Presentation
13 March 2024 Attention-based weakly-supervised deep learning for the identification and localization of drug fingerprints based on label-free hyperspectral CARS microscopy
Author Affiliations +
Abstract
Understanding drug fingerprints in complex biological samples is essential for drug development. We demonstrate a deep learning-assisted hyperspectral coherent anti-Stokes Raman scattering (HS-CARS) imaging approach for identifying drug fingerprints at single-cell resolution. The attention-based deep neural network, Hyperspectral Attention Net (HAN), highlights informative spatial and spectral regions in a weakly supervised manner. Using this approach, drug fingerprints of a hepatitis B virus therapy in murine liver tissues was investigated. Higher classification accuracy was observed with increasing drug dosage, reaching an average AUC of 0.942. Results demonstrate the potential for label-free profiling and localization of drug fingerprints in complex biological samples.
Conference Presentation
© (2024) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Jindou Shi, Kajari Bera, Prabuddha Mukherjee, Aneesh Alex, Eric J. Chaney, Bradley Spencer-Dene, Jan Majer, Marina Marjanovic, Darold R. Spillman Jr., Steve R. Hood, and Stephen A. Boppart "Attention-based weakly-supervised deep learning for the identification and localization of drug fingerprints based on label-free hyperspectral CARS microscopy", Proc. SPIE PC12821, Visualizing and Quantifying Drug Distribution in Tissue VIII, PC1282106 (13 March 2024); https://doi.org/10.1117/12.3001269
Advertisement
Advertisement
KEYWORDS
Microscopy

Deep learning

Biological samples

Complex systems

Nervous system

Nondestructive evaluation

Optical imaging

Back to Top