Delayed brain development of Rolandic epilepsy profiled by deep learning-based neuroanatomic imaging

Objectives Although Rolandic epilepsy (RE) has been regarded as a brain developmental disorder, neuroimaging studies have not yet ascertained whether RE has brain developmental delay. This study employed deep learning-based neuroanatomic biomarker to measure the changed feature of brain age in RE. Methods The study constructed a 3D-CNN brain age prediction model through 1155 cases of typically developing children's morphometric brain MRI from open-source datasets and further applied to a local dataset of 167 RE patients and 107 typically developing children. The brain-predicted age difference was measured to quantitatively estimate brain age changes in RE and further investigated the relevancies with cognitive and clinical variables. Results The brain age estimation network model presented a good performance for brain age prediction in typically developing children. The children with RE showed a 0.45-year delay of brain age by contrast with typically developing children. Delayed brain age was associated with neuroanatomic changes in the Rolandic regions and also associated with cognitive dysfunction of attention. Conclusion This study provided neuroimaging evidence to support the notion that RE has delayed brain development.

Automated summary

This study utilized deep learning technology and neuroimaging to demonstrate delayed brain development in Rolandic epilepsy (RE), with children with RE showing a delay in brain age compared to typically developing children. This delay was associated with neuroanatomic changes in Rolandic regions and cognitive dysfunction in attention.