FLIM data analysis based on laguerre polynomial decomposition and machine-learning
Guo S, Silge A, Bae H, Tolstik T, Meyer T, Matziolis G, Schmitt M, Popp J, Bocklitz T (2021)
Publication Type: Journal article
Publication year: 2021
Journal
Book Volume: 26
Article Number: 022909
Journal Issue: 2
DOI: 10.1117/1.JBO.26.2.022909
Abstract
FLIM data analysis based on laguerre polynomial decomposition and machine-learning (ML) was performed. It was proposed to extract the lifetimes and abundances directly from the decay traces through machine learning (ML). The ML-based approach was verified with simulated testing data in which the lifetimes and abundances were known exactly. Its performance was compared with the commercial software SPCImage based on datasets measured from biological samples on a time-correlated single photon counting system. The decay traces were reconstructed using the lifetime and abundance values estimated by ML and SPCImage methods and utilized the root-mean-squared-error (RMSE) as marker. The RMSE, which represented the difference between the reconstructed and measured decay traces, was observed to be lower for ML than for SPCImage. In addition, it was possible to demonstrate the high potential and flexibility of the ML method to deal with more than two lifetime components, with a three-component analysis.
Involved external institutions
Germany (DE)How to cite
APA:
Guo, S., Silge, A., Bae, H., Tolstik, T., Meyer, T., Matziolis, G.,... Bocklitz, T. (2021). FLIM data analysis based on laguerre polynomial decomposition and machine-learning. Journal of Biomedical Optics, 26(2). https://doi.org/10.1117/1.JBO.26.2.022909
MLA:
Guo, Shuxia, et al. "FLIM data analysis based on laguerre polynomial decomposition and machine-learning." Journal of Biomedical Optics 26.2 (2021).
BibTeX: Download