Practical sensorless aberration estimation for 3D microscopy with deep learning

TL;DR

This paper presents a deep learning method for sensorless aberration estimation in 3D microscopy that trains on simulated data and performs well on real experimental images, validated across multiple modalities.

Contribution

It demonstrates that neural networks trained solely on simulated data can accurately predict aberrations in real microscopy images, reducing the need for ground truth data.

Findings

Neural networks trained on simulated data perform well on real images.

Wavefront symmetry influences aberration predictability.

Open source implementation provided for practical use.

Abstract

Estimation of optical aberrations from volumetric intensity images is a key step in sensorless adaptive optics for 3D microscopy. Recent approaches based on deep learning promise accurate results at fast processing speeds. However, collecting ground truth microscopy data for training the network is typically very difficult or even impossible thereby limiting this approach in practice. Here, we demonstrate that neural networks trained only on simulated data yield accurate predictions for real experimental images. We validate our approach on simulated and experimental datasets acquired with two different microscopy modalities, and also compare the results to non-learned methods. Additionally, we study the predictability of individual aberrations with respect to their data requirements and find that the symmetry of the wavefront plays a crucial role. Finally, we make our implementation freely available as open source software in Python.