Presentation
5 March 2021 Deep learning-based multiplexed virtual staining of unlabeled tissue for micro-structured stain blending
Author Affiliations +
Abstract
We virtually generate multiple histological stains through a single deep-neural-network, using at its input autofluorescence images of the unlabeled tissue alongside a user-defined digital-staining-matrix. By feeding this digital-staining-matrix to the network, the user indicates which stain to apply on each pixel or region-of-interest, enabling virtual blending of multiple stains according to a desired micro-structure map. We demonstrated this technique by applying combinations of different stains (H&E, Masson’s Trichrome and Jones silver stain) on blindly-tested, unlabeled tissue sections. This technology avoids the histochemical staining process and enables newly-generated stains and stain-combinations to be used for inspection of label-free tissue microstructure.
Conference Presentation
© (2021) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Kevin De Haan, Yijie Zhang, Yair Rivenson, Jingxi Li, and Aydogan Ozcan "Deep learning-based multiplexed virtual staining of unlabeled tissue for micro-structured stain blending", Proc. SPIE 11655, Label-free Biomedical Imaging and Sensing (LBIS) 2021, 116550A (5 March 2021); https://doi.org/10.1117/12.2579426
Advertisement
Advertisement
KEYWORDS
Tissues

Multiplexing

Neural networks

Chemical analysis

Inspection

Silver

Standards development

Back to Top