Learning Data Augmentation for Brain Tumor Segmentation with Coarse-to-Fine Generative Adversarial Networks

TL;DR

This paper introduces a novel GAN-based data augmentation method that learns to generate synthetic MRI data, improving brain tumor segmentation performance and achieving state-of-the-art results on the BRATS15 dataset.

Contribution

A new coarse-to-fine GAN architecture for automatic data augmentation tailored to biomedical image segmentation tasks.

Findings

Achieved 3.5% improvement in Dice coefficient over traditional augmentation.

Successfully boosted segmentation network to state-of-the-art performance on BRATS15.

Demonstrated effectiveness of learned augmentation in medical imaging.

Abstract

There is a common belief that the successful training of deep neural networks requires many annotated training samples, which are often expensive and difficult to obtain especially in the biomedical imaging field. While it is often easy for researchers to use data augmentation to expand the size of training sets, constructing and generating generic augmented data that is able to teach the network the desired invariance and robustness properties using traditional data augmentation techniques is challenging in practice. In this paper, we propose a novel automatic data augmentation method that uses generative adversarial networks to learn augmentations that enable machine learning based method to learn the available annotated samples more efficiently. The architecture consists of a coarse-to-fine generator to capture the manifold of the training sets and generate generic augmented data. In our experiments, we show the efficacy of our approach on a Magnetic Resonance Imaging (MRI) image, achieving improvements of 3.5% Dice coefficient on the BRATS15 Challenge dataset as compared to traditional augmentation approaches. Also, our proposed method successfully boosts a common segmentation network to reach the state-of-the-art performance on the BRATS15 Challenge.