UP2D: Uncertainty-aware Progressive Pseudo-label Denoising for Source-Free Domain Adaptive Medical Image Segmentation

TL;DR

UP2D introduces an uncertainty-aware, progressive pseudo-label denoising framework for source-free domain adaptation in medical image segmentation, effectively handling noisy labels and class imbalance to improve performance.

Contribution

The paper proposes UP2D, a novel framework combining prototype filtering, uncertainty-guided teacher updates, and entropy minimization for improved source-free domain adaptation.

Findings

Achieves state-of-the-art results on retinal fundus benchmarks.

Effectively reduces pseudo-label noise and class imbalance.

Maintains high boundary precision in segmentation.

Abstract

Medical image segmentation models face severe performance drops under domain shifts, especially when data sharing constraints prevent access to source images. We present a novel Uncertainty-aware Progressive Pseudo-label Denoising (UP2D) framework for source-free domain adaptation (SFDA), designed to mitigate noisy pseudo-labels and class imbalance during adaptation. UP2D integrates three key components: (i) a Refined Prototype Filtering module that suppresses uninformative regions and constructs reliable class prototypes to denoise pseudo-labels, (ii) an Uncertainty-Guided EMA (UG-EMA) strategy that selectively updates the teacher model based on spatially weighted boundary uncertainty, and (iii) a quantile-based entropy minimization scheme that focuses learning on ambiguous regions while avoiding overconfidence on easy pixels. This single-stage student-teacher framework progressively improves pseudo-label quality and reduces confirmation bias. Extensive experiments on three challenging retinal fundus benchmarks demonstrate that UP2D achieves state-of-the-art performance across both standard and open-domain settings, outperforming prior UDA and SFDA approaches while maintaining superior boundary precision.