Validation of T 1w‐based segmentations of white matter hyperintensity volumes in large‐scale datasets of aging

Collins

et al. 2019

Preprint

Self Cite

Background and Purpose: Neuropsychiatric symptoms (NPS) are frequently encountered in patients with Alzheimer's disease (AD). Focal grey matter atrophy has been linked to NPS development. Cerebrovascular disease can cause focal lesions and is common among AD patients. As cerebrovascular disease can be detected on MRI as white matter hyperintensities (WMH), this study evaluated WMH burden in mild cognitive impairment (MCI), AD and normal controls and determined their relationship with NPS. Methods: NPS were assessed using the Neuropsychiatric Inventory and grouped into subsyndromes. WMH were measured using an automatic segmentation technique and mean deformation-based morphometry was used to measure atrophy of grey matter regions. Results: WMHs and grey matter atrophy both contributed significantly to NPS subsyndromes in MCI and AD subjects, however, WMH burden played a greater role. Conclusions: This study could provide a better understanding of the pathophysiology of NPS in AD.

Section: Mri Processingmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 98%

White matter hyperintensities and neuropsychiatric symptoms in Alzheimer’s disease and mild cognitive impairment

Misquitta

Collins

et al. 2019

Preprint

Self Cite

“…One of the major challenges when performing tissue classification on aging subjects or individuals with neurodegenerative diseases is the presence of white matter hyperintensities (WMHs). WMHs are areas of increased signal on T2-weighed and FLAIR MRI sequences, which appear as hypointense on T1w images (Dadar et al, 2018b). These hypointense WMH regions can present with a similar intensity profile to the gray matter in T1w images and can be segmented as GM by tissue classification methods that are solely or highly dependent on image intensities.…”

Section: Introductionmentioning

confidence: 99%

BISON: Brain tISue segmentatiON pipeline using T1-weighted magnetic resonance images and a random forests classifier

Collins

2019

Preprint

Self Cite

Introduction: Accurate differentiation of brain tissue types from T1-weighted magnetic resonance images (MRIs) is a critical requirement in many neuroscience and clinical applications. Accurate automated tissue segmentation is challenging due to the variabilities in the tissue intensity profiles caused by differences in scanner models and acquisition protocols, in addition to the varying age of the subjects and potential presence of pathology.In this paper, we present BISON (Brain tISue segmentatiON), a new pipeline for tissue segmentation.Methods: BISON performs tissue segmentation using a random forests classifier and a set of intensity and location priors obtained based on T1-weighted images. The proposed method has been developed and cross-validated based on multi-center and multi-scanner manual labels of 72 subjects aging from 5-96 years old, ensuring the generalizability of the results to new data from various age ranges. In addition, we assessed the test-retest reliability of BISON on 2 datasets; a. using 20 subjects that had scan/re-scan MRIs and manual segmentations available, and b. using a human phantom dataset including 90 scans from a single individual acquired across 10 years. Results:The results of the proposed method were compared against Atropos, a commonly used tissue classification method from ANTs. The proposed method yielded cross-validation Dice Kappa values of κGM = 0.88 ± 0.03, κWM = 0.85 ± 0.03, κCSF = 0.77 ± 0.11, outperforming ANTs Atropos (κGM = 0.79 ± 0.05, κWM = 0.84 ± 0.05, κCSF = 0.64 ± 0.22) as well as test-retest Dice Kappa values of κGM = 0.94 ± 0.006, κWM = 0.92 ± 0.006, κCSF = 0.77 ± 0.11 outperforming both manual (κGM = 0.92 ± 0.01, κWM = 0.91 ± 0.01, κCSF = 0.74 ± 0.03) andANTs Atropos (κGM = 0.87 ± 0.001, κWM = 0.92 ± 0.001, κCSF = 0.79 ± 0.05). The human phantom dataset validations showed high generalizability for both Atropos (κGM = 0.97 ± 0.01, κWM = 0.96 ± 0.01, κCSF = 0.93 ± 0.02) and BISON (κGM = 0.95 ± 0.01, κWM = 0.94 ± 0.01, κCSF = 0.85 ± 0.03), while Atropos tended to consistently under-segment the cortical CSF. Finally, our assessment of BISON, Atropos, FAST from FSL, and SPM12 segmentations in presence of white matter hyperintensities (WMHs) showed that BISON outperforms the other three methods, correctly detecting WMHs as WM. Conclusion:Our results show that BISON can provide accurate and robust segmentations in data from different age ranges and various scanner models, making it ideal for performing tissue classification in large multi-center and multi-scanner databases.

“…The image processing and WMH segmentation pipelines used in this study have been designed to process data from multi-center studies, are able to control biases due to multi-site MRI scanning (i.e. differences in acquisition parameters), and have been previously applied successfully to a number of multi-site projects [51][52][53] . The WMH segmentation pipeline has been trained and extensively validated on data from multiple scanners and different acquisition parameters to ensure inter-site and inter-scanner generalizability 26 .…”

Section: Regardless Of Etiology Prevention and Treatment Of Vascularmentioning

confidence: 99%

White Matter Hyperintensities and Cognitive Decline in de Novo Parkinson’s Disease Patients

Zeighami

Yau

et al. 2017

Preprint

Self Cite

ObjectiveWhite Matter Hyperintensities (WMHs) are associated with cognitive decline in normative aging and Alzheimer’s disease. However, the pathogenesis of cognitive decline in Parkinson’s disease (PD) is not directly related to vascular causes, and therefore the role of WMHs in PD remains unclear. If WMH has a higher impact on cognitive decline in PD, vascular pathology should be assessed and treated with a higher priority in this population. Here we investigate whether WMH leads to increased cognitive decline in PD, and if these effects relate to cortical thinningMethodsTo investigate the role of WMHs in PD, it is essential to study recently-diagnosed/non-treated patients. De novo PD patients and age-matched controls (NPD=365,NControl=174) with FLAIR/T2-weighted scans at baseline were selected from Parkinson’s Progression Markers Initiative (PPMI). WMHs and cortical thickness were measured to analyse the relationship between baseline WMHs and future cognitive decline (follow-up:4.09±1.14 years) and cortical thinning (follow-up:1.05±0.10 years).ResultsHigh WMH load (WMHL) at baseline in PD was associated with increased cognitive decline, significantly more than i) PDs with low WMHL and ii) controls with high WMHL. Furthermore, PD patients with higher baseline WMHL showed more cortical thinning in right frontal lobe than subjects with low WMHL. Cortical thinning of this region also predicted decline in performance on a cognitive test.InterpretationPresence of WMHs in de novo PD patients predicts greater future cognitive decline and cortical thinning than in normal aging. Recognizing WMHs as a potential predictor of cognitive deficit in PD provides an opportunity for timely interventions.