Advertisement
Published in:
2021 | OriginalPaper | Chapter
Covid Prediction from Chest X-Rays Using Transfer Learning
Authors : D. Haritha, M. Krishna Pranathi
Published in: Advanced Computing
Publisher: Springer Singapore
Activate our intelligent search to find suitable subject content or patents.
Select sections of text to find matching patents with Artificial Intelligence. powered by
Select sections of text to find additional relevant content using AI-assisted search. powered by
Abstract
The novel corona virus is a rapidly spreading viral infection that has became a pandemic causing destructive effects on public health and global economy. So, early detection and Covid-19 patient early quarantine is having the significant impact on curtailing it’s transmission rate. But it has become a major challenge due to critical shortage of test kits. A new promising method that overcomes this challenge by predicting Covid-19 from patient X-rays using transfer learning, a deep learning technique is proposed in this paper. For this we used a dataset consisting of chest x-rays of Covid-19 infected and normal people. we used VGG, GoogleNet-Inception v1, ResNet, CheXNet models of transfer learning which is a deep learning technique for its benefit of decreasing the training time for a neural network model. Using these we show accuracies of 99.49%, 99%, 98.63%, 99.93% respectively in Covid-19 prediction from x-ray of suspected patient.