DTEA: Dynamic Topology Weaving and Instability-Driven Entropic Attenuation for Medical Image Segmentation

2025-10-13

AI Summary

To address poor generalizability in medical image segmentation caused by weak structural representation and insufficient contextual modeling, this paper proposes a Dynamic Topology Weaving and Entropy-Driven Attenuation framework. Our key contributions are: (1) a Semantic Topology Reconfiguration module that constructs dynamic hypergraphs to explicitly model cross-scale anatomical dependencies; (2) an Entropy-Perturbation Gating mechanism that adaptively suppresses unstable features and enhances attention to critical regions via channel-wise information entropy; and (3) a novel skip-connection architecture integrating dynamic hypergraph representation with entropy-aware gating. Evaluated on three public medical imaging datasets, our method achieves average Dice score improvements of 2.1%–3.7% over strong baselines, demonstrating significantly enhanced robustness and generalization across multi-center and multi-device scenarios.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Graph-based Machine Learning
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web query analysis, representation and understanding

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}.

Problem

• Addresses limited structural representation in medical image segmentation
• Improves contextual modeling for complex clinical scenarios
• Enhances generalization across diverse medical imaging datasets

Innovation

• Dynamic hypergraph models cross-resolution anatomical dependencies
• Entropy-based filtering emphasizes clinically important regions
• Instability-driven attenuation improves segmentation generalization