CovidNet: A Light-Weight CNN for the Detection of COVID-19 Using Chest X-Ray Images
Abstract:
Corona virus more popularly known as COVID-19 is an extremely virulent strain from the Corona virus family of viruses and their origin is attributed to bats and civet cats. Currently, there is no cure for this virus nor are there any vaccines available to prevent this. Chest X-ray images are used for diagnosing the presence of this virus in the human body. Chest X-rays can be diagnosed only by expert radiotherapists for evaluation. Thus, the development of a system that would detect whether a person is infected by the Corona virus or not without any delay would be very helpful for people as well as doctors. In this research article, we proposed a novel deep learning model named CovidNet to detect the presence of Corona virus in a human body. We performed extensive experiments on the proposed model and pre-trained models, and the experiments show that the proposed model outperformed other pre-trained models. The proposed CovidNet model achieved best testing accuracy of 98.5%.
Publication: Advanced computing
Publisher: Springer Link
Authors: Tejalal Choudhary, Aditi Godbole, Vaibhav Gattyani, Aditya Gurnani, Aditi Verma & Aditya Babar
Keywords: Transfer learning, Deep learning, Image classification, Chest X-ray, COVID-19, Convolutional Neural Network
Meet one of the Author:
Affiliations:
Stay In the Know
Get Latest updates and industry insights every month.