A fundamental challenge in fluorescence microscopy is the photon shot noise arising from the inevitable stochasticity of photon detection. Noise increases measurement uncertainty and limits imaging resolution, speed and sensitivity. To achieve high-sensitivity fluorescence imaging beyond the shot-noise limit, we present DeepCAD-RT, a self-supervised deep learning method for real-time noise suppression. Based on our previous framework DeepCAD, we reduced the number of network parameters by 94%, memory consumption by 27-fold and processing time by a factor of 20, allowing real-time processing on a two-photon microscope. A high imaging signal-to-noise ratio can be acquired with tenfold fewer photons than in standard imaging approaches. We demonstrate the utility of DeepCAD-RT in a series of photon-limited experiments, including in vivo calcium imaging of mice, zebrafish larva and fruit flies, recording of three-dimensional (3D) migration of neutrophils after acute brain injury and imaging of 3D dynamics of cortical ATP release. DeepCAD-RT will facilitate the morphological and functional interrogation of biological dynamics with a minimal photon budget.

Fluorescence imaging with high signal-to-noise ratios has become the foundation of accurate visualization and analysis of biological phenomena. However, the inevitable noise poses a formidable challenge to imaging sensitivity. Here we provide the 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. Second, we designed a lightweight spatiotemporal transformer architecture to capture long-range dependencies and high-resolution features at low computational cost. SRDTrans can restore high-frequency information without producing oversmoothed 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 various imaging modalities and biological applications.

Widefield microscopy can provide optical access to multi-millimeter fields of view and thousands of neurons in mammalian brains at video rate. However, tissue scattering and background contamination results in signal deterioration, making the extraction of neuronal activity challenging, laborious and time consuming. Here we present our deep-learning-based widefield neuron finder (DeepWonder), which is trained by simulated functional recordings and effectively works on experimental data to achieve high-fidelity neuronal extraction. Equipped with systematic background contribution priors, DeepWonder conducts neuronal inference with an order-of-magnitude-faster speed and improved accuracy compared with alternative approaches. DeepWonder removes background contaminations and is computationally efficient. Specifically, DeepWonder accomplishes 50-fold signal-to-background ratio enhancement when processing terabytes-scale cortex-wide functional recordings, with over 14,000 neurons extracted in 17 h.

Fluorescence microscopy has become an indispensable tool for revealing the dynamic regulation of cells and organelles. However, stochastic noise inherently restricts optical interrogation quality and exacerbates observation fidelity when balancing the joint demands of high frame rate, long-term recording and low phototoxicity. Here we propose DeepSeMi, a self-supervised-learning-based denoising framework capable of increasing signal-to-noise ratio by over 12 dB across various conditions. With the introduction of newly designed eccentric blind-spot convolution filters, DeepSeMi effectively denoises images with no loss of spatiotemporal resolution. In combination with confocal microscopy, DeepSeMi allows for recording organelle interactions in four colors at high frame rates across tens of thousands of frames, monitoring migrasomes and retractosomes over a half day, and imaging ultra-phototoxicity-sensitive Dictyostelium cells over thousands of frames. Through comprehensive validations across various samples and instruments, we prove DeepSeMi to be a versatile and biocompatible tool for breaking the shot-noise limit.

Photon noise is one of the fundamental limits in fluorescence imaging. Despite broad applications, existing self-supervised denoising methods rely on either temporal redundancy or spatial redundancy, leading to degradation in either temporal resolution or spatial resolution, especially for 3D imaging. Here, we propose light field denoising (LF-denoising), a self-supervised transformer framework leveraging spatial-angular redundancy based on the high-dimensional light field measurements to achieve high-fidelity denoising without relying on temporal information and avoiding associated artefacts in spatial domain. We demonstrate the advantage of LF-denoising over previous methods in highly dynamic 3D imaging with both simulations and experimental data across different species. Combined with state-of-the-art light field microscopy variants, we achieve long-term high-speed high-resolution 3D intravital imaging on diverse animals including zebrafish, Drosophila and mice, with ultra-low excitation power of 10 μW/mm². Specifically, we show that LF-denoising well preserved the temporal causality with superior denoising performance, which is critical for quantitative biology analysis in immunology and neuroscience.