Epilepsy Detection by Different Modalities with the Use of AI-Assisted Models

Abstract

Epilepsy is characterized by recurrent seizures originating from any four brain lobes. It includes focal seizures with symptoms of alterations in consciousness and cognitive impairments, including memory and language difficulties. It must be radiologically identified by proper diagnosis and course of therapy. However, a visual inspection of images may not always yield an accurate interpretation from radiologists, necessitating AI-assisted methods. The computer-vision-based radiological methods are used to enhance the treatment of epilepsy by image bio-markers and deep learning algorithms. These methods are used to predict disease progression and treatment. It specifies the focus of the research on epilepsy detection using new U-transfer reinforced Gaussian network (U-TRGN) classification models. These models used for lateralization and localization of brain activity in this process. This study gives the idea of preoperative findings of different imaging modalities and postoperative findings of Electroencephalography (EEG) data analysis. The data have been pre-processed through normalization, smoothing, and noise removal techniques. The data are then classified using U-TRGN, after feature selection by kernel convolutional analysis. The performance metrics are evaluated through the training accuracy, validation accuracy, precision, dice coefficient, and area under a region of the convergence curve. The proposed technique attained an accuracy of 97.04%, precision of 94.12%, dice coefficient of 2.96%, and AUC of 99.56%, which is better than the existing methods, and it will be a baseline for upcoming studies.