A University of Dubai-led team has developed an efficient and accurate deep learning model for rapid detection of COVID-19 and non-COVD-19 pneumonia infections using lung X-rays of symptomatic patients.
The COVID-DeepNet deep learning model proposed by the team achieved a classification accuracy of 99.67%, which is in line with state-of-the-art models, demonstrating its potential as an alternative solution for COVID-19 detection that could be used in conjunction with the antibody test for the faster screening of the pandemic. Deep learning is part of a broader family of machine learning methods based on artificial neural networks with representation learning.
The research team was composed of University of Dubai (UD) Assistant Professor of Electronics Engineering Dr. Alavikunhu Panthakkan, Thangal Kunju Musaliar (TKM) College of Engineering Kollam Assistant Professor of Electronics and Communication Engineering Dr. S. M. Anzar, Mohammed Bin Rashid Space Center Applications Development and Analysis Section Head Eng. Saeed Al Mansoori and UD Provost and Chief Academic Officer Dr. Hussain Al Ahmad. Their research was the focus of a paper published in the journal Biomedical Signal Processing and Control.
“Recent radiological imaging findings confirm that lung X-ray and CT scans provide an excellent indication of the progression of COVID-19 infection in acute symptomatic carriers. A novel and highly efficient COVID-DeepNet model is presented for the accurate and rapid prediction of COVID-19 infection using state-of-the-art artificial intelligence techniques. The proposed model provides a multi-class classification of lung X-ray images into COVID-19, non-COVID pneumonia, and normal (healthy),” the researchers stated in their paper on the subject.