61 results about "Vascular segmentation" patented technology

The invention discloses a coronary angiography image blood vessel segmentation system based on multi-scale feature fusion. According to the invention, through the innovative design of the adaptive morphological sensing module, the system can dynamically analyze the anatomical structure characteristics of the blood vessel: the differentiable morphological operation layer converts the corrosion expansion operation into a learnable feature extraction process, so that the network can autonomously identify the gradient change and boundary trend of the blood vessel wall; the dynamic nuclear adaptation mechanism adjusts the scale and direction of morphological operation in real time according to the local blood vessel diameter and curvature characteristics, interference of surrounding tissues in a main blood vessel area can be inhibited, and continuous expression can be enhanced for capillary branches. Through deep fusion of dissection driving and data driving, the topological structure integrity of a segmentation result at a blood vessel bifurcation point and a narrow lesion area is remarkably improved, and the common problems of blood vessel fracture and misconnection in a traditional method are effectively avoided.

The invention discloses a two-stage segmentation method for a vascular structure in a medical CT image and a related device. The method comprises the following steps: acquiring the medical CT image and a coarse segmentation image thereof; performing blood vessel shape interpolation processing on the coarse segmentation image and performing HU value similarity judgment to generate first annotation data and HU value similarity mapping data; performing vessel connectivity judgment on the HU value similarity mapping data, extracting a condition label and generating second annotation data; and extracting a target region in the repair compensation data by using a blood vessel extraction method based on boundary corrosion, and finally obtaining a target segmentation result. By combining HU value judgment, vessel connectivity analysis and boundary corrosion technologies, the accuracy and connectivity of vessel segmentation are improved, and the method is suitable for fine extraction of complex vessel structures.

The invention discloses a blood vessel continuous segmentation method based on a graph network, and relates to the technical field of blood vessel continuous segmentation, multi-scale texture features based on coronary artery influence and topological structure features of blood vessels are fused, and correlation among different features is enhanced through an attention mechanism; segmenting the fused multi-scale texture features influenced by the coronary artery and topological structure features of the blood vessel, extracting multi-scale features, and reducing the resolution; gradually recovering the resolution by using a decoder to obtain a segmentation result, and optimizing the network weight by using an error between the segmentation result and a real label; and applying the trained segmentation network to test data to obtain a three-dimensional segmentation result of the coronary artery, and evaluating the accuracy of the segmentation result by comparing the difference between a predicted value and a true value to obtain connection constraint loss. The problem that a three-dimensional blood vessel structure is difficult to extract by a general medical segmentation model is solved, so that a blood vessel segmentation result is more continuous and more accurate.

The invention provides a cross-modal fundus image registration method and device, equipment and a medium, and the method comprises the steps: converting a to-be-matched multi-modal image into a blood vessel image through a wide-area blood vessel segmentation network, the multi-modal image being two fundus images of different modals obtained by the same fundus of the same patient at different times and in different imaging modes; performing feature matching on the vascular image of the to-be-matched multi-modal image through the key point detection model to obtain a matching set; and realizing coordinate transformation of the to-be-matched multi-modal image by using a double-fitting strategy based on the matching set, and completing image registration. Therefore, according to the registration strategy, the best registration performance at present is achieved, the registration performance of other existing models is greatly improved through the cutting alignment strategy and the double-fitting strategy, and the cross-modal fundus image registration method can be widely applied to cross-modal fundus image registration under the large-view-difference condition.

The invention provides a fracture repair and topology analysis method for a blood vessel segmentation mask in a liver CT image, and the method specifically comprises the steps: 1) carrying out the skeletonization of the liver blood vessel segmentation mask, and extracting a blood vessel skeleton, a skeleton end point, and a blood vessel radius rough value at a skeleton point; 2) solving a connected blood vessel center line (1) for the purpose of fracture repair without considering removal of wrong adhesion of hepatic veins and portal veins; 3) considering possible wrong adhesion for removing the hepatic vein and the portal vein, setting a stricter connection condition to obtain a broken blood vessel center line, and solving a broken blood vessel center line (2) in which the hepatic vein and the portal vein are obviously distinguished by taking classification as a purpose; and 4) combining the center lines (1) and (2), reconstructing missing blood vessel segments in the original blood vessel segmentation mask, and combining the reconstructed blood vessel segments into the original segmentation mask to obtain a final blood vessel mask and center line topological structure after fracture repair.

The invention discloses a coronary artery segmentation method in combination with MambaASPP and a combined loss function. The method comprises the following steps: 1, through non-zero data cutting and resampling adjustment, computing resources are saved, and a model can better process images with different resolutions; and 2, on the basis of the U-Net model, a residual structure is added to each block in an encoder and a decoder, and then a MambaASPP module is added to a bottleneck layer, so that local boundary positioning and background and foreground contrast are enhanced, and small blood vessel segmentation accuracy is improved. And 3, in the U architecture of the model, adding a segmentation head to each layer to obtain a segmentation result, and supervising the module of each layer through a loss function to enable the model to learn detail information in advance. And 4, supervising model training: combining the cross entropy, Dice and cbDice according to a weight ratio of 3: 1: 2 to form a loss function, supervising from different angles, and improving the segmentation effect.

The present invention discloses a vascular segmentation model and method. The vascular segmentation model includes an encoder and a decoder. The encoder extracts features from computed tomography images to obtain a basic neural network feature map. The decoder includes a vascular perception module and an upsampling layer. The vascular perception module fuses prior knowledge of blood vessels with the basic neural network feature map to output a vascular segmentation map. The upsampling layer restores the vascular segmentation map processed by the vascular perception module to a size corresponding to the CT image. The technical solution of this application can effectively improve vascular segmentation accuracy.

A vascular image processing method performed by a processor includes extracting, from a vascular image, a first vascular region corresponding to an entire blood vessel included in the vascular image, a second vascular region corresponding to a target vessel and one or more branch vessels connected to the target vessel, and a third vascular region corresponding to the target vessel, and predicting a vascular structure in the vascular image, based on the first vascular region, the second vascular region, and the third vascular region, which are extracted from the vascular image.

A three-dimensional liver blood vessel segmentation model construction method based on a space channel mixed attention and skeleton loss function comprises the steps that a three-dimensional encoder-decoder backbone network of a symmetrical structure is constructed, the three-dimensional encoder-decoder backbone network comprises four layers of encoders and decoders, each layer of each encoder comprises an LVSN Block convolution module and a down-sampling module, and each layer of each decoder comprises an up-sampling module and an LVSN Block convolution module; the space channel mixed attention module is integrated in a sampling stage under the encoder and is used for enhancing blood vessel features and inhibiting background noise; and based on a skeletonized prior continuity loss function, constraining the continuity of a segmentation result from a topological structure level. According to the method, the accuracy and the structural rationality of three-dimensional liver blood vessel segmentation can be improved, and the requirements of clinical refined analysis are met.

The application discloses a kind of nnUNet zebra fish juvenile whole brain vascular system segmentation methods based on autonomous data set training, it is related to high-resolution imaging technology, image processing and medical image segmentation field, the method makes full use of zebra fish live transparency and fluorescent label advantage, obtains high-resolution whole brain three-dimensional vascular image data, and constructs high-quality segmentation truth value database by semi-automatic segmentation and artificial correction, training is carried out using nnU-Net deep learning model, realize the three-dimensional automatic segmentation of zebra fish brain vascular system signal.The application method significantly improves the degree of automation and precision of image segmentation, effectively solves the problems of low efficiency, high artificial dependence and poor repeatability of traditional brain vascular segmentation.The method is suitable for large-scale high-throughput data processing, can provide efficient, standardized image processing scheme for zebra fish brain vascular development mechanism and brain vascular disease model research, and has wide application prospect.

The invention discloses a collaborative optimization multi-task non-enhanced CT blood vessel segmentation device. The collaborative optimization multi-task non-enhanced CT blood vessel segmentation device comprises an image acquisition module, an image preprocessing module, a network construction module, a multi-task multi-scale joint loss function construction module, a branch loss construction module, a joint training module and a branch training module. According to the method, collaborative optimization of double tasks can be promoted while the parameter quantity is greatly reduced in an encoder sharing mode, branch parameters of the tasks are independently and finely adjusted, so that the branch parameters of the tasks are optimal, and the blood vessel form mask and the blood vessel structure mask can be effectively segmented from the non-enhanced CT image.

The invention belongs to the technical field of medical image processing and neural image analysis, and particularly discloses a cerebral apoplexy prognosis prediction method which comprises the following steps: step 1, performing whole cerebral vessel segmentation and morphological feature extraction on a CTA image to obtain 40 blood vessel morphological features; 2, extracting high-throughput omics characteristics from an infarction core and a half-dark band region in the DWI image, and obtaining 1026 image omics characteristics; 3, screening high-resolution features based on minimum absolute contraction and a selection operator, establishing a support vector machine classification model, and predicting a prognosis classification result of a three-month improved Rankin scale of the stroke patient; the deep learning network is used for automatically segmenting the whole brain blood vessel, so that subjective difference of manual recognition is reduced; starting from pathophysiology of occurrence and development of cerebral apoplexy, vascular morphological characteristics and infarction region imageomics characteristics are comprehensively incorporated to carry out prognosis prediction on cerebral apoplexy.

A method of nidus segmentation includes: acquiring a medical image to be processed; performing a vessel segmentation on the medical image to be processed to obtain a first vessel segmentation result; extracting a first centerline of a first vessel according to the first vessel segmentation result; cutting the medical image to be processed for several times to obtain a plurality of first sections and further obtain a first object medical image by synthesizing the plurality of sections, and cutting the first vessel segmentation result for several times to obtain a plurality of second sections and further obtain a first object vessel segmentation result by synthesizing the plurality of second sections; and obtaining a nidus segmentation result based on the first object medical image and the first object vessel segmentation result.

The embodiment of the present application discloses a method and computer device for determining blood vessel flow velocity. The method includes: acquiring angiography sequence images, finding a coronary angiography image that meets the best development conditions in the angiography sequence images as the best coronary angiography image, selecting the coronary angiography image arranged before the timestamp of the best coronary angiography image in the angiography sequence images in sequence as the target coronary angiography image, the target coronary angiography image and the best coronary angiography image forming an image segmentation set, generating a blood vessel length change graph based on the image segmentation set, determining the conduction start time and the conduction end time based on the blood vessel length change graph, and determining the blood vessel flow velocity based on the main branch vessel length, the conduction start time and the conduction end time. The embodiment of the present application does not need to analyze all coronary angiography images, and selects the best coronary angiography image and the target coronary angiography image arranged before the best coronary angiography image for analysis, which can reduce the number of blood vessel segmentations.

The invention discloses a cerebral vascular hemodynamic measurement method and device based on transcranial color Doppler. The method comprises the following steps: training a plurality of sample images to establish a multi-target cerebrovascular segmentation model; inputting a to-be-segmented image into the multi-target cerebrovascular segmentation model to obtain a segmentation region of each cerebrovascular in the to-be-segmented image; performing central axis transformation on the segmented region of each cerebral vessel, and extracting a skeleton structure of each cerebral vessel; and based on the skeleton structure of each cerebral vessel, calculating to obtain an optimal measurement position and an optimal measurement angle for measuring cerebral vessel hemodynamic parameters. According to the method, more accurate analysis can be provided for diagnosis and evaluation of cerebral vessels under transcranial color Doppler, errors caused by manual operation are reduced, and improvement of accuracy and reliability of medical image analysis is facilitated.

The vessels of a biological object are to be segmented more reliably. To this end, a method for training a machine learning algorithm to segment such vessels is proposed. First, a 3D reconstruction (8) of the vessels is provided. A starting vessel region (7) is identified in the 3D reconstruction (8). Sub-regions representing a starting vessel segment are extracted from the starting vessel region (7). The algorithm is trained using these extracted sub-regions. Subsequently, the trained algorithm is applied to a first neighboring region (10) immediately adjacent to the starting vessel region (7). This identifies a first vessel segment in the first neighboring region (10). Finally, the algorithm is retrained using the first vessel segment identified in the first neighboring region (10).

An apparatus for evaluating a vessel of interest and a corresponding method are provided, wherein the modeling of hemodynamic parameters using a fluid dynamic model can be verified by deriving feature values ​​from the segmented vessel of interest and inputting these feature values ​​into a classifier. The classifier can then determine based on the feature values ​​whether the segmentation has been performed from proximal to distal, from distal to proximal or cannot be determined from the provided data. An incorrect segmentation order can thus be identified and possibly corrected, thereby avoiding inaccurate simulation results.

The present invention discloses a liver blood vessel segmentation method, device, equipment and medium based on weak supervised learning, and the method includes: training two liver blood vessel segmentation network models with differences through noisy labels; using the two models to segment respectively to obtain predicted labels; assigning weights to predicted labels and noisy labels through a label optimization module to obtain weighted optimized labels; using the optimized labels to iteratively train the two models respectively to obtain two iterative models; using the two iterative models to continue segmenting to obtain new predicted labels; when the segmentation effect of the iterative model is improved, continue to call the label optimization module to obtain new optimized labels, and continue to iterate the model until convergence; segment the input CT image through the converged model to obtain the segmentation result. The present invention can effectively reduce the adverse effects of noisy labels on the segmentation results, thereby reducing the manpower, material resources and time consumed by label annotation.

The invention relates to the technical field of blood vessel image processing, in particular to a blood vessel processing optimization method based on StyleGAN data enhancement and a retina image. According to the method, data enhancement, blood vessel segmentation and classification training are organically combined through complete process design. StyleGAN is utilized to generate a synthetic retina image expansion data set, the problem of data imbalance is relieved, and the generalization ability of the model is improved; precise blood vessel segmentation is achieved through IterNet, classification training is completed through a FullSizeUNetBlock model, retina images are systematically processed in the whole process, a closed loop is formed from data to segmentation to classification, a comprehensive and logically clear solution is provided for blood vessel classification, and the accuracy and reliability of final blood vessel category prediction are ensured.

The present invention provides a vascular image segmentation method, apparatus, device, storage medium, and program product, relating to the field of image processing technology. The method comprises: obtaining an original vascular image and its corresponding initial vascular segmentation image; extracting the vascular skeleton structure based on the vascular segmentation image and determining endpoints on the vascular skeleton structure; superimposing the original vascular image and the vascular segmentation image to obtain a dual-channel image; determining, for each endpoint, a local segmentation window corresponding to the endpoint, performing iterative vascular segmentation on the local image corresponding to the local segmentation window in the dual-channel image, and updating the vascular segmentation image based on the iterative vascular segmentation results; and traversing all endpoints to obtain a final vascular segmentation image. The present invention improves segmentation accuracy while conserving computing resources.

The present application relates to a coronary artery segmentation method based on a continuous frame sequence of DSA images, a computer device, and a readable storage medium. The method includes: obtaining a training data set, the training data set including an input data set and an output data set, the input data set being the first continuous frame with a sequence length of N in the continuous frame sequence of coronary DSA images, and the output data set being an intermediate frame pre-labeled with a target vessel and located in the middle of the first continuous frame; using the training data set to train a deep learning network model: the deep learning network model includes a feature fusion device, an encoder, and a decoder, the feature fusion device performs feature fusion on the first continuous frame to obtain a three-dimensional image, the three-dimensional image passes through the encoder and decoder in sequence, and the output of the decoder is connected to the intermediate frame; continuously training until a trained deep learning network model is obtained, using the trained deep learning network model to detect the input continuous frame sequence of coronary DSA images, and outputting a segmentation prediction map of the target vessel.

The present application relates to a kind of DSA coronary vessel segmentation deep learning method of edge and topological feature, comprising the following steps: obtaining DSA coronary angiography image dataset and corresponding coronary vessel label dataset;Data is input into deep learning network, the deep learning network is end-to-end U type deep learning network, include improved bidirectional Transformer module and multi-scale semantic fusion module, and encoder and decoder are connected by jump connection and multi-scale semantic fusion module;Coronary vessel segmentation model is trained in three stages using the composite loss function comprising Dice loss, Focal loss, edge loss and topological loss, the segmentation model of the training completion can be carried out complete segmentation to the coronary vessel in DSA coronary angiography picture;Using composite evaluation index, the overall segmentation accuracy of segmentation model, edge segmentation accuracy and the ability of keeping topological consistency are comprehensively evaluated.

A three-dimensional liver vessel segmentation model based on enhanced attention mechanism context bridging and its establishment method include: an input layer for receiving input three-dimensional liver medical CT image data to obtain image features; first to fourth image overlapping feature encoding layers for performing overlapping feature encoding operations on low-dimensional image features; first to fourth enhanced attention mechanism downsampling layers, which are alternately connected with the first to fourth image overlapping feature encoding layers in sequence, for feature extraction and generating four different-scale image features; first to fourth enhanced attention mechanism context bridging layers connected in series, for fusing multi-scale image features and further extracting features to obtain the association of local and global information of multi-scale image features; first to fourth image block expansion layers, which are used to re-divide high-dimensional image features into lower-dimensional image features while increasing the width, height, and depth of the image features; first to fourth enhanced attention mechanism upsampling layers, which are alternately connected with the first to fourth image block expansion layers in sequence, for recursively splicing and further extracting features from image features of different scales to obtain final image features; and an output layer, which is used to calculate the final image features and generate three-dimensional liver vessel segmentation results. The present invention can achieve accurate three-dimensional liver vessel segmentation and assist doctors in diagnosing diseases such as liver vessels and tumors.

The present invention belongs to the field of medical image processing technology and discloses an ASL image processing system, device, and terminal for cerebral artery stenosis and occlusion. The ASL image processing system for cerebral artery stenosis and occlusion comprises: a scanning parameter acquisition module, an image acquisition module, a central control module, a data post-processing module, an image pre-processing module, a CBF image generation module, a CBF image processing module, a vascular region demarcation module, a vascular segmentation module, a three-dimensional reconstruction module, a parameter calculation module, a data analysis module, and a display module. The present invention eliminates data errors caused by initial machine operation instability by deleting the earliest scan data. Simultaneously, the scan data is corrected and registered to avoid artifacts caused by user movement during processing, thereby improving image reliability and data analysis accuracy.

This invention discloses a method and device for cerebral artery segmentation and classification based on MRI images, belonging to the field of medical image processing. The method uses a U-Net network as its basic architecture, introducing a Swing Transformer module in the encoder to achieve hierarchical feature extraction. First, the 3D MRI image is preprocessed; then, multi-scale features are extracted through a multi-level Swing Transformer encoding stage, and a shift-window attention mechanism is combined to enhance global context awareness; next, a graph structure is constructed to fuse and enhance multi-level features to preserve vascular topology; finally, a convolutional decoder upsamples layer by layer and performs skip connections with the graph fused features to achieve accurate reconstruction and classification of vascular structures. This invention effectively integrates the global modeling capabilities of the Transformer with the local detail extraction advantages of convolutional networks, improving the accuracy and structural integrity of vascular segmentation and classification.

The embodiment of the invention discloses a blood vessel contour recognition method, device and equipment and a storage medium, and the method comprises the steps: obtaining a blood vessel ultrasonic image sequence, and carrying out the cross section blood vessel segmentation of each blood vessel ultrasonic image, so as to obtain a plurality of original blood vessel contour maps; identifying contour points in each original blood vessel contour map; respectively determining the uncertainty of each contour point in each original blood vessel contour map; and retaining or adjusting the position corresponding to the contour point according to the uncertainty so as to obtain the target blood vessel contour. According to the technical scheme, the problem that in the prior art, when the blood vessel contour in the IVUS image is recognized, the recognition accuracy is low is solved, the positions of the corresponding contour points can be adjusted based on the uncertainty of the contour points in the image, and the blood vessel contour recognition accuracy is improved.

The present invention provides a coronary artery growth method and system based on CTA images. For seed point generation, a regression algorithm is used to obtain the probability that a point in the initial mask is a seed point, and the first screening is performed according to the distance from the left and right coronary artery ostium points. Then, the second screening is performed according to the probability size and interval sampling. For the coronary artery growth model, most bright and evenly distributed Hu vessels are segmented. For the calcified growth model, the centerline is traced and identified within the vascular calcification lesions to improve the stability of the centerline. For the stenosis and small vessel growth patterns, the vascular stenosis lesions and vessels under low Hu are traced and identified. The edge of the vascular segmentation is also optimized by graph cut.

The present invention discloses an uncertainty-guided retinal vascular image segmentation method and system, which belongs to the field of medical image processing. The present invention first constructs an uncertainty network to quantify the uncertainty in the fundus image to obtain an uncertainty mapping matrix, and uses the mean value of the uncertainty network output as the prior mapping matrix; then constructs a segmentation network based on UNet, and performs multiple feature fusions on the feature map obtained in the encoding stage and the uncertainty mapping matrix to learn the uncertainty area in the fundus image; the loss function of the segmentation network is composed of a prior loss function and a cross-entropy loss function, wherein the prior loss function is constructed based on the prior mapping matrix; then, the fundus image training set is input into the segmentation network to train the segmentation network; finally, the fundus image is input into the trained segmentation network to obtain a retinal vascular segmentation image. The present invention effectively improves the retinal vascular segmentation performance and has practical clinical value.

The vascular image segmentation method, device and equipment based on the differential learning model provided by the present invention relate to the fields of neural networks and image processing. The present invention obtains a 3D vascular original image set of different modalities and inputs it into a vascular image segmentation model. In the segmentation model, a modality difference marking method is used to obtain a reconstructed image embedded with modality features; the reconstructed image is input into a 3D UNet encoder to extract low-level features; according to the low-level features, high-level features are generated through a position encoder and a self-attention mechanism; the high-level features are unfolded into one-dimensional vectors through a linear layer and optimized by a Transformer encoder to generate optimized features; then, the features optimized by the Transformer are used to calculate the difference features between modalities by element-wise subtraction, so as to obtain difference fusion features; the difference fusion features are reshaped by the Transformer encoder to obtain the final vascular segmentation result. The present invention can accurately capture the morphological features of small blood vessels and effectively improve the accuracy of vascular image segmentation.

The present invention relates to the field of image processing technology, and discloses a cerebrovascular image segmentation method based on an attention multi-core convolutional network, comprising the following steps: collecting mouse cerebrovascular images, and preprocessing them, and dividing the preprocessed mouse cerebrovascular images into a training data set and a test data set; constructing a mouse cerebrovascular segmentation model, including a feature encoder module, an attention module, and a feature decoder module: training the mouse cerebrovascular segmentation model through the training data set and a loss function composed of a weighted cross entropy loss and a Dice coefficient loss; inputting the mouse cerebrovascular image in the test data set into the trained mouse cerebrovascular segmentation model to obtain a segmentation result. The multi-core module based on attention of the present invention effectively captures cerebrovascular features of different scales, thereby achieving more accurate vascular segmentation.