DTEA: Dynamic Topology Weaving and Instability-Driven Entropic Attenuation for Medical Image Segmentation
Year: 2025
Type: preprint
Abstract: In medical image segmentation, skip connections are used to merge global context and reduce the semantic gap between encoder and decoder. Current methods often struggle with limited structural representation and insufficient contextual modeling, affecting generalization in complex clinical scenarios. We propose the DTEA model, featuring a new skip connection framework with the Semantic Topology Reconfiguration (STR) and Entropic Perturbation Gating (EPG) modules. STR reorganizes multi-scale semantic features into a dynamic hypergraph to better model cross-resolution anatomical dependencies, enhancing structural and semantic representation. EPG assesses channel stability after perturbation and filters high-entropy channels to emphasize clinically important regions and improve spatial attention. Extensive experiments on three benchmark datasets show our framework achieves superior segmentation accuracy and better generalization across various clinical settings. The code is available at \href{https://github.com/LWX-Research/DTEA}{https://github.com/LWX-Research/DTEA}.
Source: arXiv (Cornell University)
Authors: Li, Weixuan, Li, Quanjun, Yu, Guang, Yang, Song, Li, Zimeng, Pun, Chi-Man, Liu, Yupeng, Chen, Xuhang
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Award: G3508708550
OpenAlex ID: W7091186743
Cites:
Cited by:
Related to: