文献类型：期刊文献

英文题名：TS-Net: Trans-Scale Network for Medical Image Segmentation

作者：Wang, Huifang[1];Liu, Yatong[1];Ye, Jiongyao[1];Yang, Dawei[2,3];Zhu, Yu[1]

机构：[1]East China Univ Sci & Technol, Sch Informat Sci & Engn, Shanghai, Peoples R China;[2]Fudan Univ, Zhongshan Hosp, Dept Pulm & Crit Care Med, Shanghai, Peoples R China;[3]Shanghai Engn Res Ctr Internet Things Resp Med, Shanghai, Peoples R China

年份：2025

卷号：35

期号：2

外文期刊名：INTERNATIONAL JOURNAL OF IMAGING SYSTEMS AND TECHNOLOGY

收录：;EI(收录号：20251218097942);WOS:【SCI-EXPANDED(收录号:WOS:001446551200001)】；

基金：The authors greatly appreciate the financial support of the National Natural Science Foundation of China (62476088, 82170110), Fujian Province Department of Science and Technology (2022D014), Science and Technology Commission of Shanghai Municipality (20DZ2254400, 20DZ2261200), Shanghai Municipal Science and Technology Major Project (ZD2021CY001) and Shanghai Municipal Key Clinical Specialty (shslczdzk02201).

语种：英文

外文关键词：convolution modulation; deep supervision; edge loss; feature complementarity; medical image segmentation

摘要：Accurate medical image segmentation is crucial for clinical diagnosis and disease treatment. However, there are still great challenges for most existing methods to extract accurate features from medical images because of blurred boundaries and various appearances. To overcome the above limitations, we propose a novel medical image segmentation network named TS-Net that effectively combines the advantages of CNN and Transformer to enhance the feature extraction ability. Specifically, we design a Multi-scale Convolution Modulation (MCM) module to simplify the self-attention mechanism through a convolution modulation strategy that incorporates multi-scale large-kernel convolution into depth-separable convolution, effectively extracting the multi-scale global features and local features. Besides, we adopt the concept of feature complementarity to facilitate the interaction between high-level semantic features and low-level spatial features through the designed Scale Inter-active Attention (SIA) module. The proposed method is evaluated on four different types of medical image segmentation datasets, and the experimental results show its competence with other state-of-the-art methods. The method achieves an average Dice Similarity Coefficient (DSC) of 90.79% +/- 1.01% on the public NIH dataset for pancreas segmentation, 76.62% +/- 4.34% on the public MSD dataset for pancreatic cancer segmentation, 80.70% +/- 6.40% on the private PROMM (Prostate Multi-parametric MRI) dataset for prostate cancer segmentation, and 91.42% +/- 0.55% on the public Kvasir-SEG dataset for polyp segmentation. The experimental results across the four different segmentation tasks for medical images demonstrate the effectiveness of the Trans-Scale network.