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

Mahsa Dadar, Tharick A. Pascoal, Sarinporn Manitsirikul, Karen Misquitta, Vladimir S. Fonov, M. Carmela Tartaglia, John Breitner, Pedro Rosa-Neto, Owen T. Carmichael, Charles DeCarli, D. Louis Collins

Research output: Contribution to journalArticle

15 Citations (Scopus)

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\pm 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.

Original languageEnglish (US)
Article number7898360
Pages (from-to)1758-1768
Number of pages11
JournalIEEE Transactions on Medical Imaging
Volume36
Issue number8
DOIs
StatePublished - Aug 1 2017

Fingerprint

Alzheimer Disease
Aging of materials
Cognition
Blood Vessels
White Matter
Brain
Healthy Volunteers
Classifiers
Tissue
Imaging techniques
Datasets
Monitoring

Keywords

  • aging
  • Alzheimer's disease
  • segmentation
  • White matter hyperintensities

ASJC Scopus subject areas

  • Software
  • Radiological and Ultrasound Technology
  • Computer Science Applications
  • Electrical and Electronic Engineering

Cite this

Dadar, M., Pascoal, T. A., Manitsirikul, S., Misquitta, K., Fonov, V. S., Tartaglia, M. C., ... Collins, D. L. (2017). Validation of a Regression Technique for Segmentation of White Matter Hyperintensities in Alzheimer's Disease. IEEE Transactions on Medical Imaging, 36(8), 1758-1768. [7898360]. https://doi.org/10.1109/TMI.2017.2693978

Validation of a Regression Technique for Segmentation of White Matter Hyperintensities in Alzheimer's Disease. / Dadar, Mahsa; Pascoal, Tharick A.; Manitsirikul, Sarinporn; Misquitta, Karen; Fonov, Vladimir S.; Tartaglia, M. Carmela; Breitner, John; Rosa-Neto, Pedro; Carmichael, Owen T.; DeCarli, Charles; Collins, D. Louis.

In: IEEE Transactions on Medical Imaging, Vol. 36, No. 8, 7898360, 01.08.2017, p. 1758-1768.

Research output: Contribution to journalArticle

Dadar, M, Pascoal, TA, Manitsirikul, S, Misquitta, K, Fonov, VS, Tartaglia, MC, Breitner, J, Rosa-Neto, P, Carmichael, OT, DeCarli, C & Collins, DL 2017, 'Validation of a Regression Technique for Segmentation of White Matter Hyperintensities in Alzheimer's Disease', IEEE Transactions on Medical Imaging, vol. 36, no. 8, 7898360, pp. 1758-1768. https://doi.org/10.1109/TMI.2017.2693978
Dadar, Mahsa ; Pascoal, Tharick A. ; Manitsirikul, Sarinporn ; Misquitta, Karen ; Fonov, Vladimir S. ; Tartaglia, M. Carmela ; Breitner, John ; Rosa-Neto, Pedro ; Carmichael, Owen T. ; DeCarli, Charles ; Collins, D. Louis. / Validation of a Regression Technique for Segmentation of White Matter Hyperintensities in Alzheimer's Disease. In: IEEE Transactions on Medical Imaging. 2017 ; Vol. 36, No. 8. pp. 1758-1768.
@article{62a28710b53e463c8c0c954ddf27928d,
title = "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\pm 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.",
keywords = "aging, Alzheimer's disease, segmentation, White matter hyperintensities",
author = "Mahsa Dadar and Pascoal, {Tharick A.} and Sarinporn Manitsirikul and Karen Misquitta and Fonov, {Vladimir S.} and Tartaglia, {M. Carmela} and John Breitner and Pedro Rosa-Neto and Carmichael, {Owen T.} and Charles DeCarli and Collins, {D. Louis}",
year = "2017",
month = "8",
day = "1",
doi = "10.1109/TMI.2017.2693978",
language = "English (US)",
volume = "36",
pages = "1758--1768",
journal = "IEEE Transactions on Medical Imaging",
issn = "0278-0062",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "8",

}

TY - JOUR

T1 - Validation of a Regression Technique for Segmentation of White Matter Hyperintensities in Alzheimer's Disease

AU - Dadar, Mahsa

AU - Pascoal, Tharick A.

AU - Manitsirikul, Sarinporn

AU - Misquitta, Karen

AU - Fonov, Vladimir S.

AU - Tartaglia, M. Carmela

AU - Breitner, John

AU - Rosa-Neto, Pedro

AU - Carmichael, Owen T.

AU - DeCarli, Charles

AU - Collins, D. Louis

PY - 2017/8/1

Y1 - 2017/8/1

N2 - 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\pm 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.

AB - 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\pm 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.

KW - aging

KW - Alzheimer's disease

KW - segmentation

KW - White matter hyperintensities

UR - http://www.scopus.com/inward/record.url?scp=85020408519&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85020408519&partnerID=8YFLogxK

U2 - 10.1109/TMI.2017.2693978

DO - 10.1109/TMI.2017.2693978

M3 - Article

C2 - 28422655

AN - SCOPUS:85020408519

VL - 36

SP - 1758

EP - 1768

JO - IEEE Transactions on Medical Imaging

JF - IEEE Transactions on Medical Imaging

SN - 0278-0062

IS - 8

M1 - 7898360

ER -