GIL-CNN: A Novel Multipath Features for COVID-19 Detection Using CT-Scan Images

ABSTRACT

The rapid expansion of coronavirus illness (COVID-19) became a global problem, with over 40 million confirmed individuals infected as of February 2022. Medical imaging, such as CT scans, can be used for diagnostics to counteract its spread. Automatic COVID detection tools are required to ease the process using CT scan images. This work categorizes the healthy and COVID patients based on CT scan images. As such, a GIL-CNN model is proposed to detect COVID patients in the present paper. The proposed model provides the global, intermediate, and local features that help better CT scan image feature representation by avoiding spatial loss. The support vector machine, a standard machine learning classifier, is used to classify the normal and COVID images using the GIL-CNN features. The proposed model is trained and tested on publicly available COVID-19 CT scan images. The proposed model has produced better results than state-of-the-art techniques. The proposed model can assist in the automated identification of COVID-19 patients, reducing the strain on healthcare systems.

Keywords:

• COVID-19
• CT scan images
• Convolutional neural networks
• Feature extraction
• Machine learning
• Classification

DISCLOSURE STATEMENT

No potential conflict of interest was reported by the author(s).

Additional information

Notes on contributors

N. Jagan Mohan

N Jagan Mohan is currently pursuing his PhD degree at the National Institute of Technology Silchar in bio-medical image processing. He received his master's degree in embedded systems from JNTU Hyderabad. He received his bachelor's degree in electronics and communication engineering from JNTU Hyderabad. Before enrolling PhD, he worked as an assistant professor in the Department of Electronics and Communication Engineering in Chaitanya Bharathi Institute of Technology (CBIT) Gandipet, Hyderabad. He published three journal publications, five conferences, two book chapters. His area of interest includes bio-medical image processing, medical imaging, machine learning, deep learning, computer vision, pattern recognition, retinal image analysis. Email: [email protected]

D. N. Kiran Pandiri

D N Kiran Pandiri received the MTech degree in embedded systems from Amrita Vishwa Vidyapeetham University, India in 2012. He completed his BTech in the stream of electronics and communication engineering from JNTU Kakinada, India in 2009. He currently pursuing a PhD in NIT Silchar, Assam. He worked as an assistant professor from 2014 to 2019 in the Department of Electronics and Communication Engineering, Madanapalle Institute of Technology & Science, Madanapalle, Andhra Pradesh, India. He worked as a programmer analyst in Cognizant Technology Solutions India Private Ltd., from 2012 to 2014.