DNN based approach to classify Covid’19 using convolutional neural network and transfer learning

Abstract

The Coronavirus pandemic has taken the world by surprise in its ability to change the way everything functions today. It has severely impacted the health, both mental as well as physical, of citizens around the world. Every country's health care systems have faced a mounting challenge to provide sufficient testing and treatment options to patients as the disease has progressed around the world. Covid-19 is said to affect the lungs of patients and early studies have shown abnormalities in the chest radiograms of infected patients. Inspired by earlier works, this research aims at applying deep learning methods in order to diagnose patients with Covid-19 by making use of X-Ray images. A comparison is made between three different proposed methods, a convolutional neural network with a novel custom architecture and two transfer learning based approaches. The first transfer learning approach uses a MobileNetV2 architecture and the second uses a DenseNet121 architecture with an unsharp mask applied on the images. The achieved performance is highly encouraging and sets a base for wider networks that can be trained on much larger datasets in the future. The experiments were conducted on images from publicly available datasets comprising multiple X-ray images. All three models achieved state-of-the-art results and outperformed other models in various metrics. The performance of the proposed models was compared to previous work and showed better accuracy, precision, recall, and also showed excellent results in certain metrics that are not explored in previous work, such as Mean Absolute Error (MAE) and Root Mean Squared Error (RMSE).

KEYWORDS:

• Deep learning
• convolutional neural network
• machine learning
• transfer learning
• Covid-19

Disclosure statement

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

Correction Statement

This article has been corrected with minor changes. These changes do not impact the academic content of the article.

Additional information

Notes on contributors

Bhavya Joshi

Ms. Bhavya Joshi received her B.Tech. in Information Technology from Manipal University Jaipur, working in Data Science and AI stream. She was WIE vice chair in IEEE WIE chapter. She has experience in Data science and AI related fields.

Akhilesh Kumar Sharma

Dr. Akhilesh Kumar Sharma: Currently working in Manipal University Jaipur, India as Associate Prof., Ph.D. in CSE, M.E. B.E. in CSE. Chaired sessions and acted as Expert for keynotes in IITs, NITs, Vietnam, Thailand, Malaysia, Australia and China etc. He is affiliated with IEEE, ACM, CSI, (IUCEE), and MIR Lab, (USA). He has organized various FDP's, events and Conferences, workshops etc. Written many research papers in Intl. journal of high repute.

Narendra Singh Yadav

Dr. Narendra Singh Yadav received his M.Tech. Degree in Computer Science from Birla Institute of Technology, Ranchi and Ph.D degree from Malaviya National Institute of Technology, Jaipur. He is currently an Associate Professor (Senior Scale) of Information Technology with Manipal University Jaipur, Jaipur. His research interests include Computer Networks, Network Security, Digital Forensics, Cyber Security, Malware and Reverse Engineering. He is an active member of various professional bodies and has published over 50 papers in International/national Journals/conferences.

Shamik Tiwari

Dr. Shamik Tiwari currently working as Sr. Associate Professor in the Department of Virtualization at SoCS, University of Petroleum and Energy Studies, Dehradun. He has rich experience of around eighteen years as an academician. His interest areas are digital image processing, computer vision, biometrics, machine learning especially deep learning, and health informatics. He has written many national and international publications, including books in these fields.