DPSeg: Differentiated Perception Medical Image Segmentation via Context-Aware Compensation and Stratified Uncertainty Attention
IEEE Transactions on Image Processing · 2026 · 35 · 11255-11269
DOI: 10.1109/tip.2026.3744284 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Image Processing, 2026. Verfasst von Guosheng Gu und 8 weiteren Autor:innen. Die Arbeit nennt 55 Literaturangaben. Gefördert von: Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application, National Natural Science Foundation of China, Natural Science Foundation for Distinguished Young Scholars of Guangdong Province.
Abstract (Originalsprache)
In medical image segmentation, accurate recognition of regions hindered by blurry boundaries, low contrast, and complex backgrounds is crucial. These issues lead to significant differences in segmentation difficulty within a single image. However, existing methods typically adopt a uniform modeling strategy across the entire feature map, overlooking the mismatch between segmentation difficulty and attention intensity. Consequently, they fail to adequately focus on key regions, diluting the representations of challenging regions. To address these challenges, we propose DPSeg, a differentiated perception medical image segmentation framework via context-aware compensation and stratified uncertainty attention. Specifically, DPSeg comprises three key components. The Context-Aware Compensation (CAC) module refines encoder features by integrating key region-aware prompts and contextual information, compensating for encoding-induced distortions and enabling differentiated perception, thereby providing higher-quality representations for decoding. Additionally, the Stratified Uncertainty Transformer (SUTrans) module explicitly modulates the attention intensity of different regions based on their segmentation uncertainty, thereby possessing differentiated perception ability while effectively suppressing redundant feature interactions. Moreover, we propose a Foreground-Uncertainty Adaptive Weighted Loss (FUAWL) to enable differentiated supervision across decoding stages, applying stronger guidance to uncertain regions in shallow decoding and emphasizing foreground regions in deep decoding to improve boundary delineation and mitigate foreground-background imbalance. Extensive experiments on four challenging datasets demonstrate that DPSeg achieves competitive segmentation performance.
Förderung
- Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application
- National Natural Science Foundation of China
- Natural Science Foundation for Distinguished Young Scholars of Guangdong Province
Zitieren
APA
Gu, G., Jiang, Q., Zhang, J., Li, F., Li, S., Deng, J., Liu, P., Liu, Z., & Han, C. (2026). DPSeg: Differentiated Perception Medical Image Segmentation via Context-Aware Compensation and Stratified Uncertainty Attention. IEEE Transactions on Image Processing, 35, 11255-11269. https://doi.org/10.1109/tip.2026.3744284
Vancouver
Gu G, Jiang Q, Zhang J, Li F, Li S, Deng J, et al. DPSeg: Differentiated Perception Medical Image Segmentation via Context-Aware Compensation and Stratified Uncertainty Attention. IEEE Transactions on Image Processing. 2026;35:11255-11269. doi:10.1109/tip.2026.3744284
BibTeX
@article{Gu2026,
author = {Gu, Guosheng and Jiang, Qian and Zhang, Jian and Li, Fan and Li, Si and Deng, Jiehang and Liu, Ping and Liu, Zaiyi and Han, Chu},
title = {DPSeg: Differentiated Perception Medical Image Segmentation via Context-Aware Compensation and Stratified Uncertainty Attention},
journal = {IEEE Transactions on Image Processing},
year = {2026},
volume = {35},
pages = {11255--11269},
doi = {10.1109/tip.2026.3744284}
}
EUVIMED