Neuroimaging techniques such as fMRI, EEG, and MEG, alongside behavioral data, have provided invaluable insights into the neural mechanisms underlying cognitive processes. However, challenges remain in processing and interpreting multimodal data, particularly when integrating information across diverse brain regions, time scales, and tasks. Advances in artificial intelligence (AI), particularly generative AI techniques, have opened new pathways for overcoming these challenges. AI-driven approaches have shown promise in enhancing the resolution, accuracy, and interpretability of neuroimaging data, enabling the discovery of novel biomarkers for cognitive states and disorders. This research topic aims to explore how AI can further improve our understanding of brain-behavior relationships during cognitive tasks.
The goal of this Research Topic is to provide an overview of recent advancements in AI techniques for processing, integrating, and interpreting neuroimaging and behavioral data in cognitive neuroscience. Despite significant progress in the field, the complexity and heterogeneity of cognitive tasks require innovative methods to bridge the gap between different types of data. AI-enabled approaches hold great potential to enhance the sensitivity of neuroimaging in detecting subtle brain-behavior interactions, facilitate real-time monitoring of cognitive tasks, and ultimately contribute to better diagnostics and treatment strategies for neurocognitive disorders. In this special issue, we aim to highlight cutting-edge methodologies, including AI models for multimodal data integration, transfer learning, and explainability, with a focus on their application in cognitive neuroscience and psychology.
This Research Topic will cover the application of AI techniques to neuroimaging data (e.g., fMRI, EEG, PET, MEG) and behavioral data, with a particular focus on cognitive tasks and resting states that reveal underlying brain activity. We invite contributions that discuss AI-enabled solutions for integrating neuroimaging data across modalities, improving the interpretability of complex datasets, and linking neural signals to cognitive behavior. We are interested in original research, reviews, and methodological papers that explore themes such as AI for real-time neuroimaging analysis, cross-modal data fusion, predictive modeling of cognitive states, and applications in both healthy and clinical populations. Authors are encouraged to submit manuscripts that propose new models, algorithms, or applications within these areas, as well as those that critically assess current trends and challenges in the field.
Keywords: Generative AI, Neuroimages, Behaviours, Multimodality, Explainability
Important note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.
