Identification and Classification of COVID-19 using Radiological Images
COVID-19, Artificial Intelligence, Convolution Neural Network, CT scan, Class Activation Mapping, Graph-cut Method, Region Of Interest
The outbreak of the COVID-19 has put the whole world in an unpleasant situation. There is a surge in number of people affected by this disease day by day. Many people have lost their lives to this pandemic disease. At present, the detection of corona virus disease 2019 (COVID-19) is one of the main challenges in the world. This paper implements an artificial intelligence technique based on a deep Convolution Neural Network (CNN) models to detect COVID-19 automatically using real-world datasets. A qualitative analysis is performed to inspect the decisions made by CNN model using a technique known as Class Activation Mapping (CAM). Using CAM, the activations contributed most to the decision of CNN models can be mapped to visualize the most discriminating regions on the input image. Chest CT scan plays a very crucial role in determining the severity of the disease in the infected patients. An AI based image-assisted system is formulated to extract COVID-19 infected sections from lung CT scans (axial view).Threshold filter is applied to extract the lung region and eliminate possible artifacts. Then image segmentation is performed using graph-cut method to extract the region of interest (lung area and infected regions). The binary images of region of interest are then employed to identify the pixel ratio between the lung area and infection sections to calculate the severity level of infection. The classification of COVID-19 infected cases based on severity assist the pulmonologist not only to detect but also to help plan the treatment process efficiently.
Article Details
Unique Paper ID: 155873

Publication Volume & Issue: Volume 9, Issue 2

Page(s): 277 - 288
Article Preview & Download

Share This Article

Join our RMS

Conference Alert

NCSEM 2024

National Conference on Sustainable Engineering and Management - 2024

Last Date: 15th March 2024

Call For Paper

Volume 11 Issue 1

Last Date for paper submitting for Latest Issue is 25 June 2024

About Us enables door in research by providing high quality research articles in open access market.

Send us any query related to your research on

Social Media

Google Verified Reviews