Investigating the impact of CNN depth on neonatal seizure detection performance

Simple item page
dc.contributor.authorO'Shea, Alison
dc.contributor.authorLightbody, Gordon
dc.contributor.authorBoylan, Geraldine B.
dc.contributor.authorTemko, Andriy
dc.contributor.funderWellcome Trusten
dc.contributor.funderScience Foundation Irelanden
dc.date.accessioned2021-08-26T08:50:59Z
dc.date.available2021-08-26T08:50:59Z
dc.date.issued2018-10-29
dc.date.updated2021-08-26T08:40:23Z
dc.description.abstractThis study presents a novel, deep, fully convolutional architecture which is optimized for the task of EEG-based neonatal seizure detection. Architectures of different depths were designed and tested; varying network depth impacts convolutional receptive fields and the corresponding learned feature complexity. Two deep convolutional networks are compared with a shallow SVMbased neonatal seizure detector, which relies on the extraction of hand-crafted features. On a large clinical dataset, of over 800 hours of multichannel unedited EEG, containing 1389 seizure events, the deep 11-layer architecture significantly outperforms the shallower architectures, improving the AUC90 from 82.6% to 86.8%. Combining the end-to-end deep architecture with the feature-based shallow SVM further improves the AUC90 to 87.6%. The fusion of classifiers of different depths gives greatly improved performance and reduced variability, making the combined classifier more clinically reliable.en
dc.description.sponsorshipWellcome Trust (Strategic Translational Award 098983/Z/12)en
dc.description.statusPeer revieweden
dc.description.versionAccepted Versionen
dc.format.mimetypeapplication/pdfen
dc.identifier.citationO'Shea, A., Lightbody, G., Boylan, G. and Temko, A. (2018) 'Investigating the impact of CNN depth on neonatal seizure detection performance', 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Honolulu, HI, USA, 18-21 July, pp. 5862-5865. doi: 10.1109/EMBC.2018.8513617en
dc.identifier.doi10.1109/EMBC.2018.8513617en
dc.identifier.eissn1558-4615
dc.identifier.endpage5865en
dc.identifier.isbn978-1-5386-3646-6
dc.identifier.isbn978-1-5386-3645-9
dc.identifier.isbn978-1-5386-3647-3
dc.identifier.issn1557-170X
dc.identifier.startpage5862en
dc.identifier.urihttps://hdl.handle.net/10468/11788
dc.language.isoenen
dc.publisherInstitute of Electrical and Electronics Engineers (IEEE)en
dc.relation.projectinfo:eu-repo/grantAgreement/SFI/SFI Research Centres/12/RC/2272/IE/Irish Centre for Fetal and Neonatal Translational Research (INFANT)/en
dc.rights© 2018, IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.en
dc.subjectPediatricsen
dc.subjectSupport vector machinesen
dc.subjectFeature extractionen
dc.subjectConvolutionen
dc.subjectElectroencephalographyen
dc.subjectFilter banksen
dc.subjectTask analysisen
dc.titleInvestigating the impact of CNN depth on neonatal seizure detection performanceen
dc.typeConference itemen
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
5925.pdf
Size:
422.5 KB
Format:
Adobe Portable Document Format
Description:
Accepted Version
Download
License bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
license.txt
Size:
2.71 KB
Format:
Item-specific license agreed upon to submission
Description:
Download
Collections
Electrical and Electronic Engineering - Conference Items
INFANT Research Centre - Conference Items
Paediatrics and Child Health - Conference Items