GAN-based Data Augmentation for Chest X-ray Classification

TL;DR

This paper explores the use of GANs to generate synthetic chest X-ray images to address data scarcity and class imbalance, improving classification performance especially in low-data scenarios.

Contribution

It demonstrates that GAN-based data augmentation outperforms traditional methods in enhancing chest X-ray classification, particularly for underrepresented classes.

Findings

GAN augmentation improves classification accuracy for minority classes

GAN-based augmentation is especially effective with limited data

Synthetic data helps prevent overfitting in medical image analysis

Abstract

A common problem in computer vision -- particularly in medical applications -- is a lack of sufficiently diverse, large sets of training data. These datasets often suffer from severe class imbalance. As a result, networks often overfit and are unable to generalize to novel examples. Generative Adversarial Networks (GANs) offer a novel method of synthetic data augmentation. In this work, we evaluate the use of GAN- based data augmentation to artificially expand the CheXpert dataset of chest radiographs. We compare performance to traditional augmentation and find that GAN-based augmentation leads to higher downstream performance for underrepresented classes. Furthermore, we see that this result is pronounced in low data regimens. This suggests that GAN-based augmentation a promising area of research to improve network performance when data collection is prohibitively expensive.