method based on a U-Net model, aiming at solving the problem that the existing blood vessel segmentation method based on deep learning is difficult to effectively balance global context and local details. In order to solve the problem of inaccurate blood vessel structure segmentation caused by factors such as poor image quality and low contrast ratio, a method of combining a wavelet and a visual state space model and an adaptive dynamic fusion module is provided to improve the integrity of a slender blood vessel and the structural segmentation accuracy of a complex blood vessel network in a fundus blood vessel image. By integrating multiple efficient feature extraction mechanisms, accurate recognition of small blood vessels and the whole blood vessel structure is achieved, the accuracy and robustness of blood vessel segmentation in complex medical images are remarkably improved, and the method can be widely applied to analysis of eye blood vessels such as retinopathy and hypertensive fundus lesion and research of biomarkers related to the blood vessels.

The invention provides a coronary angiography tree structure, a central line path extraction method, a central line path extraction device, equipment and a medium. The method comprises the following steps: acquiring a coronary angiography image; the coronary angiography image is input to a feature extraction module based on a Vision Transform architecture, and the feature extraction module is used for extracting the coronary angiography image; a feature extraction module based on a Vision Transform architecture is used for extracting multi-scale features; inputting the multi-scale features into an image segmentation decoder and a key point extraction decoder to generate a blood vessel segmentation result and key point coordinates; wherein the key point coordinates comprise a starting point coordinate and an end point coordinate on the path; fusing the key point coordinates, the blood vessel segmentation result and the coronary angiography image to serve as target input information; a center line path is extracted according to the target input information on the basis of a path generation algorithm of Vision Transform; and fusing the center line paths to form a coronary artery tree structure and a path map thereof.

The application provides a blood vessel classification method and device, electronic equipment, medium and computer program product. The method comprises the following steps: obtaining a blood vessel segmentation result image to be processed, and the blood vessels in the blood vessel segmentation result image correspond to predicted blood vessel categories; center line extraction is performed on the blood vessels in the blood vessel segmentation result image to obtain blood vessel center lines, and an initial blood vessel tree is generated based on the blood vessel center lines; the initial blood vessel tree is converted into an undirected graph, and the undirected graph is split according to the predicted blood vessel categories to obtain a plurality of undirected subgraphs; target blood vessel trees corresponding to the undirected subgraphs are obtained based on the initial blood vessel tree, and target blood vessel categories corresponding to the blood vessels in the blood vessel segmentation result image are determined based on the target blood vessel trees. The application classifies the blood vessels in the blood vessel segmentation result image in detail with the aid of the predicted blood vessel categories, can correct the wrong classification in the original prediction, and improves the accuracy of blood vessel classification.

The invention generally provides systems and methods for performing vessel segmentation from flow data, such as but not limited to 4D flow Magnetic Resonance Imaging (MRI) data. In certain aspects, the systems and methods of the invention may involve receiving flow data representative of flow in a vessel (such as 4D MRI flow data); identifying net flow effects in the flow data (such as 4D MRI flow data) according to a standardized difference of means (SDM) velocity that involves quantifying a ratio between net flow and observed flow pulsatility in each voxel of the received flow data (such as 4D MRI flow data); and identifying voxels with higher SDM velocity values than stationary tissue voxels, thereby performing vessel segmentation from flow data (such as 4D MRI flow data).

The invention relates to the field of fundus photograph enhancement and segmentation, and provides a fundus photograph enhancement segmentation method and device based on Diffusion, and the method comprises the steps: obtaining a fundus photograph, inputting the fundus photograph into a pre-trained Diffusion-based combined image enhancement segmentation model, and obtaining a fundus photograph enhancement image and a fundus photograph retinal blood vessel segmentation image; the model comprises a Diffusion-based image enhancement branch, an image segmentation branch and a symbiotic information interaction module, and the symbiotic information interaction module is used for realizing information flow between the image enhancement branch and the image segmentation branch, so that the image enhancement branch generates a fundus color photograph enhancement image based on a fundus color photograph and information from the image segmentation branch. Meanwhile, the image segmentation branch generates a fundus color photoretinal blood vessel segmentation image based on the fundus color photograph and information from the image enhancement branch. According to the invention, the understanding and analysis of the model on the image can be improved, and accurate blood vessel segmentation is provided while the image quality is improved.

The application discloses a blood flow reserve fraction determination method, device, system and storage medium. The method comprises the following steps: acquiring an initial blood vessel image, inputting the initial blood vessel image into a pre-trained blood vessel segmentation model to obtain a first blood vessel segmentation model; determining a stenosis region of the first blood vessel segmentation model, performing a de-stenosis processing on the stenosis region of the first blood vessel segmentation model to obtain a second blood vessel segmentation model; acquiring flow data of the stenosis region of the first blood vessel segmentation model and flow data of a de-stenosis region of the second blood vessel segmentation model; and determining a blood flow reserve fraction based on the flow data of the stenosis region of the first blood vessel segmentation model and the flow data of the de-stenosis region of the second blood vessel segmentation model. The technical solution can effectively reduce the error of the determined blood flow reserve fraction by determining the blood flow reserve fraction based on the flow data of the stenosis region of the first blood vessel segmentation model and the flow data of the de-stenosis region of the second blood vessel segmentation model.

The present application belongs to the field of medical image segmentation, and particularly relates to a retinal blood vessel image segmentation method. In view of the problems of low segmentation accuracy, insufficient segmentation ability of small blood vessels at the edge of eyeball, fracture at the blood vessel branch, and excessive interference of image noise in the existing retinal blood vessel image segmentation, the method comprises the steps of retinal image preprocessing and establishment of a retinal blood vessel segmentation model, wherein the preprocessing comprises converting a color retinal image into a gray image by giving different weights to the RGB three channels of the color retinal image; using a normalized and contrast-limited adaptive histogram equalization method to improve the image; using a local adaptive gamma change algorithm to adjust the retinal image; using translation, rotation, and noise increase to expand the data set; and the model establishment comprises feature extraction, feature fusion, and retinal blood vessel image segmentation.

The embodiment of the invention provides a blood vessel segmentation method, computing equipment, a computer storage medium and a computer program product. The blood vessel segmentation method comprises the following steps: acquiring original medical image data containing blood vessels; performing feature extraction on the original medical image data to generate image feature data; based on the image feature data, modifying a pixel intensity value of a pixel in the original medical image data to obtain first medical image data; performing edge detection on the first medical image data to obtain edge information of the blood vessel, and generating second medical image data containing a blood vessel boundary mask; and based on the blood vessel boundary mask, performing blood vessel segmentation on the second medical image data to obtain a target blood vessel image. The technical scheme provided by the embodiment of the invention can improve the accuracy of blood vessel segmentation.

The invention discloses a method, device and equipment for repairing a blood vessel fracture in a CAT blood vessel segmentation image. The method comprises the following steps: acquiring the CAT blood vessel segmentation image and two connection points of a marked fractured blood vessel; performing connected domain analysis on the CAT blood vessel segmentation image, separating at least one component image, and determining a target component image where two connection points are located; extracting a skeleton of the target component image to obtain skeleton points on a blood vessel center line, and constructing a blood vessel skeleton mapping a blood vessel center line structure based on the skeleton points; determining a blood vessel fracture type according to the target component image, and searching a fractured blood vessel starting point corresponding to each connection point by adopting a corresponding starting point searching strategy; and tracking the center line of the target blood vessel based on the searched starting point of the fractured blood vessel, and imaging the fractured blood vessel based on the tracked center line of the target blood vessel. Therefore, the problems that an existing blood vessel fracture connection method is low in calculation efficiency and cannot adaptively select a proper operation method according to the specific blood vessel form are solved.

The invention provides an angiography image segmentation method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining an initial angiography image which comprises a to-be-segmented blood vessel structure region; based on a preset blood vessel response function, performing enhancement processing on a blood vessel structure region contained in the initial angiography image to obtain an enhanced angiography image; segmenting the enhanced angiography image through the target segmentation model to obtain an initial blood vessel structure region corresponding to the enhanced angiography image, the initial blood vessel structure region including a blood vessel center line; and performing expansion processing on the blood vessel center line based on the initial blood vessel structure region to obtain a blood vessel segmentation result. According to the embodiment provided by the scheme, the accuracy and reliability of angiography image segmentation can be improved.

A lightweight 3D attention-based dual-path U-Net segmentation method for lung CT vessels, belonging to the field of medical image processing technology, solves the problems of low accuracy and poor segmentation of small vessels due to loss of key information when using existing techniques for vessel segmentation. The key technical points of this invention are: acquiring the image to be segmented, labeling and preprocessing the image, extracting the largest connected region of the image, constructing a DS-ResUNet network, training the DS-ResUNet network, inputting the image into the trained DS-ResUNet network, and outputting a predicted image, which is the result of dual-path U-Net segmentation of lung CT vessels. This invention is applicable to the segmentation of lung CT vessels.

The invention relates to the field of retinal arteriovenous blood vessel image segmentation, and provides a retinal arteriovenous blood vessel image segmentation method and device, and the method comprises the steps: obtaining a to-be-segmented fundus color photo; inputting the fundus color photo into the trained retina artery and vein segmentation model to obtain corresponding artery and vein segmentation maps; wherein the retina arteriovenous blood vessel segmentation model comprises a feature extraction module, a feature fusion module and a result generation module; the feature extraction module is used for extracting global features, local features and frequency features of the input image; the feature fusion module is used for fusing the global features and the local features into multi-scale features and fusing the local features and the frequency features into multi-dimensional features; and the result generation module is used for generating artery and vein segmentation maps according to the multi-scale features and the multi-dimensional features. According to the invention, the detail part of the segmentation result is more complete and real, the segmentation accuracy of the vascular structure can be improved, and the segmentation result is more reasonable in topology.

The invention relates to the technical field of medical image processing, in particular to a digital ophthalmology virtual intelligent doctor system based on artificial intelligence, and the system comprises an image obtaining module which is used for obtaining and preprocessing a fundus image to form a standardized image; the blood vessel segmentation module is used for extracting a blood vessel network, constructing a blood vessel topological map and recording blood vessel branch and path information; the micro-hemorrhage candidate generation module is used for screening red spots and performing path matching in combination with vascular topology to form candidate spots; the staged reasoning module is used for roughly scanning and finely classifying the candidate spots to generate micro bleeding points; the historical image management module is used for comparing the candidate points with historical images of the patient, marking new or changing spots and forming priority information; and the output and feedback module is used for generating a detection result according to the candidate micro bleeding points and the priority information. Automatic identification and sorting of the micro bleeding points are realized, and the screening efficiency and reliability are improved.

The invention discloses a method for blood vessel segmentation, feature value extraction and data integration based on V-net, and relates to the technical field of medical image analysis. Comprising the steps that S1, a CT image of a patient is acquired and preprocessed; s2, constructing and training a V-net neural network, inputting the preprocessed CT image into the trained V-net neural network, and reconstructing a blood vessel model; s3, feature value extraction is carried out on the blood vessel model. By constructing and training the V-net neural network, the blood vessels in the patient's abdomen CT medical image are segmented and reconstructed to obtain portal vein, hepatic artery, aorta and other blood vessel models with good segmentation effects, and feature values of the blood vessel models are extracted and data are standardized through an algorithm, so that the accuracy of the blood vessel models is improved. Therefore, the CT image information can show the blood vessel form and the characteristic value in a model and datamation form, and the concerned blood vessel characteristic information can be obtained from the complex CT image.

The application discloses an imaging system and method for cardiovascular and cerebrovascular detection, and relates to the technical field of medical image processing.The system comprises the following steps: monitoring the physiological state of a patient and recording the medical history of the patient to form initial data; transmitting the initial data to a Hadoop data processing platform to perform standardization processing on the data; generating a data set; importing the data set into a random forest algorithm model to select an imaging mode; and performing pre-scanning on the data set based on the selected imaging mode.The application integrates wearable device data acquisition, Hadoop data processing, random forest imaging mode selection, deep learning automatic segmentation and feature extraction, and isolated forest anomaly detection, and solves the problem of insufficient accuracy of blood vessel segmentation and feature extraction.

The invention provides an unmarked photoacoustic microscopy blood flow direction and speed combined measurement method based on space-time cross correlation, which comprises the following steps: acquiring a two-dimensional structure image of a target tissue through a photoacoustic microscopy imaging platform, and carrying out image preprocessing and blood vessel enhancement on the two-dimensional structure image to obtain an enhanced tubular region; based on the enhanced tubular region, performing blood vessel segmentation, morphological optimization, center line extraction and direction calculation to obtain blood vessel direction information; path planning, scanning point sequence optimization and time sequence synchronization are carried out based on the blood vessel direction information, and a directional scanning path is obtained; a photoacoustic signal sequence is collected in the blood vessel direction, and space-time cross-correlation analysis is carried out; the blood flow direction and the blood flow speed are quantitatively calculated and visually displayed. According to the method, structural information guidance can be combined, rapid scanning in the blood vessel direction can be achieved, directional blood flow analysis is achieved through space-time cross-correlation, and the measuring speed and precision are remarkably improved.

Some embodiments of the disclosure provide a measuring method and measuring apparatus of a blood vessel diameter of a fundus image. In some examples, the measuring method include the following steps: acquiring a fundus image, generating a blood vessel segmentation image based on the fundus image, performing resolution enhancement on the blood vessel segmentation image, extracting blood vessel skeletons from the enhanced blood vessel segmentation image and performing fitting on the blood vessel skeletons to obtain a continuous blood vessel skeleton and a vessel diameter measurement direction of measurement pixel points, generating a blood vessel contour corresponding to the measurement pixel points based on the enhanced blood vessel segmentation image, and calculating a blood vessel diameter corresponding to the measurement pixel points based on a number of blood vessel pixel points in the blood vessel contour.

The invention relates to the field of medical images, and discloses a blood vessel segmentation method based on a medical image, and the method comprises the steps: carrying out the preliminary blood vessel segmentation of a three-dimensional medical image through a segmentation model, and generating a preliminary blood vessel segmentation result; positioning the blood vessel according to the preliminary blood vessel segmentation result to generate a first graph structure; encoding the first graph structure by using a double-flow encoder based on a graph channel attention network and a graph space attention network, and outputting a result to a double-flow decoder based on the graph channel attention network and the graph space attention network through a graph convolutional network for decoding to obtain a second graph structure; the graph channel attention network pays attention to mutual influence between node feature channels in the graph structure, and the graph space attention network pays attention to node information and a relation thereof in a space channel of the graph structure; and generating an updated blood vessel segmentation result according to the second graph structure. According to the invention, high-difficulty blood vessels can be detected more accurately, and the feature expression ability of the network is enhanced.

The invention discloses a bifocal rectal vessel image segmentation method and device. The method comprises the following steps: obtaining an infrared video and a visible light video of the same rectal vessel region, and extracting an image pair; registering each image pair, and fusing the registered image pair with cross-modal features; segmenting and labeling the blood vessels in the fused image based on a blood vessel segmentation matrix VesselMat; training a segmentation model CLIP-VIS based on the fused image, the corresponding labeling information and a blood vessel segmentation mask result; and carrying out mask refining and instance tracking processing on the blood vessel bounding box coordinates, the blood vessel category prediction result and the blood vessel instance mask output by the fused image and the separation model. According to the method, complementary advantages of different imaging modes are fully utilized through multi-light-source information fusion, pixel-level accurate segmentation of the rectal blood vessel is realized by using CLIP-VIS, and the problem that the blood vessel segmentation precision and integrity are insufficient under a complex background is effectively solved.

The application provides a blood vessel center line extraction method and device, a blood vessel straightening method and device, an electronic device and a computer readable storage medium, and relates to the field of medical image processing. The method comprises the following steps: determining the blood vessel segmentation data, the blood vessel skeleton and the region CTA image of each target blood vessel region based on the head and neck CTA image and the blood vessel segmentation data of the head and neck CTA image; for each target blood vessel region in the plurality of target blood vessel regions, determining the optimal path between the starting point and the ending point of the blood vessel skeleton based on the CT value of the pixel in the region CTA image of the target blood vessel region and the blood vessel segmentation data of the target blood vessel region; determining the center line of the target blood vessel region based on the optimal path to obtain the center line corresponding to the target blood vessel region; and fusing the blood vessel skeleton of the target blood vessel region and the center line corresponding to the target blood vessel region to obtain the blood vessel center line corresponding to the target blood vessel region. The method can effectively alleviate the center line deviation problem, so that a more accurate blood vessel center line is obtained.

The invention discloses an eye fundus image blood vessel segmentation method and system based on deep learning, and relates to the field of image processing, and the method comprises a receiving module which is used for receiving an original eye fundus image, carrying out the noise reduction, contrast adjustment and size normalization preprocessing of the image, and outputting standardized eye fundus image data; the segmentation module is used for performing blood vessel region pixel-level segmentation on the standardized fundus image based on a blood vessel feature recognition network constructed by deep learning and outputting an initial blood vessel segmentation image; according to the method, targeted preprocessing is carried out on the original fundus image, a filtering window can be dynamically optimized, the contrast ratio can be accurately adjusted, the image quality is effectively improved, a foundation is laid for subsequent blood vessel segmentation, and based on the blood vessel feature recognition network constructed based on deep learning, multi-scale feature extraction and cross-layer complementary fusion are carried out. And a pixel-level segmentation result is recovered in combination with transposed convolution, so that the blood vessel segmentation accuracy is greatly improved.

The invention discloses an eye fundus image retina thickness prediction method and system based on a depth estimation network. According to the retina thickness prediction method, a final retina thickness map is predicted by processing an eye fundus image through a constructed retina thickness prediction model. The retina thickness prediction model is designed based on a U-Net structure, a residual structure, a convolution block attention module and a blood vessel guiding attention mechanism are introduced into an encoder for feature extraction, and blood vessel mask information is fully utilized; meanwhile, a blood vessel segmentation network, a global thickness prediction branch and a blood vessel residual error correction branch are arranged in a decoder, wherein the global thickness prediction branch and the blood vessel residual error correction branch are parallel; the blood vessel segmentation network is used for carrying out information extraction on the eye fundus image and embedding the extracted information into a blood vessel residual error correction branch; the global thickness prediction branch is responsible for generating a basic global thickness map, and the blood vessel residual correction branch is used for locally correcting the global thickness map to obtain the final predicted retina thickness.

The invention provides a method and a device for planning an electrode implantation point during brain surface pulsation, and a storage medium. The method comprises the following steps: acquiring continuous multi-frame blood vessel images which are acquired in real time according to a time sequence during brain surface pulsation; processing a target blood vessel image in the continuous multi-frame blood vessel images to obtain a blood vessel segmentation map; determining at least one target implantation point on the blood vessel segmentation map according to the dispersion arrangement rule of the implantation points, and generating a tracking image containing the target implantation point; determining real-time tracking trajectory data of the target implantation point based on the tracking image and the continuous multi-frame blood vessel image; based on the real-time tracking trajectory data, determining a real-time pulse period of the brain blood vessel of the implantation area and a prediction trajectory result of the target implantation point; and planning an implantation strategy of the electrode according to the real-time pulsation period and the predicted trajectory result. According to the method, the implantation strategy of the electrode can be planned in real time, so that the implantation accuracy and safety of the electrode can be ensured according to the real-time condition of the patient in the operation process.

Embodiments of the present application disclose a blood vessel segmentation method and device, a medical imaging device and a storage medium. The method comprises: acquiring a blood vessel image to be segmented and a blood vessel distribution map corresponding to the blood vessel image to be segmented; inputting the blood vessel image to be segmented and the blood vessel distribution map into a preset blood vessel segmentation model to obtain a blood vessel segmentation result. The above technical solution solves the problem that the blood vessel segmentation method in the prior art is not applicable to the segmentation of relatively complex blood vessel images such as coronary images, and improves the blood vessel segmentation precision.