检索结果-内蒙古大学图书馆

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

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 Univ Sci & Technol Sch Comp Sci & Engn Nanjing 210094 Peoples R China Hong Kong Univ Sci & Technol Dept Elect & Comp Engn Hong Kong Peoples R China Hong Kong Univ Sci & Technol Dept Comp Sci & Engn Hong Kong Peoples R China Nanjing Med Univ Affiliated Hosp 1 Sch Clin Med 1 Dept Gen Surg Nanjing 210029 Peoples R 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.

关键词： Context modeling image segmentation Computational modeling Visualization Transformers Medical diagnostic imaging Adaptation models Feature extraction Natural language processing Merging Context clustering medical image segmentation vision mamba visual state space model

来源：评论

学校读者我要写书评

暂无评论

FlowSDF: Flow Matching for Medical image segmentation Using Distance Transforms

引用

INTERNATIONAL JOURNAL OF COMPUTER VISION 2025年 1-13页

作者： Bogensperger, Lea Narnhofer, Dominik Falk, Alexander Schindler, Konrad Pock, Thomas Graz Univ Technol Inst Comp G & Vis Graz Austria Swiss Fed Inst Technol Photogrammetry & Remote Sensing Zurich Switzerland

Medical image segmentation plays an important role in accurately identifying and isolating regions of interest within medical images. Generative approaches are particularly effective in modeling the statistical properties of segmentation masks that are closely related to the respective structures. In this work we introduce FlowSDF, an image-guided conditional flow matching framework, designed to represent the signed distance function (SDF), and, in turn, to represent an implicit distribution of segmentation masks. The advantage of leveraging the SDF is a more natural distortion when compared to that of binary masks. Through the learning of a vector field associated with the probability path of conditional SDF distributions, our framework enables accurate sampling of segmentation masks and the computation of relevant statistical measures. This probabilistic approach also facilitates the generation of uncertainty maps represented by the variance, thereby supporting enhanced robustness in prediction and further analysis. We qualitatively and quantitatively illustrate competitive performance of the proposed method on a public nuclei and gland segmentation data set, highlighting its utility in medical image segmentation applications.

关键词： Flow matching image segmentation Conditional generative models Signed distance function

来源：评论

学校读者我要写书评

暂无评论

Ultra-Lightweight Network for Medical image segmentation Inspired by Bio-Visual Interaction

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 2025年第4期35卷 3486-3497页

作者： Cai, Zhefei Fan, Yingle Zhu, Minwei Fang, Tao Hangzhou Dianzi Univ Sch Automat Hangzhou 310018 Peoples R China Univ Miami Dept Biomed Engn Miami FL 33124 USA

Computer-aided medical image segmentation helps to assist physicians in locating lesion area for the subsequent diagnosis and treatment. Due to the irregular shape of the target and the uneven sample size between the target and the background area, automatic segmentation of medical images is a challenging task. Many CNN-Based, Transformer-Based models deepen the number of network layers or introduce complex modules in order to improve the segmentation accuracy. Limited by the computational resources, these types of large models are not suitable for the actual clinical environment. Inspired by the rapidity, accuracy, and low consumption characteristics of bio-visual processing, the Ultra-Lightweight Network Inspired by Bio-Visual Interaction (BVI-Net) is constructed in this paper. The Global Pathway is constructed by simulating the dorsal stream, in order to extract global features rapidly, and the Local Pathway is constructed by simulating the ventral stream, in order to process local features finely. At the same time, the skip connection module integrating Graph Convolutional Network (GCN) attention mechanism is constructed to simulate the synchronous integration ability of the visual pathway for multi-level features. The International Skin Imaging Collaboration (ISIC) dataset, the Liver Tumor segmentation (LiTS) dataset, and the Brain Tumor segmentation Challenge (BraTS) dataset are used for experiments. The BVI-Net proposed in this paper requires only 0.026M parameters to achieve the excellent performance in three representative medical image segmentation datasets, which has certain advantages over state-of-the-art (SOTA) methods. The biological vision mechanism and the artificial intelligence algorithm are integrated in this paper, which provides new ideas for the construction of biological vision-guided deep learning models and promotes the development of biomimetic computational vision.

关键词： Feature extraction image segmentation Transformers Kernel Accuracy Visualization Computational modeling Biological system modeling Lesions Streaming media Biological visual pathway dual encoder architecture GCN attention mechanism state space models medical image segmentation

来源：评论

学校读者我要写书评

暂无评论

Exploring Contrastive Pre-Training for Domain Connections in Medical image segmentation

引用

IEEE TRANSACTIONS ON MEDICAL IMAGING 2025年第4期44卷 1686-1698页

作者： Zhang, Zequn Jiang, Yun Wang, Yunnan Xie, Baao Zhang, Wenyao Li, Yuhang Chen, Zhen Jin, Xin Zeng, Wenjun Univ Sci & Technol China USTC Dept Elect Engn & Informat Sci Hefei 230026 Peoples R China Eastern Inst Technol EIT Ningbo Ningbo 315200 Peoples R China Northwest Normal Univ Coll Comp Sci & Engn Lanzhou 730071 Peoples R China EIT Ningbo Ningbo Inst Digital Twin Ningbo 315200 Peoples R China Chinese Acad Sci Hong Kong Inst Sci & Innovat Hong Kong Peoples R China

Unsupervised domain adaptation (UDA) in medical image segmentation aims to improve the generalization of deep models by alleviating domain gaps caused by inconsistency across equipment, imaging protocols, and patient conditions. However, existing UDA works remain insufficiently explored and present great limitations: 1) Exhibit cumbersome designs that prioritize aligning statistical metrics and distributions, which limits the model's flexibility and generalization while also overlooking the potential knowledge embedded in unlabeled data;2) More applicable in a certain domain, lack the generalization capability to handle diverse shifts encountered in clinical scenarios. To overcome these limitations, we introduce MedCon, a unified framework that leverages general unsupervised contrastive pre-training to establish domain connections, effectively handling diverse domain shifts without tailored adjustments. Specifically, it initially explores a general contrastive pre-training to establish domain connections by leveraging the rich prior knowledge from unlabeled images. Thereafter, the pre-trained backbone is fine-tuned using source-based images to ultimately identify per-pixel semantic categories. To capture both intra- and inter-domain connections of anatomical structures, we construct positive-negative pairs from a hybrid aspect of both local and global scales. In this regard, a shared-weight encoder-decoder is employed to generate pixel-level representations, which are then mapped into hyper-spherical space using a non-learnable projection head to facilitate positive pair matching. Comprehensive experiments on diverse medical image datasets confirm that MedCon outperforms previous methods by effectively managing a wide range of domain shifts and showcasing superior generalization capabilities.

关键词： Training image segmentation Generators Measurement Data models Anatomical structure Semantics Prototypes Head Buildings Domain connectivity unsupervised domain adaptation unsupervised contrastive pre-training cross-domain medical image segmentation

来源：评论

学校读者我要写书评

暂无评论

DRLSU-Net: Level set with U-Net for medical image segmentation

引用

DIGITAL SIGNAL PROCESSING 2025年 157卷

作者： Wang, Xiaofeng Liu, Jiashan Yang, Rentao Wu, Zhize Sun, Lingma Zou, Le Hefei Univ Sch Artificial Intelligence & Big Data Hefei 230601 Anhui Peoples R China

Convolutional neural networks (CNN) have been extensively utilized for image segmentation tasks, with the UNet architecture emerging as a classical model in medical imaging due to its simple structure and high scalability. However, for complex medical images, particularly those with blurred lesion boundaries, the U-Net model often loses significant edge information during feature extraction. Each layer in the encoder section is convolved with a simple stack of equal design, which is clearly not able to obtain sufficient feature information from an otherwise low-quality image. In order to solve this problem, the DRLSU-Net model is proposed which combines an enhanced U-Net architecture with distance regularized level set evolution (DRLSE). The DRLSU-Net model takes the results of U-Net pre-segmentation as an intermediate medium, combines the U-Net model with the level set method. Indirectly represent the target contour through the zero level set to obtain a more intuitive target edge location. Specifically, the Parallel Dilated Convolutional Sequence (PDCS) is introduced in the U-Net encoder to minimize information loss during down-sampling, and preserve more edge details. Secondly, the Mixed Attention Mechanism (MAM) is introduced into the decoder, aiding the network in recovering important information during image reconstruction, thus generating a more accurate output sequence. Finally, the pre-segmentation label mapping is converted into a level set function representation, which serves as a priori information for the level set method. A new energy functional is constructed to guide the evolution of the level set curves, helping to obtain a clear contour boundary. The performance of the DRLSU-Net model is evaluated on the ISIC2017, ISIC2018, CVC-ClinicDB, and Lung datasets. Extensive experiment results show better performance than other state-of-the-art (SOTA) methods in terms of mIoU and F1-socre, and the results indicate that the DRLSU-Net model performs competit

关键词： Convolutional neural network image segmentation U-Net Level set

来源：评论

学校读者我要写书评

暂无评论

SHPNeXt: A Novel Method of Multi-Scale and Variable Resolution AI-Based Tongue image segmentation

引用

IEEE ACCESS 2025年 13卷 54504-54516页

作者： Peng, Chong-Xiao Gao, Zhi-Jun Wang, Jin-Huan Yue, Xin Li, Yi Sun, Li-Li Sun, Yin-Huan Du, Fu-Quan Heilongjiang Univ Sci & Technol Sch Comp Informat & Engn Harbin 150022 Peoples R China Heilongjiang Univ Chinese Med Affiliated Hosp 1 Harbin 150040 Peoples R China

In the domain of Traditional Chinese Medicine, accurately segmenting tongue images is fundamental for computer-assisted diagnosis. Yet, current models often falter with images of diverse scales and clarity, impeding their widespread application. To address this challenge, we propose SHPNeXt, an innovative network designed to accurately segment tongue images across different scales and resolutions. This model blends PoolFormer and Hire-MLP to adeptly discern both overarching and nuanced details, ensuring accurate segmentation across varying tongue image sizes. Furthermore, SHPNeXt's precision was further enhanced by integrating a Nuclear-Norm Non-negative Matrix Factorization (NMF) approach, which robustly counters noise in lower quality images. Experiments on three benchmark datasets demonstrate SHPNeXt's superior performance, achieving mean Intersection over Union (mIoU) scores of 99.64%, 97.05%, and 96.82%. Balancing efficiency and accuracy, SHPNeXt's architecture comprises 5.984 million parameters and operates at 1.22 GFLOPs, rendering it an exceptionally effective tool for real-world tongue diagnosis in TCM. The code has been released on github: (https://***/Kuanzhaipcx/***).

关键词： Tongue image segmentation Medical diagnostic imaging Transformers Convolution Computational modeling Accuracy Matrix decomposition Feature extraction Decoding Tongue image segmentation SHPNeXt multi-scale variable resolution images deep learning

来源：评论

学校读者我要写书评

暂无评论

Dynamic comprehensive learning-based dung beetle optimizer using triangular mutation for polyps image segmentation

引用

COMPUTATIONAL BIOLOGY AND CHEMISTRY 2025年 118卷 108474页

作者： Abd Elaziz, Mohamed Oliva, Diego El-Bary, Alaa A. Aseeri, Ahmad O. Ibrahim, Rehab Ali Zagazig Univ Fac Sci Dept Math Zagazig 44519 Egypt Galala Univ Fac Comp Sci & Engn Suze 435611 Egypt Ajman Univ Coll Engn & Informat Technol Artificial Intelligence Res Ctr AIRC Ajman U Arab Emirates Univ Guadalajara CUCEI Dept Ingn Electrofoton Guadalajara 44430 Mexico Arab Acad Sci Technol & Maritime Transport Basic & Appl Sci Inst POB 1029 Alexandria Egypt Acad Sci Res & Technol Natl Comm Math Cairo Egypt Acad Sci Res & Technol Council Future Studies & Risk Management Cairo Egypt Prince Sattam Bin Abdulaziz Univ Coll Comp Engn & Sci Dept Comp Sci Al Kharj 11942 Saudi Arabia

The process of early diagnosis of polyps is considered a critical point of preventive healthcare, as it can significantly improve the prognosis and treatment outcomes of patients with colorectal cancer. Since the Polyps are constructed in the colon, they can grow up to be cancerous over time. We present an alternative Polyps image segmentation approach according to multilevel thresholding techniques (MLTs) to ensure effective early polyp diagnosis. The developed MLT Polyps image segmentation method depends on improving the performance of the Dung beetle optimizer (DBO) algorithm based on the operators of Triangular Mutation (TMO), Comprehensive learning (CL), and dynamic update of the search domain. We conducted a comprehensive evaluation of the performance of the DCTDBO using eight Polyps images and compared it with other image segmentation methods, ensuring a rigorous and thorough process. The results show the high ability of the DCTDBO according to performance measures to segment the Polyps images. In terms of peak signal-to-noise ratio (PSNR), structural similarity index (SSIM), and feature similarity (FSIM), DCTDBO performed better than the basic version of the DBO and other methods. For example, the average of DCTDBO overall threshold levels and tested images in terms of FSIM, SSIM, and PSNR is 0.9668, 0.99217, and 28.9338, respectively. This indicates the influence of TMO and CL on enhancing the performance of DBO.

关键词： Polyps images image segmentation Multilevel thresholding Dung beetle optimizer (DBO)

来源：评论

学校读者我要写书评

暂无评论

Deep convolutional neural networks meet variational shape compactness priors for image segmentation

引用

NEUROCOMPUTING 2025年 623卷

作者： Zhang, Kehui Li, Lingfeng Liu, Hao Yuan, Jing Tai, Xue-Cheng Hong Kong Baptist Univ Dept Math Kowloon Tong Hong Kong Peoples R China Hong Kong Ctr Cerebro Cardiovasc Hlth Engn Sha Tin Hong Kong Peoples R China Zhejiang Normal Univ Coll Math Med Jinhua Zhejiang Peoples R China Norwegian Res Ctr Bergen Norway

Integrating spatial priors into image segmentation methods is essential for enhancing prediction accuracy and robustness. In this work, we focus on the shape compactness prior, which measures the circularity of objects, for variational image segmentation tasks. segmentation of circular objects has significant applications across various fields. We propose utilizing shape compactness as a tool to address these applications. Existing algorithms face challenges such as computational inefficiency, model nonconvexity, and the need for extensive hyperparameter fine-tuning. To overcome these issues, we introduce two novel optimization algorithms coupled with the primal-dual formulation of the original problem: the primal-dual threshold dynamics (PD-TD) and the primal-dual soft threshold-dynamics algorithm (PD-STD). The PD-STD is a relaxed version of the PD-TD and offers superior computational efficiency. Building on the variational explanation of the sigmoid function, the proposed PD-STD algorithm can be integrated into deep neural networks (DNNs) to enhance segmentation results for circular objects. Conventional DNNs often act as black boxes, making them susceptible to noise and adversarial attacks, which leads to inconsistencies in segmentation when input images are corrupted. Our approach improves the robustness and stability of DNNs by enforcing the shape compactness prior information. Extensive experiments demonstrate that the proposed algorithms outperform state-of-the-art methods in both numerical efficiency and effectiveness. This is particularly evident when the algorithms are tested on Iris datasets with high levels of noise. Our findings highlight the potential of incorporating shape compactness priors to enhance image segmentation in challenging scenarios.

关键词： Shape compactness image segmentation Deep neural networks Threshold dynamics

来源：评论

学校读者我要写书评

暂无评论

A Regret Bound for the AdaMax Algorithm With image segmentation Application

引用

MATHEMATICAL METHODS IN THE APPLIED SCIENCES 2025年第9期48卷 10208-10214页

作者： Jirakipuwapat, Wachirapong King Mongkuts Univ Technol North Bangkok KMUTNB Fac Sci Energy & Environm Rayong Thailand

The AdaMax algorithm provides enhanced convergence properties for stochastic optimization problems. In this paper, we present a regret bound for the AdaMax algorithm, offering a tighter and more refined analysis compared to existing bounds. This theoretical advancement provides deeper insights into the optimization landscape of machine learning algorithms. Specifically, the You Only Look Once (YOLO) framework has become well-known as an extremely effective object segmentation tool, mostly because of its extraordinary accuracy in real-time processing, which makes it a preferred option for many computer vision applications. Finally, we used this algorithm for image segmentation.

关键词： AdaMax deep learning image segmentation regret bound YOLO

来源：评论

学校读者我要写书评

暂无评论

Research on the SEGDC-UNet electron microscope image segmentation algorithm based on channel attention mechanism

引用

JOURNAL OF MICROSCOPY 2025年第3期298卷 293-304页

作者： Li, Yue Zhao, Qian Sun, Haijing Shao, Yichuan Wang, Yong Shenyang Univ Technol Coll Sci Shenyang Liaoning Peoples R China Shenyang Univ Coll Intelligent Sci & Engn Shenyang Liaoning Peoples R China Liaoning Prov Transportat Planning & Design Inst C Shenyang Liaoning Peoples R China

In this paper, we propose SEGDC-UNet, a segmentation algorithm for electron microscope (EM) images based on the channel attention mechanism. This algorithm integrates the channel attention mechanism and the GELU activation function into the DC-UNet network. By leveraging global information to selectively enhance primary features and suppress less relevant ones, the channel attention mechanism improves focus on important image channels and characteristics. Additionally, the GELU activation function enhances training performance and convergence speed. To evaluate its effectiveness, we compar SEGDC-UNet with six major lightweight image segmentation models on EMPS-Augmented electron microscopy image dataset. Experimental results demonstrate that the SEGDC-UNet model achieves higher Dice coefficient, IoU, Pixel Accuracy and Recall in electron microscopy image segmentation.

关键词： channel attention mechanism DC-UNet electron microscope image GELU image segmentation U-Net

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：