文献类型：期刊文献

英文题名：An adaptive U-Net framework for dermatological lesion segmentation☆

作者：Huang, Ru[1];Qian, Zhimin[1];Zhou, Zhengbing[2];Chen, Zijian[3];Liu, Jiannan[4];Han, Jing[4];Zhou, Shuo[1];He, Jianhua[5];Chu, Xiaoli[6]

机构：[1]East China Univ Sci & Technol, Sch Informat Sci & Engn, Shanghai 200237, Peoples R China;[2]Shanghai Jiao Tong Univ, Shanghai Peoples Hosp 6, Sch Med, Shanghai 200233, Peoples R China;[3]Shanghai Jiao Tong Univ, Inst Image Commun & Informat Proc, Shanghai 200240, Peoples R China;[4]Shanghai Jiao Tong Univ, Shanghai Peoples Hosp 9, Sch Med, Shanghai 200023, Peoples R China;[5]Univ Essex, Sch Comp Sci & Elect Engn, Colchester CO4 3SQ, England;[6]Univ Sheffield, Dept Elect & Elect Engn, Sheffield S1 3JD, England

年份：2026

卷号：92

外文期刊名：DISPLAYS

收录：;EI(收录号：20254819612044);WOS:【SCI-EXPANDED(收录号:WOS:001630502300002)】；

基金：This work was supported by the National Natural Science Foundation of China under Grant 62322114, in part by the Fundamental Research Funds for the Central Universities, China under Grant YG2023LC06, in part by the Natural Science Foundation of Shanghai, China under Grant 20ZR1413800, and in part by the Shanghai Key Laboratory Open Project under Grant STCSM 22DZ2229005. The manuscript has been read and approved by all named authors.

语种：英文

外文关键词：Medical image segmentation; Skin lesion; Mamba; MultiScale attention; Adaptive feature fusion

摘要：With the deep integration of information technology, medical image segmentation has become a crucial tool for dermatological image analysis. However, existing dermatological lesion segmentation methods still face numerous challenges when dealing with complex lesion regions, which result in limited segmentation accuracy. Therefore, this study presents an adaptive segmentation network that draws inspiration from U-Net's symmetric architecture, with the goal of improving the precision and generalizability of dermatological lesion segmentation. The proposed Visual Scaled Mamba (VSM) module incorporates residual pathways and adaptive scaling factors to enhance fine-grained feature extraction and enable hierarchical representation learning. Additionally, we propose the Multi-Scaled Cross-Axial Attention (MSCA) mechanism, integrating multiscale spatial features and enhancing blurred boundary recognition through dual cross-axial attention. Furthermore, we design an Adaptive Wave-Dilated Bottleneck (AWDB), employing adaptive dilated convolutions and wavelet transforms to improve feature representation and long-range dependency modeling. Through experimental results on the ISIC 2016, ISIC 2018, and PH2 public datasets show that our network achieves a good compromise between model complexity and segmentation accuracy, leading to considerable performance increases in dermatological image segmentation.