Practical sensorless aberration estimation for 3D microscopy with deep learning
This addresses a practical limitation in sensorless adaptive optics for microscopy researchers, enabling accurate aberration estimation without difficult-to-obtain experimental training data, though it builds incrementally on existing deep learning approaches.
The researchers tackled the problem of estimating optical aberrations in 3D microscopy without requiring ground truth experimental data for training, by demonstrating that neural networks trained only on simulated data can accurately predict aberrations from real experimental images, achieving results comparable to non-learned methods across two microscopy modalities.
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.