DCLCA-UNet: Dynamic Cross-Level Contextual Attention for 3D Medical Image Segmentation
Journal of Imaging · 02.11.2026 · 12 (11) · 546
DOI: 10.3390/jimaging12110546 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Imaging, online erschienen am 02.11.2026. Verfasst von Gang Liu und 1 weiteren Autor:innen. Die Arbeit nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Hubei Design and Research Center of Cultural and Creative Industry Open Fund, Joint Funds for the Innovation of Science and Technology, Fujian Province.
Abstract (Originalsprache)
Accurate 3D medical image segmentation requires effective integration of encoder details and decoder semantics. However, their relative contributions vary across decoding stages and spatial locations, and attention based only on the current feature pair may provide limited guidance in ambiguous regions. To address these challenges, we propose Dynamic Cross-Level Contextual Attention U-Net (DCLCA-UNet), which reconstructs cross-level context at each decoding stage from the incoming decoder feature and encoder features at the corresponding and shallower levels. The Cross-Level Contextual Attention Fusion (CLCAF) module uses this context to adaptively weight encoder and decoder features before fusion. The Context-Guided Feature Modulation (CGFM) module then reuses the context to refine the fused representation through scaling and additive correction. Experiments on Synapse, BTCV, and BraTS2023 yield average Dice scores of 88.70%, 84.13%, and 92.34%, respectively, with the lowest corresponding average Hausdorff distance (HD) or 95th-percentile Hausdorff distance (HD95) among the compared methods. These improvements are accompanied by increased computational cost. Repeated experiments and evaluation on AMOS22 provide additional evidence of stability and cross-dataset generalization. Ablation studies further assess the contributions of contextual fusion, modulation, and stage-specific context reconstruction. Together, these results support the effectiveness of contextual guidance in volumetric segmentation.
Förderung
- Hubei Design and Research Center of Cultural and Creative Industry Open Fund
- Joint Funds for the Innovation of Science and Technology, Fujian Province
Zitieren
APA
Liu, G., & Yang, H. (2026). DCLCA-UNet: Dynamic Cross-Level Contextual Attention for 3D Medical Image Segmentation. Journal of Imaging, 12(11), 546. https://doi.org/10.3390/jimaging12110546
Vancouver
Liu G, Yang H. DCLCA-UNet: Dynamic Cross-Level Contextual Attention for 3D Medical Image Segmentation. Journal of Imaging. 2026;12(11):546. doi:10.3390/jimaging12110546
BibTeX
@article{Liu2026,
author = {Liu, Gang and Yang, Hao},
title = {DCLCA-UNet: Dynamic Cross-Level Contextual Attention for 3D Medical Image Segmentation},
journal = {Journal of Imaging},
year = {2026},
volume = {12},
number = {11},
pages = {546},
doi = {10.3390/jimaging12110546}
}
EUVIMED