Standard

Enlarged perivascular spaces in brain MRI : Automated quantification in four regions. / Dubost, Florian; Yilmaz, Pinar; Adams, Hieab; Bortsova, Gerda; Ikram, M. Arfan; Niessen, Wiro; Vernooij, Meike; de Bruijne, Marleen.

In: NeuroImage, Vol. 185, 2019, p. 534-544.

Research output: Contribution to journalArticleScientificpeer-review

Harvard

Dubost, F, Yilmaz, P, Adams, H, Bortsova, G, Ikram, MA, Niessen, W, Vernooij, M & de Bruijne, M 2019, 'Enlarged perivascular spaces in brain MRI: Automated quantification in four regions' NeuroImage, vol. 185, pp. 534-544. https://doi.org/10.1016/j.neuroimage.2018.10.026

APA

Dubost, F., Yilmaz, P., Adams, H., Bortsova, G., Ikram, M. A., Niessen, W., ... de Bruijne, M. (2019). Enlarged perivascular spaces in brain MRI: Automated quantification in four regions. NeuroImage, 185, 534-544. https://doi.org/10.1016/j.neuroimage.2018.10.026

Vancouver

Author

Dubost, Florian ; Yilmaz, Pinar ; Adams, Hieab ; Bortsova, Gerda ; Ikram, M. Arfan ; Niessen, Wiro ; Vernooij, Meike ; de Bruijne, Marleen. / Enlarged perivascular spaces in brain MRI : Automated quantification in four regions. In: NeuroImage. 2019 ; Vol. 185. pp. 534-544.

BibTeX

@article{904efe4f335d412b902a0051d880c311,
title = "Enlarged perivascular spaces in brain MRI: Automated quantification in four regions",
abstract = "Enlarged perivascular spaces (PVS) are structural brain changes visible in MRI, are common in aging, and are considered a reflection of cerebral small vessel disease. As such, assessing the burden of PVS has promise as a brain imaging marker. Visual and manual scoring of PVS is a tedious and observer-dependent task. Automated methods would advance research into the etiology of PVS, could aid to assess what a “normal” burden is in aging, and could evaluate the potential of PVS as a biomarker of cerebral small vessel disease. In this work, we propose and evaluate an automated method to quantify PVS in the midbrain, hippocampi, basal ganglia and centrum semiovale. We also compare associations between (earlier established) determinants of PVS and visual PVS scores versus the automated PVS scores, to verify whether automated PVS scores could replace visual scoring of PVS in epidemiological and clinical studies. Our approach is a deep learning algorithm based on convolutional neural network regression, and is contingent on successful brain structure segmentation. In our work we used FreeSurfer segmentations. We trained and validated our method on T2-contrast MR images acquired from 2115 subjects participating in a population-based study. These scans were visually scored by an expert rater, who counted the number of PVS in each brain region. Agreement between visual and automated scores was found to be excellent for all four regions, with intraclass correlation coefficients (ICCs) between 0.75 and 0.88. These values were higher than the inter-observer agreement of visual scoring (ICCs between 0.62 and 0.80). Scan-rescan reproducibility was high (ICCs between 0.82 and 0.93). The association between 20 determinants of PVS, including aging, and the automated scores were similar to those between the same 20 determinants of PVS and visual scores. We conclude that this method may replace visual scoring and facilitate large epidemiological and clinical studies of PVS.",
keywords = "Deep learning, Dementia, Enlarged perivascular spaces, Machine learning, Perivascular spaces, Virchow-Robin spaces",
author = "Florian Dubost and Pinar Yilmaz and Hieab Adams and Gerda Bortsova and Ikram, {M. Arfan} and Wiro Niessen and Meike Vernooij and {de Bruijne}, Marleen",
year = "2019",
doi = "10.1016/j.neuroimage.2018.10.026",
language = "English",
volume = "185",
pages = "534--544",
journal = "NeuroImage",
issn = "1053-8119",
publisher = "Academic Press Inc.",

}

RIS

TY - JOUR

T1 - Enlarged perivascular spaces in brain MRI

T2 - NeuroImage

AU - Dubost, Florian

AU - Yilmaz, Pinar

AU - Adams, Hieab

AU - Bortsova, Gerda

AU - Ikram, M. Arfan

AU - Niessen, Wiro

AU - Vernooij, Meike

AU - de Bruijne, Marleen

PY - 2019

Y1 - 2019

N2 - Enlarged perivascular spaces (PVS) are structural brain changes visible in MRI, are common in aging, and are considered a reflection of cerebral small vessel disease. As such, assessing the burden of PVS has promise as a brain imaging marker. Visual and manual scoring of PVS is a tedious and observer-dependent task. Automated methods would advance research into the etiology of PVS, could aid to assess what a “normal” burden is in aging, and could evaluate the potential of PVS as a biomarker of cerebral small vessel disease. In this work, we propose and evaluate an automated method to quantify PVS in the midbrain, hippocampi, basal ganglia and centrum semiovale. We also compare associations between (earlier established) determinants of PVS and visual PVS scores versus the automated PVS scores, to verify whether automated PVS scores could replace visual scoring of PVS in epidemiological and clinical studies. Our approach is a deep learning algorithm based on convolutional neural network regression, and is contingent on successful brain structure segmentation. In our work we used FreeSurfer segmentations. We trained and validated our method on T2-contrast MR images acquired from 2115 subjects participating in a population-based study. These scans were visually scored by an expert rater, who counted the number of PVS in each brain region. Agreement between visual and automated scores was found to be excellent for all four regions, with intraclass correlation coefficients (ICCs) between 0.75 and 0.88. These values were higher than the inter-observer agreement of visual scoring (ICCs between 0.62 and 0.80). Scan-rescan reproducibility was high (ICCs between 0.82 and 0.93). The association between 20 determinants of PVS, including aging, and the automated scores were similar to those between the same 20 determinants of PVS and visual scores. We conclude that this method may replace visual scoring and facilitate large epidemiological and clinical studies of PVS.

AB - Enlarged perivascular spaces (PVS) are structural brain changes visible in MRI, are common in aging, and are considered a reflection of cerebral small vessel disease. As such, assessing the burden of PVS has promise as a brain imaging marker. Visual and manual scoring of PVS is a tedious and observer-dependent task. Automated methods would advance research into the etiology of PVS, could aid to assess what a “normal” burden is in aging, and could evaluate the potential of PVS as a biomarker of cerebral small vessel disease. In this work, we propose and evaluate an automated method to quantify PVS in the midbrain, hippocampi, basal ganglia and centrum semiovale. We also compare associations between (earlier established) determinants of PVS and visual PVS scores versus the automated PVS scores, to verify whether automated PVS scores could replace visual scoring of PVS in epidemiological and clinical studies. Our approach is a deep learning algorithm based on convolutional neural network regression, and is contingent on successful brain structure segmentation. In our work we used FreeSurfer segmentations. We trained and validated our method on T2-contrast MR images acquired from 2115 subjects participating in a population-based study. These scans were visually scored by an expert rater, who counted the number of PVS in each brain region. Agreement between visual and automated scores was found to be excellent for all four regions, with intraclass correlation coefficients (ICCs) between 0.75 and 0.88. These values were higher than the inter-observer agreement of visual scoring (ICCs between 0.62 and 0.80). Scan-rescan reproducibility was high (ICCs between 0.82 and 0.93). The association between 20 determinants of PVS, including aging, and the automated scores were similar to those between the same 20 determinants of PVS and visual scores. We conclude that this method may replace visual scoring and facilitate large epidemiological and clinical studies of PVS.

KW - Deep learning

KW - Dementia

KW - Enlarged perivascular spaces

KW - Machine learning

KW - Perivascular spaces

KW - Virchow-Robin spaces

UR - http://www.scopus.com/inward/record.url?scp=85055525908&partnerID=8YFLogxK

U2 - 10.1016/j.neuroimage.2018.10.026

DO - 10.1016/j.neuroimage.2018.10.026

M3 - Article

VL - 185

SP - 534

EP - 544

JO - NeuroImage

JF - NeuroImage

SN - 1053-8119

ER -

ID: 47373699