COVID-19 Classification Using Deep Learning Two-Stage Approach

TL;DR

This study compares one-stage and two-stage deep learning models for classifying COVID-19 and other lung conditions from X-ray images, finding that a single VGG16 model performs best with 95% accuracy.

Contribution

It introduces a two-stage classification approach for COVID-19 X-ray analysis and compares its performance to a one-shot model, highlighting the effectiveness of fine-tuned VGG16 networks.

Findings

VGG16 achieved 95% accuracy with one-shot classification.

Two-stage approach did not outperform one-shot in current implementation.

Future work aims to improve the two-stage model's data flow.

Abstract

In this paper, deep-learning-based approaches namely fine-tuning of pretrained convolutional neural networks (VGG16 and VGG19), and end-to-end training of a developed CNN model, have been used in order to classify X-Ray images into four different classes that include COVID-19, normal, opacity and pneumonia cases. A dataset containing more than 20,000 X-ray scans was retrieved from Kaggle and used in this experiment. A two-stage classification approach was implemented to be compared to the one-shot classification approach. Our hypothesis was that a two-stage model will be able to achieve better performance than a one-shot model. Our results show otherwise as VGG16 achieved 95% accuracy using one-shot approach over 5-fold of training. Future work will focus on a more robust implementation of the two-stage classification model Covid-TSC. The main improvement will be allowing data to flow from the output of stage-1 to the input of stage-2, where stage-1 and stage-2 models are VGG16 models fine-tuned on the Covid-19 dataset.