wmh_seg: Transformer based U-Net for Robust and Automatic White Matter Hyperintensity Segmentation across 1.5T, 3T and 7T

TL;DR

This paper introduces wmh_seg, a transformer-based U-Net model that achieves robust, accurate white matter hyperintensity segmentation across various MRI field strengths and artifacts, including the first effective segmentation on 7T images.

Contribution

We developed a novel transformer-based U-Net model trained on diverse datasets, enabling consistent WMH segmentation across different MRI field strengths and artifact conditions.

Findings

Stable performance across 1.5T, 3T, and 7T MRI scans.

Robust segmentation despite MRI artifacts and inhomogeneities.

First successful WMH segmentation on 7T FLAIR images.

Abstract

White matter hyperintensity (WMH) remains the top imaging biomarker for neurodegenerative diseases. Robust and accurate segmentation of WMH holds paramount significance for neuroimaging studies. The growing shift from 3T to 7T MRI necessitates robust tools for harmonized segmentation across field strengths and artifacts. Recent deep learning models exhibit promise in WMH segmentation but still face challenges, including diverse training data representation and limited analysis of MRI artifacts' impact. To address these, we introduce wmh_seg, a novel deep learning model leveraging a transformer-based encoder from SegFormer. wmh_seg is trained on an unmatched dataset, including 1.5T, 3T, and 7T FLAIR images from various sources, alongside with artificially added MR artifacts. Our approach bridges gaps in training diversity and artifact analysis. Our model demonstrated stable performance across magnetic field strengths, scanner manufacturers, and common MR imaging artifacts. Despite the unique inhomogeneity artifacts on ultra-high field MR images, our model still offers robust and stable segmentation on 7T FLAIR images. Our model, to date, is the first that offers quality white matter lesion segmentation on 7T FLAIR images.