Covid-19 Detection from Chest X-Ray using Convolution Neural Networks. Issue 1 (February 2021)

• Record Type: Journal Article
• Authors: Mahesh, Pillalamarry; Prathyusha, Yakkala Gnana; Sahithi, Botlagunta; Nagendram, S
• Is Part Of: Journal of physics. Volume 1804:Issue 1(2021)
• Publication Date: 2021-02
• Subjects: Physics -- Congresses; 530.5
• DOI: 10.1088/1742-6596/1804/1/012197
• Languages: English
• ISSNs: 1742-6588

Abstract

Abstract: A corona virus has infected more than 36, 087, 836 people and 1, 055, 387 Deaths since December 2019. As it rapidly spreads across the planet, scientists and public-health experts are racing to slow down the spreading and trying to find methodologies to detect it. To do that, they need to understand the new virus. It's called severe acute respiratory syndrome coronavirus 2, or SARS-CoV-2. There are different ways to diagnose the COVID-19, but they are cost-effective and increasing the time taken to produce, buy using chest x-ray we can reduce cost and result in time. But to diagnose x-ray's we need expert radiotherapists. Thus, we developed a model that automatically detect COVID and non-COVID X-rays. These days Deep Learning algorithms showing the foremost results in Disease classification. Also, features learned by pre-trained Convolution Neural Networks (CNN) models on large-scale datasets are much useful in image classification tasks. we train and test our model to analyze the images as COVID or normal. we analytically determine the optimal CNN model for the purpose. The accuracy metrics are used to validate the classification of the model.