Brain imaging technologies (e.g., MRI, PET, advanced microscopy) are foundational tools for deciphering the brain's anatomical organization. However, the inherent complexity, high dimensionality, and heterogeneity of neuroanatomical data pose substantial challenges to in-depth analysis. Traditional approaches can struggle to quantify subtle structural variations and fully map the intricate connectivity patterns hidden within these datasets.

Artificial General Intelligence (AGI) is emerging as a transformative force in quantitative neuroanatomy. With its ability to autonomously learn, reason, and generalize from multi-modal data, AGI can serve as an unparalleled analytical engine. It can excavate complex patterns in connectivity, cytoarchitecture, and even subcellular organization, holding immense promise for advancing our understanding of the brain's structural design in both healthy and pathological states. Nevertheless, integrating AGI into neuroanatomical research is still in an exploratory stage, facing challenges in model interpretability, data standardization, and bridging the gap between computational innovation and fundamental anatomical investigation.

Hosted by Frontiers in Neuroanatomy, this Research Topic aims to showcase cutting-edge advances in how Artificial General Intelligence (AGI) is empowering neuroanatomical analysis. We are interested in the full spectrum of applications, from mapping large-scale circuits to identifying subtle cellular alterations. The goal is to facilitate interdisciplinary collaborations among neuroanatomists, computer scientists, and physicists to develop and validate innovative AGI-based methodologies.

The core objective is to promote novel computational methods for quantitative anatomical analysis that deepen our understanding of the brain's design principles. By accelerating the synergy between AGI and neuroanatomy, this Topic endeavors to establish a high-quality academic platform that will contribute to fundamental breakthroughs in neuroscience.

We invite submissions of original research, reviews, and perspective articles on topics including, but not limited to:

• AGI frameworks and algorithms tailored for processing complex neuroanatomical data (e.g., denoising, segmentation, registration of high-resolution imaging).
• AGI-driven identification and classification of neuroanatomical phenotypes in brain disorders (e.g., altered connectivity in neurodegeneration, cytoarchitectural changes near tumors).
• AGI-driven discovery of novel structural and connectivity-based biomarkers to elucidate the anatomical progression of brain diseases.
• Interpretable AGI models for brain imaging analysis that enhance anatomical and biological interpretability.
• Integration of AGI with multi-modal imaging and data types (e.g., tractography, electron microscopy, scRNA-seq) to build comprehensive anatomical atlases.
• Validation studies comparing AGI-based anatomical findings with classical histological and pathological evidence.
• Challenges and solutions in applying AGI to neuroanatomy (e.g., data scarcity, cross-cohort generalization, and standardization for large-scale anatomical studies).
• AGI-facilitated analysis correlating imaging-derived anatomical features with molecular and genetic data (e.g., from protein or gene expression patterns).
• AGI-enabled neuroanatomical analysis for Brain-Computer Interfaces (BCI) (i.e., decoding anatomical correlates of neural signals, mapping motor/sensory/cognitive related brain connectivity, deciphering structural principles of neural information transmission)

Are you interested in contributing a manuscript to this Research Topic?

Artificial General Intelligence Empowers Brain Imaging Analysis: from Diagnosis to Pathogenesis