Title: COVID-19 prediction using AI deep VGG16 model from X-ray images
Authors: Narenthirakumar Appavu; C. Nelsonkennedybabu
Addresses: Saveetha School of Engineering, Saveetha Institute of Medical and Technical Sciences, Chennai, Tamilnadu, India ' Saveetha School of Engineering, Saveetha Institute of Medical and Technical Sciences, Chennai, Tamilnadu, India
Abstract: Using human lung X-rays, an advanced technique is currently being used to diagnose COVID-19. Many deep learning concepts piece an imperative role in detecting COVID-19. In this proposed thesis, we presented VGG16 deep learning model for COVID-19 in a precise and timely way. The proposed model used a two-way classification system to differentiate the lung X-rays according to the given input. Finally, it detects affected and normal lung X-rays. The effectiveness of the proposed system is gaged by evaluation criteria as in accuracy, precision, recall and F1 score. More than 2,000 samples were used to diagnose COVID-19. The VGG16 model gives the best results of 99.58% COVID-19 recognition performance for the provided sample size's two-class categorisation. It is superior compared to all existing approaches in the literature. Medical professionals and healthcare workers can use the proposed system to accurately identify COVID-19 using X-rays of human lungs.
Keywords: X-rays; CNN; COVID-19; VGG16; VGG19.
DOI: 10.1504/IJBRA.2023.132635
International Journal of Bioinformatics Research and Applications, 2023 Vol.19 No.2, pp.125 - 140
Received: 11 Nov 2022
Accepted: 08 Feb 2023
Published online: 31 Jul 2023 *