COVID-19 Identification from Chest X-Rays
Iosif Mporas, Prasitthichai Naronglerdrit
Abstract
Artificial Intelligence and Data Science community has contributed to the global response against the new coronavirus, COVID-19. Significant attention has been given to detection and diagnosis tools with rapid diagnostic tools based on X-rays using deep learning being proposed. In this paper we present an evaluation of several well-known pretrained deep CNN models in a transfer learning setup for COVID-19 detection from chest X-ray images. Two different publicly available datasets were employed and different setups were tested using each of them separately of mixing them. The best performing models among the evaluated ones were the DenseNet, ResNet and Xception models, with the results indicating the possibility of identifying COVID-19 positive cases from chest X-ray images.