Adversarial training and dilated convolutions for brain MRI segmentation

TL;DR

This paper introduces an adversarial training method combined with dilated convolutions to enhance CNN-based brain MRI segmentation, resulting in improved accuracy demonstrated across multiple datasets and architectures.

Contribution

The study presents a novel adversarial training approach that incorporates an additional loss function to produce more accurate brain MRI segmentations.

Findings

Improved segmentation performance with adversarial training.

Enhanced Dice coefficients across different datasets.

Visual improvements in segmentation quality.

Abstract

Convolutional neural networks (CNNs) have been applied to various automatic image segmentation tasks in medical image analysis, including brain MRI segmentation. Generative adversarial networks have recently gained popularity because of their power in generating images that are difficult to distinguish from real images. In this study we use an adversarial training approach to improve CNN-based brain MRI segmentation. To this end, we include an additional loss function that motivates the network to generate segmentations that are difficult to distinguish from manual segmentations. During training, this loss function is optimised together with the conventional average per-voxel cross entropy loss. The results show improved segmentation performance using this adversarial training procedure for segmentation of two different sets of images and using two different network architectures, both visually and in terms of Dice coefficients.