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

arXiv: https://arxiv.org/abs/1806.07201 · HTML: https://mlsanity.com/paper/1806.07201/

## Key facts

- Cited by 49 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Jun 2018.

## Built on by (most cited first, 30 of 49)

- [Domain Adaptation for Medical Image Analysis: A Survey](https://mlsanity.com/paper/2102.09508/) (2021)
- [Deep Unsupervised Domain Adaptation: A Review of Recent Advances and Perspectives](https://mlsanity.com/paper/2208.07422/) (2022)
- [Deep Learning for Chest X-ray Analysis: A Survey](https://mlsanity.com/paper/2103.08700/) (2021)
- [Source-Free Domain Adaptive Fundus Image Segmentation with Denoised Pseudo-Labeling](https://mlsanity.com/paper/2109.09735/) (2021)
- [Domain Adaptation for Time Series Under Feature and Label Shifts](https://mlsanity.com/paper/2302.03133/) (2023)
- [Source-Free Domain Adaptation for Image Segmentation](https://mlsanity.com/paper/2108.03152/) (2021)
- [Domain Generalization on Medical Imaging Classification using Episodic Training with Task Augmentation](https://mlsanity.com/paper/2106.06908/) (2021)
- [DLTTA: Dynamic Learning Rate for Test-time Adaptation on Cross-domain Medical Images](https://mlsanity.com/paper/2205.13723/) (2022)
- [LE-UDA: Label-efficient unsupervised domain adaptation for medical image segmentation](https://mlsanity.com/paper/2212.02078/) (2022)
- [MT-UDA: Towards Unsupervised Cross-modality Medical Image Segmentation with Limited Source Labels](https://mlsanity.com/paper/2203.12454/) (2022)
- [Deep learning for unsupervised domain adaptation in medical imaging: Recent advancements and future perspectives](https://mlsanity.com/paper/2308.01265/) (2023)
- [Domain Generalization for Mammography Detection via Multi-style and Multi-view Contrastive Learning](https://mlsanity.com/paper/2111.10827/) (2021)
- [Domain Adaptation Meets Zero-Shot Learning: An Annotation-Efficient Approach to Multi-Modality Medical Image Segmentation](https://mlsanity.com/paper/2203.10332/) (2022)
- [Duo-SegNet: Adversarial Dual-Views for Semi-Supervised Medical Image Segmentation](https://mlsanity.com/paper/2108.11154/) (2021)
- [Unsupervised Model Adaptation for Source-free Segmentation of Medical Images](https://mlsanity.com/paper/2211.00807/) (2022)
- [Domain Adaptation for the Segmentation of Confidential Medical Images](https://mlsanity.com/paper/2101.00522/) (2021)
- [Self-Supervised 2D/3D Registration for X-Ray to CT Image Fusion](https://mlsanity.com/paper/2210.07611/) (2022)
- [Adapt Everywhere: Unsupervised Adaptation of Point-Clouds and Entropy Minimisation for Multi-modal Cardiac Image Segmentation](https://mlsanity.com/paper/2103.08219/) (2021)
- [Federated Whole Prostate Segmentation in MRI with Personalized Neural Architectures](https://mlsanity.com/paper/2107.08111/) (2021)
- [CellTranspose: Few-shot Domain Adaptation for Cellular Instance Segmentation](https://mlsanity.com/paper/2212.14121/) (2022)
- [Anatomy-Constrained Contrastive Learning for Synthetic Segmentation without Ground-truth](https://mlsanity.com/paper/2107.05482/) (2021)
- [GAN-based disentanglement learning for chest X-ray rib suppression](https://mlsanity.com/paper/2110.09134/) (2021)
- [Reciprocal Adversarial Learning for Brain Tumor Segmentation: A Solution to BraTS Challenge 2021 Segmentation Task](https://mlsanity.com/paper/2201.03777/) (2022)
- [Anatomy-guided Multimodal Registration by Learning Segmentation without Ground Truth: Application to Intraprocedural CBCT/MR Liver Segmentation and Registration](https://mlsanity.com/paper/2104.07056/) (2021)
- [CATS: Mitigating Correlation Shift for Multivariate Time Series Classification](https://mlsanity.com/paper/2504.04283/) (2025)
- [Unsupervised Domain Adaptive Fundus Image Segmentation with Category-level Regularization](https://mlsanity.com/paper/2207.03684/) (2022)
- [Reconstruction-driven Dynamic Refinement based Unsupervised Domain Adaptation for Joint Optic Disc and Cup Segmentation](https://mlsanity.com/paper/2304.04581/) (2023)
- [Unsupervised Domain Adaptation for Vestibular Schwannoma and Cochlea Segmentation via Semi-supervised Learning and Label Fusion](https://mlsanity.com/paper/2201.10647/) (2022)
- [MSCDA: Multi-level Semantic-guided Contrast Improves Unsupervised Domain Adaptation for Breast MRI Segmentation in Small Datasets](https://mlsanity.com/paper/2301.02554/) (2023)
- [MS-MT: Multi-Scale Mean Teacher with Contrastive Unpaired Translation for Cross-Modality Vestibular Schwannoma and Cochlea Segmentation](https://mlsanity.com/paper/2303.15826/) (2023)

## Abstract (arXiv)

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%).