Probing Brain Asymmetry: Computational and Data-Driven Approaches

Brain asymmetry — the structural and functional specialization of the left and right cerebral hemispheres — is one of the most fundamental organizing principles of the human brain. From language dominance and handedness to emotion regulation and spatial cognition, hemispheric lateralization shapes nearly every aspect of human behavior. Disruptions to typical asymmetry patterns have been implicated in a range of neurological and psychiatric conditions, including schizophrenia, autism spectrum disorder, dyslexia, and depression, making it a critical target for both basic and translational neuroscience research.Despite decades of investigation, our understanding of brain asymmetry remains incomplete. Traditional neuroimaging approaches have been limited by small sample sizes, inconsistent analytical methods, and an inability to capture the full complexity of lateralization across brain regions, developmental stages, and clinical populations. The rapid advancement of artificial intelligence — including deep learning, graph neural networks, and large-scale data-driven modeling — now offers unprecedented tools to probe brain asymmetry with greater sensitivity, reproducibility, and scalability than ever before. AI also opens up the possibility of computationally modeling brain lateralization itself. In parallel, the availability of large-scale datasets including thousands of individuals from multiple developmental stages enables robust characterization of brain lateralization patterns through diverse methodological approaches—including multivariate statistics, geometric morphometrics, network-based analyses, and Bayesian modeling—to complement AI-driven methods and better understand the intricacies of hemispheric specialization.This Research Topic invites contributions that leverage AI and machine learning methods to advance our understanding of brain lateralization across the lifespan and across health and disease. We welcome original research, reviews, and methodological articles addressing, but not limited to, the following themes:- AI-driven detection, quantification, and modeling of structural and functional brain asymmetry- Deep learning approaches to lateralization in large-scale neuroimaging datasets (e.g., UK Biobank, HCP, ABCD)- Brain asymmetry as a biomarker in neurological and psychiatric disorders- Developmental trajectories of hemispheric specialization using AI- Sex, handedness, and genetic influences on brain lateralization- Multimodal integration (MRI, fMRI, EEG, PET) for asymmetry analysis- Explainability and interpretability of AI models in lateralization research- Statistical and computational modeling of lateralization patterns across populations and developmental stages- Mathematical and multivariate approaches to quantifying brain asymmetry (e.g., structural covariance, graph-theoretic, geometric morphometric methods)By bringing together experts in neuroimaging, computational neuroscience, and AI, this Research Topic aims to catalyze a new wave of discoveries in brain asymmetry research and accelerate the translation of findings into clinical applications. Topic editors: Xiang-Zhen Kong, Amaia Carrión-Castillo, Suyu Zhong, Clyde Francks Source: https://www.frontiersin.org/research-topics/83871/probing-brain-asymmetry-computational-and-data-driven-approaches