Evaluation of Poor Prognosis in rRT-PCR Positive Covid-19 Cases with Using Deep Transfer Learning Network

The infection called Covid-19 caused by the new type of coronavirus (SARS-CoV-2) is an epidemic and deadly disease that spreads rapidly all over the world. Early detection of Covid-19 will enable the patient to receive appropriate treatment and increase the chance of survival. In this study, it is aimed to investigate the detection of poor prognosis from chest CT images in Covid-19 patients who died and healed using deep learning. For this purpose, a dataset containing a total of 5997 CT images were used and images were classified using the Inception-V3. In order to evaluate the classifier ROC curves are drawn, AUC and accuracy values are used as performance metrics. Inception-V3 model was run 10 times, and a maximum classification performance of 97,55% and an average of 97,01% was achieved. The classification results prove that Inception-V3 can classify CT images with a high accuracy rate for evaluation of Covid-19 prognosis.