An Efficient CADNet for Classification of High-frequency Oscillations in Magnetoencephalography

Zhang, M; Liu, J; Liu, C; Wu, T; Peng, X

An Efficient CADNet for Classification of High-frequency Oscillations in Magnetoencephalography

Zhang, M Liu, J Liu, C Wu, T Peng, X

Permalink

Publisher:: IEEE
Publication Type:: Conference Proceeding
Citation:: 2022 4th International Conference on Robotics and Computer Vision, ICRCV 2022, 2022, 00, pp. 25-30
Issue Date:: 2022-01-01

Embargoed

	Filename	Description	Size
	bdedda3a-0e81-4c23-bbd9-977320972b82.pdf	Accepted version	1.2 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Embargoed
Open Access

This item is currently unavailable due to the publisher's embargo.

The embargo period expires on 30 Nov 2024

Full metadata record

Field	Value	Language
dc.contributor.author	Zhang, M
dc.contributor.author	Liu, J
dc.contributor.author	Liu, C
dc.contributor.author	Wu, T
dc.contributor.author	Peng, X https://orcid.org/0000-0002-8901-1472
dc.date	2022-09-25
dc.date.accessioned	2023-02-10T05:13:03Z
dc.date.available	2023-02-10T05:13:03Z
dc.date.issued	2022-01-01
dc.identifier.citation	2022 4th International Conference on Robotics and Computer Vision, ICRCV 2022, 2022, 00, pp. 25-30
dc.identifier.isbn	9781665481700
dc.identifier.uri	http://hdl.handle.net/10453/166050
dc.description.abstract	Epilepsy is a chronic neurological disease, and locating the lesions precisely is crucial to the success of epilepsy surgery. The high-frequency oscillations (HFOs) in magnetoencephalography (MEG) of epileptic patients can be used to detect seizures. Due to the inefficient and error-prone operation of traditional HFOs detection, it is necessary to develop an approach for the detection of HFOs, which can automatically classify HFOs in MEG. In this paper, We proposed a novel deep learning-based CADNet for the classification of HFOs in MEG. First, we preprocessed acquired MEG data by short-time Fourier transform (STFT), and the extracted time-frequency domain information was applied for model training after pictorialism. Then, we captured the features from these images through convolutional neural network combined with multi-head self-attention, all these features were input into Dendrite Net for classification. We evaluated our model on MEG dataset, and the accuracy, precision, recall, and F1-score of the optimized model reached 0.97, 0.98, 0.97, 0.97. We compared the proposed CADNet with other deep learning models, the result demonstrates that our model outperforms others.
dc.language	en
dc.publisher	IEEE
dc.relation.ispartof	2022 4th International Conference on Robotics and Computer Vision, ICRCV 2022
dc.relation.ispartof	2022 4th International Conference on Robotics and Computer Vision (ICRCV)
dc.relation.isbasedon	10.1109/ICRCV55858.2022.9953255
dc.rights	info:eu-repo/semantics/embargoedAccess
dc.title	An Efficient CADNet for Classification of High-frequency Oscillations in Magnetoencephalography
dc.type	Conference Proceeding
utslib.citation.volume	00
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Strength - AAII - Australian Artificial Intelligence Institute
utslib.copyright.status	embargoed	*
utslib.copyright.embargo	2024-11-30T00:00:00+1000Z
dc.date.updated	2023-02-10T05:12:59Z
pubs.finish-date	2022-09-27
pubs.publication-status	Published
pubs.start-date	2022-09-25
pubs.volume	00

Abstract:

Epilepsy is a chronic neurological disease, and locating the lesions precisely is crucial to the success of epilepsy surgery. The high-frequency oscillations (HFOs) in magnetoencephalography (MEG) of epileptic patients can be used to detect seizures. Due to the inefficient and error-prone operation of traditional HFOs detection, it is necessary to develop an approach for the detection of HFOs, which can automatically classify HFOs in MEG. In this paper, We proposed a novel deep learning-based CADNet for the classification of HFOs in MEG. First, we preprocessed acquired MEG data by short-time Fourier transform (STFT), and the extracted time-frequency domain information was applied for model training after pictorialism. Then, we captured the features from these images through convolutional neural network combined with multi-head self-attention, all these features were input into Dendrite Net for classification. We evaluated our model on MEG dataset, and the accuracy, precision, recall, and F1-score of the optimized model reached 0.97, 0.98, 0.97, 0.97. We compared the proposed CADNet with other deep learning models, the result demonstrates that our model outperforms others.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/166050