Detection and classification of COVID-19 using supervised deep learning on MRI images
by J. Chinna Babu; Mudassir Khan; Mallikharjuna Rao Nuka; C.H. Nagaraju
International Journal of Bioinformatics Research and Applications (IJBRA), Vol. 19, No. 4, 2023

Abstract: Healthcare services in many parts of the world, but especially in emerging countries, have been made aware of the risks presented by the COVID-19 pandemic. In areas where bulk traditional testing is not practical, new computer-assisted diagnosis methods are clearly needed to provide speedy and cost-effective screening. Pulmonary ultrasonography can be used to diagnose lung disease since it is portable, easy to clean, inexpensive, and non-invasive. In recent years, computer-assisted analysis of lung ultrasound images has showed considerable promise for identifying respiratory disorders, including COVID-19 screening and diagnosis. Detecting COVID-19 infections from lung ultrasound images using deep-learning algorithms and comparing their results. It was possible to use a variety of pre-trained deep learning architectures to this problem. There are 3,326 lung ultrasound images in the POCUS dataset, which we used to train and fine-tune our algorithm. Computed tomography (CT) proved useful in the diagnosis of corona virus infection particularly in the pandemic of new corona virus (COVID-19). Radiation from patients who underwent CT scans experienced alterations that were comparable to those seen in MRI scans. A chest MRI should be performed if a CT scan is unavailable, according to the study's findings.

Online publication date: Wed, 06-Dec-2023

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Bioinformatics Research and Applications (IJBRA):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com