Deep Convolutional Neural Network and Reverse Biorthogonal Wavelet Scalograms for Automatic Identification of High Frequency Micro-Scale Spike Transients in the Post-Hypoxic-Ischemic EEG

Show simple item record

dc.contributor.author Abbasi, Seyed en
dc.contributor.author Gunn, Alistair en
dc.contributor.author Bennet, Laura en
dc.contributor.author Unsworth, CP en
dc.coverage.spatial Montreal, Canada en
dc.date.accessioned 2020-06-11T03:00:50Z en
dc.date.available 2020-04-11 en
dc.date.issued 2020-07-20 en
dc.identifier.citation Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS. 2020-July: 1015-1018. 01 Jul 2020 en
dc.identifier.uri http://hdl.handle.net/2292/51476 en
dc.description.abstract Diagnosis of hypoxic-ischemic encephalopathy (HIE) is currently limited and prognostic biological markers are required for early identification of at risk infants at birth. Using pre-clinical data from our fetal sheep models, we have shown that micro-scale EEG patterns, such as high-frequency spikes and sharp waves, evolve superimposed on a significantly suppressed background during the early hours of recovery (0-6 h), after an HI insult. In particular, we have demonstrated that the number of micro-scale gamma spike transients peaks within the first 2-2.5 hours of the insult and automatically quantified sharp waves in this period are predictive of neural outcome. This period of time is optimal for the initiation of neuroprotection treatments such as therapeutic hypothermia, which has a limited window of opportunity for implementation of 6 h or less after an HI insult. Clinically, it is hard to determine when an insult has started and thus the window of opportunity for treatment. Thus, reliable automatic algorithms that could accurately identify EEG patterns that denote the phase of injury is a valuable clinical tool. We have previously developed successful machine-learning strategies for the identification of HI micro-scale EEG patterns in a preterm fetal sheep model of HI. This paper employs, for the first time, reverse biorthogonal Wavelet-scalograms (WS) as the inputs to a 17-layer deep-trained convolutional neural network (CNN) for the precise identification of high-frequency micro-scale spike transients that occur in the 80-120Hz gamma band during first 2 h period of an HI insult. The rbio-WS-CNN classifier robustly identified spike transients with an exceptionally high-performance of 99.82%. Clinical relevance—The suggested classifier would effectively identify and quantify EEG patterns of a similar morphology in preterm newborns during recovery from an HI-insult. en
dc.description.uri https://embc.embs.org/2020/ en
dc.publisher IEEE en
dc.relation.ispartof 42nd Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC'20) en
dc.rights Items in ResearchSpace are protected by copyright, with all rights reserved, unless otherwise indicated. Previously published items are made available in accordance with the copyright policy of the publisher. en
dc.rights.uri https://researchspace.auckland.ac.nz/docs/uoa-docs/rights.htm en
dc.subject Deep Neural Network en
dc.subject Deep learning en
dc.subject Convolutional Neural Network en
dc.subject hypoxic-ischemic encephalopathy (HIE) en
dc.subject EEG Biomarker en
dc.subject Neonatal Seizure en
dc.subject Automatic detection en
dc.subject Brain injury en
dc.subject Early diagnosis en
dc.subject spike transients en
dc.subject sharp wave en
dc.subject pattern recognition en
dc.subject wavelet en
dc.subject spectral analysis en
dc.subject machine learning en
dc.subject preterm brain en
dc.subject clinical recording en
dc.subject biorthogonal basis en
dc.subject Scalograms en
dc.subject newborns en
dc.subject signal processing en
dc.subject image processing en
dc.subject neuroscience en
dc.subject sheep en
dc.title Deep Convolutional Neural Network and Reverse Biorthogonal Wavelet Scalograms for Automatic Identification of High Frequency Micro-Scale Spike Transients in the Post-Hypoxic-Ischemic EEG en
dc.type Conference Item en
dc.identifier.doi 10.1109/EMBC44109.2020.9176499 en
dc.rights.holder Copyright: IEEE en
pubs.finish-date 2020-07-24 en
pubs.publication-status Accepted en
pubs.start-date 2020-07-20 en
dc.rights.accessrights http://purl.org/eprint/accessRights/OpenAccess en
pubs.subtype Conference Paper en
pubs.elements-id 800480 en
pubs.org-id Bioengineering Institute en
pubs.org-id Medical and Health Sciences en
pubs.org-id Medical Sciences en
pubs.org-id Physiology Division en
pubs.record-created-at-source-date 2020-04-29 en


Files in this item

Find Full text

This item appears in the following Collection(s)

Show simple item record

Share

Search ResearchSpace


Browse

Statistics