Sars Detection: An Automated Detection of Covid-19 Through Convolutional Neural Network Using Lung Ct Scans and Symptom-Based Analysis

Abstract – The SARS-CoV-2 virus, which produced the COVID-19 pandemic, has presented hitherto unheard-of difficulties for international healthcare systems, making precise and effective diagnostic techniques essential to crisis management. In order to improve diagnostic reliability, this study combines lung CT scan analysis with a symptom-based checker module to present an enhanced deep learning-based system for the automated detection of COVID-19. We present C-COVIDNet, a lightweight convolutional neural network (CNN) with an accuracy of 96.39% that can categorize lung CT images into three groups: COVID-19, viral pneumonia, and normal (healthy) people. To make sure that only pertinent characteristics are supplied into the network, the model uses an image preprocessing pipeline to extract the region of interest (ROI) from CT scans. in order for the input to contain the necessary qualities. The accuracy of this lightweight method based on convolution neural networks (CNNs) is 96.39%. The Kaggle dataset is used to generate the model's input images. The state-of-the-art has been surpassed by the performance. The encouraging outcomes will undoubtedly aid in hastening the creation of radiography-based deep learning-based COVID-19 diagnostic tools. Key Words: COVID-19 detection, Deep learning, Convolutional neural network,Image processing, Symptom checker, SQL database, Django framework