An Uncertainty-guided Tiered Self-training Framework for Active Source-free Domain Adaptation in Prostate Segmentation

TL;DR

This paper introduces a novel uncertainty-guided tiered self-training framework for active source-free domain adaptation in prostate MRI segmentation, significantly improving performance with minimal annotation effort.

Contribution

It proposes a new active source-free domain adaptation method combining uncertainty-guided sample selection and tiered self-training for medical image segmentation.

Findings

Achieved an average Dice score improvement of 9.78% and 7.58% in two target domains.

Utilized only 5% annotation to reach performance comparable to fully supervised models.

Demonstrated effectiveness on cross-center prostate MRI datasets.

Abstract

Deep learning models have exhibited remarkable efficacy in accurately delineating the prostate for diagnosis and treatment of prostate diseases, but challenges persist in achieving robust generalization across different medical centers. Source-free Domain Adaptation (SFDA) is a promising technique to adapt deep segmentation models to address privacy and security concerns while reducing domain shifts between source and target domains. However, recent literature indicates that the performance of SFDA remains far from satisfactory due to unpredictable domain gaps. Annotating a few target domain samples is acceptable, as it can lead to significant performance improvement with a low annotation cost. Nevertheless, due to extremely limited annotation budgets, careful consideration is needed in selecting samples for annotation. Inspired by this, our goal is to develop Active Source-free Domain Adaptation (ASFDA) for medical image segmentation. Specifically, we propose a novel Uncertainty-guided Tiered Self-training (UGTST) framework, consisting of efficient active sample selection via entropy-based primary local peak filtering to aggregate global uncertainty and diversity-aware redundancy filter, coupled with a tiered self-learning strategy, achieves stable domain adaptation. Experimental results on cross-center prostate MRI segmentation datasets revealed that our method yielded marked advancements, with a mere 5% annotation, exhibiting an average Dice score enhancement of 9.78% and 7.58% in two target domains compared with state-of-the-art methods, on par with fully supervised learning. Code is available at:https://github.com/HiLab-git/UGTST