Fourier-based three-dimensional multistage transformer for aberration correction in multicellular specimens
Open Access
- 1 October 2025
- journal article
- research article
- Published by Springer Nature in Nature Methods
- Vol. 22 (10) , 2171-2179
Abstract
High-resolution tissue imaging is often compromised by sample-induced optical aberrations that degrade resolution and contrast. Although wavefront sensor-based adaptive optics (AO) can measure these aberrations, such hardware solutions are typically complex, expensive to implement and slow when serially mapping spatially varying aberrations across large fields of view. Here we introduce AOViFT (adaptive optical vision Fourier transformer)—a machine learning-based aberration sensing framework built around a three-dimensional multistage vision transformer that operates on Fourier domain embeddings. AOViFT infers aberrations and restores diffraction-limited performance in puncta-labeled specimens with substantially reduced computational cost, training time and memory footprint compared to conventional architectures or real-space networks. We validated AOViFT on live gene-edited zebrafish embryos, demonstrating its ability to correct spatially varying aberrations using either a deformable mirror or postacquisition deconvolution. By eliminating the need for the guide star and wavefront sensing hardware and simplifying the experimental workflow, AOViFT lowers technical barriers for high-resolution volumetric microscopy across diverse biological samples.Keywords
All Related Versions
Funding Information
- Howard Hughes Medical Institute
- Lawrence Berkeley National Laboratory (7647437)
- Lawrence Berkeley National Laboratory (7721359)
- Lawrence Berkeley National Laboratory (7647437)
- Lawrence Berkeley National Laboratory (7721359)
- Center for Information Technology (R35GM118149)
- Center for Information Technology (1R01DC021710)
- Center for Information Technology (1R01DC021710)
- Center for Information Technology (1R01DC021710)
- Center for Information Technology (R35GM118149)
- Center for Information Technology (1R01DC021710)
- Alexander von Humboldt-Stiftung
This publication has 36 references indexed in Scilit:
- A Cell Observatory to reveal the subcellular foundations of lifeNature Methods, 2024
- Universal adaptive optics for microscopy through embedded neural network controlLight: Science & Applications, 2023
- Deep learning-driven adaptive optics for single-molecule localization microscopyNature Methods, 2023
- Deep learning-based adaptive optics for light sheet fluorescence microscopyBiomedical Optics Express, 2023
- Adaptive optics for optical microscopy [Invited]Biomedical Optics Express, 2023
- Practical sensorless aberration estimation for 3D microscopy with deep learningOptics Express, 2020
- Membrane dynamics of dividing cells imaged by lattice light-sheet microscopyMolecular Biology of the Cell, 2016
- Rapid adaptive optical recovery of optimal resolution over large volumesNature Methods, 2014
- Generalized phase diversity for wave-front sensingOptics Letters, 2004
- Phase‐retrieved pupil functions in wide‐field fluorescence microscopyJournal of Microscopy, 2004