Automatic Detection of Pneumonia on Compressed Sensing Images using Deep Learning

Abstract

Pneumonia is one of the life threatening very common disease and needs proper diagnosis at an early stage for proper treatment of recovery. Chest X-ray is used as an imagining modality to identify the disease by a professional radiologist. This paper suggests a Compressed Sensing (CS) based deep learning framework for automatic detection of pneumonia on X-ray images to assist the medical practitioners. Extensive simulation results show that the proposed approach enables detection of pneumonia with 97.34% prediction accuracy and an improvement on reconstruction quality of the X-ray images in terms of PSNR by $1 \pm 0. 76 dB$ and SSIM by $0. 2 \pm 0.05$ using the proposed method compared to the other state-of-the-art methods.