White matter hyperintensity segmentation from T1 and FLAIR images using fully convolutional neural networks enhanced with residual connections

TL;DR

This paper introduces a residual-connection enhanced fully convolutional neural network that effectively segments white matter hyperintensities from T1 and FLAIR MRI images, demonstrating superior generalization and accuracy.

Contribution

The paper presents a novel FCN architecture with residual connections specifically designed for WMH segmentation using combined T1 and FLAIR images, improving generalization and efficiency.

Findings

Achieved top performance on WMH segmentation metrics.

Outperformed competitors in hausdorff distance and volume difference.

Demonstrated strong generalization on unseen MRI scanners.

Abstract

Segmentation and quantification of white matter hyperintensities (WMHs) are of great importance in studying and understanding various neurological and geriatric disorders. Although automatic methods have been proposed for WMH segmentation on magnetic resonance imaging (MRI), manual corrections are often necessary to achieve clinically practical results. Major challenges for WMH segmentation stem from their inhomogeneous MRI intensities, random location and size distributions, and MRI noise. The presence of other brain anatomies or diseases with enhanced intensities adds further difficulties. To cope with these challenges, we present a specifically designed fully convolutional neural network (FCN) with residual connections to segment WMHs by using combined T1 and fluid-attenuated inversion recovery (FLAIR) images. Our customized FCN is designed to be straightforward and generalizable, providing efficient end-to-end training due to its enhanced information propagation. We tested our method on the open WMH Segmentation Challenge MICCAI2017 dataset, and, despite our method's relative simplicity, results show that it performs amongst the leading techniques across five metrics. More importantly, our method achieves the best score for hausdorff distance and average volume difference in testing datasets from two MRI scanners that were not included in training, demonstrating better generalization ability of our proposed method over its competitors.