COVID-19 Infection Map Generation and Detection from Chest X-Ray Images

TL;DR

This paper introduces a comprehensive deep learning approach for COVID-19 detection, localization, and severity grading from chest X-ray images, utilizing the largest annotated dataset and achieving high accuracy and reliable infection localization.

Contribution

It presents a novel joint localization, severity grading, and detection method using infection maps, supported by the largest publicly available CXR dataset with ground-truth masks.

Findings

Achieved 83.20% F1-score in infection localization

Detected COVID-19 with 94.96% sensitivity and 99.88% specificity

Compiled and released the largest annotated CXR dataset with 119,316 images

Abstract

Computer-aided diagnosis has become a necessity for accurate and immediate coronavirus disease 2019 (COVID-19) detection to aid treatment and prevent the spread of the virus. Numerous studies have proposed to use Deep Learning techniques for COVID-19 diagnosis. However, they have used very limited chest X-ray (CXR) image repositories for evaluation with a small number, a few hundreds, of COVID-19 samples. Moreover, these methods can neither localize nor grade the severity of COVID-19 infection. For this purpose, recent studies proposed to explore the activation maps of deep networks. However, they remain inaccurate for localizing the actual infestation making them unreliable for clinical use. This study proposes a novel method for the joint localization, severity grading, and detection of COVID-19 from CXR images by generating the so-called infection maps. To accomplish this, we have compiled the largest dataset with 119,316 CXR images including 2951 COVID-19 samples, where the annotation of the ground-truth segmentation masks is performed on CXRs by a novel collaborative human-machine approach. Furthermore, we publicly release the first CXR dataset with the ground-truth segmentation masks of the COVID-19 infected regions. A detailed set of experiments show that state-of-the-art segmentation networks can learn to localize COVID-19 infection with an F1-score of 83.20%, which is significantly superior to the activation maps created by the previous methods. Finally, the proposed approach achieved a COVID-19 detection performance with 94.96% sensitivity and 99.88% specificity.