In vivo neuropil density from anatomical MRI and machine learning.

Brain energy budgets specify metabolic costs emerging from underlying mechanisms of cellular and synaptic activities. While current bottom-up energy budgets use prototypical values of cellular density and synaptic density, predicting metabolism from a person's individualized neuropil density would be ideal. We hypothesize that in vivo neuropil density can be derived from magnetic resonance imaging (MRI) data, consisting of longitudinal relaxation (T1) MRI for gray/white matter distinction and diffusion MRI for tissue cellularity (apparent diffusion coefficient, ADC) and axon directionality (fractional anisotropy, FA). We present a machine learning algorithm that predicts neuropil density from in vivo MRI scans, where ex vivo Merker staining and in vivo synaptic vesicle glycoprotein 2A Positron Emission Tomography (SV2A-PET) images were reference standards for cellular and synaptic density, respectively. We used Gaussian-smoothed T1/ADC/FA data from 10 healthy subjects to train an artificial neural network, subsequently used to predict cellular and synaptic density for 54 test subjects. While excellent histogram overlaps were observed both for synaptic density (0.93) and cellular density (0.85) maps across all subjects, the lower spatial correlations both for synaptic density (0.89) and cellular density (0.58) maps are suggestive of individualized predictions. This proof-of-concept artificial neural network may pave the way for individualized energy atlas prediction, enabling microscopic interpretations of functional neuroimaging data.

Switching of brain networks across different cerebral perfusion states: insights from EEG dynamic microstate analyses.

The alteration of neural interactions across different cerebral perfusion states remains unclear. This study aimed to fulfill this gap by examining the longitudinal brain dynamic information interactions before and after cerebral reperfusion. Electroencephalogram in eyes-closed state at baseline and postoperative 7-d and 3-month follow-ups (moyamoya disease: 20, health controls: 23) were recorded. Dynamic network analyses were focused on the features and networks of electroencephalogram microstates across different microstates and perfusion states. Considering the microstate features, the parameters were disturbed of microstate B, C, and D but preserved of microstate A. The transition probabilities of microstates A-B and B-D were increased to play a complementary role across different perfusion states. Moreover, the microstate variability was decreased, but was significantly improved after cerebral reperfusion. Regarding microstate networks, the functional connectivity strengths were declined, mainly within frontal, parietal, and occipital lobes and between parietal and occipital lobes in different perfusion states, but were ameliorated after cerebral reperfusion. This study elucidates how dynamic interaction patterns of brain neurons change after cerebral reperfusion, which allows for the observation of brain network transitions across various perfusion states in a live clinical setting through direct intervention.

Revealing neural dynamical structure of C. elegans with deep learning.

Caenorhabditis elegans serves as a common model for investigating neural dynamics and functions of biological neural networks. Data-driven approaches have been employed in reconstructing neural dynamics. However, challenges remain regarding the curse of high-dimensionality and stochasticity in realistic systems. In this study, we develop a deep neural network (DNN) approach to reconstruct the neural dynamics of C. elegans and study neural mechanisms for locomotion. Our model identifies two limit cycles in the neural activity space: one underpins basic pirouette behavior, essential for navigation, and the other introduces extra Ω turns. The combination of two limit cycles elucidates predominant locomotion patterns in neural imaging data. The corresponding energy landscape explains the switching strategies between two limit cycles, quantitatively, and provides testable predictions on neural functions and circuit roles. Our work provides a general approach to study neural dynamics by combining imaging data and stochastic modeling.