Automatic quantification of ischemic injury on diffusion-weighted MRI of neonatal hypoxic ischemic encephalopathy

dc.contributor.authorMurphy, Keelin
dc.contributor.authorvan der Aa, Niek E.
dc.contributor.authorNegro, Simona
dc.contributor.authorGroenendaal, Floris
dc.contributor.authorde Vries, Linda S.
dc.contributor.authorViergever, Max A.
dc.contributor.authorBoylan, Geraldine B.
dc.contributor.authorBenders, Manon
dc.contributor.authorIšgum, Ivana
dc.contributor.funderScience Foundation Irelanden
dc.contributor.funderIrish Research Councilen
dc.date.accessioned2017-02-01T12:06:15Z
dc.date.available2017-02-01T12:06:15Z
dc.date.issued2017-01-11
dc.date.updated2017-02-01T11:55:44Z
dc.description.abstractA fully automatic method for detection and quantification of ischemic lesions in diffusion-weighted MR images of neonatal hypoxic ischemic encephalopathy (HIE) is presented. Ischemic lesions are manually segmented by two independent observers in 1.5 T data from 20 subjects and an automatic algorithm using a random forest classifier is developed and trained on the annotations of observer 1. The algorithm obtains a median sensitivity and specificity of 0.72 and 0.99 respectively. F1-scores are calculated per subject for algorithm performance (median = 0.52) and observer 2 performance (median = 0.56). A paired t-test on the F1-scores shows no statistical difference between the algorithm and observer 2 performances. The method is applied to a larger dataset including 54 additional subjects scanned at both 1.5 T and 3.0 T. The algorithm findings are shown to correspond well with the injury pattern noted by clinicians in both 1.5 T and 3.0 T data and to have a strong relationship with outcome. The results of the automatic method are condensed to a single score for each subject which has significant correlation with an MR score assigned by experienced clinicians (p < 0.0001). This work represents a quantitative method of evaluating diffusion-weighted MR images in neonatal HIE and a first step in the development of an automatic system for more in-depth analysis and prognostication.en
dc.description.sponsorshipScience Foundation Ireland (SFI grant no. 10/IN.1/B3036 and 12/RC/2272); Irish Research Council (GOIPD/2013/146)en
dc.description.statusPeer revieweden
dc.description.versionPublished Versionen
dc.format.mimetypeapplication/pdfen
dc.identifier.citationMurphy, K., van der Aa, N. E., Negro, S., Groenendaal, F., de Vries, L. S., Viergever, M. A., Boylan, G. B., Benders, M. J. N. L. and Išgum, I. (2017) 'Automatic quantification of ischemic injury on diffusion-weighted MRI of neonatal hypoxic ischemic encephalopathy', NeuroImage: Clinical, 14, pp. 222-232. doi:10.1016/j.nicl.2017.01.005en
dc.identifier.doi10.1016/j.nicl.2017.01.005
dc.identifier.endpage232en
dc.identifier.issn2213-1582
dc.identifier.journaltitleNeuroimage: Clinicalen
dc.identifier.startpage222en
dc.identifier.urihttps://hdl.handle.net/10468/3550
dc.identifier.volume14en
dc.language.isoenen
dc.publisherElsevieren
dc.rights© 2017 The Authors. Published by Elsevier Inc. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).en
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/4.0/en
dc.subjectAutomatic quantificationen
dc.subjectHIEen
dc.subjectMRIen
dc.subjectDiffusion-weighted lesionsen
dc.subjectSegmentationen
dc.subjectNeonatal hypoxic ischemic encephalopathyen
dc.titleAutomatic quantification of ischemic injury on diffusion-weighted MRI of neonatal hypoxic ischemic encephalopathyen
dc.typeArticle (peer-reviewed)en
Files
Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
2300.pdf
Size:
1.87 MB
Format:
Adobe Portable Document Format
Description:
Published Version
License bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
license.txt
Size:
2.71 KB
Format:
Item-specific license agreed upon to submission
Description: