Coordinate-based neural representations for computational adaptive optics in widefield microscopy
arXiv:2307.03812 · doi:10.1038/s42256-024-00853-3
Abstract
Widefield microscopy is widely used for non-invasive imaging of biological structures at subcellular resolution. When applied to complex specimen, its image quality is degraded by sample-induced optical aberration. Adaptive optics can correct wavefront distortion and restore diffraction-limited resolution but require wavefront sensing and corrective devices, increasing system complexity and cost. Here, we describe a self-supervised machine learning algorithm, CoCoA, that performs joint wavefront estimation and three-dimensional structural information extraction from a single input 3D image stack without the need for external training dataset. We implemented CoCoA for widefield imaging of mouse brain tissues and validated its performance with direct-wavefront-sensing-based adaptive optics. Importantly, we systematically explored and quantitatively characterized the limiting factors of CoCoA's performance. Using CoCoA, we demonstrated the first in vivo widefield mouse brain imaging using machine-learning-based adaptive optics. Incorporating coordinate-based neural representations and a forward physics model, the self-supervised scheme of CoCoA should be applicable to microscopy modalities in general.
60 pages, 20 figures, 2 tables. Nat Mach Intell (2024)
References in corpus (7)
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- Noise2Noise: Learning Image Restoration without Clean Data
- Diffraction tomography with a deep image prior
- Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representations
- Practical sensorless aberration estimation for 3D microscopy with deep learning
- Real-time multiframe blind deconvolution of solar images
- Accelerated deep self-supervised ptycho-laminography for three-dimensional nanoscale imaging of integrated circuits