GAN Augmentation: Augmenting Training Data using Generative Adversarial Networks
This addresses data scarcity in medical imaging for researchers and practitioners, but it is incremental as it applies an existing GAN method to a new domain.
The paper tackled the problem of limited labeled data in medical imaging by using Generative Adversarial Networks (GANs) to generate synthetic training samples, resulting in improvements of 1 to 5 percentage points in Dice Similarity Coefficient for brain segmentation tasks, especially with fewer than ten training images.
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.