Rapid Fluorescence Lifetime Imaging for Live Cells and Retinal Endogenous Fluorophores

Fluorescence lifetime imaging microscopy (FLIM) is a powerful tool to quantify molecular compositions and study molecular states in the complex cellular environment as the lifetime readings are not biased by fluorophore concentration or excitation power. However, the current methods to generate FLIM images are either computationally intensive or unreliable when the number of photons acquired at each pixel is low. Here we introduce a new deep learning-based method termed flimGANE that can generate fast, fit-free, precise, and high-quality FLIM images even under the photon-starved conditions (80-200 photon counts per pixel).