Validation of a Regression Technique for Segmentation of White Matter Hyperintensities in Alzheimer’s Disease

Abstract

Segmentation and volumetric quantification of white matter hyperintensities (WMHs) is essential in assessment and monitoring of the vascular burden in aging and Alzheimer's disease (AD), especially when considering their effect on cognition. Manually segmenting WMHs in large cohorts is technically unfeasible due to time and accuracy concerns. Automated tools that can detect WMHs robustly and with high accuracy are needed. Here, we present and validate a fully automatic technique for segmentation and volumetric quantification of WMHs in aging and AD. The proposed technique combines intensity and location features frommultiplemagnetic resonance imaging contrasts and manually labeled training data with a linear classifier to perform fast and robust segmentations. It provides both a continuous subject specific WMH map reflecting different levels of tissue damage and binary segmentations. Themethodwas used to detectWMHs in 80 elderly/AD brains (ADC data set) as well as 40 healthy subjects at risk of AD (PREVENT-AD data set). Robustness across different scanners was validated using ten subjects from ADNI2/GO study. Voxel-wise and volumetric agreements were evaluated using Dice similarity index (SI) and intra-class correlation (ICC), yielding ICC=0.96 , SI = 0.62±0.16 for ADC data set and ICC=0.78 , SI=0.51±0.15 for PREVENT-AD data set. The proposed method was robust in the independent sample yielding SI=0.64±0.17 with ICC=0.93 for ADNI2/GO subjects. The proposed method provides fast, accurate, and robust segmentations on previously unseen data from different models of scanners, making it ideal to study WMHs in large scale multi-site studies.

Validation of T1w‐based segmentations of white matter hyperintensity volumes in large‐scale datasets of aging

“…A previously validated fully automatic WMH segmentation technique was used to automatically segment the WMHs in all three datasets using a set of intensity and spatial features and a Random Forest classifier (Dadar et al, , ). The intensity features include voxel intensity for all available modalities, the probability of a specific intensity value being a WMH ( p WMH ) or non‐WMH ( p non‐WMH ) for each available modality, and the ratio of these two probabilities for each available modality.…”

Plasma biomarkers of astrocytic and neuronal dysfunction in early‐ and late‐onset Alzheimer's disease

“…43 Linear and nonlinear transformations between the group template space and International Consortium of Brain Mapping were applied. WMH quantification was estimated by WMH segmentation 44,45 using fluid attenuated inversion recovery and T1-weighted images.…”

A longitudinal characterization of perfusion in the aging brain and associations with cognition and neural structure

“…WMHs were quantified using a previously-described, automated algorithm (Staffaroni et al, 2018) based on a regression algorithm (Dadar et al, 2017) using Hidden Markov Random Field with Expectation Maximization software (Avants, Tustison, Wu, Cook, & Gee, 2011). Global WMH burden in mm 3 was log transformed to achieve a normal distribution.…”