Automatic quantification of ischemic injury on diffusion-weighted MRI of neonatal hypoxic ischemic encephalopathy
| dc.contributor.author | Murphy, Keelin | |
| dc.contributor.author | van der Aa, Niek E. | |
| dc.contributor.author | Negro, Simona | |
| dc.contributor.author | Groenendaal, Floris | |
| dc.contributor.author | de Vries, Linda S. | |
| dc.contributor.author | Viergever, Max A. | |
| dc.contributor.author | Boylan, Geraldine B. | |
| dc.contributor.author | Benders, Manon | |
| dc.contributor.author | IĆĄgum, Ivana | |
| dc.contributor.funder | Science Foundation Ireland | en |
| dc.contributor.funder | Irish Research Council | en |
| dc.date.accessioned | 2017-02-01T12:06:15Z | |
| dc.date.available | 2017-02-01T12:06:15Z | |
| dc.date.issued | 2017-01-11 | |
| dc.date.updated | 2017-02-01T11:55:44Z | |
| dc.description.abstract | A 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.sponsorship | Science Foundation Ireland (SFI grant no. 10/IN.1/B3036 and 12/RC/2272); Irish Research Council (GOIPD/2013/146) | en |
| dc.description.status | Peer reviewed | en |
| dc.description.version | Published Version | en |
| dc.format.mimetype | application/pdf | en |
| dc.identifier.citation | Murphy, 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 IĆĄgum, 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.2017.01.005 | en |
| dc.identifier.doi | 10.1016/j.nicl.2017.01.005 | |
| dc.identifier.endpage | 232 | en |
| dc.identifier.issn | 2213-1582 | |
| dc.identifier.journaltitle | Neuroimage: Clinical | en |
| dc.identifier.startpage | 222 | en |
| dc.identifier.uri | https://hdl.handle.net/10468/3550 | |
| dc.identifier.volume | 14 | en |
| dc.language.iso | en | en |
| dc.publisher | Elsevier | en |
| 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.uri | http://creativecommons.org/licenses/by-nc-nd/4.0/ | en |
| dc.subject | Automatic quantification | en |
| dc.subject | HIE | en |
| dc.subject | MRI | en |
| dc.subject | Diffusion-weighted lesions | en |
| dc.subject | Segmentation | en |
| dc.subject | Neonatal hypoxic ischemic encephalopathy | en |
| dc.title | Automatic quantification of ischemic injury on diffusion-weighted MRI of neonatal hypoxic ischemic encephalopathy | en |
| dc.type | Article (peer-reviewed) | en |
