Estimation of Optical Aberrations in 3D Microscopic Bioimages

TL;DR

This paper extends a neural network-based method to estimate and correct optical aberrations in 3D biological microscopy images, improving image quality through PSF prediction and deconvolution.

Contribution

It introduces an object-specific training approach for PhaseNet, enabling aberration estimation in complex biological samples, and combines this with image restoration techniques.

Findings

Enhanced aberration estimation in 3D biological images

Effective correction of simulated and real aberrations

Improved microscopic image quality after deconvolution

Abstract

The quality of microscopy images often suffers from optical aberrations. These aberrations and their associated point spread functions have to be quantitatively estimated to restore aberrated images. The recent state-of-the-art method PhaseNet, based on a convolutional neural network, can quantify aberrations accurately but is limited to images of point light sources, e.g. fluorescent beads. In this research, we describe an extension of PhaseNet enabling its use on 3D images of biological samples. To this end, our method incorporates object-specific information into the simulated images used for training the network. Further, we add a Python-based restoration of images via Richardson-Lucy deconvolution. We demonstrate that the deconvolution with the predicted PSF can not only remove the simulated aberrations but also improve the quality of the real raw microscopic images with unknown residual PSF. We provide code for fast and convenient prediction and correction of aberrations.