Chest X-ray Inpainting with Deep Generative Models
This work addresses the need for realistic medical image inpainting to potentially enhance and detect abnormalities in chest X-rays, but it is incremental as it applies existing methods to a new domain.
The paper tackled the problem of applying deep generative models to inpainting in chest X-rays, evaluating three existing models on 1.2M patches and showing that outputs are highly realistic, with an observer study indicating poor human detection of inpainted regions, especially for the contextual attention model.
Generative adversarial networks have been successfully applied to inpainting in natural images. However, the current state-of-the-art models have not yet been widely adopted in the medical imaging domain. In this paper, we investigate the performance of three recently published deep learning based inpainting models: context encoders, semantic image inpainting, and the contextual attention model, applied to chest x-rays, as the chest exam is the most commonly performed radiological procedure. We train these generative models on 1.2M 128 $\times$ 128 patches from 60K healthy x-rays, and learn to predict the center 64 $\times$ 64 region in each patch. We test the models on both the healthy and abnormal radiographs. We evaluate the results by visual inspection and comparing the PSNR scores. The outputs of the models are in most cases highly realistic. We show that the methods have potential to enhance and detect abnormalities. In addition, we perform a 2AFC observer study and show that an experienced human observer performs poorly in detecting inpainted regions, particularly those generated by the contextual attention model.