Brain Waves Decoded: Cutting-Edge Seizure Recognition with Graph Fourier and BrainGNN

Dhruvi Thakkar; Zankhana Patel; Dhruv Dudhat; Dr. Rocky Upadhyay; Ankita Kothari; Dhara Parikh

doi:10.32628/CSEIT2410612405

Authors

Dhruvi Thakkar Student at Krishna School of Emerging Technology and Applied Research, Drs. Kiran & Pallavi Patel Global University, Vadodara-Mumbai NH#8, Varnama, Vadodara-391243, Gujarat, India Author
Zankhana Patel Student at Krishna School of Emerging Technology and Applied Research, Drs. Kiran & Pallavi Patel Global University, Vadodara-Mumbai NH#8, Varnama, Vadodara-391243, Gujarat, India Author
Dhruv Dudhat Student at Krishna School of Emerging Technology and Applied Research, Drs. Kiran & Pallavi Patel Global University, Vadodara-Mumbai NH#8, Varnama, Vadodara-391243, Gujarat, India Author
Dr. Rocky Upadhyay HOD & Associate Professor at Krishna School of Emerging Technology and Applied Research, Drs. Kiran & Pallavi Patel Global University, Vadodara-Mumbai NH#8, Varnama, Vadodara-391243, Gujarat, India Author
Ankita Kothari Assistant Professor at Krishna School of Emerging Technology and Applied Research, Drs. Kiran & Pallavi Patel Global University, Vadodara-Mumbai NH#8, Varnama, Vadodara-391243, Gujarat, India Author
Dhara Parikh Assistant Professor at Krishna School of Emerging Technology and Applied Research, Drs. Kiran & Pallavi Patel Global University, Vadodara-Mumbai NH#8, Varnama, Vadodara-391243, Gujarat, India Author

DOI:

https://doi.org/10.32628/CSEIT2410612405

Keywords:

Brain Graph Neural Networks, Graph Fourier Transforms, EEG Signal Analysis, Neural Dynamics, Non-Invasive Diagnostics, Epileptic Seizures

Abstract

For effective therapy, epileptic seizures, which are characterized by sudden electrical disruptions in the brain, must be identified accurately and promptly. Conventional techniques, such feature extraction and EEG signal analysis, have demonstrated limits in terms of robustness and precision. In order to greatly improve seizure recognition, this paper present a novel method that integrates Brain Graph Neural Networks (BrainGNN) and Graph Fourier Transforms (GFT). By transforming brain wave impulses into the frequency domain, the GFT examines brain wave signals and reveals complex patterns associated with epileptic activity. With great accuracy, BrainGNN––which is optimized for graph-structure data––capture the temporal and spatial correlations in these signals to differentiate between seizure and normal states. Our combined GFT and BrainGNN method outperformed conventional technique by a significant margin, achieving outstanding test accuracies of 99.77%. This sophisticated method offers insights into the neural dynamics of seizures to enhancing detection abilities. It also emphasizes the potential of fusing neural network and graph-based techniques to improve neurophysiological disorder diagnostics, which could lead to more potent, non-invasive tools for the management of epilepsy.

Downloads

Download data is not yet available.

References

Kunekar, P., Gupta, M. K., & Gaur, P. (2024). Detection of epileptic seizure in EEG signals using machine learning and deep learning techniques. Journal of Engineering and Applied Science, 71(21), 21. https://doi.org/10.1186/s44147-023-00353-y DOI: https://doi.org/10.1186/s44147-023-00353-y

Wang B, Yang X, Li S, Wang W, Ouyang Y, Zhou J and Wang C (2023) Automatic epileptic seizure detection based on EEG using a moth-flame optimization of one-dimensional convolutional neural networks. Front. Neurosci. 17:1291608. doi: 10.3389/fnins.2023.1291608 DOI: https://doi.org/10.3389/fnins.2023.1291608

Alalayah, K.M.; Senan, E.M.; Atlam, H.F.; Ahmed, I.A.; Shatnawi, H.S.A. Effective Early Detection of Epileptic Seizures through EEG Signals Using Classification Algorithms Based on t-Distributed Stochastic Neighbor Embedding and K-Means. Diagnostics 2023, 13, 1957. DOI: https://doi.org/10.3390/diagnostics13111957

Mekruksavanich, S.; Jitpattanakul, A. Effective Detection of Epileptic Seizures through EEG Signals Using Deep Learning Approaches. Mach. Learn. Knowl. Extr. 2023, 5, 1937–1952. https://doi.org/10.3390/make5040094 DOI: https://doi.org/10.3390/make5040094

Omar, A., & El-Hafeez, T. A. (2024). Optimizing epileptic seizure recognition performance with feature scaling and dropout layers. Neural Computing and Applications, 36(2835–2852). https://doi.org/10.1007/s00521-023-09204-6 DOI: https://doi.org/10.1007/s00521-023-09204-6

Wang, X., Wang, Y., Liu, D., Wang, Y., & Wang, Z. (2023). Automated recognition of epilepsy from EEG signals using a combining space–time algorithm of CNN LSTM. Scientific Reports, 13(1), 14876. https://doi.org/10.1038/s41598-023-41537-z DOI: https://doi.org/10.1038/s41598-023-41537-z

Xiaoxiao Li, Yuan Zhou, Nicha Dvornek, Muhan Zhang, Siyuan Gao, Juntang Zhuang, Dustin Scheinost, Lawrence H. Staib, Pamela Ventola, James S. Duncan. "BrainGNN: Interpretable Brain Graph Neural Network for fMRI Analysis." Med Image Anal. 2021 Dec; 74: 102233. doi:10.1016/j.media.2021.102233. DOI: https://doi.org/10.1016/j.media.2021.102233

Li, X., Zhou, Y., Dvornek, N., Zhang, M., Gao, S., Zhuang, J., Scheinost, D., Staib, L., Ventola, P., & Duncan, J. (2021). BrainGNN: Interpretable Brain Graph Neural Network for fMRI Analysis. bioRxiv. https://doi.org/10.1101/2020.05.16.100057 DOI: https://doi.org/10.1101/2020.05.16.100057

Zhang, S.; Yang, J.; Zhang, Y.; Zhong, J.; Hu, W.; Li, C.; Jiang, J. The Combination of a Graph Neural Network Technique and Brain Imaging to Diagnose Neurological Disorders: A Review and Outlook. Brain Sci. 2023, 13, 1462. https://doi.org/10.3390/brainsci13101462 DOI: https://doi.org/10.3390/brainsci13101462

Cui, Hejie, Kan, Xuan, and Yang, Carl. "Tutorial: Brain Connectome Analysis with Graph Neural Networks." Department of Computer Science, Emory University. This tutorial provides a comprehensive overview of brain network construction pipelines, GNN designs, and practical instructions on the BrainGB Python package. It aims to bridge researchers in neuroscience and machine learning and foster future research in brain network analysis.

Cui, Hejie, Wei Dai, Yanqiao Zhu, Xuan Kan, Antonio Aodong Chen Gu, Joshua Lukemire, Liang Zhan, Lifang He, Ying Guo, and Carl Yang. "BrainGB: A Benchmark for Brain Network Analysis with Graph Neural Networks." IEEE Transactions on Medical Imaging.

Shimojo, Sakaki, and Hiroyuki Akama. "Prediction and Analysis of Structural Brain Health Indicators Using Deep Learning Models with Functional Brain Images as Input." May 29, 2023. https://doi.org/10.32388/RWZH4Y. DOI: https://doi.org/10.32388/RWZH4Y

Huang, J., Zhang, D., Wang, Y., Goh, R.S.M., Wang, L., & Sun, Y. (2023). Hodge-Laplacian Heterogeneous Graph Convolutional Neural Network for fMRI Analysis. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2023, pp. 12345-12352.

Gaotang Li, Marlena Duda, Xiang Zhang, Danai Koutra, and Yujun Yan. "Interpretable Sparsification of Brain Graphs: Better Practices and Effective Designs for Graph Neural Networks." In Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD '23), August 6–10, 2023, Long Beach, CA, USA. ACM, New York, NY, USA, 12 pages. https://doi.org/10.1145/3580305.3599394. DOI: https://doi.org/10.1145/3580305.3599394

Hongting Ye, Yalu Zheng, Yueying Li, Ke Zhang, Youyong Kong, Yonggui Yuan. "RH-BrainFS: Regional Heterogeneous Multimodal Brain Networks Fusion Strategy." 37th Conference on Neural Information Processing Systems (NeurIPS 2023).

Kan, X., Dai, W., Cui, H., Zhang, Z., Guo, Y., & Yang, C. (2022). BRAIN NETWORK TRANSFORMER. Proceedings of the 36th Conference on Neural Information Processing Systems (NeurIPS). Retrieved from https://github.com/Wayfear/BrainNetworkTransformer.

Masci, J., Meier, U., Cire ̧san, D., Schmidhuber, J. (2011). Stacked convolutional auto-encoders for hierarchical feature extraction. Artificial Neural Networks and Machine Learning–ICANN 2011, 52–59. DOI: https://doi.org/10.1007/978-3-642-21735-7_7