Spatial redundancy transformer for self-supervised fluorescence image denoising

Fluorescence imaging with high signal-to-noise ratios has become the foundation of accurate visualization and analysis of biological phenomena. However, the inevitable photon shot noise poses a formidable challenge on imaging sensitivity. In this paper, we provide a spatial redundancy denoising transformer (SRDTrans) to remove noise from fluorescence images in a self-supervised manner. First, a sampling strategy based on spatial redundancy is proposed to extract adjacent orthogonal training pairs, which eliminates the dependence on high imaging speed. Secondly, to break the performance bottleneck of convolutional neural networks (CNNs), we designed a lightweight spatiotemporal transformer architecture to capture long-range dependencies and high-resolution features at a low computational cost. SRDTrans can overcome the inherent spectral bias of CNNs and restore high-frequency information without producing over-smoothed structures and distorted fluorescence traces. Finally, we demonstrate the state-of-the-art denoising performance of SRDTrans on single-molecule localization microscopy and two-photon volumetric calcium imaging. SRDTrans does not contain any assumptions about the imaging process and the sample, thus can be easily extended to a wide range of imaging modalities and biological applications.