# Encoding CT Anatomy Knowledge for Unpaired Chest X-ray Image Decomposition

arXiv: https://arxiv.org/abs/1909.12922 · HTML: https://mlsanity.com/paper/1909.12922/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Sep 2019.

## Built on by (most cited first, 7 of 7)

- [Deep Learning for Chest X-ray Analysis: A Survey](https://mlsanity.com/paper/2103.08700/) (2021)
- [FIBA: Frequency-Injection based Backdoor Attack in Medical Image Analysis](https://mlsanity.com/paper/2112.01148/) (2021)
- [Learning Disentangled Representations in the Imaging Domain](https://mlsanity.com/paper/2108.12043/) (2021)
- [GAN-based disentanglement learning for chest X-ray rib suppression](https://mlsanity.com/paper/2110.09134/) (2021)
- [An Efficient and Robust Method for Chest X-Ray Rib Suppression that Improves Pulmonary Abnormality Diagnosis](https://mlsanity.com/paper/2302.09696/) (2023)
- [X-ray Dissectography Enables Stereotography to Improve Diagnostic Performance](https://mlsanity.com/paper/2111.15040/) (2021)
- [Rib Suppression in Digital Chest Tomosynthesis](https://mlsanity.com/paper/2203.02772/) (2022)

## Abstract (arXiv)

Although chest X-ray (CXR) offers a 2D projection with overlapped anatomies, it is widely used for clinical diagnosis. There is clinical evidence supporting that decomposing an X-ray image into different components (e.g., bone, lung and soft tissue) improves diagnostic value. We hereby propose a decomposition generative adversarial network (DecGAN) to anatomically decompose a CXR image but with unpaired data. We leverage the anatomy knowledge embedded in CT, which features a 3D volume with clearly visible anatomies. Our key idea is to embed CT priori decomposition knowledge into the latent space of unpaired CXR autoencoder. Specifically, we train DecGAN with a decomposition loss, adversarial losses, cycle-consistency losses and a mask loss to guarantee that the decomposed results of the latent space preserve realistic body structures. Extensive experiments demonstrate that DecGAN provides superior unsupervised CXR bone suppression results and the feasibility of modulating CXR components by latent space disentanglement. Furthermore, we illustrate the diagnostic value of DecGAN and demonstrate that it outperforms the state-of-the-art approaches in terms of predicting 11 out of 14 common lung diseases.