Net-FLICS: fast quantitative wide-field fluorescence lifetime imaging with compressed sensing – a deep learning approach by Ruoyang Yao, Marien Ochoa, Pingkun Yan, Xavier Intes.
Macroscopic fluorescence lifetime imaging (MFLI) via compressed sensed (CS) measurements enables efficient and accurate quantification of molecular interactions in vivo over a large field view (FOV). However, the current data-processing workflow is slow, complex performs poorly under photon-starved conditions. In this paper, we propose Net-FLICS, novel image reconstruction method based on convolutional neural network (CNN), to directly reconstruct intensity images from raw time-resolved CS data. By carefully designing simulated dataset, Net-FLICS successfully trained achieves outstanding performance both vitro experimental data even superior results at low photon count levels for quantification.
Read Net-FLICS: fast quantitative wide-field fluorescence lifetime imaging with compressed sensing – a deep learning approach on OA.mg