Edge Features Research Articles

Ship Detection in Synthetic Aperture Radar Images under Complex Geographical Environments, Based on Deep Learning and Morphological Networks.

Synthetic Aperture Radar (SAR) ship detection is applicable to various scenarios, such as maritime monitoring and navigational aids. However, the detection process is often prone to errors due to interferences from complex environmental factors like speckle noise, coastlines, and islands, which may result in false positives or missed detections. This article introduces a ship detection method for SAR images, which employs deep learning and morphological networks. Initially, adaptive preprocessing is carried out by a morphological network to enhance the edge features of ships and suppress background noise, thereby increasing detection accuracy. Subsequently, a coordinate channel attention module is integrated into the feature extraction network to improve the spatial awareness of the network toward ships, thus reducing the incidence of missed detections. Finally, a four-layer bidirectional feature pyramid network is designed, incorporating large-scale feature maps to capture detailed characteristics of ships, to enhance the detection capabilities of the network in complex geographic environments. Experiments were conducted using the publicly available SAR Ship Detection Dataset (SSDD) and High-Resolution SAR Image Dataset (HRSID). Compared with the baseline model YOLOX, the proposed method increased the recall by 3.11% and 0.22% for the SSDD and HRSID, respectively. Additionally, the mean Average Precision (mAP) improved by 0.7% and 0.36%, reaching 98.47% and 91.71% on these datasets. These results demonstrate the outstanding detection performance of our method.

Convolutional Neural Network‐Based CT Image Segmentation of Kidney Tumours

ABSTRACTKidney tumours are one of the most common tumours in humans and the main current treatment is surgical removal. The CT images are usually manually segmented by a specialist for pre‐operative planning, but this can be influenced by the surgeon's experience and skill and can be time‐consuming. Due to the complex lesions and different morphologies of kidney tumours that make segmentation difficult, this article proposes a convolutional neural network‐based automatic segmentation method for CT images of kidney tumours to address the most common problems of boundary blurring and false positives in tumour segmentation images. The method is highly accurate and reliable, and is used to assist doctors in surgical planning as well as diagnostic treatment, relieving medical pressure to a certain extent. The EfficientNetV2‐UNet segmentation model proposed in this article includes three main parts: feature extractor, reconstruction network and Bayesian decision algorithm. Firstly, for the phenomenon of tumour false positives, the EfficientNetV2 feature extractor, which has high training accuracy and efficiency, is selected as the backbone network, which extracts shallow features such as tumour location, morphology and texture in the CT image by downsampling. Secondly, on the basis of the backbone network, the reconstruction network is designed, which mainly consists of conversion block, deconvolution block, convolution block and output block. Then, the up‐sampling architecture is constructed to gradually recover the spatial resolution of the feature map, fully identify the contextual information and form a complete encoding–decoding structure. Multi‐scale feature fusion is achieved by superimposing all levels of feature map channels on the left and right sides of the network, preventing the loss of details and performing accurate tumour segmentation. Finally, a Bayesian decision algorithm is designed for the edge blurring phenomenon of segmented tumours and cascaded over the output of the reconstruction network, combining the edge features of the original CT image and the segmented image for probability estimation, which is used to improve the accuracy of the model edge segmentation. Medical images in NII special format were converted to Numpy matrix format using python, and then more than 2000 CT images containing only kidney tumours were selected from the KiTS19 dataset as the dataset for the model, and the dimensions were standardised to 128 × 128, and the experimental results show that the model outperforms many other advanced models with good segmentation performance.

Aggregate-aware model with bidirectional edge generation for medical image segmentation

Accurate segmentation of lesion areas plays an important role in medical imaging-assisted diagnosis and treatment. Accurate boundary information can help doctors develop precise surgical plans and improve patient prognosis. However, automatic segmentation methods often struggle to accurately segment edges due to the random shape, size, and location of regions of interest (ROI). This problem is compounded in medical images, where the difference in pixel intensity between foreground and background is significantly smaller than in natural images. In this study, we propose an aggregate-aware model with bidirectional edge generation (Ambeg) for medical image segmentation. To overcome the problem of blurred edges between foreground and background in medical images, we design a deep learning model via a multi-task learning strategy and obtain richer visual features to guide segmentation. Furthermore, an Edge Feature Fusion (EFF) module is developed to combine spatial correlation information of lesion edges between adjacent images for more accurate edge segmentation. Finally, we design a new evaluation metric, the Boundary DSC segmentation consistency measure, to evaluate the edge segmentation accuracy of medical image segmentation methods. We utilize dilation and erosion operations in morphological methods to construct lesion edge labels. In addition, we use expansion and erosion rates to regulate the dimensions of the edge region to assess the requirements of different diseases for edge segmentation accuracy. The proposed approach is particularly noteworthy for achieving state-of-the-art results on medical image segmentation datasets, including BraTS 2022 (MRI), BraTS 2020 (MRI) and COVID-19–20 (CT), which have different modalities of datasets. It has an impressive Hausdorff distance of 4.62 mm and a sensitivity score of 92.45 % on BraTS 2020. Compared with existing assessment methods such as Dice score, Boundary DSC segmentation consistency measure focuses on the hard-to-segment lesion edge region rather than the easy-to-segment lesion center region, which provides a more comprehensive reference for physicians to choose automatic segmentation methods. In addition, since the boundary shapes of medical images are complex and diverse, we utilize morphological methods to obtain the boundary labels to ensure the smoothness of the boundary. Moreover, the approach is easy to implement and has a low computational cost, making it an attractive option for practical medical imaging applications.

TLTNet: A novel transscale cascade layered transformer network for enhanced retinal blood vessel segmentation

Extracting global and local feature information is still challenging due to the problems of retinal blood vessel medical images like fuzzy edge features, noise, difficulty in distinguishing between lesion regions and background information, and loss of low-level feature information, which leads to insufficient extraction of feature information. To better solve these problems and fully extract the global and local feature information of the image, we propose a novel transscale cascade layered transformer network for enhanced retinal blood vessel segmentation, which consists of an encoder and a decoder and is connected between the encoder and decoder by a transscale transformer cascade module. Among them, the encoder consists of a local–global transscale transformer module, a multi-head layered transscale adaptive embedding module, and a local context(LCNet) module. The transscale transformer cascade module learns local and global feature information from the first three layers of the encoder, and multi-scale dependent features, fuses the hierarchical feature information from the skip connection block and the channel-token interaction fusion block, respectively, and inputs it to the decoder. The decoder includes a decoding module for the local context network and a transscale position transformer module to input the local and global feature information extracted from the encoder with retained key position information into the decoding module and the position embedding transformer module for recovery and output of the prediction results that are consistent with the input feature information. In addition, we propose an improved cross-entropy loss function based on the difference between the deterministic observation samples and the prediction results with the deviation distance, which is validated on the DRIVE and STARE datasets combined with the proposed network model based on the dual transformer structure in this paper, and the segmentation accuracies are 97.26% and 97.87%, respectively. Compared with other state-of-the-art networks, the results show that the proposed network model has a significant competitive advantage in improving the segmentation performance of retinal blood vessel images.

Adaptive multi-scale Graph Neural Architecture Search framework

Graph neural networks (GNNs) have gained significant attention for their ability to learn representations from graph-structured data, in which message passing and feature fusion strategies play an essential role. However, traditional Graph Neural Architecture Search (GNAS) mainly focuses on optimization with a static perceptive field to ease the search process. To efficiently utilize latent relationships between non-adjacent nodes as well as edge features, this work proposes a novel two-stage approach that is able to optimize GNN structures more effectively by adaptively aggregating neighborhood features in multiple scales. This adaptive multi-scale GNAS is able to assign optimal weights for different neighbors in different graphs and learning tasks. In addition, it takes latent relationships and edge features into message passing into account, and can incorporate different feature fusion strategies. Compared with traditional ones, our proposed approach can explore a much larger and more diversified search space efficiently. We also prove that traditional multi-hop GNNs are low-pass filters, which can lead to the removal of important low-frequency components of signals from remote neighbors in a graph, and they are not even expressive enough to distinguish some simple regular graphs, justifying the superiority of our approach. Experiments with seven datasets across three graph learning tasks, including graph regression, node classification, and graph classification, demonstrate that our method yields significant improvement compared with state-of-the-art GNAS approaches and human-designed GNN approaches. Specifically, for example, with our framework, the MAE of the 12-layer AM-GNAS was 0.102 for the ZINC dataset, yielding over 25% improvement.

Edge-Guided Hierarchical Network for Building Change Detection in Remote Sensing Images

Building change detection monitors building changes by comparing and analyzing multi-temporal images acquired from the same area and plays an important role in land resource planning, smart city construction and natural disaster assessment. Different from change detection in conventional scenes, buildings in the building change detection task usually appear in a densely distributed state, which is easy to be occluded; at the same time, building change detection is easily interfered with by shadows generated by light and similar-colored features around the buildings, which makes the edges of the changed region challenging to be distinguished. Aiming at the above problems, this paper utilizes edge information to guide the neural network to learn edge features related to changes and suppress edge features unrelated to changes, so as to accurately extract building change information. First, an edge-extracted module is designed, which combines deep and shallow features to supplement the lack of feature information at different resolutions and to extract the edge structure of the changed features; second, an edge-guided module is designed to fuse the edge features with different levels of features and to guide the neural network to focus on the confusing building edge regions by increasing the edge weights to improve the network’s ability to detect the edges that have changed. The proposed building change detection algorithm has been validated on two publicly available data (WHU and LEVIR-CD building change detection datasets). The experimental results show that the proposed model achieves 91.14% and 89.76% in F1 scores, respectively, demonstrating superior performance compared to some recent learning change detection methods.

UTE-CrackNet: transformer-guided and edge feature extraction U-shaped road crack image segmentation

UTE-CrackNet: transformer-guided and edge feature extraction U-shaped road crack image segmentation

Enhancing Multi-Class Attack Detection in Graph Neural Network through Feature Rearrangement

As network sizes grow, attack schemes not only become more varied but also increase in complexity. This diversification leads to a proliferation of attack variants, complicating the identification and differentiation of potential threats. Enhancing system security necessitates the implementation of multi-class intrusion detection systems. This approach enables the categorization of incoming network traffic into distinct intrusion types and illustrates the specific attack encountered within the Internet. Numerous studies have leveraged deep learning (DL) for Network-based Intrusion Detection Systems (NIDS), aiming to improve intrusion detection. Among these DL algorithms, Graph Neural Networks (GNN) stand out for their ability to efficiently process unstructured data, especially network traffic, making them particularly suitable for NIDS applications. Although NIDS usually monitors incoming and outgoing flows in a network, represented as edge features in graph format, traditional GNN studies only consider node features, overlooking edge features. This oversight can result in losing important flow data and diminish the system’s ability to detect attacks effectively. To address this limitation, our research makes several key contributions: (1) Emphasize the significance of edge features for enhancing GNN for multi-class intrusion detection, (2) Utilize port information, which is essential for identifying attacks but often overlooked during training, (3) Reorganize features embedded within the graph. By doing this, the graph can represent close to the actual network, which is the node showing endpoint identification information such as IP addresses and ports; the edge contains information related to flow such as Duration, Number of Packet/s, and Length…; (4) Compared to traditional methods, our experiments demonstrate significant performance improvements on both CIC-IDS-2017 (98.32%) and UNSW-NB15 (96.71%) datasets.

Offloading Strategy Based on Graph Neural Reinforcement Learning in Mobile Edge Computing

In the mobile edge computing (MEC) architecture, base stations with computational capabilities are subject to service coverage limitations, and the mobility of devices leads to dynamic changes in their connections, directly impacting the offloading decisions of agents. The connections between base stations and mobile devices, as well as the connections between base stations themselves, are abstracted into an MEC structural diagram due to the difficulty of deep reinforcement learning (DRL) in capturing the complex relationships between nodes and their multi-order neighboring nodes in the graph; decisions solely generated by DRL have limitations. To address this issue, this study proposes a hierarchical mechanism strategy based on Graph Neural Reinforcement Learning (M-GNRL) under multiple constraints. Specifically, the MEC structural graph constructed with the current device as an observation point aggregates to learn node features, thus comprehensively considering the contextual information of nodes, and the learned graph information serves as the environment for deep reinforcement learning, effectively integrating a graph neural network (GNN) with DRL. In the M-GNRL strategy, edge features from GNN are introduced into the architecture of the DRL network to enhance the accuracy of agents’ decision-making. Additionally, this study proposes an updated algorithm to obtain graph data that change with observation points. Comparative experiments demonstrate that the M-GNRL algorithm outperforms other baseline algorithms in terms of system cost and convergence performance.

GLAN: A graph-based linear assignment network

Differentiable solvers for the linear assignment problem (LAP) have attracted much research attention in recent years, which are usually embedded into learning frameworks as components. However, previous algorithms, with or without learning strategies, usually suffer from the degradation of the optimality with the increment of the problem size. In this paper, we propose a learnable linear assignment solver based on deep graph networks. Specifically, we first transform the cost matrix to a bipartite graph and convert the assignment task to the problem of selecting reliable edges from the constructed graph. Subsequently, a deep graph network is developed to aggregate and update the features of nodes and edges. Finally, the network predicts a label for each edge that indicates the assignment relationship. The experimental results on a synthetic dataset reveal that our method outperforms state-of-the-art baselines and achieves consistently high accuracy with the increment of the problem size. Furthermore, we also embed the proposed solver, in comparison with state-of-the-art baseline solvers, into a popular multi-object tracking (MOT) framework to train the tracker in an end-to-end manner. The experimental results on MOT benchmarks illustrate that the proposed LAP solver improves the tracker by the largest margin.

Remote Sensing Image Classification Based on Canny Operator Enhanced Edge Features.

Remote sensing image classification plays a crucial role in the field of remote sensing interpretation. With the exponential growth of multi-source remote sensing data, accurately extracting target features and comprehending target attributes from complex images significantly impacts classification accuracy. To address these challenges, we propose a Canny edge-enhanced multi-level attention feature fusion network (CAF) for remote sensing image classification. The original image is specifically inputted into a convolutional network for the extraction of global features, while increasing the depth of the convolutional layer facilitates feature extraction at various levels. Additionally, to emphasize detailed target features, we employ the Canny operator for edge information extraction and utilize a convolution layer to capture deep edge features. Finally, by leveraging the Attentional Feature Fusion (AFF) network, we fuse global and detailed features to obtain more discriminative representations for scene classification tasks. The performance of our proposed method (CAF) is evaluated through experiments conducted across three openly accessible datasets for classifying scenes in remote sensing images: NWPU-RESISC45, UCM, and MSTAR. The experimental findings indicate that our approach based on incorporating edge detail information outperforms methods relying solely on global feature-based classifications.

Mini-infrared thermal imaging system image denoising with multi-head feature fusion and detail enhancement network

The mini-infrared thermal imaging system (MITIS) has been widely applied in outdoor photography, military observation, medical auxiliary diagnosis, and so on. However, due to the limitations of infrared sensor performance, imaging system size, and environment interference, the infrared images captured by the current MITIS generally encounter noise interference and low contrast issues. To solve these issues, we propose a multi-head feature fusion and detail enhancement network, namely MdNet, for complex features (texture and edges) retaining and denoising of infrared images obtained from the MITIS. Specifically, MdNet consists of a multi-head feature fusion block (MFFB), detail enhancement block (DEB), and reconstruction convolution. The MFFB is designed to extract and fuse multi-scale feature information, including multi-scale and feature fusion blocks. The DEB is developed to enhance the noise feature and reduce the loss of detailed information by three multi-level local feature attention blocks and residual learning. Quantitative and qualitative experimental results demonstrate that the MdNet achieves competitive performance in removing synthetic and natural noises compared with other state-of-the-art infrared image denoising methods and provides an effective solution for MITIS image denoising.

A Visual Measurement Method for Deep Holes in Composite Material Aerospace Components.

The visual measurement of deep holes in composite material workpieces constitutes a critical step in the robotic assembly of aerospace components. The positioning accuracy of assembly holes significantly impacts the assembly quality of components. However, the complex texture of the composite material surface and mutual interference between the imaging of the inlet and outlet edges of deep holes significantly challenge hole detection. A visual measurement method for deep holes in composite materials based on the radial penalty Laplacian operator is proposed to address the issues by suppressing visual noise and enhancing the features of hole edges. Coupled with a novel inflection-point-removal algorithm, this approach enables the accurate detection of holes with a diameter of 10 mm and a depth of 50 mm in composite material components, achieving a measurement precision of 0.03 mm.

A Method for Roof Wireframe Reconstruction Based on Self-Supervised Pretraining

Abstract. In this paper, we present a two-stage method for roof wireframe reconstruction employing a self-supervised pretraining technique. The initial stage utilizes a multi-scale mask autoencoder to generate point-wise features. The subsequent stage involves three steps for edge parameter regression. Firstly, the initial edge directions are generated under the guidance of edge point identification. The next step employs edge parameter regression and matching modules to extract the parameters (namely, direction vector and length) of edge representation from the obtained edge features. Finally, a specifically designed edge non-maximum suppression and an edge similarity loss function are employed to optimize the representation of the final wireframe models and eliminate redundant edges. Experimental results indicate that the pre-trained self-supervised model, enriched by the roof wireframe reconstruction task, demonstrates superior performance on both the publicly available Building3D dataset and its post-processed iterations, specifically the Dense dataset, outperforming even traditional methods.

Intelligent Detection of Tunnel Leakage Based on Improved Mask R-CNN

The instance segmentation model based on deep learning has addressed the challenges in intelligently detecting water leakage in shield tunneling. Due to the limited generalization ability of the baseline model, occurrences of missed detections, false detections, and repeated detections are encountered during the actual detection of tunnel water leakage. This paper adopts Mask R-CNN as the baseline model and introduces a mask cascade strategy to enhance the quality of positive samples. Additionally, the backbone network in the model is replaced with RegNetX to enlarge the model’s receptive field, and MDConv is introduced to enhance the model’s feature extraction capability in the edge receptive field region. Building upon these improvements, the proposed model is named Cascade-MRegNetX. The backbone network MRegNetX features a symmetrical block structure, which, when combined with deformable convolutions, greatly assists in extracting edge features from corresponding regions. During the dataset preprocessing stage, we augment the dataset through image rotation and classification, thereby improving both the quality and quantity of samples. Finally, by leveraging pre-trained models through transfer learning, we enhance the robustness of the target model. This model can effectively extract features from water leakage areas of different scales or deformations. Through instance segmentation experiments conducted on a dataset comprising 766 images of tunnel water leakage, the experimental results demonstrate that the improved model achieves higher precision in tunnel water leakage mask detection. Through these enhancements, the detection effectiveness, feature extraction capability, and generalization ability of the baseline model are improved. The improved Cascade-MRegNetX model achieves respective improvements of 7.7%, 2.8%, and 10.4% in terms of AP, AP0.5, and AP0.75 compared to the existing Cascade Mask R-CNN model.

Application of image processing technology based on field programmable gate array in mechanical part inspection

Introduction: In the field of industrial manufacturing, accurate inspection of mechanical components such as gears and bearings is of Paramount importance. However, the traditional mechanical testing methods are often disturbed by human factors, which not only affects the stability of the test results, but also leads to low efficiency and large error. In order to solve these problems, this research focuses on developing a new edge detection model.Methods: A novel edge detection model based on field-programmable gate array image processing technology was used in this study. The model uses adaptive threshold multi-directional edge detection technology to identify the edge features of mechanical gears and bearings, aiming at improving the precision of detection.Results and Discussion: After performance verification, the running time of the model was controlled within 11 s, and the detection error was limited to less than 9%. Compared with the control group and the experimental group, their performance was superior. Further analysis data show that the detection accuracy of this model is as high as 0.9004, its internal resource utilization rate is 88%, and the detection rate is as high as 91%, which are better than the comparison model.Conclusion: The proposed test model not only significantly improves the efficiency and accuracy of the test, but also fully meets the requirements of the test. This new edge detection model has potential application value in industrial manufacturing field, and provides a new solution for industrial manufacturing quality inspection.

Learning Graph Representations Through Learning and Propagating Edge Features.

Graph convolutional networks have achieved considerable success in various graph domain tasks. Recently, numerous types of graph convolutional networks have been developed. A typical rule for learning a node's feature in these graph convolutional networks is to aggregate node features from the node's local neighborhood. However, in these models, the interrelation information between adjacent nodes is not well-considered. This information could be helpful to learn improved node embeddings. In this article, we present a graph representation learning framework that generates node embeddings through learning and propagating edge features. Instead of aggregating node features from a local neighborhood, we learn a feature for each edge and update a node's representation by aggregating local edge features. The edge feature is learned from the concatenation of the edge's starting node feature, the input edge feature, and the edge's end node feature. Unlike node feature propagation-based graph networks, our model propagates different features from a node to its neighbors. In addition, we learn an attention vector for each edge in aggregation, enabling the model to focus on important information in each feature dimension. By learning and aggregating edge features, the interrelation between a node and its neighboring nodes is integrated in the aggregated feature, which helps learn improved node embeddings in graph representation learning. Our model is evaluated on graph classification, node classification, graph regression, and multitask binary graph classification on eight popular datasets. The experimental results demonstrate that our model achieves improved performance compared with a wide variety of baseline models.

Adversarial Learning Based Node-Edge Graph Attention Networks for Autism Spectrum Disorder Identification.

Graph neural networks (GNNs) have received increasing interest in the medical imaging field given their powerful graph embedding ability to characterize the non-Euclidean structure of brain networks based on magnetic resonance imaging (MRI) data. However, previous studies are largely node-centralized and ignore edge features for graph classification tasks, resulting in moderate performance of graph classification accuracy. Moreover, the generalizability of GNN model is still far from satisfactory in brain disorder [e.g., autism spectrum disorder (ASD)] identification due to considerable individual differences in symptoms among patients as well as data heterogeneity among different sites. In order to address the above limitations, this study proposes a novel adversarial learning-based node-edge graph attention network (AL-NEGAT) for ASD identification based on multimodal MRI data. First, both node and edge features are modeled based on structural and functional MRI data to leverage complementary brain information and preserved in the constructed weighted adjacent matrix for individuals through the attention mechanism in the proposed NEGAT. Second, two AL methods are employed to improve the generalizability of NEGAT. Finally, a gradient-based saliency map strategy is utilized for model interpretation to identify important brain regions and connections contributing to the classification. Experimental results based on the public Autism Brain Imaging Data Exchange I (ABIDE I) data demonstrate that the proposed framework achieves a classification accuracy of 74.7% between ASD and typical developing (TD) groups based on 1007 subjects across 17 different sites and outperforms the state-of-the-art methods, indicating satisfying classification ability and generalizability of the proposed AL-NEGAT model. Our work provides a powerful tool for brain disorder identification.

MRFS: Mining Rating Fraud Subgraph in Bipartite Graph for Users and Products

Fraud in e-commerce fields (e.g., Amazon, Taobao, and so on) and social networks (e.g., Twitter and Weibo) has recently brought a very bad user experience. Rating fraud detection is an urgent issue for improving user experiences. However, existing methods have lots of limitations in some respects, because it is always very hard to acquire sufficient labeled data for fraud detection and detect new fraud patterns. Fortunately, the relationship for users rating (e.g., purchasing and following) products can be represented as a bipartite graph. So the problem of rating fraud detection can be transformed into the problem of abnormal subgraph detection in the bipartite graph. The major challenge of fraud detection is to distinguish fake rates from real user rates. In this article, we focus on mining rating fraud-connected subgraphs in a bipartite graph. The motivation for this work is fraud detection tasks, which can usually be formulated as mining a bipartite graph formed by source nodes (followers and users) and target nodes (followees and products) for malicious patterns. Now, smart fraudsters evade existing detection methods by buying a large pool of users and hijacking honest users, making them look “normal”-this behavior is called “ <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">camouflage</i> .” Accordingly, we propose a fraud detection approach for mining rating fraud subgraph (MRFS), which addresses the problem from the intrinsic metric (e.g., fraudulence, badness and unreliability). The proposed MRFS mines the intrinsic characteristics of nodes and edges from node behavior information, which is an effective and scalable (linear on the input size) algorithm. A large number of comparative experimental results on real-world rating networks show that our proposed MRFS is efficient and universal.

A Semi-supervised Four-Chamber Echocardiographic Video Segmentation Algorithm Based on Multilevel Edge Perception and Calibration Fusion

ObjectiveEchocardiographic videos are commonly used for automatic semantic segmentation of endocardium, which is crucial in evaluating cardiac function and assisting doctors to make accurate diagnoses of heart disease. However, this task faces two distinct challenges: one is the edge blurring, which is caused by the presence of speckle noise or excessive de-noising operation, and the other is the lack of an effective feature fusion approach for multilevel features for obtaining accurate endocardium. MethodsIn this study, a deep learning model, based on multilevel edge perception and calibration fusion is proposed to improve the segmentation performance. First, a multilevel edge perception module is proposed to comprehensively extract edge features through both a detail branch and a semantic branch to alleviate the adverse impact of noise. Second, a calibration fusion module is proposed that calibrates and integrates various features, including semantic and detailed information, to maximize segmentation performance. Furthermore, the features obtained from the calibration fusion module are stored by using a memory architecture to achieve semi-supervised segmentation through both labeled and unlabeled data. ResultsOur method is evaluated on two public echocardiography video data sets, achieving average Dice coefficients of 93.05% and 93.93%, respectively. Additionally, we validated our method on a local hospital clinical data set, achieving a Pearson correlation of 0.765 for predicting left ventricular ejection fraction. ConclusionThe proposed model effectively solves the challenges encountered in echocardiography by using semi-supervised networks, thereby improving the segmentation accuracy of the ventricles. This indicates that the proposed model can assist cardiologists in obtaining accurate and effective research and diagnostic results.