Structure and Progress Aware Diffusion for Medical Image Segmentation

2026-03-09

AI Summary

Medical image segmentation often suffers from performance degradation due to ambiguous boundaries and noise interference. To address this challenge, this work proposes a Structure- and Progress-Aware Diffusion framework (SPAD), which models the segmentation process in two stages: Semantic-concentrated Diffusion (ScD) and Boundary-concentrated Diffusion (BcD). The early stage focuses on preserving stable semantic structures, while the later stage refines boundary details. SPAD introduces semantic anchor-preserving perturbations and a progress-aware boundary noise mechanism, complemented by a progress-aware scheduler that enables gradual learning from structural understanding to boundary refinement. Experimental results demonstrate that SPAD significantly improves segmentation accuracy and exhibits enhanced robustness and generalization, particularly in challenging scenarios involving tumors and lesions with ill-defined boundaries.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Structured Learning
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Medical image segmentation is crucial for computer-aided diagnosis, which necessitates understanding both coarse morphological and semantic structures, as well as carving fine boundaries. The morphological and semantic structures in medical images are beneficial and stable clues for target understanding. While the fine boundaries of medical targets (like tumors and lesions) are usually ambiguous and noisy since lesion overlap, annotation uncertainty, and so on, making it not reliable to serve as early supervision. However, existing methods simultaneously learn coarse structures and fine boundaries throughout the training process. In this paper, we propose a structure and progress-aware diffusion (SPAD) for medical image segmentation, which consists of a semantic-concentrated diffusion (ScD) and a boundary-centralized diffusion (BcD) modulated by a progress-aware scheduler (PaS). Specifically, the semantic-concentrated diffusion introduces anchor-preserved target perturbation, which perturbs pixels within a medical target but preserves unaltered areas as semantic anchors, encouraging the model to infer noisy target areas from the surrounding semantic context. The boundary-centralized diffusion introduces progress-aware boundary noise, which blurs unreliable and ambiguous boundaries, thus compelling the model to focus on coarse but stable anatomical morphology and global semantics. Furthermore, the progress-aware scheduler gradually modulates noise intensity of the ScD and BcD forming a coarse-to-fine diffusion paradigm, which encourage focusing on coarse morphological and semantic structures during early target understanding stages and gradually shifting to fine target boundaries during later contour adjusting stages.

Problem

• medical image segmentation
• coarse-to-fine learning
• ambiguous boundaries
• semantic structure
• annotation uncertainty

Innovation

• structure-aware diffusion
• progress-aware scheduling
• semantic-concentrated diffusion
• boundary-centralized diffusion
• coarse-to-fine segmentation