Medical Image Augmentation Framework for Resolving Chest X-Ray Data Imbalance

Abstract

Deep learning techniques, particularly convolutional neural networks (CNNs), have led to an enormous breakthrough in the field of medical imaging. Since the onset of the COVID-19 pandemic, studies based on deep learning systems have shown excellent results for diagnosis through the use of Chest X-rays. However, these methods are data sensitive, and their effectiveness depends on the availability and reliability of data. Models trained on a class-imbalanced dataset tend to be biased towards the majority class. The class-imbalanced datasets can be balanced by augmenting them with synthetically generated images. This paper proposes a method for generating synthetic COVID-19 Chest X-Rays images using Generative Adversarial Networks (GANs). The images generated using the proposed GAN were augmented to three imbalanced datasets of real images. It was observed that the performance of the CNN model for COVID-19 classification improved with the augmented images. Significant improvement was seen in the sensitivity or recall, which is a very critical metric. The sensitivity achieved by adding GAN-generated synthetic images to each of the imbalanced datasets matched the sensitivity levels of the balanced dataset. Hence, the proposed solution can be used to generate images that boost the sensitivity of COVID-19 diagnosis to the level of a balanced dataset. Furthermore, this approach of synthetic data augmentation can be used in other medical classification applications for improved diagnosis recommendations.