3DM: deep decomposition and deconvolution microscopy for rapid neural activity imaging

Decomposition-Estimation-Reconstruction: An Automatic and Accurate Neuron Extraction Paradigm

The extraction of spatiotemporal neuron activity from calcium imaging videos plays a crucial role in unraveling the coding properties of neurons. While existing neuron extraction approaches have shown promising results, disturbing and scattering background and unused depth still impede their performance. To address these limitations, we develop an automatic and accurate neuron extraction paradigm, dubbed as decomposition-estimation-reconstruction (DER), consisting of D-procedure, E-procedure, and R-procedure. Specifically, the D-procedure first decomposes the raw data into a low-rank background and a sparse neuron signal, and regularizes L0 -norm priors of intensity and gradient of the neuron signal to suppress blurring and artifact effects. Then, the E-procedure estimates the depth-dependent transmission of the neuron signal based on its bright and dark channel priors. The R-procedure finally integrates the depth estimation of the neuron signal as a content-importance weight into a constrained non-negative matrix decomposition framework, which facilitates accurate neuron locations to boost the quality of extracted neurons. These three procedures are coupled in a cascade manner, where the former copes with calcium imaging data to facilitate the subsequent one. Comprehensive experiments on neuron extraction from calcium imaging videos demonstrate the superiority of our DER paradigm in both qualitative results and quantitative assessments over state-of-the-art methods.

Statistically unbiased prediction enables accurate denoising of voltage imaging data

Here we report SUPPORT (statistically unbiased prediction utilizing spatiotemporal information in imaging data), a self-supervised learning method for removing Poisson-Gaussian noise in voltage imaging data. SUPPORT is based on the insight that a pixel value in voltage imaging data is highly dependent on its spatiotemporal neighboring pixels, even when its temporally adjacent frames alone do not provide useful information for statistical prediction. Such dependency is captured and used by a convolutional neural network with a spatiotemporal blind spot to accurately denoise voltage imaging data in which the existence of the action potential in a time frame cannot be inferred by the information in other frames. Through simulations and experiments, we show that SUPPORT enables precise denoising of voltage imaging data and other types of microscopy image while preserving the underlying dynamics within the scene.

Volumetric light sheet imaging with adaptive optics correction

Light sheet microscopy has developed quickly over the past decades and become a popular method for imaging live model organisms and other thick biological tissues. For rapid volumetric imaging, an electrically tunable lens can be used to rapidly change the imaging plane in the sample. For larger fields of view and higher NA objectives, the electrically tunable lens introduces aberrations in the system, particularly away from the nominal focus and off-axis. Here, we describe a system that employs an electrically tunable lens and adaptive optics to image over a volume of 499 × 499 × 192 μm3 with close to diffraction-limited resolution. Compared to the system without adaptive optics, the performance shows an increase in signal to background ratio by a factor of 3.5. While the system currently requires 7s/volume, it should be straightforward to increase the imaging speed to under 1s per volume.

Three-dimensional fluorescence microscopy through virtual refocusing using a recursive light propagation network

Three-dimensional fluorescence microscopy has an intrinsic performance limit set by the number of photons that can be collected from the sample in a given time interval. Here, we extend our earlier work - a recursive light propagation network (RLP-Net) - which is a computational microscopy technique that overcomes such limitations through virtual refocusing that enables volume reconstruction from two adjacent 2-D wide-field fluorescence images. RLP-Net employs a recursive inference scheme in which the network progressively predicts the subsequent planes along the axial direction. This recursive inference scheme reflects that the law of physics for the light propagation remains spatially invariant and therefore a fixed function (i.e., a neural network) for a short distance light propagation can be recursively applied for a longer distance light propagation. In addition, we employ a self-supervised denoising method to enable accurate virtual light propagation over a long distance. We demonstrate the capability of our method through high-speed volumetric imaging of neuronal activity of a live zebrafish brain. The source code used in the paper is available at https://github.com/NICALab/rlpnet.