Diffusion-MRI-Based Estimation of Cortical Architecture via Machine Learning (DECAM) in Primate Brains

The cerebral cortical cytoarchitecture underlying brain functions is reshaped across the lifespan and in various brain disorders. Accumulated evidence indicates it is important to disease biology. The cortical cytoarchitecture is conventionally accessible only through invasive neuropathological techniques. Diffusion MRI (dMRI) holds the potential to reveal whole-brain cytoarchitecture noninvasively. However, current dMRI signal models are constrained by simplified assumptions, which limit their ability to accurately quantify cortical architecture. Here, we present Diffusion-MRI-based Estimation of Cortical Architecture using Machine-learning (DECAM), a cutting-edge data-driven translational framework capable of accurately and directly mapping the heterogeneous, whole-brain soma density in primates. Leveraging high-resolution multi-shell dMRI and histological datasets of the non-human primate brain, the DECAM deep learning framework is optimized through a novel best response constraint. Cortical label vectors are developed to address dMRI-histology misregistration in primate brains with complex morphology. The DECAM framework is generalizable. It can be further extended for noninvasively estimating other neuropathological measures, such as neurite density, and extended for estimating neuropathological measures in human brains. DECAM generates high-fidelity, reproducible whole-brain soma density maps validated with histology and paves the way for noninvasive virtual histology for translational applications.