Review of Deep Learning Models With Spiking Neural Networks for Modeling and Analysis of Multimodal Neuroimaging Data

Abstract

Medical imaging has become an essential tool for identifying and treating neurological conditions. Traditional deep learning (DL) models have made tremendous advances in neuroimaging analysis; however, they face difficulties when modeling complicated spatiotemporal brain data. Spiking Neural Networks (SNNs), which are inspired by real neurons, provide a promising option for efficiently processing spatiotemporal data. This review discusses current improvements in using SNNs for multimodal neuroimaging analysis. Quantitative and thematic analyses were conducted on 21 selected publications to assess trends, research topics, and geographical contributions. Results show that SNNs outperform traditional DL approaches in classification, feature extraction, and prediction tasks, especially when combining multiple modalities. Despite their potential, challenges of multimodal data fusion, computational demands, and limited large-scale datasets persist. We discussed the growth of SNNs in analysis, prediction, and diagnosis of neurological data, along with the emphasis on future direction and improvements for more efficient and clinically applicable models.