A framework for seizure detection using effective connectivity, graph theory, and multi-level modular network. (May 2020)

• Record Type: Journal Article
• Authors: Akbarian, Behnaz; Erfanian, Abbas
• Is Part Of: Biomedical signal processing and control. Volume 59(2020)
• Publication Date: 2020-05
• Subjects: AIC Akaike Information Criterion -- AE auto-encoder -- CHB Children's Hospital Boston -- COH Coherence -- CSP common spatial pattern -- COR correlation -- COV covariance -- xCOR cross-correlation -- dDTF direct DTF -- DC directed coherence -- DTF directed transfer function -- EBC effective brain connectivity -- EEG electroencephalography -- FPR false positive rate -- FN False Negative -- FP False Positive -- ffDTF full frequency DTF -- FBC functional brain connectivity -- GMM Gaussian mixture model -- GPDC generalized partial directed coherence -- GC Granger causality -- MIT Massachusetts Institute of Technology -- MENN modular effective neural networks -- MFNN modular frequency neural networks -- MLMN multi-level Modular networks -- MVAR multivariate autoregressive models -- MI mutual information -- PDC partial directed coherence -- PTZ pentylenetetrazole -- PSI phase slope index -- PLV phase-locking value -- PPV positive predictive value -- PSD power spectral density -- PNES psychogenic nonepileptic seizures -- SOZ seizure onset zone -- SVM support vector machine -- t-SNE t-Distributed Stochastic Neighbor Embedding -- CA classification accuracy -- TN True Negative -- TP True Positive; Effective brain connectivity -- Graph theory -- Autoencoder -- Modular frequency neural networks -- Modular effective neural networks -- Multi-level modular networks; Signal processing -- Periodicals; Biomedical engineering -- Periodicals; Signal Processing, Computer-Assisted -- Periodicals; Image Processing, Computer-Assisted -- Periodicals; Biomedical Engineering -- Periodicals; 610.28
• DOI: 10.1016/j.bspc.2020.101878
• Languages: English
• ISSNs: 1746-8094

Abstract

Highlights: A method based on effective brain connectivity, graph theory, and multi-level modular networks is presented. The method is used for distinguishing between seizure and nonseizure. The combination of the global and nodal graph theory measures based on effective brain connectivity are introduced. Single layer autoencoder is used for feature extraction and feature reduction from the initial features. Multi-level modular network is used as classifier. Abstract: Objective: An epileptic seizure has a characteristic EEG pattern, which allows for its automatic detection. Statistical dependence between different brain regions measures by functional brain connectivity (FBC). Specific directional effects cannot be considered by FBC, and thus effective brain connectivity (EBC) is used to measure causal dependencies between brain regions. Our main purpose is to provide a reliable automatic seizure detection approach. Methods: In this study, three new methods are provided. Multi-level modular network (MLMN) is proposed based on combining various EBC classification results at different frequencies. Another method named "modular effective neural networks (MENN)." This method combines the classification results of the three different EBCs at a specific frequency. "Modular frequency neural networks (MFNN)" is another method that combines the classification results of specific EBC at seven different frequencies. Results: The mean accuracies of MFNN are 97.14 %, 98.53 %, and 97.91 % using directed transfer function (DTF), directed coherence (DC), and generalized partial directed coherence (GPDC), respectively. By using MENN method, the highest mean accuracy is 98.34 %. Finally, MLMN has the highest mean accuracy, which is equal to 99.43. To the best of our knowledge, the proposed method is a new method that provides the highest accuracy in comparison to other studies – that used the MIT-CHB database. Conclusion and significance: The knowledge of structure-function relationships between different areas of the brain is necessary for characterizing the underlying dynamics. Hence, features based on EBC can provide a more reliable automatic seizure detection approach.