Distribution-Aware Replay for Continual MRI Segmentation
This work addresses privacy and out-of-distribution challenges in continual learning for medical image segmentation, offering an incremental improvement over existing rehearsal methods.
The paper tackled the problem of performance deterioration in continual MRI segmentation due to distribution shifts, by introducing a distribution-aware replay strategy that mitigates forgetting and detects model failure, achieving competitive results on hippocampus and prostate MRI segmentation tasks.
Medical image distributions shift constantly due to changes in patient population and discrepancies in image acquisition. These distribution changes result in performance deterioration; deterioration that continual learning aims to alleviate. However, only adaptation with data rehearsal strategies yields practically desirable performance for medical image segmentation. Such rehearsal violates patient privacy and, as most continual learning approaches, overlooks unexpected changes from out-of-distribution instances. To transcend both of these challenges, we introduce a distribution-aware replay strategy that mitigates forgetting through auto-encoding of features, while simultaneously leveraging the learned distribution of features to detect model failure. We provide empirical corroboration on hippocampus and prostate MRI segmentation.