TY - JOUR
T1 - White matter hyperintensity quantification in large-scale clinical acute ischemic stroke cohorts – The MRI-GENIE study
AU - on behalf of the MRI-GENIE Investigators
AU - Schirmer, Markus D.
AU - Dalca, Adrian V.
AU - Sridharan, Ramesh
AU - Giese, Anne Katrin
AU - Donahue, Kathleen L.
AU - Nardin, Marco J.
AU - Mocking, Steven J.T.
AU - McIntosh, Elissa C.
AU - Frid, Petrea
AU - Wasselius, Johan
AU - Cole, John W.
AU - Holmegaard, Lukas
AU - Jern, Christina
AU - Jimenez-Conde, Jordi
AU - Lemmens, Robin
AU - Lindgren, Arne G.
AU - Meschia, James F.
AU - Roquer, Jaume
AU - Rundek, Tatjana
AU - Sacco, Ralph L.
AU - Schmidt, Reinhold
AU - Sharma, Pankaj
AU - Slowik, Agnieszka
AU - Thijs, Vincent
AU - Woo, Daniel
AU - Vagal, Achala
AU - Xu, Huichun
AU - Kittner, Steven J.
AU - McArdle, Patrick F.
AU - Mitchell, Braxton D.
AU - Rosand, Jonathan
AU - Worrall, Bradford B.
AU - Wu, Ona
AU - Golland, Polina
AU - Rost, Natalia S.
N1 - Publisher Copyright:
© 2019 The Authors
PY - 2019
Y1 - 2019
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85067075360&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85067075360&partnerID=8YFLogxK
U2 - 10.1016/j.nicl.2019.101884
DO - 10.1016/j.nicl.2019.101884
M3 - Article
C2 - 31200151
AN - SCOPUS:85067075360
SN - 2213-1582
VL - 23
JO - NeuroImage: Clinical
JF - NeuroImage: Clinical
M1 - 101884
ER -