A disentangled generative model for disease decomposition in chest X-rays via normal image synthesis

1 code implementation • 7 Oct 2020 • Tang, Zhu, Y., Xiao, J., & Summers, R. M.

Unlike previous CXR computer-aided diagnosis works that focused on disease diagnosis/classification, we firstly propose a deep disentangled generative model (DGM) simultaneously generating abnormal disease residue maps and “radiorealistic” normal CXR images from an input abnormal CXR image.

Data Augmentation Image Generation