Task Driven Generative Modeling for Unsupervised Domain Adaptation: Application to X-ray Image Segmentation

Abstract

Automatic parsing of anatomical objects in X-ray images is critical to many clinical applications in particular towards image-guided invention and workflow automation. Existing deep network models require a large amount of labeled data. However, obtaining accurate pixel-wise labeling in X-ray images relies heavily on skilled clinicians due to the large overlaps of anatomy and the complex texture patterns. On the other hand, organs in 3D CT scans preserve clearer structures as well as sharper boundaries and thus can be easily delineated. In this paper, we propose a novel model framework for learning automatic X-ray image parsing from labeled CT scans. Specifically, a Dense Image-to-Image network (DI2I) for multi-organ segmentation is first trained on X-ray like Digitally Reconstructed Radiographs (DRRs) rendered from 3D CT volumes. Then we introduce a Task Driven Generative Adversarial Network (TD-GAN) architecture to achieve simultaneous style transfer and parsing for unseen real X-ray images. TD-GAN consists of a modified cycle-GAN substructure for pixel-to-pixel translation between DRRs and X-ray images and an added module leveraging the pre-trained DI2I to enforce segmentation consistency. The TD-GAN framework is general and can be easily adapted to other learning tasks. In the numerical experiments, we validate the proposed model on 815 DRRs and 153 topograms. While the vanilla DI2I without any adaptation fails completely on segmenting the topograms, the proposed model does not require any topogram labels and is able to provide a promising average dice of 85% which achieves the same level accuracy of supervised training (88%).

References in corpus (3)

• Conditional Generative Adversarial Nets
• Domain Separation Networks
• X-ray In-Depth Decomposition: Revealing The Latent Structures

Cited by in corpus (44)

• Generative Adversarial Network in Medical Imaging: A Review
• Domain Adaptation for Medical Image Analysis: A Survey
• Deep Learning for Chest X-ray Analysis: A Survey
• Embracing Imperfect Datasets: A Review of Deep Learning Solutions for Medical Image Segmentation
• Patch-based Output Space Adversarial Learning for Joint Optic Disc and Cup Segmentation
• DoFE: Domain-oriented Feature Embedding for Generalizable Fundus Image Segmentation on Unseen Datasets
• LE-UDA: Label-efficient unsupervised domain adaptation for medical image segmentation
• Domain Generalization for Medical Imaging Classification with Linear-Dependency Regularization
• PnP-AdaNet: Plug-and-Play Adversarial Domain Adaptation Network with a Benchmark at Cross-modality Cardiac Segmentation
• Domain Adaptation Meets Zero-Shot Learning: An Annotation-Efficient Approach to Multi-Modality Medical Image Segmentation
• Synergistic Image and Feature Adaptation: Towards Cross-Modality Domain Adaptation for Medical Image Segmentation
• When Unseen Domain Generalization is Unnecessary? Rethinking Data Augmentation
• MT-UDA: Towards Unsupervised Cross-modality Medical Image Segmentation with Limited Source Labels
• i3PosNet: Instrument Pose Estimation from X-Ray in temporal bone surgery
• Unsupervised domain adaptation based COVID-19 CT infection segmentation network
• Constrained domain adaptation for Image segmentation
• Cross-Domain Object Detection Using Unsupervised Image Translation
• GASNet: Weakly-supervised Framework for COVID-19 Lesion Segmentation
• An Inductive Transfer Learning Approach using Cycle-consistent Adversarial Domain Adaptation with Application to Brain Tumor Segmentation
• Boundary and Entropy-driven Adversarial Learning for Fundus Image Segmentation
• Multi-organ segmentation: a progressive exploration of learning paradigms under scarce annotation
• Unsupervised Bidirectional Cross-Modality Adaptation via Deeply Synergistic Image and Feature Alignment for Medical Image Segmentation
• Deep Mining External Imperfect Data for Chest X-ray Disease Screening
• Convex Shape Prior for Deep Neural Convolution Network based Eye Fundus Images Segmentation
• Data Efficient Unsupervised Domain Adaptation for Cross-Modality Image Segmentation
• Unsupervised Domain Adaptation for Vestibular Schwannoma and Cochlea Segmentation via Semi-supervised Learning and Label Fusion
• Towards Continuous Domain adaptation for Healthcare
• Deep Learning in Multi-organ Segmentation
• Cross-Modality Brain Tumor Segmentation via Bidirectional Global-to-Local Unsupervised Domain Adaptation
• TUNA-Net: Task-oriented UNsupervised Adversarial Network for Disease Recognition in Cross-Domain Chest X-rays
• Unsupervised Instance Segmentation in Microscopy Images via Panoptic Domain Adaptation and Task Re-weighting
• Source-Free Domain Adaptive Fundus Image Segmentation with Denoised Pseudo-Labeling
• Anatomy-Constrained Contrastive Learning for Synthetic Segmentation without Ground-truth
• Dispensed Transformer Network for Unsupervised Domain Adaptation
• Encoding CT Anatomy Knowledge for Unpaired Chest X-ray Image Decomposition
• One-to-one Mapping for Unpaired Image-to-image Translation
• 3D Organ Shape Reconstruction from Topogram Images
• Privacy-Preserving Constrained Domain Generalization via Gradient Alignment
• MI^2GAN: Generative Adversarial Network for Medical Image Domain Adaptation using Mutual Information Constraint
• On Direct Distribution Matching for Adapting Segmentation Networks
• Federated Whole Prostate Segmentation in MRI with Personalized Neural Architectures
• Anatomy-guided Multimodal Registration by Learning Segmentation without Ground Truth: Application to Intraprocedural CBCT/MR Liver Segmentation and Registration
• Domain Generalization for Mammography Detection via Multi-style and Multi-view Contrastive Learning
• Domain-Agnostic Learning with Anatomy-Consistent Embedding for Cross-Modality Liver Segmentation