Computer-aided Diagnosis Of Chest X-ray For Covid-19 Diagnosis In External Validation Study By Radiologists With And Without Deep Learning System

This retrospective study was conducted to develop and evaluate a deep learning model for detecting COVID-19 cases from chest X-rays. The CXR datasets used for this study contained CXRs for three categories: normal, non-COVID-19 pneumonia, and COVID-19 pneumonia. The datasets used were two public (COVIDx and COVID) and one private (COVID) datasets. Compared to the previous study, the current study added 37, 7, and 31 cases of NORMAL, PNEUMONIA, and COVID, respectively. The additional CXRs included 530 CXRs (176 NORMAL, 148 PNEUMONIA, and 206 COVID).