Encoding CT Anatomy Knowledge for Unpaired Chest X-ray Image Decomposition
This work addresses a clinical need for improved diagnostic accuracy in chest X-ray analysis by enabling decomposition without paired data, though it is incremental as it builds on existing generative adversarial network methods.
The authors tackled the problem of decomposing chest X-ray images into anatomical components like bone, lung, and soft tissue using unpaired data, achieving superior unsupervised bone suppression and outperforming state-of-the-art methods in predicting 11 out of 14 common lung diseases.
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.