Advances in the field of image classification using convolutional neural networks (CNNs) have greatly improved the accuracy of medical image diagnosis by radiologists. Numerous research groups have applied CNN methods to diagnose respiratory illnesses from chest X-rays and have extended this work to prove the feasibility of rapidly diagnosing COVID-19 with high degrees of accuracy. One issue in previous research has been the use of datasets containing only a few hundred images of chest X-rays containing COVID-19, causing CNNs to overfit the image data. This leads to lower accuracy when the model attempts to classify new images, as would be clinically expected. In this work, we present a model trained on the COVID-QU-Ex dataset containing 33,920 chest X-ray images, with an equal share of COVID-19, Non-COVID pneumonia, and Normal images. The model is an ensemble of pre-trained CNNs (ResNet50, VGG19, and VGG16) and GLCM textural features. The model achieved a 98.34% binary classification accuracy (COVID-19/no COVID-19) on a test dataset of 6581 chest X-rays and 94.68% for distinguishing between COVID-19, Non-COVID pneumonia, and normal chest X-rays. The results also demonstrate that a higher 98.82% three-class test accuracy can be achieved using the model if the training dataset only contains a few thousand images. However, the generalizability of the model suffers due to the smaller dataset size. This study highlights the benefits of both ensemble CNN techniques and larger dataset sizes for medical image classification performance.

Advances in the field of image classification using convolutional neural networks (CNNs) have greatly improved the accuracy of medical image diagnosis by radiologists. Numerous research groups have applied CNN methods to diagnose respiratory illnesses from chest x-rays, and have extended this work to prove the feasibility of rapidly diagnosing COVID-19 to high degrees of accuracy. One issue in previous research has been the use of datasets containing only a few hundred images of chest x-rays containing COVID-19, causing CNNs to overfit the image data. This leads to a lower accuracy when the model attempts to classify new images, as would be clinically expected of it. In this work, we present a model trained on the COVID-QU-Ex dataset, overall containing 33,920 chest x-ray images, with an equal share of COVID-19, Non-COVID pneumonia, and Normal images. The model itself is an ensemble of pre-trained CNNs (ResNet50, VGG19, VGG16) and GLCM textural features. It achieved a 98.34% binary classification accuracy (COVID-19/no COVID-19) on a balanced test dataset of 6581 chest x-rays, and 94.68% for distinguishing between COVID-19, Non-COVID pneumonia and normal chest x-rays. Also, we herein discuss the effects of dataset size, demonstrating that a 98.82% 3-class accuracy can be achieved using the model if the training dataset only contains a few thousand images, but that generalisability of the model suffers with such small datasets.