Seizure Prediction in Scalp EEG Using 3D Convolutional Neural Networks With an Image-Based Approach

• Published in: IEEE transactions on neural systems and rehabilitation engineering Vol. 27; no. 11; pp. 2284 - 2293
• Main Authors: Ozcan, Ahmet Remzi, Erturk, Sarp
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.11.2019; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Artificial neural networks; Brain modeling; Color imagery; Convolutional neural networks; Convulsions & seizures; Datasets; EEG; Electrodes; Electroencephalography; Epilepsy; epileptic stage length; Feature extraction; Image processing; Multichannel communication; Neural networks; Scalp; scalp EEG; seizure prediction; Seizures; Spatial data; Statistical analysis; subject-specific modelling; Three dimensional models; Three-dimensional displays; Topology; unbalanced classification
• ISSN: 1534-4320; 1558-0210; 1558-0210
• DOI: 10.1109/TNSRE.2019.2943707

Epileptic seizures occur as a result of a process that develops over time and space in epileptic networks. In this study, we aim at developing a generalizable method for patient-specific seizure prediction by evaluating the spatio-temporal correlation in the features obtained from multichannel EEG s...