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

TL;DR

This paper introduces a novel unsupervised domain adaptation framework using task-driven generative modeling to accurately segment X-ray images by leveraging labeled CT scans and style transfer techniques.

Contribution

It proposes a combined style transfer and segmentation model (TD-GAN) that adapts labeled CT data to X-ray images without requiring X-ray labels, improving segmentation accuracy.

Findings

Achieves 85% dice score on real X-ray images without X-ray labels.

Outperforms baseline models that lack domain adaptation.

Demonstrates generalizability to other tasks.

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%).