CT-Lung Screening COVID-19 Detection and Classification with Machine Learning

This research makes use of machine learning methods in order to improve the identification of coronavirus in CT lung screens. The very dangerous acute respiratory disease that is produced by this extremely infectious virus is the primary motivation for this research. Over 19 million cases of COVID-19 have been officially recognised by the World Health Organisation (WHO), with a fatality rate that exceeds 500,000. Because there is currently no vaccine available, the most effective method for reducing the disease's spread and mitigating its effects, in particular the risk of deadly lung damage, is the early discovery of the illness. Although there are professionals who support the use of RT-PCR testing, there is another school of thought that proposes CT lung scans might provide a diagnostic solution that is both more accurate and more cost-effective than PCR testing. This has piqued the attention of a large number of researchers, who are now working on the development of Computer-Aided Diagnostic (CAD) tools to aid radiologists in finding COVID-19 in lung scans. The fundamental purpose of this project is to develop an effective computer-aided design (CAD) system that is capable of recognising and classifying the presence of the COVID-19 virus in CT images via the use of machine learning. CT Lung Screening data collection, preprocessing to improve ground glass opacity visibility (initially indistinct and faint), region of interest (ROI) detection using a modified K-means algorithm, and feature extraction and classification using RBF and SVM classifiers are part of the proposed CAD system. This method improves CT lung scan COVID-19 detection by reducing false negatives.