Evaluation of Deep Convolutional Generative Adversarial Networks for data augmentation of chest X-ray images

TL;DR

This paper explores using deep convolutional GANs to generate synthetic chest X-ray images for data augmentation, aiming to improve classification performance on imbalanced medical datasets.

Contribution

It demonstrates the effectiveness of GAN-based data augmentation in medical imaging, achieving a low FID score indicating high-quality synthetic images.

Findings

GAN-generated images are similar to real data.

Data augmentation with GANs improves model performance.

FID score of 1.289 indicates high-quality synthetic images.

Abstract

Medical image datasets are usually imbalanced, due to the high costs of obtaining the data and time-consuming annotations. Training deep neural network models on such datasets to accurately classify the medical condition does not yield desired results and often over-fits the data on majority class samples. In order to address this issue, data augmentation is often performed on training data by position augmentation techniques such as scaling, cropping, flipping, padding, rotation, translation, affine transformation, and color augmentation techniques such as brightness, contrast, saturation, and hue to increase the dataset sizes. These augmentation techniques are not guaranteed to be advantageous in domains with limited data, especially medical image data, and could lead to further overfitting. In this work, we performed data augmentation on the Chest X-rays dataset through generative modeling (deep convolutional generative adversarial network) which creates artificial instances retaining similar characteristics to the original data and evaluation of the model resulted in Fr\'echet Distance of Inception (FID) score of 1.289.