Automated White Matter Total Lesion Volume Segmentation in Diabetes

Abstract

Background and Purpose WM lesion segmentation is often performed with the use of subjective rating scales because manual methods are laborious and tedious; however, automated methods are now available. We compared the performance of total lesion volume grading computed by use of an automated WM lesion segmentation algorithm with that of subjective rating scales and expert manual segmentation in a cohort of subjects with type 2 diabetes. Materials and Methods Structural T1 and FLAIR MR imaging data from 50 subjects with diabetes (age, 67.7 ± 7.2 years) and 50 nondiabetic sibling pairs (age, 67.5 ± 9.4 years) were evaluated in an institutional review board–approved study. WM lesion segmentation maps and total lesion volume were generated for each subject by means of the Statistical Parametric Mapping (SPM8) Lesion Segmentation Toolbox. Subjective WM lesion grade was determined by means of a 0–9 rating scale by 2 readers. Ground-truth total lesion volume was determined by means of manual segmentation by experienced readers. Correlation analyses compared manual segmentation total lesion volume with automated and subjective evaluation methods. Results Correlation between average lesion segmentation and ground-truth total lesion volume was 0.84. Maximum correlation between the Lesion Segmentation Toolbox and ground-truth total lesion volume (ρ = 0.87) occurred at the segmentation threshold of k = 0.25, whereas maximum correlation between subjective lesion segmentation and the Lesion Segmentation Toolbox (ρ = 0.73) occurred at k = 0.15. The difference between the 2 correlation estimates with ground-truth was not statistically significant. The lower segmentation threshold (0.15 versus 0.25) suggests that subjective raters overestimate WM lesion burden. Conclusions We validate the Lesion Segmentation Toolbox for determining total lesion volume in diabetes-enriched populations and compare it with a common subjective WM lesion rating scale. The Lesion Segmentation Toolbox is a readily available substitute for subjective WM lesion scoring in studies of diabetes and other populations with changes of leukoaraiosis.

White matter hyperintensities, cognitive impairment and dementia: an update

“…The total volume and location of WMHs are important determinants of the clinical relevance of these lesions, [16][17][18] and visual and automated rating scales have been developed to assess the severity and progression of WMHs. [19][20][21][22][23] Furthermore, evidence is accumulating that novel imaging techniques, such as diffusion tensor imaging (DTI), can detect subtle impairments in white matter tract integrity before they can be seen on conventional MRI, suggesting that WMHs represent only the extreme end of a continuous spectrum of white matter injury. 24,25 MRI also enables the measurement of progression of WMHs over time.…”

Lesion filling effect in regional brain volume estimations: a study in multiple sclerosis patients with low lesion load

“…2D FLAIR images, which typically have lower resolution and different image contrast, are more commonly available. The LST has been validated using 2D T2-FLAIR images acquired on a 1.5-T MRI system in a cohort of patients with diabetes [10], but it has not been tested in similar images acquired in MS patients. The aims of study are to assess the production of lesion masks with the LST software using 2D T2-FLAIR images acquired on a 3.0-T MRI system in a cohort of MS patients, and to evaluate the results obtained when the masks are used in the LST lesion filling procedure in terms of GM and WM voxel classification and calculation of the WM and GM fractions (WMF, GMF).…”

Memory impairment in occipital periventricular hyperintensity patients is associated with reduced functional responses in the insula and Heschl's gyrus

“…The total volume and WMH location are important determinants for the clinical relevance of these lesions [20][21][22]. Visual and automated rating scales also have been developed to assess the severity and progression of WMHs [23][24][25][26][27]. Furthermore, two subtypes have been proposed based on their proximity to the ventricles: periventricular lesions and deep WMH lesions [28][29][30][31].…”