Off-The-Grid Covariance-Based Super-Resolution Fluctuation Microscopy

Laville, Bastien; Blanc‐Féraud, Laure; Aubert, Gilles

doi:10.1109/icassp43922.2022.9746845

Cited by 1 publication

(2 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For reconstructing filaments, a solution is to use a regularising term promoting curves. Such method is proposed, e.g., in [18] in an off-the-grid setting, but the numerical aspects are difficult and still under development. To overcome this limitation, in the following section, we propose a Plug-and-Play extension of the approach above where the proximal step is replaced by a denoiser D σ trained on an appropriate dataset of covariance images representing the geometrical structures of interest.…”

Section: Algorithm 1 Model-based and Pnp Support Estimationmentioning

confidence: 99%

“…This is particularly limiting when continuous curvilinear structures are desired, which is the case in several biological applications. For that, suitable regularisers can indeed be defined [18], with the major limitation of remaining tailored to particular shapes only. With the intent of developing a flexible regularisation approach suited to adapt to different geometries, we present in the following a data-driven optimization-inspired technique relying on the use of the so-called Plug-and-Play (PnP) approaches [31], which, over the last decade have been proved to represent an efficient framework for solving inverse image restoration problems, see [15] for a review.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Fluctuation-based deconvolution in fluorescence microscopy using plug-and-play denoisers

Stergiopoulou¹,

Mukherjee²,

Calatroni³

et al. 2023

Preprint

View full text Add to dashboard Cite

The spatial resolution of images of living samples obtained by fluorescence microscopes is physically limited due to the diffraction of visible light, which makes the study of entities of size less than the diffraction barrier (around 200 nm in the x-y plane) very challenging. To overcome this limitation, several deconvolution and super-resolution techniques have been proposed. Within the framework of inverse problems, modern approaches in fluorescence microscopy reconstruct a superresolved image from a temporal stack of frames by carefully designing suitable hand-crafted sparsity-promoting regularisers. Numerically, such approaches are solved by proximal gradient-based iterative schemes. Aiming at obtaining a reconstruction more adapted to sample geometries (e.g. thin filaments), we adopt a plug-and-play denoising approach with convergence guarantees and replace the proximity operator associated with the explicit image regulariser with an image denoiser (i.e. a pretrained network) which, upon appropriate training, mimics the action of an implicit prior. To account for the independence of the fluctuations between molecules, the model relies on second-order statistics. The denoiser is then trained on covariance images coming from data representing sequences of fluctuating fluorescent molecules with filament structure. The method is evaluated on both simulated and real fluorescence microscopy images, showing its ability to correctly reconstruct filament structures with high values of peak signal-to-noise ratio (PSNR).

show abstract

Section: Algorithm 1 Model-based and Pnp Support Estimationmentioning

confidence: 99%