Preprint Highlight: Real-time denoising of fluorescence time-lapse imaging enables high-sensitivity observations of biological dynamics beyond the shot-noise limit.

Abstract

Denoising in fluorescence imaging is a key technology to boost sensitivity and detect low signals buried in noise. While previous deep learning-based algorithms have been demonstrated to improve denoising quality, their application has been limited by the time-consuming processing step. This study demonstrates a much faster deep learning-based denoising algorithm, DeepCAD-RT, that enables real-time processing of fluorescence live cell images and can be incorporated into the data acquisition pipeline of a microscopy system. In addition to its obvious advantage in improving workflow efficiency, DeepCAD-RT could also have an impact on robotics technologies, such as automatic microinjection and cell picking, that require highly sensitive and real-time recognition of cells under a microscope.