LE-UDA: Label-efficient unsupervised domain adaptation for medical image segmentation

Abstract

While deep learning methods hitherto have achieved considerable success in medical image segmentation, they are still hampered by two limitations: (i) reliance on large-scale well-labeled datasets, which are difficult to curate due to the expert-driven and time-consuming nature of pixel-level annotations in clinical practices, and (ii) failure to generalize from one domain to another, especially when the target domain is a different modality with severe domain shifts. Recent unsupervised domain adaptation~(UDA) techniques leverage abundant labeled source data together with unlabeled target data to reduce the domain gap, but these methods degrade significantly with limited source annotations. In this study, we address this underexplored UDA problem, investigating a challenging but valuable realistic scenario, where the source domain not only exhibits domain shift~w.r.t. the target domain but also suffers from label scarcity. In this regard, we propose a novel and generic framework called ``Label-Efficient Unsupervised Domain Adaptation"~(LE-UDA). In LE-UDA, we construct self-ensembling consistency for knowledge transfer between both domains, as well as a self-ensembling adversarial learning module to achieve better feature alignment for UDA. To assess the effectiveness of our method, we conduct extensive experiments on two different tasks for cross-modality segmentation between MRI and CT images. Experimental results demonstrate that the proposed LE-UDA can efficiently leverage limited source labels to improve cross-domain segmentation performance, outperforming state-of-the-art UDA approaches in the literature. Code is available at: https://github.com/jacobzhaoziyuan/LE-UDA.

arXiv commentAccepted by IEEE Transactions on Medical Imaging, 2022

References in corpus (16)

• Temporal Ensembling for Semi-Supervised Learning
• ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation
• A review of deep learning in medical imaging: Imaging traits, technology trends, case studies with progress highlights, and future promises
• Deeply-Supervised Nets
• Domain Adaptation for Medical Image Analysis: A Survey
• CHAOS Challenge -- Combined (CT-MR) Healthy Abdominal Organ Segmentation
• Models Genesis
• Transfer Learning for Domain Adaptation in MRI: Application in Brain Lesion Segmentation
• SynSeg-Net: Synthetic Segmentation Without Target Modality Ground Truth
• Task Driven Generative Modeling for Unsupervised Domain Adaptation: Application to X-ray Image Segmentation
• DSAL: Deeply Supervised Active Learning from Strong and Weak Labelers for Biomedical Image Segmentation
• MT-UDA: Towards Unsupervised Cross-modality Medical Image Segmentation with Limited Source Labels
• Hierarchical Consistency Regularized Mean Teacher for Semi-supervised 3D Left Atrium Segmentation
• Semi-supervised Medical Image Segmentation through Dual-task Consistency
• COSMOS: Cross-Modality Unsupervised Domain Adaptation for 3D Medical Image Segmentation based on Target-aware Domain Translation and Iterative Self-Training
• ICMSC: Intra- and Cross-modality Semantic Consistency for Unsupervised Domain Adaptation on Hip Joint Bone Segmentation

Cited by in corpus (5)

• A Comprehensive Study on Medical Image Segmentation using Deep Neural Networks
• Meta-learners for few-shot weakly-supervised optic disc and cup segmentation on fundus images
• BCMDA: Bidirectional Correlation Maps Domain Adaptation for Mixed Domain Semi-Supervised Medical Image Segmentation
• Performance Analysis and Optimization of 3D Generative Diffusion Models across GPU Architectures
• TCSA-UDA: Text-Driven Cross-Semantic Alignment for Unsupervised Domain Adaptation in Medical Image Segmentation