Automatic segmentation and volumetry of multiple sclerosis brain lesions from MR images.

Saurabh Jain,Annemie Ribbens,Diana M Sima,Sabine Van Huffel,Hugo Vrenken,Marita Daams,Martijn D Steenwijk,Anke Maertens,Frederik Maes,Melissa Cambron,Frederik Barkhof,Johan De Mey,Dirk Smeets,Wim Van Hecke

doi:10.1016/j.nicl.2015.05.003

Abstract

The location and extent of white matter lesions on magnetic resonance imaging (MRI) are important criteria for diagnosis, follow-up and prognosis of multiple sclerosis (MS). Clinical trials have shown that quantitative values, such as lesion volumes, are meaningful in MS prognosis. Manual lesion delineation for the segmentation of lesions is, however, time-consuming and suffers from observer variability. In this paper, we propose MSmetrix, an accurate and reliable automatic method for lesion segmentation based on MRI, independent of scanner or acquisition protocol and without requiring any training data. In MSmetrix, 3D T1-weighted and FLAIR MR images are used in a probabilistic model to detect white matter (WM) lesions as an outlier to normal brain while segmenting the brain tissue into grey matter, WM and cerebrospinal fluid. The actual lesion segmentation is performed based on prior knowledge about the location (within WM) and the appearance (hyperintense on FLAIR) of lesions. The accuracy of MSmetrix is evaluated by comparing its output with expert reference segmentations of 20 MRI datasets of MS patients. Spatial overlap (Dice) between the MSmetrix and the expert lesion segmentation is 0.67 ± 0.11. The intraclass correlation coefficient (ICC) equals 0.8 indicating a good volumetric agreement between the MSmetrix and expert labelling. The reproducibility of MSmetrix' lesion volumes is evaluated based on 10 MS patients, scanned twice with a short interval on three different scanners. The agreement between the first and the second scan on each scanner is evaluated through the spatial overlap and absolute lesion volume difference between them. The spatial overlap was 0.69 ± 0.14 and absolute total lesion volume difference between the two scans was 0.54 ± 0.58 ml. Finally, the accuracy and reproducibility of MSmetrix compare favourably with other publicly available MS lesion segmentation algorithms, applied on the same data using default parameter settings.

Highlights

Multiple sclerosis (MS) is the most common inflammatory demyelinating disease of the central nervous system that is characterised by the presence of white matter (WM) lesions (Compston and Coles, 2008)
MSmetrix is introduced, a robust automatic method for WM lesion segmentation based on 3D T1-weighted and 3D FLAIR MR images
Spatial agreement is reported by the Dice similarity index (Dice, 1945), defined as the ratio between the number of voxels where both the automatic and the expert reference segmentation agree and the mean number of voxels labelled as lesion by the two methods

Summary

Introduction

Multiple sclerosis (MS) is the most common inflammatory demyelinating disease of the central nervous system that is characterised by the presence of white matter (WM) lesions (Compston and Coles, 2008). These WM lesions are visible on a magnetic resonance imaging (MRI) brain scan and appear hyper-intense on T2-weighted or Fluid. S. Jain et al / NeuroImage: Clinical 8 (2015) 367–375 lesion segmentation approach, as it can further decrease the observer dependency as well as the time needed from the expert. Results are compared both quantitatively and qualitatively with two well-known and publicly available automatic unsupervised lesion segmentation software implementations: LST (Schmidt et al, 2012) and Lesion-TOADS (Shiee et al, 2010)

Method description

Other methods

Dataset 1 20 MS patients participated in a study at VU University Medical

Dataset 2

Performance tests

Results