Detection of COVID19 in Chest X-Ray Images Using Transfer Learning

TL;DR

This study explores transfer learning with VGGNet models to detect COVID-19 in chest X-ray images, demonstrating effective classification on small datasets and aiding rapid diagnosis.

Contribution

It investigates the application of transfer learning with VGG-16 and VGG-19 for COVID-19 detection in chest X-rays, optimizing hyperparameters for improved accuracy.

Findings

Transfer learning improves COVID-19 detection accuracy.

Fine-tuning VGG models prevents overfitting on small datasets.

Models achieve promising results in multiclass and binary classification.

Abstract

COVID19 is a highly contagious disease infected millions of people worldwide. With limited testing components, screening tools such as chest radiography can assist the clinicians in the diagnosis and assessing the progress of disease. The performance of deep learning-based systems for diagnosis of COVID-19 disease in radiograph images has been encouraging. This paper investigates the concept of transfer learning using two of the most well-known VGGNet architectures, namely VGG-16 and VGG-19. The classifier block and hyperparameters are fine-tuned to adopt the models for automatic detection of Covid-19 in chest x-ray images. We generated two different datasets to evaluate the performance of the proposed system for the identification of positive Covid-19 instances in a multiclass and binary classification problems. The experimental outcome demonstrates the usefulness of transfer learning for small-sized datasets particularly in the field of medical imaging, not only to prevent over-fitting and convergence problems but also to attain optimal classification performance as well.