In vivo neuropil density from anatomical MRI and machine learning
Cerebral Cortex · 2024
DOI: 10.1093/cercor/bhae200 ↗Kurz gefasst
Fachartikel in der Zeitschrift Cerebral Cortex, 2024. Verfasst von Adil Akif und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Biomedical Engineering, Yale University, 55 Prospect St, New Haven, CT 06511, United States. Hauptthemen laut MEDLINE: Machine Learning, Magnetic Resonance Imaging, Neuropil, Brain. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 36 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: Alzheimer's Disease Neuroimaging Initiative, DOD ADNI, Alzheimer's Association.
Abstract (Originalsprache)
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.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Biomedical Engineering, Yale University, 55 Prospect St, New Haven, CT 06511, United States.
- Department of Radiology and Biomedical Imaging, Yale University, 300 Cedar St, New Haven, CT 06520, United States.
- Department of Electrical Engineering, Yale University, 17 Hillhouse Ave, New Haven, CT 06511, United States.
- Magnetic Resonance Research Center, Yale University, 300 Cedar St, New Haven, CT 06520, United States.
- Research Institute of Intelligent and Complex Systems, State Key Laboratory of Medical Neurobiology and MOE Frontiers Center for Brain Science, Institute of Science and Technology for Brain-Inspired Intelligence, 220 Ha…
Förderung
- Alzheimer's Disease Neuroimaging Initiative
- DOD ADNI
- Alzheimer's Association
- BioClinica, Inc
- CereSpir, Inc.
- AbbVie
- NIDDK NIH HHS
- Cogstate
Zitieren
APA
Akif, A., Staib, L., Herman, P., Rothman, D. L., Yu, Y., & Hyder, F. (2024). In vivo neuropil density from anatomical MRI and machine learning. Cerebral Cortex. https://doi.org/10.1093/cercor/bhae200
Vancouver
Akif A, Staib L, Herman P, Rothman DL, Yu Y, Hyder F. In vivo neuropil density from anatomical MRI and machine learning. Cerebral Cortex. 2024. doi:10.1093/cercor/bhae200
BibTeX
@article{Akif2024,
author = {Akif, Adil and Staib, Lawrence and Herman, Peter and Rothman, Douglas L and Yu, Yuguo and Hyder, Fahmeed},
title = {In vivo neuropil density from anatomical MRI and machine learning},
journal = {Cerebral Cortex},
year = {2024},
doi = {10.1093/cercor/bhae200}
}
EUVIMED