Comparative analysis of some selected generative adversarial network models for image augmentation: a case study of COVID-19 x-ray and CT images

Abstract

Listen

Translate article

One of the fastest-growing fields in today’s world is data analytics. Data analytics paved the way for a significant number of research and development in various fields including medicine and vaccine development, DNA analysis, artificial intelligence and many more. Data plays a very important role in providing the required results and helps in making critical decisions and predictions. However, ethical and legislative restrictions sometimes make it difficult for scientists to acquire data. For example, during the COVID-19 pandemic, data was very limited due to privacy and regulatory issues. To address data unavailability, data scientists usually leverage machine learning algorithms such as Generative Adversarial Networks (GAN) to augment data from existing samples. Today, there are over 450 algorithms that are designed to re-generate or augment data in case of unavailability of the data. With many algorithms in the market, it is practically impossible to predict which algorithm best fits the problem in question, unless many algorithms are tested. In this study, we select the most common types of GAN algorithms available for image augmentation to generate samples capable of representing a whole data distribution. To test the selected models, we used two unique datasets, namely COVID-19 CT images and COVID-19 X-Ray images. Five different GAN algorithms, namely CGAN, DCGAN, f-GAN, WGAN, and CycleGAN, were selected and applied to the samples to see how each algorithm reacts to the samples. To evaluate their performances, Visual Turing Test (VTT) and Fréchet Inception Distance (FID) were used. The VTT result shows that a human expert can accurately distinguish between different samples that were produced. Hence, CycleGAN scored 80% in CT image dataset and 77% in X-Ray image dataset. In contrast, the FID result revealed that CycleGAN had a high convergence and therefore generated high quality and clearer images on both datasets compared to CGAN, DCGAN, f-GAN, and WGAN. This study concluded that the CycleGAN model is the best when it comes to image augmentation due to its friendliness and high convergence.