PnP-AdaNet: Plug-and-Play Adversarial Domain Adaptation Network with a Benchmark at Cross-modality Cardiac Segmentation

Abstract

Deep convolutional networks have demonstrated the state-of-the-art performance on various medical image computing tasks. Leveraging images from different modalities for the same analysis task holds clinical benefits. However, the generalization capability of deep models on test data with different distributions remain as a major challenge. In this paper, we propose the PnPAdaNet (plug-and-play adversarial domain adaptation network) for adapting segmentation networks between different modalities of medical images, e.g., MRI and CT. We propose to tackle the significant domain shift by aligning the feature spaces of source and target domains in an unsupervised manner. Specifically, a domain adaptation module flexibly replaces the early encoder layers of the source network, and the higher layers are shared between domains. With adversarial learning, we build two discriminators whose inputs are respectively multi-level features and predicted segmentation masks. We have validated our domain adaptation method on cardiac structure segmentation in unpaired MRI and CT. The experimental results with comprehensive ablation studies demonstrate the excellent efficacy of our proposed PnP-AdaNet. Moreover, we introduce a novel benchmark on the cardiac dataset for the task of unsupervised cross-modality domain adaptation. We will make our code and database publicly available, aiming to promote future studies on this challenging yet important research topic in medical imaging.

References in corpus (8)

• How transferable are features in deep neural networks?
• Learning Transferable Features with Deep Adaptation Networks
• Deep Domain Confusion: Maximizing for Domain Invariance
• Adversarial Discriminative Domain Adaptation
• Task Driven Generative Modeling for Unsupervised Domain Adaptation: Application to X-ray Image Segmentation
• Domain and Geometry Agnostic CNNs for Left Atrium Segmentation in 3D Ultrasound
• Semantic-Aware Generative Adversarial Nets for Unsupervised Domain Adaptation in Chest X-ray Segmentation
• Risk Bounds for Unsupervised Cross-Domain Mapping with IPMs

Cited by in corpus (12)

• Embracing Imperfect Datasets: A Review of Deep Learning Solutions for Medical Image Segmentation
• Domain Generalization for Medical Imaging Classification with Linear-Dependency Regularization
• Learning domain-agnostic visual representation for computational pathology using medically-irrelevant style transfer augmentation
• Domain adaptation based self-correction model for COVID-19 infection segmentation in CT images
• Multi-organ segmentation: a progressive exploration of learning paradigms under scarce annotation
• Data Efficient Unsupervised Domain Adaptation for Cross-Modality Image Segmentation
• On Direct Distribution Matching for Adapting Segmentation Networks
• Consistent Posterior Distributions under Vessel-Mixing: A Regularization for Cross-Domain Retinal Artery/Vein Classification
• Multi-sequence Cardiac MR Segmentation with Adversarial Domain Adaptation Network
• A New Bidirectional Unsupervised Domain Adaptation Segmentation Framework
• ErrorNet: Learning error representations from limited data to improve vascular segmentation
• Domain-Agnostic Learning with Anatomy-Consistent Embedding for Cross-Modality Liver Segmentation