SL: Stable Learning in Source-Free Domain Adaption for Medical Image Segmentation
This addresses privacy concerns in medical imaging by enabling domain adaptation without simultaneous access to source and target data, though it is incremental as it builds on existing source-free methods.
The paper tackles the problem of over-fitting in source-free unsupervised domain adaptation for medical image segmentation, where longer training leads to worse performance, and proposes a Stable Learning strategy that improves results, as proven by comparative experiments.
Deep learning techniques for medical image analysis usually suffer from the domain shift between source and target data. Most existing works focus on unsupervised domain adaptation (UDA). However, in practical applications, privacy issues are much more severe. For example, the data of different hospitals have domain shifts due to equipment problems, and data of the two domains cannot be available simultaneously because of privacy. In this challenge defined as Source-Free UDA, the previous UDA medical methods are limited. Although a variety of medical source-free unsupervised domain adaption (MSFUDA) methods have been proposed, we found they fall into an over-fitting dilemma called "longer training, worse performance." Therefore, we propose the Stable Learning (SL) strategy to address the dilemma. SL is a scalable method and can be integrated with other research, which consists of Weight Consolidation and Entropy Increase. First, we apply Weight Consolidation to retain domain-invariant knowledge and then we design Entropy Increase to avoid over-learning. Comparative experiments prove the effectiveness of SL. We also have done extensive ablation experiments. Besides, We will release codes including a variety of MSFUDA methods.