Neonatal seizure detection: a deep learning approach

Show simple item record

dc.contributor.advisor Lightbody, Gordon en
dc.contributor.advisor Temko, Andriy en
dc.contributor.author O'Shea, Alison
dc.date.accessioned 2021-09-16T11:50:33Z
dc.date.available 2021-09-16T11:50:33Z
dc.date.issued 2020-09-04
dc.date.submitted 2020-09-04
dc.identifier.citation O'Shea, A. 2020. Neonatal seizure detection: a deep learning approach. PhD Thesis, University College Cork. en
dc.identifier.endpage 173 en
dc.identifier.uri http://hdl.handle.net/10468/11936
dc.description.abstract The 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.format.mimetype application/pdf en
dc.language.iso en en
dc.publisher University College Cork en
dc.rights © 2020, Alison O'Shea. en
dc.rights.uri https://creativecommons.org/licenses/by-sa/4.0/ en
dc.subject Deep learning en
dc.subject Signal processing en
dc.subject EEG en
dc.subject Neonatal seizures en
dc.subject Machine learning en
dc.title Neonatal seizure detection: a deep learning approach en
dc.type Doctoral thesis en
dc.type.qualificationlevel Doctoral en
dc.type.qualificationname PhD - Doctor of Philosophy en
dc.internal.availability Full text not available en
dc.description.version Accepted Version en
dc.description.status Not peer reviewed en
dc.internal.school Electrical and Electronic Engineering en
dc.internal.conferring Autumn 2021 en
dc.internal.ricu Irish Centre for Fetal and Neonatal Translational Research (INFANT) en
dc.availability.bitstream embargoed
dc.check.date 2022-09-30


Files in this item

This item appears in the following Collection(s)

Show simple item record

© 2020, Alison O'Shea. Except where otherwise noted, this item's license is described as © 2020, Alison O'Shea.
This website uses cookies. By using this website, you consent to the use of cookies in accordance with the UCC Privacy and Cookies Statement. For more information about cookies and how you can disable them, visit our Privacy and Cookies statement