T cell differentiation has warranted intense study to understand the mechanisms behind the adaptive immune system. While much of the research so far has relied on antibody staining and flow cytometry separation to isolate and study T cells, we present hyperspectral stimulated Raman scattering (SRS) microscopy as a potential label-free imaging method to directly observe and characterize T cells. We show that a deep learning model can be trained to identify and classify T cell differentiations from hyperspectral SRS images with 99% accuracy. We also show that fluorescent T cells in lymph node tissue can be predicted from SRS images, demonstrating potential towards an entirely label-free in-situ imaging strategy. SRS microscopy augmented with deep learning shows strong promise towards label-free in situ observation of T Cells.
In recent studies, stimulated Raman scattering (SRS) and transient absorption microscopy (TAM) have been employed for label-free mapping of biomolecules (e.g., proteins and lipids) in brain tissues and hemoglobin in red blood cells, respectively. In this study, we combined SRS and TAM to simultaneously image cell densities and capillary structure in vivo at the highest reported imaging depth, ~300 µm, for either technique. This multimodal approach resulted in label-free identification of endothelial cells and pericytes in vivo with 90% accuracy using a machine learning classifier. Simultaneous two-photon excited fluorescence microscopy serving as the ground truth.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.