To the top

Page Manager: Webmaster
Last update: 9/11/2012 3:13 PM

Tell a friend about this page
Print version

Big Data Approaches to Ph… - University of Gothenburg, Sweden Till startsida
Sitemap
To content Read more about how we use cookies on gu.se

Big Data Approaches to Phenotyping Acute Ischemic Stroke Using Automated Lesion Segmentation of Multi-Center Magnetic Resonance Imaging Data

Journal article
Authors O. Wu
S. Winzeck
A. K. Giese
B. L. Hancock
M. R. Etherton
Mjrj Bouts
K. Donahue
M. D. Schirmer
R. E. Irie
S. J. T. Mocking
E. C. McIntosh
R. Bezerra
K. Kamnitsas
P. Frid
J. Wasselius
J. W. Cole
H. C. Xu
Lukas Holmegaard
J. Jimenez-Conde
R. Lemmens
Erik Lorentzen
P. F. McArdle
J. F. Meschia
J. Roquer
T. Rundek
R. L. Sacco
R. Schmidt
P. Sharma
A. Slowik
Tara M Stanne
V. Thijs
A. Vagal
D. Woo
S. Bevan
S. J. Kittner
B. D. Mitchell
J. Rosand
B. B. Worrall
Christina Jern
A. G. Lindgren
J. Maguire
N. S. Rost
Published in Stroke
Volume 50
Issue 7
Pages 1734-1741
ISSN 0039-2499
Publication year 2019
Published at Institute of Neuroscience and Physiology
Institute of Biomedicine
Pages 1734-1741
Language en
Links dx.doi.org/10.1161/strokeaha.119.02...
Keywords diffusion magnetic resonance imaging, machine learning, phenotype, risk factors, stroke, cerebral-ischemia, brain, rationale, genetics, network, mri, Neurosciences & Neurology, Cardiovascular System & Cardiology
Subject categories Neurosciences

Abstract

Background and Purpose- We evaluated deep learning algorithms' segmentation of acute ischemic lesions on heterogeneous multi-center clinical diffusion-weighted magnetic resonance imaging (MRI) data sets and explored the potential role of this tool for phenotyping acute ischemic stroke. Methods- Ischemic stroke data sets from the MRI-GENIE (MRI-Genetics Interface Exploration) repository consisting of 12 international genetic research centers were retrospectively analyzed using an automated deep learning segmentation algorithm consisting of an ensemble of 3-dimensional convolutional neural networks. Three ensembles were trained using data from the following: (1) 267 patients from an independent single-center cohort, (2) 267 patients from MRI-GENIE, and (3) mixture of (1) and (2). The algorithms' performances were compared against manual outlines from a separate 383 patient subset from MRI-GENIE. Univariable and multivariable logistic regression with respect to demographics, stroke subtypes, and vascular risk factors were performed to identify phenotypes associated with large acute diffusion-weighted MRI volumes and greater stroke severity in 2770 MRI-GENIE patients. Stroke topography was investigated. Results- The ensemble consisting of a mixture of MRI-GENIE and single-center convolutional neural networks performed best. Subset analysis comparing automated and manual lesion volumes in 383 patients found excellent correlation (rho=0.92; P<0.0001). Median (interquartile range) diffusion-weighted MRI lesion volumes from 2770 patients were 3.7 cm(3) (0.9-16.6 cm(3)). Patients with small artery occlusion stroke subtype had smaller lesion volumes (P<0.0001) and different topography compared with other stroke subtypes. Conclusions- Automated accurate clinical diffusion-weighted MRI lesion segmentation using deep learning algorithms trained with multi-center and diverse data is feasible. Both lesion volume and topography can provide insight into stroke subtypes with sufficient sample size from big heterogeneous multi-center clinical imaging phenotype data sets.

Page Manager: Webmaster|Last update: 9/11/2012
Share:

The University of Gothenburg uses cookies to provide you with the best possible user experience. By continuing on this website, you approve of our use of cookies.  What are cookies?