检索结果-内蒙古大学图书馆

Active contour model based on fuzzy C-means and local pre-fitting energy for image segmentation

SIGNAL image AND VIDEO PROCESSING 2025年第2期19卷 1-11页

作者： Huang, Keya Ouyang, Jingzhi Weng, Guirong Soochow Univ Sch Mech & Elect Engn 8 Jixue Rd Suzhou 215137 Jiangsu Peoples R China

Active contour models (ACM) have achieved remarkable results in image segmentation. However, existing ACMs have some shortcomings, such as over-dependence on the initial contour, complex parameter adjustments, and difficulty in balancing segmentation accuracy and speed. To further improve the performance of ACM, this paper proposes an active contour model based on fuzzy c-means and local pre-fitting function (FLPF). Firstly, a linear weighted image is defined as a sample for the fuzzy c-means (FCM) clustering algorithm to pre-fit the image intensity. A pre-processing operation is proposed to improve the FCM clustering algorithm and increase the computation speed. Then, second-order differential data-driven terms based on the local pre-fitting energy are designed to guide the curve evolution rapidly and adaptively toward the target boundary. In addition, adaptive regularization functions are constructed to optimize and normalize the data-driven terms and level set functions, which improves the robustness of the proposed model. Finally, an improved parameter tuning framework based on the deep learning algorithm YOLOv5 is proposed for the FLPF model to achieve automated parameter adjustments. Compared to the other six models, our model has advantages in segmentation speed and accuracy, reducing the average segmentation time by 77.5% and improving the average segmentation accuracy by more than 7.6% of 10 images.

关键词： image segmentation Active contour model Local pre-fitting Deep learning

来源：评论

学校读者我要写书评

暂无评论

Consistency-Guided Differential Decoding for Enhancing Semi-Supervised Medical image segmentation

引用

IEEE TRANSACTIONS ON MEDICAL IMAGING 2025年第1期44卷 44-56页

作者： Zeng, Qingjie Xie, Yutong Lu, Zilin Lu, Mengkang Zhang, Jingfeng Xia, Yong Northwestern Polytech Univ Sch Comp Sci & Engn Natl Engn Lab Integrated Aerosp Ground Ocean Big D Xian 710072 Peoples R China Univ Adelaide Australian Inst Machine Learning Adelaide SA 5000 Australia Ningbo Hosp 2 Ningbo 315000 Peoples R China Res & Dev Inst Northwestern Polytech Univ Shenzhen Shenzhen 518057 Peoples R China Ningbo Inst Northwestern Polytech Univ Ningbo 315048 Peoples R China

Semi-supervised learning (SSL) has been proven beneficial for mitigating the issue of limited labeled data, especially on volumetric medical image segmentation. Unlike previous SSL methods which focus on exploring highly confident pseudo-labels or developing consistency regularization schemes, our empirical findings suggest that differential decoder features emerge naturally when two decoders strive to generate consistent predictions. Based on the observation, we first analyze the treasure of discrepancy in learning towards consistency, under both pseudo-labeling and consistency regularization settings, and subsequently propose a novel SSL method called LeFeD, which learns the feature-level discrepancies obtained from two decoders, by feeding such information as feedback signals to the encoder. The core design of LeFeD is to enlarge the discrepancies by training differential decoders, and then learn from the differential features iteratively. We evaluate LeFeD against eight state-of-the-art (SOTA) methods on three public datasets. Experiments show LeFeD surpasses competitors without any bells and whistles, such as uncertainty estimation and strong constraints, as well as setting a new state of the art for semi-supervised medical image segmentation. Code has been released at https://***/maxwell0027/LeFeD.

关键词： Decoding image segmentation Training Semisupervised learning Task analysis Medical diagnostic imaging Labeling Semi-supervised learning medical image segmentation differential feature learning

来源：评论

学校读者我要写书评

暂无评论

An image segmentation method for solid-liquid separation on shale shaker based on an improved U2Net

引用

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2025年 149卷

作者： Wang, Wenbin Hou, Yongjun Jiang, Rui Fang, Pan Peng, Hong Li, Qing Li, Huachuan Southwest Petr Univ Sch Mechatron Engn Chengdu Peoples R China Sichuan BOMCO Special Vehicle Manufacture Co Ltd Guanghan Peoples R China

In the actual production process of shale shakers, detecting the solid-liquid separation state of the screen surface faces numerous challenges, such as difficulty in recognizing the mud boundary, insufficient anti-interference ability, and misjudgment caused by background interference. To address these issues, this paper proposes a screen surface mud image segmentation method based on U2Net, namely CBAM-U2Net. By introducing the Convolutional Block Attention Module (CBAM) and combining it with Multi-layer Recursive Residual Blocks (RSU), a network structure is designed that can efficiently fuse global and local features, significantly improving segmentation accuracy and robustness. The network includes encoder and decoder parts, employing convolution, batch normalization, ReLU activation, and multi-scale feature fusion strategies. Experimental results show that the CBAM-U2Net method demonstrates excellent segmentation performance under various working conditions, achieving outstanding results with mIoU, F1-score, Precision, and Recall at 83.38%, 89.75%, 89.38%, and 92.64%, respectively, with significantly enhanced anti-interference capability. The CBAM-U2Net method provides an efficient and reliable solution for the intelligent monitoring of the solid-liquid separation state in shale shakers, offering significant practical application value.

关键词： Shale shaker Solid-liquid separation image segmentation U2Net Convolutional block attention module

来源：评论

学校读者我要写书评

暂无评论

BiASAM: Bidirectional-Attention Guided Segment Anything Model for Very Few-Shot Medical image segmentation

引用

IEEE SIGNAL PROCESSING LETTERS 2025年 32卷 246-250页

作者： Zhou, Wei Guan, Guilin Cui, Wei Yi, Yugen Shenyang Aerosp Univ Coll Comp Sci Shenyang 110136 Peoples R China ASTAR Inst Infocomm Res I2R Singapore 138632 Singapore Jiangxi Normal Univ Sch Software Nanchang 330022 Peoples R China

The Segment Anything Model (SAM) excels in general segmentation but encounters difficulties in medical imaging due to few-shot learning challenges, particularly with extremely limited annotated data. Existing approaches often suffer from insufficient feature extraction and inadequate loss function balancing, resulting in decreased accuracy and poor generalization. To address these issues, we propose BiASAM, which uniquely incorporates two bidirectional attention mechanisms into SAM for medical image segmentation. Firstly, BiASAM integrates a spatial-frequency attention module to improve feature extraction, enhancing the model's ability to capture both fine and coarse details. Secondly, we employ an attention-based gradient update mechanism that dynamically adjusts loss weights, boosting the model's learning efficiency and adaptability in data-scarce scenarios. Additionally, BiASAM utilizes the point and box fusion prompt to enhance segmentation precision at both global and local levels. Experiments across various medical datasets show BiASAM achieves performance comparable to fully supervised methods with just two labeled samples.

关键词： Feature extraction image segmentation Biomedical imaging Frequency-domain analysis Optical losses Fast Fourier transforms Adaptation models Lungs Training Noise Bidirectional attention few-shot medical image segmentation model generalization

来源：评论

学校读者我要写书评

暂无评论

Rethinking Feature Guidance for Medical image segmentation

引用

IEEE SIGNAL PROCESSING LETTERS 2025年 32卷 641-645页

作者： Wang, Wei He, Jixing Wang, Xin Changsha Univ Sci & Technol Sch Comp & Commun Engn Changsha 410114 Peoples R China

Despite the evident advantages of variants of UNet in medical image segmentation, these methods still exhibit limitations in the extraction of foreground, background, and boundary features. Based on feature guidance, we propose a new network (FG-UNet). Specifically, adjacent high-level and low-level features are used to gradually guide the network to perceive lesion features. To accommodate lesion features of different scales, the multi-order gated aggregation (MGA) block is designed based on multi-order feature interactions. Furthermore, a novel feature-guided context-aware (FGCA) block is devised to enhance the capability of FG-UNet to segment lesions by fusing boundary-enhancing features, object-enhancing features, and uncertain areas. Eventually, a bi-dimensional interaction attention (BIA) block is designed to enable the network to highlight crucial features effectively. To appraise the effectiveness of FG-UNet, experiments were conducted on Kvasir-seg, ISIC2018, and COVID-19 datasets. The experimental results illustrate that FG-UNet achieves a DSC score of 92.70% on the Kvasir-seg dataset, which is 1.15% higher than that of the latest SCUNet++, 4.70% higher than that of ACC-UNet, and 5.17% higher than that of UNet.

关键词： Feature extraction image segmentation Lesions Medical diagnostic imaging Convolution Logic gates Transformers Data mining COVID-19 Accuracy Feature guidance feature interactions medical image segmentation

来源：评论

学校读者我要写书评

暂无评论

XSNet: A Lightweight X-Ray Security image segmentation Model Combining State-Space Models and Convolutional Neural Networks

引用

IEEE SIGNAL PROCESSING LETTERS 2025年 32卷 1351-1355页

作者： Jia, Weichao Liu, Wei Zhang, Changsheng Fu, Jian Liu, Qiong Beijing Informat Sci & Technol Univ Beijing 100192 Peoples R China Beihang Univ Ningbo Innovat Res Inst Ningbo 315800 Peoples R China Beijing Univ Aeronaut & Astronaut Beijing 100191 Peoples R China

In this letter, we propose a novel lightweight X-ray image contraband segmentation network, XSNet, which integrates State Space Models (SSM) with Convolutional Neural Networks (CNNs) to achieve a significant trade-off between segmentation accuracy and lightweight design for computer-aided X-ray security check. The model is built based on the encoder-decoder framework. Specifically, we design an Multi-scale Convolution Fusion (MCF) block for multi-scale information extraction and a Dual-branch State Space Model (DSSM) block to relieve the bias caused by the imbalance of single branch structure in feature extraction and maintain the capabilities of SSM in modeling long range pixel dependencies. In addition, we present two versions of the model in two different sizes called XSNet-s and XSNet-l respectively. The quantitative and qualitative evaluations on the public PIDray and PIXray datasets both show the superiority of two models in terms of mean Intersection over Union (mIoU) and FLOPs.

关键词： Computational modeling image segmentation Feature extraction X-ray imaging Security Training Decoding Accuracy Data mining Signal processing algorithms Contraband segmentation state space models X-ray images deep learning

来源：评论

学校读者我要写书评

暂无评论

Merging Context Clustering with Visual State Space Models for Medical image segmentation

引用

IEEE Transactions on Medical Imaging 2025年第5期44卷 2131-2142页

作者： Zhu, Yun Zhang, Dong Lin, Yi Feng, Yifei Tang, Jinhui Nanjing University of Science and Technology School of Computer Science and Engineering Nanjing210094 China The Hong Kong University of Science and Technology Department of Electronic and Computer Engineering Hong Kong Hong Kong The Hong Kong University of Science and Technology Department of Computer Science and Engineering Hong Kong Hong Kong Nanjing Medical University First School of Clinical Medicine China First Affiliated Hospital of Nanjing Medical University Department of General Surgery Nanjing China

Medical image segmentation demands the aggregation of global and local feature representations, posing a challenge for current methodologies in handling both long-range and short-range feature interactions. Recently, vision mamba (ViM) models have emerged as promising solutions for addressing model complexities by excelling in long-range feature iterations with linear complexity. However, existing ViM approaches overlook the importance of preserving short-range local dependencies by directly flattening spatial tokens and are constrained by fixed scanning patterns that limit the capture of dynamic spatial context information. To address these challenges, we introduce a simple yet effective method named context clustering ViM (CCViM), which incorporates a context clustering module within the existing ViM models to segment image tokens into distinct windows for adaptable local clustering. Our method effectively combines long-range and short-range feature interactions, thereby enhancing spatial contextual representations for medical image segmentation tasks. Extensive experimental evaluations on diverse public datasets, i.e., Kumar, CPM17, ISIC17, ISIC18, and Synapse, demonstrate the superior performance of our method compared to current state-of-the-art methods. Our code can be found at https://***/zymissy/CCViM. © 1982-2012 IEEE.

关键词： image segmentation

来源：评论

学校读者我要写书评

暂无评论

Efficient Generative-Adversarial U-Net for Multi-Organ Medical image segmentation

引用

JOURNAL OF IMAGING 2025年第1期11卷 19-19页

作者： Wang, Haoran Wu, Gengshen Liu, Yi City Univ Macau Fac Data Sci Ave Padre Tomas Pereira Taipa 999078 Macao Peoples R China Changzhou Univ Sch Comp Sci & Artificial Intelligence Changzhou 213000 Peoples R China

Manual labeling of lesions in medical image analysis presents a significant challenge due to its labor-intensive and inefficient nature, which ultimately strains essential medical resources and impedes the advancement of computer-aided diagnosis. This paper introduces a novel medical image-segmentation framework named Efficient Generative-Adversarial U-Net (EGAUNet), designed to facilitate rapid and accurate multi-organ labeling. To enhance the model's capability to comprehend spatial information, we propose the Global Spatial-Channel Attention Mechanism (GSCA). This mechanism enables the model to concentrate more effectively on regions of interest. Additionally, we have integrated Efficient Mapping Convolutional Blocks (EMCB) into the feature-learning process, allowing for the extraction of multi-scale spatial information and the adjustment of feature map channels through optimized weight values. Moreover, the proposed framework progressively enhances its performance by utilizing a generative-adversarial learning strategy, which contributes to improvements in segmentation accuracy. Consequently, EGAUNet demonstrates exemplary segmentation performance on public multi-organ datasets while maintaining high efficiency. For instance, in evaluations on the CHAOS T2SPIR dataset, EGAUNet achieves approximately 2% higher performance on the Jaccard metric, 1% higher on the Dice metric, and nearly 3% higher on the precision metric in comparison to advanced networks such as Swin-Unet and TransUnet.

关键词： image segmentation medical image analysis deep learning attention mechanism

来源：评论

学校读者我要写书评

暂无评论

U-net of joint spatial domains with multi-scale atrous convolution for rectal image segmentation

引用

Multimedia Tools and Applications 2025年 1-17页

作者： Rao, Yunbo Gao, Li Zeng, Shaoning Shao, Tingting Sun, Jihong School of Information and Software Engineering University of Electronic Science and Technology of China Chengdu611731 China Yangtze Delta Region Institute University of Electronic Science and Technology of China Huzhou313000 China Zhejiang University School of Medicine Zhejiang Hangzhou310058 China

Medical image segmentation is very important for the diagnosis of related diseases. To reduce the labeling work of related medical images, numerous models based on U-Net have been proposed to achieve automatic segmentation of target regions. However, most of these models are only trained in one coordinate system, ignoring the joint effects of different spatial coordinate systems. In addition, most of the encoding modules in these models do not pay attention to multi-scale spatial information. Our proposed solution for the aforementioned challenges involves using U-Net model with joint spatial domains and multi-scale encoding module, which enables us to segment rectal image better. The model includes a self-designed multi-layer dilated convolution encoding module named AIR (Atrous Inception Residual Block), to achieve a multi-scale content fusion. Besides this, it utilizes the center point and polar coordinates to realize attention mechanism and rotation invariance. Furthermore, retraining the output of polar coordinate network with Cartesian coordinate system realizes the translation invariance of segmentation. Compared with the commonly used medical segmentation models, the dice coefficient of our model is improved by about 2% on our in-house rectal dataset. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.

关键词： image segmentation

来源：评论

学校读者我要写书评

暂无评论

Intelligent Diagnosis Model for Stroke in Elderly Patients Based on Electrocardiogram Classification and MRI image segmentation Algorithms

引用

TRAITEMENT DU SIGNAL 2025年第1期42卷 485-494页

作者： Luo, Yingyan Shen, Jie Chen, Jialei Wu, Zhenzhen Zhejiang Business Coll Off Acad Res Hangzhou 310053 Peoples R China Zhejiang Business Coll Technol Ctr Hangzhou 310053 Peoples R China Zhejiang Prov Peoples Hosp Affiliated Peoples Hosp Hangzhou Med Coll Hlth Management CtrDept Instrumental Examinat Hangzhou 310024 Peoples R China

By the end of 2023, Athere were approximately 220 million elderly patients aged 60 and above in China, with the incidence of stroke increasing significantly with age. The incidence rate for those over 75 is 5 to 8 times higher than that of individuals aged 45-55. AElderly strokes typically have an acute onset and rapid progression, making early detection critical for prognosis. Medical research has shown that left ventricular hypertrophy (LVH) on an electrocardiogram (ECG) is an independent risk factor for stroke inApatients. Therefore, this study aims to develop an intelligent diagnostic model for stroke in elderly patients. First, we analyze 12-lead ECG data from health check-ups of elderly patients over 60 years old to construct a LVH classification model. This model, based on convolutional neural networks (CNN) Aand Transformer networks, extracts ECG features from both local waveform characteristics and global long-range dependencies. The fusion of abnormal ECG features improves the model's ability to identify specific LVH rhythm types associated with certain leads, while the inclusion of global context information optimizes model performance. Experiments demonstrate that the model, tested on a self-built dataset, achieves sensitivity, specificity, accuracy, and F1 score of 0.81, 0.92, 0.87, Aand 0.91, Arespectively, with an AUC of 0.91. ASubsequently, we integrate MRI image segmentation technology to assist doctors in diagnosing lesion areas. We propose an MRI image segmentation model based on an improved UNet network with an attention mechanism. Experimental results show that the stroke image segmentation algorithm proposed in this study achieves an accuracy of 98.78%, Asensitivity of 92.03%, Aand specificity of 96.58%. AThe research in this paper can assist doctors in clinical decision-making by first detecting potential elderly LVH patients through ECG data and then using MRI image segmentation algorithms to assist in the precise diagnosis of stroke lesions,

关键词： elderly stroke left ventricular hypertrophy (LVH) electrocardiogram (ECG) stroke MRI image segmentation deep learning

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：