SDC-UDA: Volumetric Unsupervised Domain Adaptation Framework for Slice-Direction Continuous Cross-Modality Medical Image Segmentation
This addresses the annotation cost problem in medical imaging for clinicians, though it appears incremental as it builds on existing UDA methods with specific enhancements.
The paper tackles the problem of expensive pixel-level annotations in medical image segmentation by proposing SDC-UDA, a volumetric unsupervised domain adaptation framework for cross-modality segmentation, achieving state-of-the-art performance and superior slice-direction continuity compared to previous studies.
Recent advances in deep learning-based medical image segmentation studies achieve nearly human-level performance in fully supervised manner. However, acquiring pixel-level expert annotations is extremely expensive and laborious in medical imaging fields. Unsupervised domain adaptation (UDA) can alleviate this problem, which makes it possible to use annotated data in one imaging modality to train a network that can successfully perform segmentation on target imaging modality with no labels. In this work, we propose SDC-UDA, a simple yet effective volumetric UDA framework for slice-direction continuous cross-modality medical image segmentation which combines intra- and inter-slice self-attentive image translation, uncertainty-constrained pseudo-label refinement, and volumetric self-training. Our method is distinguished from previous methods on UDA for medical image segmentation in that it can obtain continuous segmentation in the slice direction, thereby ensuring higher accuracy and potential in clinical practice. We validate SDC-UDA with multiple publicly available cross-modality medical image segmentation datasets and achieve state-of-the-art segmentation performance, not to mention the superior slice-direction continuity of prediction compared to previous studies.