UHR-Net: An Uncertainty-Aware Hypergraph Refinement Network for Medical Image Segmentation

TL;DR

UHR-Net is a novel medical image segmentation model that incorporates uncertainty estimation and hypergraph refinement to improve accuracy in challenging boundary and small-lesion cases.

Contribution

It introduces an uncertainty-aware pretraining strategy and a hypergraph refinement block that enhances lesion segmentation accuracy in ambiguous regions.

Findings

Consistent performance improvements over strong baselines on five benchmarks.

Effective use of entropy-based uncertainty maps for hypergraph refinement.

Improved segmentation of small and ambiguous lesions.

Abstract

Accurate lesion segmentation is crucial for clinical diagnosis and treatment planning. However, lesions often resemble surrounding tissues and exhibit ill-defined boundaries, leading to unstable predictions in boundary/transition regions. Moreover, small-lesion cues can be diluted by multi-scale feature extraction, causing under- or over-segmentation. To address these challenges, we propose an Uncertainty-Aware Hypergraph Refinement Network (UHR-Net). First, we introduce an Uncertainty-Oriented Instance Contrastive (UO-IC) pretraining strategy that couples geometry-aware copy-paste augmentation with hard-negative mining of lesion-like background regions to improve instance-level discrimination for small and visually ambiguous lesions. Second, we design an Uncertainty-Guided Hypergraph Refinement (UGHR) block, which derives an entropy-based uncertainty map from a coarse probability map to guide hypergraph refinement. By splitting hyperedge prototypes into foreground and background groups, UGHR decouples higher-order interactions and improves refinement in ambiguous regions. Experiments on five public benchmarks demonstrate consistent gains over strong baselines. Code is available at: https://github.com/CUGfreshman/UHR-Net.