System- and Sample-agnostic Isotropic 3D Microscopy by Weakly Physics-informed, Domain-shift-resistant Axial Deblurring

TL;DR

SSAI-3D is a novel framework for robust, system- and sample-agnostic 3D microscopy that effectively addresses axial deblurring challenges in heterogeneous tissues by leveraging weak physics-informed training and domain-shift resistance.

Contribution

It introduces SSAI-3D, a weakly physics-informed, domain-shift-resistant approach for isotropic 3D imaging that adapts to unknown blurring and noise across different microscopy systems.

Findings

Successfully applied to imaging of living organoids and human tissues.

Validated on publicly available datasets with unknown blurring and noise.

Achieved robust axial deblurring across diverse biological samples.

Abstract

Three-dimensional (3D) subcellular imaging is essential for biomedical research, but the diffraction limit of optical microscopy compromises axial resolution, hindering accurate 3D structural analysis. This challenge is particularly pronounced in label-free imaging of thick, heterogeneous tissues, where assumptions about data distribution (e.g. sparsity, label-specific distribution, and lateral-axial similarity) and system priors (e.g. independent and identically distributed (i.i.d.) noise and linear shift-invariant (LSI) point-spread functions (PSFs)) are often invalid. Here, we introduce SSAI-3D, a weakly physics-informed, domain-shift-resistant framework for robust isotropic 3D imaging. SSAI-3D enables robust axial deblurring by generating a PSF-flexible, noise-resilient, sample-informed training dataset and sparsely fine-tuning a large pre-trained blind deblurring network. SSAI-3D was applied to label-free nonlinear imaging of living organoids, freshly excised human endometrium tissue, and mouse whisker pads, and further validated in publicly available ground-truth-paired experimental datasets of 3D heterogeneous biological tissues with unknown blurring and noise across different microscopy systems.