Advanced

White matter hyperintensity quantification in large-scale clinical acute ischemic stroke cohorts – The MRI-GENIE study

Schirmer, Markus D.; Dalca, Adrian V.; Sridharan, Ramesh; Giese, Anne Katrin; Donahue, Kathleen L.; Nardin, Marco J.; Mocking, Steven J.T.; McIntosh, Elissa C.; Frid, Petrea LU and Wasselius, Johan LU , et al. (2019) In NeuroImage: Clinical 23.
Abstract

White matter hyperintensity (WMH) burden is a critically important cerebrovascular phenotype linked to prediction of diagnosis and prognosis of diseases, such as acute ischemic stroke (AIS). However, current approaches to its quantification on clinical MRI often rely on time intensive manual delineation of the disease on T2 fluid attenuated inverse recovery (FLAIR), which hinders high-throughput analyses such as genetic discovery. In this work, we present a fully automated pipeline for quantification of WMH in clinical large-scale studies of AIS. The pipeline incorporates automated brain extraction, intensity normalization and WMH segmentation using spatial priors. We first propose a brain extraction algorithm based on a fully... (More)

White matter hyperintensity (WMH) burden is a critically important cerebrovascular phenotype linked to prediction of diagnosis and prognosis of diseases, such as acute ischemic stroke (AIS). However, current approaches to its quantification on clinical MRI often rely on time intensive manual delineation of the disease on T2 fluid attenuated inverse recovery (FLAIR), which hinders high-throughput analyses such as genetic discovery. In this work, we present a fully automated pipeline for quantification of WMH in clinical large-scale studies of AIS. The pipeline incorporates automated brain extraction, intensity normalization and WMH segmentation using spatial priors. We first propose a brain extraction algorithm based on a fully convolutional deep learning architecture, specifically designed for clinical FLAIR images. We demonstrate that our method for brain extraction outperforms two commonly used and publicly available methods on clinical quality images in a set of 144 subject scans across 12 acquisition centers, based on dice coefficient (median 0.95; inter-quartile range 0.94–0.95; p < 0.01) and Pearson correlation of total brain volume (r = 0.90). Subsequently, we apply it to the large-scale clinical multi-site MRI-GENIE study (N = 2783) and identify a decrease in total brain volume of −2.4 cc/year. Additionally, we show that the resulting total brain volumes can successfully be used for quality control of image preprocessing. Finally, we obtain WMH volumes by building on an existing automatic WMH segmentation algorithm that delineates and distinguishes between different cerebrovascular pathologies. The learning method mimics expert knowledge of the spatial distribution of the WMH burden using a convolutional auto-encoder. This enables successful computation of WMH volumes of 2533 clinical AIS patients. We utilize these results to demonstrate the increase of WMH burden with age (0.950 cc/year) and show that single site estimates can be biased by the number of subjects recruited.

(Less)
Please use this url to cite or link to this publication:
author
, et al. (More)
(Less)
organization
publishing date
type
Contribution to journal
publication status
published
subject
in
NeuroImage: Clinical
volume
23
publisher
Elsevier
external identifiers
  • scopus:85067075360
ISSN
2213-1582
DOI
10.1016/j.nicl.2019.101884
language
English
LU publication?
yes
id
fd7bfa85-293c-4ca2-a928-5a0d6628e5ec
date added to LUP
2019-06-28 13:55:24
date last changed
2019-07-16 04:13:16
@article{fd7bfa85-293c-4ca2-a928-5a0d6628e5ec,
  abstract     = {<p>White matter hyperintensity (WMH) burden is a critically important cerebrovascular phenotype linked to prediction of diagnosis and prognosis of diseases, such as acute ischemic stroke (AIS). However, current approaches to its quantification on clinical MRI often rely on time intensive manual delineation of the disease on T2 fluid attenuated inverse recovery (FLAIR), which hinders high-throughput analyses such as genetic discovery. In this work, we present a fully automated pipeline for quantification of WMH in clinical large-scale studies of AIS. The pipeline incorporates automated brain extraction, intensity normalization and WMH segmentation using spatial priors. We first propose a brain extraction algorithm based on a fully convolutional deep learning architecture, specifically designed for clinical FLAIR images. We demonstrate that our method for brain extraction outperforms two commonly used and publicly available methods on clinical quality images in a set of 144 subject scans across 12 acquisition centers, based on dice coefficient (median 0.95; inter-quartile range 0.94–0.95; p &lt; 0.01) and Pearson correlation of total brain volume (r = 0.90). Subsequently, we apply it to the large-scale clinical multi-site MRI-GENIE study (N = 2783) and identify a decrease in total brain volume of −2.4 cc/year. Additionally, we show that the resulting total brain volumes can successfully be used for quality control of image preprocessing. Finally, we obtain WMH volumes by building on an existing automatic WMH segmentation algorithm that delineates and distinguishes between different cerebrovascular pathologies. The learning method mimics expert knowledge of the spatial distribution of the WMH burden using a convolutional auto-encoder. This enables successful computation of WMH volumes of 2533 clinical AIS patients. We utilize these results to demonstrate the increase of WMH burden with age (0.950 cc/year) and show that single site estimates can be biased by the number of subjects recruited.</p>},
  articleno    = {101884},
  author       = {Schirmer, Markus D. and Dalca, Adrian V. and Sridharan, Ramesh and Giese, Anne Katrin and Donahue, Kathleen L. and Nardin, Marco J. and Mocking, Steven J.T. and McIntosh, Elissa C. and Frid, Petrea and Wasselius, Johan and Cole, John W. and Holmegaard, Lukas and Jern, Christina and Jimenez-Conde, Jordi and Lemmens, Robin and Lindgren, Arne G. and Meschia, James F. and Roquer, Jaume and Rundek, Tatjana and Sacco, Ralph L. and Schmidt, Reinhold and Sharma, Pankaj and Slowik, Agnieszka and Thijs, Vincent and Woo, Daniel and Vagal, Achala and Xu, Huichun and Kittner, Steven J. and McArdle, Patrick F. and Mitchell, Braxton D. and Rosand, Jonathan and Worrall, Bradford B. and Wu, Ona and Golland, Polina and Rost, Natalia S. and , },
  issn         = {2213-1582},
  language     = {eng},
  publisher    = {Elsevier},
  series       = {NeuroImage: Clinical},
  title        = {White matter hyperintensity quantification in large-scale clinical acute ischemic stroke cohorts – The MRI-GENIE study},
  url          = {http://dx.doi.org/10.1016/j.nicl.2019.101884},
  volume       = {23},
  year         = {2019},
}