Neonatal hypoxic-ischemic encephalopathy grading from multi-channel EEG time-series data using a fully convolutional neural network

Thumbnail Image
ICNC-FSKD.pdf(1.71 MB)
Accepted Version
Yu, Shuwen
Marnane, William P.
Boylan, Geraldine B.
Lightbody, Gordon
Journal Title
Journal ISSN
Volume Title
Institute of Electrical and Electronics Engineers (IEEE)
Research Projects
Organizational Units
Journal Issue
A deep learning classifier is proposed for hypoxic-ischemic encephalopathy (HIE) grading in neonates. Rather than using any features, this architecture can be fed with raw EEG. Fully convolutional layers were adopted both in the feature extraction and classification blocks, which makes this architecture simpler, and deeper, but with fewer parameters. Here two large (335h and 338h respectively) multi-center neonatal continuous EEG datasets were used for training and test. The model was trained based on weak labels and channel independence. A majority vote method was used for the post-processing of the classifier results (across time and channels) to increase the robustness of the prediction. The proposed system achieved an accuracy of 86.09% (95% confidence interval: 82.41% ∼89.78%), an MCC of 0.7691, and an AUC of 86.23% on the large unseen test set. Two convolutional neural network architectures which utilized time-frequency distribution features were selected as the baseline as they had been developed or tested on the same datasets. A relative improvement of 23.65% in test accuracy was obtained as compared with the best baseline.
Hypoxic-ischemic encephalopathy (HIE) , EEG , Fully convolutional neural network
Yu, S., Marnane, W. P., Boylan, G. B. and Lightbody, G. (2023) 'Neonatal hypoxic-ischemic encephalopathy grading from multi-channel EEG time-series data using a fully convolutional neural network', 2023 19th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD), Harbin, China, 29-31 July, pp. 1-9. doi: 10.1109/ICNC-FSKD59587.2023.10280986
Link to publisher’s version
© 2023, 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.