Image projective transformation rectification with synthetic data for smartphone-captured chest X-ray photos classification

Abstract

Automatic interpretation of chest X-ray (CXR) photos taken by smartphones at the same performance level as with digital CXRs is challenging, due to the projective transformation caused by the non-ideal camera position. Existing rectification methods for other camera-captured photos (document photos, license plate photos, etc.) cannot precisely rectify the projective transformation of CXR photos, due to its specific projective transformation type. In this paper, we propose an innovative deep learning-based Projective Transformation Rectification Network (PTRN) to automatically rectify the projective transformation of CXR photos by predicting the projective transformation matrix. Additionally, synthetic CXR photos are generated for training with the consideration of visual artifacts of natural images. The effectiveness of the proposed classification pipeline with PTRN is evaluated in the CheXphoto smartphone-captured CXR photo classification competition. It achieves first place with a huge performance improvement (ours 0.850, second-best 0.762, in AUC). Moreover, experimental results show that our approach successfully achieves the same performance level of digital CXR classification (AUC 0.893) on CXR photo classification (AUC 0.893).