检索结果-内蒙古大学图书馆

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

Neural Network Pruning for Lightweight Metal Corrosion image segmentation Models

引用

IEEE Access 2025年 13卷 71673-71687页

作者： Yu, Vincent F. Santiyuda, Gemilang Lin, Shih-Wei Pasaribu, Udjianna S. Afrianti, Yuli Sri National Taiwan University of Science and Technology Department of Industrial Management Taipei106335 Taiwan Institut Bisnis dan Teknologi Indonesia Faculty of Technology and Informatics Bali Denpasar80225 Indonesia Chang Gung University Department of Information Management Taoyuan333 Taiwan Ming Chi University of Technology Department of Industrial Engineering and Management Taoyuan333 Taiwan Keelung Chang Gung Memorial Hospital Department of Emergency Medicine Keelung203 Taiwan Bandung Institute of Technology Statistics Research Group Faculty of Mathematics and Natural Sciences Bandung40132 Indonesia

Metal corrosion detection is essential for ensuring structural safety and minimizing economic losses. While deep learning (DL)-based image segmentation has improved corrosion detection accuracy and efficiency, its high computational demands hinder deployment on resource-constrained edge devices. This study investigates lightweight DL models for corrosion segmentation by applying structured pruning to reduce computational costs while maintaining accuracy. We evaluate five segmentation architectures (U-Net, U-Net++, FPN, LinkNet, and MA-Net) and three pruning strategies (linear, automated gradual pruning, and movement pruning) on two corrosion image datasets (NEA and SSCS). Detailed trade-off analysis between model size, computational cost (MAC), and segmentation performance (IoU) reveals that pruning up to 90% sparsity leads to a ≤ 10% IoU drop on SSCS and ≤ 5% on NEA, demonstrating that significant compression is possible with minimal accuracy loss. However, some architectures (e.g., LinkNet) and pruning strategies (e.g., movement pruning) show significant performance deterioration, suggesting that pruning effectiveness varies across models. These findings provide insights into optimizing corrosion segmentation models for efficient deployment on edge devices, balancing accuracy and resource constraints. © 2013 IEEE.

关键词： image segmentation

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

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

CNN-Transformer Rectified Collaborative Learning for Medical image segmentation

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 2025年第5期35卷 4072-4086页

作者： Wu, Lanhu Zhang, Miao Piao, Yongri Yao, Zhenyan Sun, Weibing Tian, Feng Lu, Huchuan Dalian Univ Technol Sch Informat & Commun Engn Dalian 116024 Peoples R China Dalian Univ Technol Key Lab Ubiquitous Network & Serv Software Liaonin Dalian 116024 Peoples R China Dalian Univ Technol DUT RU Int Sch Informat Sci & Engn Dalian 116024 Peoples R China Dalian Univ Affiliated Zhongshan Hosp Dalian 116024 Peoples R China

Automatic and precise medical image segmentation (MIS) is of vital importance for clinical diagnosis and analysis. Current MIS methods mainly rely on the convolutional neural network (CNN) or self-attention mechanism (Transformer) for feature modeling. However, CNN-based methods suffer from the inaccurate localization owing to the limited global dependency while Transformer-based methods always present the coarse boundary for the lack of local emphasis. Although some CNN-Transformer hybrid methods are designed to synthesize the complementary local and global information for better performance, the combination of CNN and Transformer introduces numerous parameters and increases the computation cost. To this end, this paper proposes a CNN-Transformer rectified collaborative learning (CTRCL) framework to learn stronger CNN-based and Transformer-based models for MIS tasks via the bi-directional knowledge transfer between them. Specifically, we propose a rectified logit-wise collaborative learning (RLCL) strategy which introduces the ground truth to adaptively select and rectify the wrong regions in student soft labels for accurate knowledge transfer in the logit space. We also propose a class-aware feature-wise collaborative learning (CFCL) strategy to achieve effective knowledge transfer between CNN-based and Transformer-based models in the feature space by granting their intermediate features the similar capability of category perception. Extensive experiments on three popular MIS benchmarks demonstrate that our CTRCL outperforms most state-of-the-art collaborative learning methods under different evaluation metrics. The source code will be publicly available at https://***/LanhooNg/CTRCL.

关键词： Transformers Federated learning Knowledge transfer image segmentation Convolutional neural networks Accuracy Feature extraction Location awareness Decoding Semantics Medical image segmentation CNN transformer collaborative learning

来源：评论

学校读者我要写书评

暂无评论

MM-UKAN++: A Novel Kolmogorov–Arnold Network-Based U-Shaped Network for Ultrasound image segmentation

引用

IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control 2025年第4期72卷 498-514页

作者： Zhang, Boheng Huang, Haorui Shen, Yi Sun, Mingjian Harbin Institute of Technology Department of Control Science and Engineering Heilongjiang Harbin150001 China Pohang University of Science and Technology Department of Convergence IT Engineering Pohang37673 Korea Republic of Harbin Institute of Technology Suzhou Research Institute Jiangsu Suzhou215000 China Harbin Institute of Technology Department of Information Science and Engineering Shandong Weihai264200 China Harbin Institute of Technology Shandong Weihai264200 China Shandong Laboratory of Advanced Biomaterials and Medical Devices Shandong Weihai264209 China

Ultrasound (US) imaging is an important and commonly used medical imaging modality. Accurate and fast automatic segmentation of regions of interest (ROIs) in US images is essential for enhancing the efficiency of clinical and robot-assisted diagnosis. However, US images suffer from low contrast, fuzzy boundaries, and significant scale variations in ROIs. Existing convolutional neural network (CNN)-based and transformer-based methods struggle with model efficiency and explainability. To address these challenges, we introduce MM-UKAN++, a novel U-shaped network based on Kolmogorov-Arnold networks (KANs). MM-UKAN++ leverages multilevel KAN layers as the encoder and decoder within the U-network architecture and incorporates an innovative multidimensional attention mechanism to refine skip connections by weighting features from frequency-channel and spatial perspectives. In addition, the network effectively integrates multiscale information, fusing outputs from different scale decoders to generate precise segmentation predictions. MM-UKAN++ achieves higher segmentation accuracy with lower computational cost and outperforms other mainstream methods on several open-source datasets for US image segmentation tasks, including achieving 69.42% IoU, 81.30% Dice, and 3.31 mm HD in the BUSI dataset with 3.17 G floating point of operations (FLOPs) and 9.90 M parameters. The excellent performance on our automatic carotid artery US scanning and diagnostic system further proves the speed and accuracy of MM-UKAN++. Besides, the good performance in other medical image segmentation tasks reveals the promising applications of MM-UKAN++. The code is available on GitHub. © 1986-2012 IEEE.

关键词： image segmentation

来源：评论

学校读者我要写书评

暂无评论

CTA image segmentation method for intracranial aneurysms based on MGLIA net

引用

SCIENTIFIC REPORTS 2025年第1期15卷 1-12页

作者： Hou, Lijie Zhang, Jian Zhao, Lihui Meng, Ke Feng, Xin Changchun Univ Sci & Technol Sch Life Sci & Technol Changchun 130000 Peoples R China JiLin Univ Neurosurg Bethune Hosp 3 Changchun 130000 Peoples R China Changchun Univ Sci & Technol Sch Comp Sci & Technol 7089 Weiguang St Changchun 130000 Peoples R China

Accurately segmenting the aneurysm area from CTA data can reconstruct the three-dimensional morphology of the aneurysm, effectively evaluating the type, size, and risk of rupture of the aneurysm. However, accurate separation of the aneurysm is limited by the accuracy of image segmentation algorithms. Currently, the segmentation methods for intracranial aneurysms using CTA big data and deep learning lack universality. When faced with a new hospital acquired imaging modality, it is usually necessary to redesign and train the segmentation network. In response to this issue, this article proposes a more universal segmentation model and develops the GLIA Net algorithm (MGLIA Net model) based on MoblieNet, which can perform adaptive target segmentation on aneurysm images collected under different conditions. To verify the effectiveness of the algorithm in intracranial aneurysm segmentation, performance tests were conducted on an open-source dataset. The results showed that the proposed algorithm achieved segmentation accuracy of 55.9% and 73.1% on two datasets, respectively, significantly better than the original GLIA-Net algorithm.

关键词： Deep learning network model Intracranial aneurysm CTA image segmentation

来源：评论

学校读者我要写书评

暂无评论

MA-SAM: A Multi-Atlas Guided SAM Using Pseudo Mask Prompts Without Manual Annotation for Spine image segmentation

引用

IEEE TRANSACTIONS ON MEDICAL IMAGING 2025年第5期44卷 2157-2169页

作者： Fan, Dingwei Zhao, Junyong Li, Chunlin Wang, Xinlong Zhang, Ronghan Zhu, Qi Wang, Mingliang Si, Haipeng Zhang, Daoqiang Sun, Liang Nanjing Univ Aeronaut & Astronaut Coll Artificial Intelligence Nanjing 211106 Peoples R China Minist Educ Key Lab Brain Machine Intelligence Technol Nanjing 211106 Peoples R China Shandong Univ Qilu Hosp Cheeloo Coll Med Dept Orthoped Jinan 250012 Peoples R China Shandong Normal Univ Coll Phys & Elect Jinan 250358 Peoples R China Nanjing Univ Informat Sci & Technol Sch Comp & Software Nanjing 210044 Peoples R China Shandong Univ Qilu Hosp Qingdao Dept Orthoped Key Lab Qingdao Med & Engn Qingdao 266035 Shandong Peoples R China Nanjing Univ Aeronaut & Astronaut Shenzhen Res Inst Nanjing 211106 Peoples R China

Accurate spine segmentation is crucial in clinical diagnosis and treatment of spine diseases. However, due to the complexity of spine anatomical structure, it has remained a challenging task to accurately segment spine images. Recently, the segment anything model (SAM) has achieved superior performance for image segmentation. However, generating high-quality points and boxes is still laborious for high-dimensional medical images. Meanwhile, an accurate mask is difficult to obtain. To address these issues, in this paper, we propose a multi-atlas guided SAM using multiple pseudo mask prompts for spine image segmentation, called MA-SAM. Specifically, we first design a multi-atlas prompt generation sub-network to obtain the anatomical structure prompts. More specifically, we use a network to obtain coarse mask of the input image. Then atlas label maps are registered to the coarse mask. Subsequently, a SAM-based segmentation sub-network is used to segment images. Specifically, we first utilize adapters to fine-tune the image encoder. Meanwhile, we use a prompt encoder to learn the anatomical structure prior knowledge from the multi-atlas prompts. Finally, a mask decoder is used to fuse the image and prompt features to obtain the segmentation results. Moreover, to boost the segmentation performance, different scale features from the prompt encoder are concatenated to the Upsample Block in the mask decoder. We validate our MA-SAM on the two spine segmentation tasks, including spine anatomical structure segmentation with CT images and lumbosacral plexus segmentation with MR images. Experiment results suggest that our method achieves better segmentation performance than SAM with points, boxes, and mask prompts.

关键词： image segmentation Accuracy Anatomical structure Deep learning Decoding Transformers Surgery Sun Diseases Computed tomography Segment anything model multi-atlas spine segmentation

来源：评论

学校读者我要写书评

暂无评论

DermaTransNet: Where Transformer Attention Meets U-Net for Skin image segmentation

引用

IEEE ACCESS 2025年 13卷 64305-64329页

作者： Salam, Anum Abdul Akram, Muhammad Usman Yousaf, Muhammad Haroon Rao, Babar Univ Engn & Technol Taxila Dept Comp Engn Taxila 47050 Pakistan Natl Univ Sci & Technol Dept Comp & Software Engn Islamabad 44000 Pakistan Rao Dermatol New York NY 10003 USA

Skin, the largest organ of the human body, serves as a protective barrier against the external environment, safeguarding the internal organs. It is composed of layers, namely the epidermis, dermis, and hypodermis. The analysis and detection of diseases heavily rely on identifying the penetration of biomarkers within each layer, thus highlighting the significance of accurate segmentation of each layer in disease diagnosis. In skin disease diagnosis, haematoxylin and eosin-stained whole slide images are the most commonly employed imaging modality. To enhance the efficacy of analysis and assist pathologists, computer-aided diagnostic systems have been proposed to automate the process of disease detection and classification. A crucial initial step in skin disease diagnosis is the accurate segmentation of skin layers, as it facilitates the identification of regions of interest for subsequent processing. This study presents a novel attention-based encoder-decoder architecture comprising a multi-axis encoder with an attention-mixing decoder to precisely segment the skin layers (Epidermis, Dermis, Hypodermis, Keratin) from stained whole slide image samples. The proposed Transformer-based encoder block has helped the model preserve global and local features, which are then passed to the decoder block through an attention-based gated skip connection. The attention mixing decoder module has combined multi-head self-attention, spatial attention, and squeeze excitation modules to enhance the spatial information gain. Additionally, the encoder block aids in extracting high and low-level features, which are further weighted before passing to the decoder block via a gated attention mechanism, thus helping the model acquire the relevant details from all spatial dimensions. The proposed architecture has been evaluated on a publicly available dataset against various evaluation metrics i.e., F1-Score, Accuracy, Precision, Recall, and Hausdorff Distance. The model yielded the highest ac

关键词： image segmentation Diseases Epidermis Accuracy Dermis Feature extraction Decoding Transformers Microscopy Medical diagnosis Histopathology whole slide image semantic segmentation transformer skin layers histopathology computer-aided diagnostics bright field microscopy UNet architecture attention

来源：评论

学校读者我要写书评

暂无评论

DenUnet: enhancing dental image segmentation through edge and body fusion

引用

Multimedia Tools and Applications 2025年第14期84卷 13201-13221页

作者： Manzari, Omid Nejati Bayrami, Farhad Khaloo, Hooman Khodakaramimaghsoud, Zahra Shokouhi, Shahriar B. School of Electrical Engineering Iran University of Science and Technology Tehran Iran University of Bologna Bologna Italy Independent Researcher Tehran Iran Department of Bioengineering University of Pennsylvania PhiladelphiaPA United States

Accurate tooth segmentation is of paramount importance in oral healthcare because it provides critical positional data for clinical diagnosis, orthodontic treatment, and surgical procedures. Despite the widespread use of convolutional neural networks (CNNs) in image segmentation, its limitations in collecting complete global context and long-range interactions are acknowledged. Although vision transformers show promise in understanding larger contextual information, they struggle to manage the spatial complexities of medical images. To tackle these issues, the proposed DenUnet leverages the strengths of both CNNs and transformers. It introduces a dual-branch encoder that simultaneously extracts edge and body information and a double-level fusion module for integrating multi-scale features. To ensure the fine fusing of edge and body information derived from the two mentioned encoders, we propose a local cross-attention feature fusion module to enhance feature fusion with accurate blending losses. Experimental results underscore the superior efficacy of DenUnet in comparison to existing methods. We achieved 95.4% accuracy and 92.7% F1-score on the DNS dataset, which is particularly evident in its ability to adeptly handle irregular boundaries of dental datasets. Code is available at https://***/Omid-Nejati/DenUnet © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： image segmentation

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：