Integrative Approach for Automated Epileptic Seizure Detection: EEG-MRI Hybrid Model Utilizing Deep Learning Techniques

Epilepsy remains a significant neurological challenge, impacting millions worldwide with recurrent seizures and profound lifestyle implications. Accurate diagnosis of epilepsy at appropriate timing is critical for effective management. This research proposes a novel hybrid approach for automated epileptic seizure detection, integrating Electroencephalography (EEG) and Magnetic Resonance Imaging (MRI) data through advanced deep learning techniques. The methodology involves EEG-based deep learning model training, integrating Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) for feature extraction and classification. Additionally, a MRI-guided fusion model is developed, incorporating structural and functional MRI data to enhance diagnostic accuracy. The hybrid model combines EEG and MRI features, offering a comprehensive understanding of seizure dynamics. Evaluation is conducted on publicly available dataset and Performance metrics including sensitivity, specificity, accuracy, precision, recall and F1-score were utilized to assess the efficacy of the proposed methodology. Results demonstrate superior performance of the hybrid model compared to other methods, highlighting its potential for accurate and efficient epileptic seizure detection.