Simple and Robust Deep Learning Approach for Fast Fluorescence Lifetime Imaging

Abstract

Fluorescence lifetime imaging (FLIM) is a powerful tool that provides unique quantitative information for biomedical research. In this study, we propose a multi-layer-perceptron-based mixer (MLP-Mixer) deep learning (DL) algorithm named FLIM-MLP-Mixer for fast and robust FLIM analysis. The FLIM-MLP-Mixer has a simple network architecture yet a powerful learning ability from data. Compared with the traditional fitting and previously reported DL methods, the FLIM-MLP-Mixer shows superior performance in terms of accuracy and calculation speed, which has been validated using both synthetic and experimental data. All results indicate that our proposed method is well suited for accurately estimating lifetime parameters from measured fluorescence histograms, and it has great potential in various real-time FLIM applications.

Quantification of blood flow index in diffuse correlation spectroscopy using a robust deep learning method

“…We used DCS-NET to analyze the ACFs generated from MCX. The proposed network is based on 1DCNN, 43 which is straightforward, quicker to train, and faster than high-dimension CNNs for time sequence analysis, such as FLIM data 43 , 60 . To evaluate DCS-NET, we compared it with the semi-infinite, three-layer fitting methods by changing tissue optical properties (μa and μs′), depths (related to ρ), and scalp/skull thicknesses (Δ1 and Δ2).…”

Deep‐learning FRET visualization in flow cytometry: At the cross road of the signaling and FRET pathways

“…As to their architectures, they are comprised of several nested convolutions—that is, a stacked composition of a series of convolutions—completed with a conventional ANN. Recently several CNN‐based fast (real‐time) and robust FLIM analysis approaches have been developed [7–11]. With the conventional FLIM analysis methods like those based on, for example, nonlinear least‐squares, maximum likelihood and Bayesian estimations, or phasors, analysis is done mainly off‐side, after data registration.…”

“…Such methods start to become quite widespread today. They are called collectively as "artificial intelligence" techniques, referring mainly to "deep-learning," (or "soft computing," "machine-vision"), and "reduction of dimensionality" [5][6][7][8][9][10][11].…”