Neonatal seizure detection: a deep learning approach

Simple item page
dc.availability.bitstreamembargoed
dc.check.date2024-03-30
dc.contributor.advisorLightbody, Gordonen
dc.contributor.advisorTemko, Andriyen
dc.contributor.authorO'Shea, Alison
dc.date.accessioned2021-09-16T11:50:33Z
dc.date.available2021-09-16T11:50:33Z
dc.date.issued2020-09-04
dc.date.submitted2020-09-04
dc.description.abstractThe detection of neonatal seizures is an important step in identifying neurological dysfunction in newborn infants. Research indicates that seizures in infants are underreported; specialist EEG monitoring equipment and neonatal neurophysiological expertise are required to reliably detect neonatal seizures due to the predominance of sub-clinical seizure events. Often, the required level of clinical expertise is not available around-the-clock in the NICU; medical experts have cited the need for decision support algorithms to assist staff during these times. In this thesis novel automated neonatal seizure detection algorithms are proposed. Here deep learning end-to-end optimised algorithms, which detect seizures from raw multi-channel EEG, are presented. The deep learning approach differs from previous rule-based and machine learning systems, which rely on hand-engineered features. An appropriate input EEG representation is selected through empirical analysis; 2-dimensional time-frequency representations of EEG are compared to 1-dimensional temporal representations in a series of experiments. Deep learning algorithms prove capable of extracting discriminative intermediate hierarchical representations from raw EEG. A deep learning algorithm for detecting seizures in term neonates is proposed. The designed algorithm utilises only convolutional layers to process multi-channel temporal EEG and is designed to exploit the large quantity of weakly labelled data available in the training stage. The effect of varying architectural parameters is thoroughly studied, and the designed architecture compares favourably in terms of performance, inference run time and number of parameters when compared with baseline systems. The developed system outperforms state-of-the-art machine learning algorithms when tested on a large database of continuous EEG recordings (duration 834h) and when further validated on a held-out publicly available dataset (duration 112h), achieving AUC results of 98.5% and 95.6% respectively. The challenges associated with detecting seizures in term EEG are exacerbated in preterm EEG due to the large variations in EEG morphology depending on gestational age and the limited amount of annotated preterm EEG available. A deep learning algorithm development framework is proposed where classifiers are trained to detect seizures for specific gestational age ranges. The developed algorithms leverage the existence of robustly trained term EEG models through transfer learning and classifier ensembling; this results in accurate seizure detection despite the scarcity of labelled training data. This preterm seizure detection framework represents the first time an algorithm of this kind has been developed; it achieves an AUC of 95.4% on a held-out test dataset (duration 575h), and detects approximately 50% of all seizure events at a false detection rate of one false alarm every four hours. In this work, algorithms are investigated through a series of visualisation techniques. This analysis gives an understanding of the EEG patterns which contribute to algorithm decisions and highlights the differences between term and preterm EEG. The developed algorithm framework is also utilised as part of a mobile brain monitoring device where the light-weight nature of the designed network and the simplicity of the inference computations are exploited through AI-on-the-edge decision support. The ability to decipher deep learning algorithms and to integrate algorithms into existing brain monitoring systems are necessary steps for the translation of the work in this thesis into clinical domain.en
dc.description.statusNot peer revieweden
dc.description.versionAccepted Versionen
dc.format.mimetypeapplication/pdfen
dc.identifier.citationO'Shea, A. 2020. Neonatal seizure detection: a deep learning approach. PhD Thesis, University College Cork.en
dc.identifier.endpage173en
dc.identifier.urihttps://hdl.handle.net/10468/11936
dc.language.isoenen
dc.publisherUniversity College Corken
dc.rights© 2020, Alison O'Shea.en
dc.rights.urihttps://creativecommons.org/licenses/by-sa/4.0/en
dc.subjectDeep learningen
dc.subjectSignal processingen
dc.subjectEEGen
dc.subjectNeonatal seizuresen
dc.subjectMachine learningen
dc.titleNeonatal seizure detection: a deep learning approachen
dc.typeDoctoral thesisen
dc.type.qualificationlevelDoctoralen
dc.type.qualificationnamePhD - Doctor of Philosophyen
Files
Original bundle
Now showing 1 - 3 of 3
Thumbnail Image
Name:
Alison thesis - final no highlight.docx
Size:
66.09 MB
Format:
Microsoft Word XML
Description:
Full Text E-thesis (Word)
Thumbnail Image
Name:
Alison O'Shea PhD thesis.pdf
Size:
5.98 MB
Format:
Adobe Portable Document Format
Description:
Full Text E-thesis
Download
Thumbnail Image
Name:
3. 110305629 - Alison O'Shea - Submission for Examination form.pdf
Size:
438.09 KB
Format:
Adobe Portable Document Format
Description:
Submission for Examination Form
License bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
license.txt
Size:
5.2 KB
Format:
Item-specific license agreed upon to submission
Description:
Download
Collections
Research Theses Submission
College of Science, Engineering and Food Science - Doctoral Theses
Electrical and Electronic Engineering - Doctoral Theses
INFANT Research Centre - Doctoral Theses