Enhanced medical image segmentation via wavelet-deformable attention networks
The Visual Computer · 2026-05 · 42 (7)
DOI: 10.1007/s00371-026-04477-z ↗Kurz gefasst
Fachartikel in der Zeitschrift The Visual Computer, online erschienen am 02.05.2026. Verfasst von Xuan Zhang und 4 weiteren Autor:innen. Die Arbeit nennt 56 Literaturangaben. Gefördert von: the National Foreign Expert Project of China, Interdisciplinary Project of Dalian University, Dalian University Student Innovation and Entrepreneurship Training Program.
Abstract (Originalsprache)
Medical image segmentation plays a crucial role in improving diagnostic accuracy and therapeutic strategies. Traditional methods often struggle with noise interference and blurred boundaries in medical images. This study introduces a novel segmentation network, termed wavelet-deformable attention network (WDANet), featuring a wavelet-enhanced deformable attention decoder (WEDA). WEDA integrates a wavelet-deformable convolutional block (WDCB) and a multi-scale frequency space fusion block (MSFB) to enhance feature extraction and contextual awareness. The WDCB combines wavelet-deformable convolution with a convolutional attention mechanism, while the MSFB jointly models multi-scale spatial representations and DCT-based frequency attention to enhance structural feature learning. Experiments on the ACDC and Synapse datasets demonstrate that WDANet achieves average Dice scores of 92.53% and 85.67%, respectively, outperforming existing state-of-the-art methods. These results validate the effectiveness of WDANet in medical image segmentation applications. The code is publicly available at https://github.com/zhangxuan-thecastle/WDANet.
Förderung
- the National Foreign Expert Project of China
- Interdisciplinary Project of Dalian University
- Dalian University Student Innovation and Entrepreneurship Training Program
- Dalian major projects of basic research
- the Basic Scientific Research Projects of the Education Department of Liaoning Province
- the 111 Project
Zitieren
APA
Zhang, X., Liu, R., Dong, J., Yi, P., & Wei, X. (2026). Enhanced medical image segmentation via wavelet-deformable attention networks. The Visual Computer, 42(7). https://doi.org/10.1007/s00371-026-04477-z
Vancouver
Zhang X, Liu R, Dong J, Yi P, Wei X. Enhanced medical image segmentation via wavelet-deformable attention networks. The Visual Computer. 2026;42(7). doi:10.1007/s00371-026-04477-z
BibTeX
@article{Zhang2026,
author = {Zhang, Xuan and Liu, Rui and Dong, Jing and Yi, Pengfei and Wei, Xiaopeng},
title = {Enhanced medical image segmentation via wavelet-deformable attention networks},
journal = {The Visual Computer},
year = {2026},
volume = {42},
number = {7},
doi = {10.1007/s00371-026-04477-z}
}
EUVIMED