Editorial: Deep learning for neurological disorders in children

The emergence of DL-based approaches in studying pediatric neurological disorders while relying on high-dimensional data and computing capacity could lead to a better understanding of downstream pathways, more accurate diagnosis, and more efficient management plans. The developed DL-based classifiers utilized various data modalities, including behavioral assessment (Laria et al.), electroencephalography (EEG) (Abdelhameed and Bayoumi), functional magnetic resonance imaging (fMRI) (McNorgan; Da Silva et al.; (Almuqhim and Saeed), histopathological imaging (Attallah), and facial imaging (Hosseini et al.). Another interesting main facet of the contributions was the DL utilization for developing simulated neuronal models to aid a better understanding of epileptic seizures (Nemzer et al.) and automatic resolution enhancement of pediatric brain magnetic resonance imaging acquired in downsized time (Molina-Maza et al.).