Automatic Detection of High-Frequency Oscillations Based on an End-to-End Bi-Branch Neural Network and Clinical Cross-Validation.

Publisher: Hindawi Pub. Corp Country of Publication: United States NLM ID: 101279357 Publication Model: eCollection Cited Medium: Internet ISSN: 1687-5273 (Electronic) NLM ISO Abbreviation: Comput Intell Neurosci Subsets: MEDLINE

Original Publication: New York, NY : Hindawi Pub. Corp.

Electroencephalography* ; Epilepsy*/diagnosis; Data Collection ; Humans ; Neural Networks, Computer ; Research Design

Accurate identification of high-frequency oscillation (HFO) is an important prerequisite for precise localization of epileptic foci and good prognosis of drug-refractory epilepsy. Exploring a high-performance automatic detection method for HFOs can effectively help clinicians reduce the error rate and reduce manpower. Due to the limited analysis perspective and simple model design, it is difficult to meet the requirements of clinical application by the existing methods. Therefore, an end-to-end bi-branch fusion model is proposed to automatically detect HFOs. With the filtered band-pass signal (signal branch) and time-frequency image (TFpic branch) as the input of the model, two backbone networks for deep feature extraction are established, respectively. Specifically, a hybrid model based on ResNet1d and long short-term memory (LSTM) is designed for signal branch, which can focus on both the features in time and space dimension, while a ResNet2d with a Convolutional Block Attention Module (CBAM) is constructed for TFpic branch, by which more attention is paid to useful information of TF images. Then the outputs of two branches are fused to realize end-to-end automatic identification of HFOs. Our method is verified on 5 patients with intractable epilepsy. In intravalidation, the proposed method obtained high sensitivity of 94.62%, specificity of 92.7%, and F1-score of 93.33%, and in cross-validation, our method achieved high sensitivity of 92.00%, specificity of 88.26%, and F1-score of 89.11% on average. The results show that the proposed method outperforms the existing detection paradigms of either single signal or single time-frequency diagram strategy. In addition, the average kappa coefficient of visual analysis and automatic detection results is 0.795. The method shows strong generalization ability and high degree of consistency with the gold standard meanwhile. Therefore, it has great potential to be a clinical assistant tool.
Competing Interests: The authors declare that there are no conflicts of interest regarding the publication of this paper.
(Copyright © 2021 Zimo Liu et al.)

Retraction in: Comput Intell Neurosci. 2023 Dec 13;2023:9820284. (PMID: 38124833)

Brain Commun. 2021 Nov 03;4(1):fcab267. (PMID: 35169696)
J Neurosci Methods. 2013 Mar 15;213(2):236-49. (PMID: 23261773)
Nat Neurosci. 2018 Apr;21(4):474-483. (PMID: 29507407)
IEEE Trans Neural Syst Rehabil Eng. 2020 Dec;28(12):2711-2720. (PMID: 33147147)
Neuroimage. 2020 Dec;223:117344. (PMID: 32898677)
Epilepsia. 2016 Nov;57(11):1735-1747. (PMID: 27677490)
Front Neurol. 2018 Nov 13;9:889. (PMID: 30483204)
Epilepsia. 2020 Aug;61(8):1553-1569. (PMID: 32729943)
IEEE Trans Neural Syst Rehabil Eng. 2021;29:1965-1976. (PMID: 34529568)
Seizure. 2019 Oct;71:304-311. (PMID: 31521052)
Front Comput Neurosci. 2019 Feb 12;13:6. (PMID: 30809142)
Sensors (Basel). 2020 Apr 11;20(8):. (PMID: 32290472)
Sci Rep. 2017 Oct 23;7(1):13836. (PMID: 29062105)
J Neurosurg. 2020 Apr 24;134(3):1251-1261. (PMID: 32330883)
IEEE Trans Neural Syst Rehabil Eng. 2018 Dec;26(12):2280-2289. (PMID: 30369447)
Epilepsia. 2021 Sep;62(9):2240-2251. (PMID: 34309835)
Clin Neurophysiol. 2007 May;118(5):1134-43. (PMID: 17382583)
J Neurosci Methods. 2018 Jan 01;293:6-16. (PMID: 28860077)
Front Neurol. 2019 Feb 12;10:94. (PMID: 30804887)
PLoS One. 2016 Jun 24;11(6):e0158276. (PMID: 27341033)
Clin Neurophysiol. 2012 Sep;123(9):1721-31. (PMID: 22652068)
Epilepsia. 2018 Apr;59(4):e51-e55. (PMID: 29508901)
Front Neurol. 2021 Oct 15;12:640526. (PMID: 34721249)
J Epilepsy Res. 2019 Jun 30;9(1):1-13. (PMID: 31482052)
J Neurophysiol. 2013 Oct;110(8):1958-64. (PMID: 23926038)
Brain Sci. 2020 Apr 08;10(4):. (PMID: 32276318)
Ann Clin Transl Neurol. 2018 Aug 09;5(9):1062-1076. (PMID: 30250863)
Sci Rep. 2020 Sep 4;10(1):14654. (PMID: 32887896)
Epilepsia. 2016 Jan;57(1):111-21. (PMID: 26611159)
Front Neurosci. 2020 Jun 04;14:546. (PMID: 32581688)
Epilepsia. 2008 Jun;49(6):1011-7. (PMID: 18363706)
Nat Commun. 2021 May 25;12(1):3095. (PMID: 34035249)
Epilepsia. 2013 Aug;54(8):1428-36. (PMID: 23899121)
J Neural Eng. 2016 Apr;13(2):026026. (PMID: 26924828)
Neurology. 2021 Mar 2;96(9):439-448. (PMID: 33408149)
IEEE Trans Neural Syst Rehabil Eng. 2021;29:587-596. (PMID: 33534708)
IEEE Trans Biomed Eng. 2017 Sep;64(9):2230-2240. (PMID: 28113293)
IEEE Trans Biomed Eng. 2016 Jan;63(1):76-85. (PMID: 25561587)
Neuroimage. 2021 May 1;231:117861. (PMID: 33592245)

Date Created: 20220107 Date Completed: 20220110 Latest Revision: 20240405

20240405

PMC8727108

10.1155/2021/7532241

34992650