HUA-Seg: A Hierarchical Framework for Uncertainty-Aware Medical Image Segmentation

Despite significant progress in medical image segmentation, clinical deployment faces challenges due to inherent uncertainties. These uncertainties primarily arise from ambiguous lesion boundaries, complex anatomical structures, and variations in imaging quality, all of which significantly affect the reliability of segmentation outcomes. To address this issue, we propose a novel Hierarchical Uncertainty-Aware Segmentation Framework (HUA-Seg), which explicitly models and utilizes uncertainty throughout the forward propagation process. HUASeg is designed to hierarchically perceive, quantify, and exploit uncertainty, enhancing segmentation robustness and generalization. Our method comprises three core components: (1) an uncertainty-modulated self-attention mechanism that adaptively emphasizes reliable features during early-stage representation learning, enabling the extraction of more robust feature embeddings; (2) an uncertainty-guided dual-strategy feature refinement module, which reallocates learning focus towards low-confidence regions-such as lesion boundaries-facilitating effective complex example mining and contour refinement; and (3) multi-scale uncertainty supervision, providing an explicit, data-dependent regularization signal that stabilizes training and enhances generalization. Extensive experiments on multiple public medical image segmentation benchmarks demonstrate that HUA-Seg consistently outperforms state-of-the-art methods, highlighting its effectiveness in handling complex and uncertain medical image segmentation scenarios.