🤖 AI Summary
Online unsupervised domain adaptation for medical image segmentation faces two key challenges: severe pseudo-label noise under continuous target-domain data streams and difficulty achieving convergence with single-step model updates.
Method: We propose an online adaptive framework that jointly integrates expert pixel-level feedback and active learning. We introduce a novel image-level uncertainty-driven pruning strategy to select high-information samples for expert annotation, and embed sparse expert feedback directly into a single forward-backward pass to enable low-overhead, real-time model adaptation.
Contribution/Results: Our method significantly outperforms existing online approaches across multiple medical imaging streaming tasks, matching the performance of offline active learning baselines while reducing expert annotation cost by 42%. It achieves robust online adaptation without requiring iterative retraining or extensive human supervision.
📝 Abstract
Unsupervised domain adaptive segmentation typically relies on self-training using pseudo labels predicted by a pre-trained network on an unlabeled target dataset. However, the noisy nature of such pseudo-labels presents a major bottleneck in adapting a network to the distribution shift between source and target datasets. This challenge is exaggerated when the network encounters an incoming data stream in online fashion, where the network is constrained to adapt to incoming streams of target domain data in exactly one round of forward and backward passes. In this scenario, relying solely on inaccurate pseudo-labels can lead to low-quality segmentation, which is detrimental to medical image analysis where accuracy and precision are of utmost priority. We hypothesize that a small amount of pixel-level annotation obtained from an expert can address this problem, thereby enhancing the performance of domain adaptation of online streaming data, even in the absence of dedicated training data. We call our method ODES: Domain Adaptation with Expert Guidance for Online Medical Image Segmentation that adapts to each incoming data batch in an online setup, incorporating feedback from an expert through active learning. Through active learning, the most informative pixels in each image can be selected for expert annotation. However, the acquisition of pixel-level annotations across all images in a batch often leads to redundant information while increasing temporal overhead in online learning. To reduce the annotation acquisition time and make the adaptation process more online-friendly, we further propose a novel image-pruning strategy that selects the most useful subset of images from the current batch for active learning. Our proposed approach outperforms existing online adaptation approaches and produces competitive results compared to offline domain adaptive active learning methods.
