No abstract

Imaging Fluorescence Correlation Spectroscopy (Imaging FCS) is a powerful tool to extract information on molecular mobilities, actions and interactions in live cells, tissues and organisms. Nevertheless, several limitations restrict its applicability. First, FCS is data hungry, requiring 50,000 frames at 1 ms time resolution to obtain accurate parameter estimates. Second, the data size makes evaluation slow. Thirdly, as FCS evaluation is model-dependent, data evaluation is significantly slowed unless analytic models are available. Here we introduce two convolutional neural networks (CNNs) — FCSNet and ImFCSNet — for correlation and intensity trace analysis, respectively. FCSNet robustly predicts parameters in 2D and 3D live samples. ImFCSNet reduces the amount of data required for accurate parameter retrieval by at least one order of magnitude and makes correct estimates even in moderately defocused samples. Both CNNs are trained on simulated data, are model-agnostic, and allow autonomous, real-time evaluation of Imaging FCS measurements.

No abstract

No abstract

Modern EMCCD and sCMOS cameras read out fluorescence data with single-molecule sensitivity at a rate of thousands of frames per second. Exploiting these capabilities in full requires data evaluation in real-time. The direct camera-read-out tool presented here allows access to the data while the camera is recording. This provides simplified and accurate alignment procedures for Total Internal Reflection and Light Sheet Fluorescence Microscopy (TIRFM, LSFM), and simplifies and accelerates fluorescence experiments. The tool handles a range of widely used EMCCD and sCMOS cameras and uses imaging Fluorescence Correlation Spectroscopy (imaging FCS) for its evaluation. It is easily extendable to other camera models and other techniques and is a base for automated TIRMF and LSFM data acquisition.