Presentation
13 March 2024 Antigen-independent single-cell phenotyping using biolaser
Author Affiliations +
Abstract
We introduce a novel, antigen-independent biolaser method to generate distinctive cellular signatures. Suspension of nucleic acid-stained cells is deposited into a Fabry-Perot cavity. The cells are excited by a pump laser at various power densities and the lasing signatures of these cells are collected. A neural network based on ResNet 34 is trained to detect and differentiate lasing patterns of CTCs from WBCs using the collected lasing signatures. This neural network structure is designed to be robust against inter-cavity discrepancies in laser cavities. We tested our system on detecting circulating pancreatic cancer cells from cell lines of T cells (Jurkat) and later spiked patient samples (filtered WBCs), from lasing cavities with uncharacterized Q factors. In both cases, we were able to differentiate the CTCs with an accuracy higher than 90%.
Conference Presentation
© (2024) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Weishu Wu, Sherman Fan, Sunitha Nagrath, Yu Zhang, and Xiaotian Tan "Antigen-independent single-cell phenotyping using biolaser", Proc. SPIE PC12846, Imaging, Manipulation, and Analysis of Biomolecules, Cells, and Tissues XXII, PC1284602 (13 March 2024); https://doi.org/10.1117/12.3001199
Advertisement
Advertisement
KEYWORDS
Cell phenotyping

White blood cells

Cancer detection

Neural networks

Tumors

Optical filters

Pancreatic cancer

Back to Top