GAN Augmentation: Augmenting Training Data using Generative Adversarial Networks

TL;DR

This paper explores using GANs to generate synthetic medical images, augmenting limited datasets to improve brain segmentation performance, especially when training data is scarce.

Contribution

It demonstrates the effectiveness of GAN-generated synthetic data in enhancing brain segmentation accuracy with small datasets.

Findings

DSC improved by 1-5 percentage points with GAN augmentation

Strongest improvements observed with fewer than ten training images

Synthetic data helps mitigate overfitting in small datasets

Abstract

One of the biggest issues facing the use of machine learning in medical imaging is the lack of availability of large, labelled datasets. The annotation of medical images is not only expensive and time consuming but also highly dependent on the availability of expert observers. The limited amount of training data can inhibit the performance of supervised machine learning algorithms which often need very large quantities of data on which to train to avoid overfitting. So far, much effort has been directed at extracting as much information as possible from what data is available. Generative Adversarial Networks (GANs) offer a novel way to unlock additional information from a dataset by generating synthetic samples with the appearance of real images. This paper demonstrates the feasibility of introducing GAN derived synthetic data to the training datasets in two brain segmentation tasks, leading to improvements in Dice Similarity Coefficient (DSC) of between 1 and 5 percentage points under different conditions, with the strongest effects seen fewer than ten training image stacks are available.