26 results about "Vessel segmentation" patented technology

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.

This invention discloses a medical image processing method, device, medium, and product, relating to the field of medical image processing technology. The method includes: acquiring the segmentation results of hemangioma and tumor-bearing vessels in a scanned image of a target vessel; determining a first point set for the hemangioma based on the hemangioma segmentation results; determining a second point set for the tumor-bearing vessels based on the tumor-bearing vessel segmentation results; determining a bidirectional neighboring point set for the first and second point sets, each bidirectional neighboring point set including at least three non-collinear pixels; determining a plane equation for the tumor diameter plane based on the bidirectional neighboring point set; determining the intersection points of the plane containing the plane equation with the first and second point sets, and using the plane enclosed by all intersection points as the tumor diameter plane. The technical solution provided by this invention solves the technical problem of slow speed in existing tumor diameter plane determination methods, improving the speed of tumor diameter plane determination.

The application discloses a method for angiogram image segmentation based on self-supervised contrast learning and frequency domain feature enhancement. The method takes UNet as the basis, inputs the original angiogram image into the symmetrical encoder-decoder structure, integrates the discrete wavelet transform path in the encoding stage, injects the high-frequency texture component into the down-sampling feature of the encoder, realizes the detail compensation of the slender branch of the blood vessel, and connects the projection layer at the end of the bottleneck layer of the encoder to perform feature mapping. In the first stage, the decoder is frozen, self-supervised pre-training is performed by minimizing the contrast loss, and the feature capturing ability of the encoder is strengthened. In the second stage, the pre-training weight is loaded and the decoder is unfrozen, the Dice similarity coefficient and the binary cross entropy loss are combined for supervised fine-tuning, and accurate blood vessel segmentation is realized. The method can deeply fuse the global semantic topology and the local detail information, significantly improve the segmentation performance and edge accuracy, and maintain high calculation speed and low resource consumption.

Embodiments of the present application provide a training method, an image segmentation method, a computer-aided diagnosis method and system. The method comprises: obtaining a prediction annotation result and a corresponding sample image, the sample image containing a sample object, the prediction annotation result being obtained from a first prediction segmentation result satisfying a target screening condition, the first prediction segmentation result being output by a first image segmentation model trained to segment the sample object, and the target screening condition being configured based on a training target of a second image segmentation model; inputting the sample image into the second image segmentation model to obtain a second prediction segmentation result output by the second image segmentation model to segment the sample object; and training the second image segmentation model using a loss value between the prediction annotation result and the second prediction segmentation result. Embodiments of the present application can improve the accuracy of coronary artery vessel segmentation of NCCT images and lay a foundation for downstream coronary stenosis detection tasks.

The application discloses a method for training a segmentation model for cerebral vascular segmentation and related products. The method comprises: obtaining a three-dimensional gray image and a corresponding three-dimensional blood vessel segmentation mask based on a three-dimensional angiogram; generating a three-dimensional gray entropy feature map according to the three-dimensional gray image; generating a three-dimensional label entropy map according to the three-dimensional blood vessel segmentation mask; performing feature fusion on the three-dimensional gray image and the three-dimensional gray entropy feature map to obtain fused features; inputting the fused features into the segmentation model for blood vessel segmentation and calculating a weighted loss based on the three-dimensional label entropy map; and training the segmentation model for cerebral vascular segmentation based on the weighted loss. The scheme of the application can improve the recognition ability of the model for blood vessel boundaries, small blood vessels and complex structure regions, effectively reduce the blood vessel adhesion phenomenon, and enhance the robustness and clinical applicability of the segmentation result.

The application discloses a kind of based on frequency domain enhancement's retinal blood vessel segmentation method, it is related to retinal blood vessel segmentation technical field, the method includes: the input retinal image is preprocessed to enhance blood vessel structure information;The spatial domain feature of image is extracted by multilevel encoder;Dynamic frequency domain enhancement processing is carried out to spatial domain feature, including using learnable Gaussian high-pass filter and K groups learnable complex Fourier base weighted fusion to generate adaptive frequency domain mask to enhance blood vessel edge high-frequency component;Frequency domain enhancement feature and spatial domain feature are input into cross-domain routing attention module and are fused;Key feature position is filtered using double-layer routing mechanism and sparse attention is calculated;Blood vessel segmentation result is output by the decoder upsampling fusion feature and output blood vessel segmentation result.The application is enhanced by learnable Gaussian high-pass filter adaptive blood vessel edge frequency domain feature, combined with spatial domain feature to carry out cross-domain routing attention fusion, realizes high-precision, high-efficiency blood vessel segmentation under the improvement U-Net architecture.

The application discloses a forearm shallow blood vessel segmentation method and device based on an NSVA-Net deep learning network, and relates to the technical field of medical image processing. The method comprises the following steps: collecting near-infrared images of the forearm shallow blood vessels of a subject by using a near-infrared light source and a near-infrared camera; performing denoising, contrast enhancement, cutting of the forearm region and normalization on the near-infrared images to obtain preprocessed images; performing two-stage image enhancement of RCAE and CLAHE on the preprocessed images to obtain enhanced images; inputting the enhanced images into a pre-trained NSVA-Net deep learning network to obtain a segmentation probability map of the forearm shallow blood vessels; performing threshold segmentation, connected domain analysis and skeletonization processing on the segmentation probability map to remove artifacts and isolated noise, and obtaining a blood vessel segmentation result and a center line; and superimposing and displaying the blood vessel segmentation result and the center line on the near-infrared images to output a final segmentation image. By using the application, the segmentation recall rate and the structural continuity of the forearm shallow small blood vessels of dialysis patients can be significantly improved.

The present disclosure relates to an aorta blood vessel segmentation method, device, storage medium and electronic equipment. The method comprises: acquiring an aorta CTA image; inputting the CTA image into a trained aorta trunk blood vessel extraction model to obtain an aorta trunk blood vessel image, the aorta trunk blood vessel image being a binary image; performing image enhancement processing on the CTA image to obtain an aorta branch blood vessel enhancement image, the aorta branch blood vessel enhancement image being a binary image; and segmenting an aorta blood vessel image from the CTA image according to the aorta trunk blood vessel image and the aorta branch blood vessel enhancement image. In this way, the complete aorta trunk blood vessel and branch blood vessel can be effectively segmented.

The application provides a blood vessel segmentation method for an infrared operation image based on an improved U-Net, comprising the following steps: step 1, converting an input original picture into standardized data with a high signal-to-noise ratio and meeting the input requirements of a model tensor; step 2, simultaneously calling pre-trained models with different random seeds, the pre-trained models performing parallel prediction and independently generating prediction results; step 3, performing a mean aggregation operation to generate an uncertainty measurement map; step 4, scaling the segmentation result back to the resolution of the original picture through interpolation, converting the continuous probability into a conclusion of whether it is a blood vessel, and finally labeling the input infrared operation image based on the conclusion. Under the premise of not increasing the model parameter quantity, the method realizes physical superposition of weak features. It utilizes the redundancy between feature map channels, forcibly fuses the information of the encoder and the decoder through addition, and significantly improves the detection rate and continuity of small blood vessels in the infrared operation image.

This invention discloses a method, apparatus, electronic device, and storage medium for blood vessel segmentation. The method includes: inputting an original medical image containing a target blood vessel into an initial blood vessel segmentation model to obtain an initial blood vessel segmentation probability map; binarizing the initial blood vessel segmentation probability map to obtain a corresponding binary blood vessel segmentation map; filtering the intersection region of the original medical image and the binary blood vessel segmentation map to obtain a set of sampling points for the target blood vessel location; performing point-by-point segmentation prediction based on the set of sampling points to obtain a segmentation prediction probability value corresponding to each sampling point; updating the initial blood vessel segmentation probability map based on the segmentation prediction probability values ​​corresponding to each sampling point to obtain a target blood vessel segmentation probability map; and determining the target blood vessel segmentation prediction result based on the target blood vessel segmentation probability map. The above technical solution can effectively improve the completeness of the blood vessel segmentation results.

The application discloses a kind of two-way asymmetric DSA sequence cerebral vessel segmentation method and system, the method includes: acquisition original contrast image pre-processing generates DSA sequence;Based on the preset double-branch encoding mechanism, the complementary space-time characteristics of DSA sequence are extracted;To complementary space-time characteristics, based on the preset selective space state model, time series modeling is carried out, and space-time dynamic characteristics are obtained;According to space-time dynamic characteristics and the preset two-way guide enhancement mechanism, obtain space-time modulation characteristics, based on the asymmetric cross attention mechanism of space leading, cross attention fusion is carried out to space-time modulation characteristics, and generates target space-time representation;Target space-time representation is decoded, and the cerebral vessel segmentation result of DSA sequence is obtained.It can be seen that the application can realize efficient space-time fusion, significantly improve the accuracy of vessel segmentation, computational efficiency and robustness.

The application discloses an OCTA retinal microvessel branch angle automatic extraction and uveitis blood vessel leakage risk prediction method and device based on deep learning and principal component analysis, and the method comprises the following steps: pretreating an OCTA image; performing blood vessel segmentation by using a deep learning model to obtain a binary blood vessel graph; performing skeletonization and topological structure analysis on the blood vessel graph, and screening out terminal-level bifurcation points directly connected with terminal ends; for each terminal-level bifurcation point, pixel point coordinate sets are extracted along each branch, a local tangent vector is estimated by principal component analysis, and the smallest included angle is calculated as the branch angle of the bifurcation point; the angles of all terminal-level bifurcation points are quantified by mean value to obtain an average blood vessel branch angle; finally, the MVA and the patient age are input into a pre-established Firth penalty likelihood Logistic regression model, and a blood vessel leakage risk probability is output. The MVA index is accurately and automatically extracted, and a noninvasive and efficient quantitative prediction tool for uveitis blood vessel leakage risk is provided.

This application provides a method, system, storage medium, and electronic device for removing horizontal lines from a blood flow map, relating to the field of fundus blood flow image processing technology. The technical solution provided in this application accurately determines the horizontal line region to be repaired based on the difference between the original fundus blood flow image and the preliminary image to be de-lined. It then uses pixel information from the neighborhood of the horizontal line region to perform interpolation repair, obtaining the repaired target image. Simultaneously, the original fundus blood flow image is segmented to extract vessel location information. Based on this vessel location information, signal preservation processing is performed on the repaired target image, restoring the pixel values ​​of the vessel region in the original fundus blood flow image to the corresponding positions in the repaired target image. This avoids the overlapping of vessel region pixel values ​​during the interpolation repair process, preventing confusion between vessel and horizontal line brightness information. Therefore, it can accurately identify horizontal lines in the blood flow map, reduce the impact on the blood flow signal, and improve the removal effect of horizontal lines in the blood flow map.

This invention relates to an unsupervised coronary angiography segmentation method that solves the problems of missing structural information and annotation dependence in two-dimensional segmentation. The method includes the following steps: First, a three-dimensional implicit representation space is constructed based on EG3D, and its neural radiation field is used to model the three-dimensional topology of blood vessels. Second, a dual-channel adversarial generation architecture is designed, and adversarial training between parallel foreground and background generators achieves decoupling of vascular and non-vascular features. Then, combining the multi-angle projection characteristics of angiography, a three-dimensional attention fusion module is used to constrain the geometric consistency of multiple views. Next, a domain-adaptive encoder is developed to embed real images into the EG3D latent space, achieving geometric feature alignment between the real and synthetic domains. Finally, the implicit three-dimensional representation is converted into multi-view projection through differentiable volume rendering, and the foreground generator outputs a spatially continuous three-dimensional blood vessel segmentation mask. This invention can generate three-dimensional structural segmentation maps of blood vessels in coronary angiography under unsupervised conditions.

The present application relates to artificial intelligence and digital medical treatment, and provides an arteriovenous vessel separation method and device based on images, an electronic device and a medium, which extracts a blood vessel skeleton in a CT image; divides the blood vessel into a plurality of blood vessel segments according to the blood vessel skeleton; constructs a blood vessel topology graph based on the plurality of blood vessel segments; extracts a plurality of features of each blood vessel segment; trains an arteriovenous vessel separation model based on the blood vessel topology graph and the plurality of features of each blood vessel segment; and inputs a CT image to be processed into the trained arteriovenous vessel separation model to separate arteriovenous vessels. The present application can improve the accuracy of arteriovenous vessel separation.

This invention belongs to the field of medical image processing and analysis technology, specifically a three-dimensional vascular registration method for digital subtraction angiography (DSA) and magnetic resonance angiography (MRA). The invention includes: preprocessing DSA and MRA images to initially align the skull and eliminate intensity differences between images; segmenting blood vessels in the DSA and MRA images to remove skull and other brain tissue from the original images; initializing a three-dimensional vascular map by converting the blood vessels in the original images into a vascular map model; performing rigid registration of the blood vessels to initially align the vascular structures in physical space; and performing non-rigid registration of the blood vessels to correct vascular deformation. This invention can achieve high-precision alignment of DSA and MRA in three-dimensional space, ensuring the consistency of vascular structures and providing more accurate image support for the diagnosis, preoperative planning, and postoperative evaluation of clinical vascular diseases.

Embodiments of the present disclosure provide a method and a system for determining a blood flow parameter of a reticular vessel. The method may be implemented on a device including at least one processing device and at least one storage device. The method may include: obtaining vessel data of an object; generating a reticular vessel model by performing, based on the vessel data, vessel segmentation; generating, by performing model partitioning based on the reticular vessel model, a plurality of vessel sub-models; and determine the blood flow parameter of the reticular vessel model by performing, based on the plurality of vessel sub-models, coupling processing.

The application discloses a medical image optimization method and system based on blood vessel branch selective virtualization. The method comprises the following steps: pre-processing and blood vessel enhancement are performed on a three-dimensional angiography DICOM image; an encoder-decoder network containing a wide activation and residual hollow space pyramid module is used for accurate blood vessel segmentation; through blood vessel topology analysis, interference branches that shield target blood vessel structures under a specific working angle are identified; based on a Poisson equation and a bidirectional convolution LSTM, selective virtualization repair is performed on the interference branches to generate an optimized image that is visually unshielded and maintains topological continuity. A safety mechanism of virtual-real combined display and multi-angle preplan is introduced to ensure the reliability of surgical navigation. Finally, the optimized 3D blood vessel model is integrated into a contrast system supporting real-time synchronization and used as a roadmap. The application can effectively solve the clinical problem that the best working angle cannot be used due to blood vessel shielding, and significantly improves the accuracy and safety of intravascular intervention surgery.

This invention relates to a method, device, and medium for blood vessel segmentation based on U-Net fusion with multi-scale dilated convolution. The method involves inputting a retinal image to be segmented into a trained DRU-Net model to obtain the blood vessel segmentation result. The DRU-Net model uses U-Net as a baseline, replacing traditional convolution with multi-scale dilated residual modules in the encoder and decoder parts, and embedding multi-level detail attention modules at skip connections. The multi-scale dilated residual module includes multiple parallel heterogeneous dilated convolution paths with different dilation rates, aggregating multi-scale features through multi-path convolution. The multi-level detail attention module aggregates information in different spatial dimensions through efficient multi-scale attention. Efficient local attention is employed, utilizing strip pooling to extract features in the horizontal and vertical directions respectively. Compared with existing technologies, this invention achieves robust modeling of blood vessel morphology from local details to global distribution in complex backgrounds, significantly reducing the breakage and blurring of small blood vessels.

The application provides an image processing method, system, storage medium and electronic device. The image processing method comprises: generating a second mask according to a first mask, the second mask comprising the first mask and a small blood vessel mask; modifying corresponding voxel points in a first image according to the small blood vessel mask to obtain a second image; and training a blood vessel segmentation model using the second image and the second mask. The image processing method can improve the sensitivity of the blood vessel segmentation model to small blood vessels.

This invention discloses a retinal vessel segmentation method based on orientation field guidance and graph neural network optimization, belonging to the field of image analysis and medical image processing technology. The invention first acquires retinal fundus images and their corresponding vessel annotation maps, and preprocesses the raw retinal fundus images. Then, it constructs a retinal vessel segmentation model based on orientation field guidance and graph neural network optimization. This model includes a backbone segmentation model based on a UNet++ network architecture and a post-processing refinement module based on a visual graph neural network. The preprocessed image is input into the backbone segmentation model to obtain a preliminary vessel segmentation probability map, which is then processed by the post-processing refinement module to obtain the final vessel segmentation result. Experiments show that this invention effectively addresses the shortcomings of existing retinal vessel segmentation methods in terms of small vessel extraction, structural connectivity preservation, and background noise suppression.

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 present application belongs to the technical field of medical image processing, and specifically relates to an ophthalmic sign-maintained fundus image enhancement method. The method of the present application adopts a CycleGAN-based image enhancement network model, which comprises a blood vessel segmentation network and a conversion enhancement network composed of two generators and two discriminators. Considering the particularity of fundus images, the model of the present application introduces a blood vessel segmentation loss and a structure damage as a constraint in addition to using a conversion loss, so that the enhanced fundus image can better retain the fundus blood vessel details and pathological morphological structure. Experimental results show that the present method can effectively enhance the fundus image, retain the fundus signs, improve the image quality, and make the enhanced fundus image more conducive to clinical medical diagnosis. The SSGAN model is superior to the existing model in terms of objective evaluation indexes and subjective evaluation results of ophthalmologists, can effectively realize fundus image enhancement, and has a wide application prospect.

The application provides a kind of semi-supervised feature fusion segmentation network based on OCT-OCTA multimodal, aims at using different modal retinal fundus vascular data to provide prior feature of different modal data for model;The pre-training large model of the application is embedded by adapter, the shape feature and global context of retinal blood vessels are integrated into the segmentation network, and the adaptability of the segmentation network to the blood vessel segmentation task is enhanced;The segmentation network includes an intra-modal information enhancement module and an inter-modal wavelet extraction and fusion module, the former is used for independent fusion and weighting of each modal information, and the latter extracts high and low frequency components by wavelet transform, captures details and global contours, and uses cross attention to mix inter-modal features;In addition, the contrast consistency learning module establishes regularization between different disturbance outputs, further improves the robustness and segmentation performance of the model.

The application discloses a medical image cerebral vessel segmentation and reconstruction system and an optimization method, and relates to the technical field of medical image processing. The system comprises a medical image acquisition module, a preprocessing module, a cerebral vessel segmentation module, a three-dimensional reconstruction module, a model optimization module and a result output module. The method comprises the steps of image acquisition, preprocessing, segmentation, reconstruction, optimization and output. The preprocessing adopts adaptive median filtering and histogram equalization to improve image quality. The segmentation is based on an improved U-Net model combined with an attention mechanism to strengthen the characteristics of blood vessels and a weighted loss function to improve accuracy. The reconstruction generates a three-dimensional model through a moving cube algorithm. The optimization improves model quality through Laplacian smoothing and topological repair, and introduces precision evaluation to form an iterative closed loop. The scheme realizes full-process automation, improves segmentation and reconstruction accuracy and efficiency, and outputs high-quality vessel models, thereby providing reliable support for the diagnosis, surgical planning and medical research of cerebral vascular diseases.