COVIDGR Dataset and COVID-SDNet Methodology for Predicting COVID-19 Based on Chest X-Ray Images

TLDR

COVID‑19 is commonly diagnosed by RT‑PCR, CT, or chest X‑ray, but CT and RT‑PCR are often unavailable, making CXR the most cost‑effective tool; deep learning holds promise for triage, yet existing datasets are heterogeneous and biased toward severe cases. The study aims to clarify why recent COVID‑19 classifiers report high sensitivities, to create a balanced database covering all severity levels, and to propose a method that improves generalization. We built the COVIDGR‑1.0 balanced CXR database and introduced the COVID‑SDNet architecture to enhance generalization of COVID‑classification models. Our approach achieves stable, high accuracy across severe, moderate, and mild cases, enables early detection, and the COVIDGR‑1.0 dataset with severity labels is publicly available.

Abstract

Currently, Coronavirus disease (COVID-19), one of the most infectious diseases in the 21st century, is diagnosed using RT-PCR testing, CT scans and/or Chest X-Ray (CXR) images. CT (Computed Tomography) scanners and RT-PCR testing are not available in most medical centers and hence in many cases CXR images become the most time/cost effective tool for assisting clinicians in making decisions. Deep learning neural networks have a great potential for building COVID-19 triage systems and detecting COVID-19 patients, especially patients with low severity. Unfortunately, current databases do not allow building such systems as they are highly heterogeneous and biased towards severe cases. This article is three-fold: (i) we demystify the high sensitivities achieved by most recent COVID-19 classification models, (ii) under a close collaboration with Hospital Universitario Clínico San Cecilio, Granada, Spain, we built COVIDGR-1.0, a homogeneous and balanced database that includes all levels of severity, from normal with Positive RT-PCR, Mild, Moderate to Severe. COVIDGR-1.0 contains 426 positive and 426 negative PA (PosteroAnterior) CXR views and (iii) we propose COVID Smart Data based Network (COVID-SDNet) methodology for improving the generalization capacity of COVID-classification models. Our approach reaches good and stable results with an accuracy of [Formula: see text], [Formula: see text], [Formula: see text] in severe, moderate and mild COVID-19 severity levels. Our approach could help in the early detection of COVID-19. COVIDGR-1.0 along with the severity level labels are available to the scientific community through this link https://dasci.es/es/transferencia/open-data/covidgr/.