Self-supervised denoising of dynamic fluorescence images via temporal gradient-empowered deep learning

Abstract

Fluorescence microscopy has become one of the most widely employed in vivo imaging modalities, enabling the discovery of new biopathological mechanisms. However, the application of fluorescence imaging is often hindered by signal-to-noise ratio issues owing to inherent noise arising from various systemic and biophysical characteristics. These limitations pose a growing challenge, especially with the desire to elucidate dynamic biomechanisms at previously unreachable rapid speeds. Here, we propose a temporal gradient (TG)-based self-supervised denoising network (TeD) that could enable an unprecedented advance in spatially dynamic fluorescence imaging. Our strategy is predicated on the insight that judicious utilization of spatiotemporal information is more advantageous for denoising predictions. Adopting the TG, which intrinsically embodies spatial dynamic features, enables TeD to prudently focus on spatiotemporal information. We showed that TeD can provide new interpretative opportunities for understanding dynamic fluorescence signals in in vivo imaging of mice, representing cellular flow. Furthermore, we demonstrated that TeD is robust even when fluorescence signals exhibit temporal kinetics without spatial dynamics, as seen in neuronal population imaging. We believe that TeD’s superior performance even with spatially dynamic samples, including the complex behavior of cells or organisms, could make a substantial contribution to various biological studies.