Deep Learning-Augmented Stimulated Raman Imaging for Cell-Type-Specific Metabolic Profiling in Live Neuronal Cocultures.
- 1Division of Chemistry and Chemical Engineering, California Institute of Technology, Pasadena, California 91125, United States.
Abstract
Neuronal metabolism is fundamental to brain functions and diseases, yet its spatial and temporal dynamics and interactions remain poorly understood. Here, we introduce a tandem deep-learning approach integrated with bioorthogonal chemical imaging using stimulated Raman scattering (SRS) microscopy. This method achieves high-speed and quantitative metabolic profiling in live neuronal cocultures. Our deep-learning framework consists of a recurrent convolutional neural network (RCNN) that enables high-resolution 3D imaging with minimal photodamage and a U-Net segmentation model for cell-type-specific metabolic analysis. Using deuterium-labeled metabolites, we demonstrate the ability to trace lipid, protein, glucose, and D2O metabolism in live neurons, astrocytes, and oligodendrocytes under physiological and pathological conditions, including NMDA receptor activation, proteasome inhibition, and Huntington's disease. Our findings reveal distinct metabolic adaptations among neuronal cell types and underscore the importance of noninvasive metabolic profiling for understanding neuronal interactions and disease mechanisms. This platform significantly advances live-cell dynamic imaging with broad applications in neuroscience, disease modeling, and therapeutic screening.
Related
- Monitoring Py8119 breast cancer cell proliferation in direct cocultures with osteoblasts and osteoclasts
- Impaired Brain Astrocytic Glycolysis in Neuropathic Pain: Insights from Transcriptomic Profiling to Metabolic Intervention
- Multi-Omic Profiling Defines the Renal Mechanisms of Cardiovascular-Kidney-Metabolic Syndrome in Pulmonary Arterial Hypertension
- Quantitative Delineation of the Morphological Heterogeneity of Anisotropic Nanostructures via Machine-Learning-Augmented Electron Microscopy.
- Salivary ¹H NMR metabolic profiling of diabetic patients with and without periodontitis: an exploratory pilot study.
BibTeX
@article{lin2026deep,
title = {{Deep Learning-Augmented Stimulated Raman Imaging for Cell-Type-Specific Metabolic Profiling in Live Neuronal Cocultures.}},
author = {Li-En Lin and Xiaotian Bi and Adrian Colazo and Haomin Wang and Lu Wei},
journal = {Chemical \& biomedical imaging},
year = {2026},
month = may,
doi = {10.1021/cbmi.6c00011},
url = {https://europepmc.org/article/MED/42953710},
note = {CC BY-NC-ND},
}
RIS
TY - JOUR
TI - Deep Learning-Augmented Stimulated Raman Imaging for Cell-Type-Specific Metabolic Profiling in Live Neuronal Cocultures.
AU - Li-En Lin
AU - Xiaotian Bi
AU - Adrian Colazo
AU - Haomin Wang
AU - Lu Wei
PY - 2026
DA - 2026/05/28
JO - Chemical & biomedical imaging
DO - 10.1021/cbmi.6c00011
UR - https://europepmc.org/article/MED/42953710
AB - Neuronal metabolism is fundamental to brain functions and diseases, yet its spatial and temporal dynamics and interactions remain poorly understood. Here, we introduce a tandem deep-learning approach integrated with bioorthogonal chemical imaging using stimulated Raman scattering (SRS) microscopy. This method achieves high-speed and quantitative metabolic profiling in live neuronal cocultures. Our deep-learning framework consists of a recurrent convolutional neural network (RCNN) that enables high-resolution 3D imaging with minimal photodamage and a U-Net segmentation model for cell-type-specific metabolic analysis. Using deuterium-labeled metabolites, we demonstrate the ability to trace lipid, protein, glucose, and D2O metabolism in live neurons, astrocytes, and oligodendrocytes under physiological and pathological conditions, including NMDA receptor activation, proteasome inhibition, and Huntington's disease. Our findings reveal distinct metabolic adaptations among neuronal cell types and underscore the importance of noninvasive metabolic profiling for understanding neuronal interactions and disease mechanisms. This platform significantly advances live-cell dynamic imaging with broad applications in neuroscience, disease modeling, and therapeutic screening.
SN - 2832-3637
ER -