Mohamed Radwan

This paper develops an EEG-based graph model using frequency-resolved connectivity features to classify Alzheimer's and frontotemporal dementia against healthy controls, achieving competitive accuracy.

This paper introduces concept bottleneck models for EEG pathology detection, showing comparable performance to black-box models but with interpretability trade-offs.

This study uses dynamic graph neural networks to classify EEG signals and analyze temporal changes in brain connectivity for epilepsy and healthy subject differentiation.

This paper uses graph neural networks to classify EEG signals for Frontotemporal Dementia, achieving 76% accuracy with saliency maps highlighting key brain regions and frequency bands.