Semi-Blind Spatially-Variant Deconvolution in Optical Microscopy with Local Point Spread Function Estimation By Use Of Convolutional Neural Networks

TL;DR

This paper introduces a semi-blind, spatially-variant deconvolution method for optical microscopy that uses CNN-based local PSF estimation combined with a regularized Richardson-Lucy algorithm, improving image quality.

Contribution

It proposes a novel semi-blind deconvolution approach that integrates CNN-based local PSF estimation with spatially-variant deconvolution for microscopy images.

Findings

Achieved 1.00 dB average SNR improvement over other methods.

Successfully deconvolved synthetic and real microscopy data.

Demonstrated computationally feasible local PSF estimation.

Abstract

We present a semi-blind, spatially-variant deconvolution technique aimed at optical microscopy that combines a local estimation step of the point spread function (PSF) and deconvolution using a spatially variant, regularized Richardson-Lucy algorithm. To find the local PSF map in a computationally tractable way, we train a convolutional neural network to perform regression of an optical parametric model on synthetically blurred image patches. We deconvolved both synthetic and experimentally-acquired data, and achieved an improvement of image SNR of 1.00 dB on average, compared to other deconvolution algorithms.