COVID-19 Classification on Chest X-ray Images Using Deep Learning Methods

Since December 2019, the coronavirus disease has significantly affected millions of people. Given the effect this disease has on the pulmonary systems of humans, there is a need for chest radiographic imaging (CXR) for monitoring the disease and preventing further deaths. Several studies have shown that deep learning models can achieve promising results for COVID-19 diagnosis from CXR images. In this study, five deep learning models (ResNet50, ResNet101, DenseNet121, DenseNet169, InceptionV3) with transfer learning were analyzed and evaluated to identify COVID-19 from chest X-ray images. All models were trained and validated on the largest publicly available repository for COVID-19 CXR images and evaluated on unseen test data. All models achieved satisfactory performance; ResNet101 was superior, achieving 96% Precision, Recall, and Accuracy. The outcomes show the potential of deep learning models for COVID-19 medical image analysis and offer a promising avenue for improved understanding and diagnosis of COVID-19.

Paul B Tchounwou, Stelios Zimeras, Styliani Geronikolou, Marios Constantinou, Themis Exarchos, Aristidis G Vrahatis, Panagiotis Vlamos