Deploying Deep Transfer Learning Models to a Web-App for Sars-Cov-2 Detection Using Chest Radiography Images

Abstract

According to the World Health Organization(WHO), the Coronavirus Disease 2019 (COVID-19) is a global hazard to the healthcare sector, with developing and highly populated countries like India influencing the country’s rising economy. In this situation, early detection and diagnosis of COVID-19 are critical for mitigating the pandemic’s impact COVID-19 is critical for mitigating the damage induced by the pandemic disease; consequently, alternate methods for detecting COVID-19 other than manual lab-testing are necessary. This work aims to build and deploy deep Convolutional Neural Networks(CNN) image classification models to a python-flask based web app which is hosted on AWS-EC2 Linux based virtual server to predict if a person is COVID-19 positive or negative just by uploading chest X-ray or computed tomography(CT)-scan image. Therefore, this method investigates the potential of Deep Transfer Learning algorithms such as Res Net 50, Inception V3, Xception, and VGG16 to act as an alternative for manual lab-based testing like reverse-transcription polymerase-chain-reaction(RT-PCR)tests, Rapid tests, and other various types of Antigen tests which, on average, takes 1-2 days to acquire the results, which is unbearable because the affected person can spread the disease to many more members of the population. The CNN models employed in this work are trained on chest X-rays and CT-scan image datasets obtained from verified radiologists’ sources, then these datasets are preprocessed and normalized to achieve higher efficiency. Finally, these trained models are integrated with web-scripting files to create user-friendly web platform, allowing users to upload the sample of the chest X-ray or CT-scan image to refer and compare the predictions made by all four types of models on a single web plat form within a few minutes.