文献类型：期刊文献

英文题名：MSCFNet: mixed-scale context fusion network for medical image segmentation

作者：Xu, Lingyi[1,3];Tang, Dongfang[2];Xiao, Ting[1,3];Wang, Hao[1,3];Wang, Zhe[1,3];Gao, Wen[2]

机构：[1]East China Univ Sci & Technol, Dept Comp Sci & Engn, Shanghai 200237, Peoples R China;[2]Fudan Univ, Dept Thorac Surg, Huadong Hosp, Shanghai, Peoples R China;[3]Minist Educ, Key Lab Smart Mfg Energy Chem Proc, Shanghai 200237, Peoples R China

年份：2026

卷号：56

期号：5

外文期刊名：APPLIED INTELLIGENCE

收录：;EI(收录号：20261320354232);WOS:【SCI-EXPANDED(收录号:WOS:001712913600001)】；

基金：This work was supported in part by the Natural Science Foundation of China under Grant No. 62476087, No. 62203117, No. 62306115, and No. 62201341, Shanghai Municipal Education Commission's Initiative on Artificial Intelligence-Driven Reform of Scientific Research Paradigms and Empowerment of Discipline Leapfrogging.

语种：英文

外文关键词：Medical image segmentation; Context fusion; Mixed-scale attention

摘要：Effective medical image segmentation results are essential for the subsequent diagnosis. Fully convolutional networks and their variants based on the encoder-decoder structure have achieved excellent performance in medical image segmentation. Despite recent progress, segmenting targets with large-scale variations and complex backgrounds remains difficult. In this paper, we propose a Mixed-Scale Context Fusion (MSCF) network for medical image segmentation. First, we introduce a context fusion module between the encoder and decoder, which can fuse multi-level features from the encoder and extract contextual information useful for the segmentation task. Second, we introduce a mixed-scale attention module, it can extract features at different scales by two branches, and learn scale information adapted to the target size using an attention mechanism to enhance the capability of multi-scale feature extraction. We conduct extensive experiments on the LIDC and MSD datasets, where MSCFNet achieves Dice scores of 85.83% and 86.09%, improving over FCN by 8.36% and 6.57%, respectively