Isotropic 3D Microscopy

Overview

Axial deblurring with SSAI-3D

Three-dimensional subcellular imaging is essential for biomedical research, but the diffraction limit of optical microscopy compromises axial resolution, hindering accurate three-dimensional 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 noise and linear shift-invariant point-spread functions are often invalid). Here, we introduce SSAI-3D, a weakly physics-informed, domain-shift-resistant framework for robust isotropic three-dimensional imaging. SSAI-3D enables robust axial deblurring by generating a diverse, noise-resilient, sample-informed training dataset and sparsely fine-tuning a large pre-trained blind deblurring network. SSAI-3D is 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 three-dimensional heterogeneous biological tissues with unknown blurring and noise across different microscopy systems.

Highlights

Imaging: SSAI-3D as an axial deblurring methodology that is generalizable to diverse 3D imaging systems and 3D biological samples.
AI: A sparse fine-tuning methodology capable of leveraging features learned from large pre-trained models and customizing them to small domain-specific datasets.
Biology: Facilitates downstream biological analysis validated with publicly available ground-truth-paired experimental datasets with unknown system and sample properties.

Results

Mechanisms of sparse fine-tuning

Sparse fine-tuning leverages features learned from large pre-trained models and efficiently customizes them to out-of-distribution datasets.

Generalizability across real-life imaging

Generalizability across different systems and samples.

Validation with hardware-corrected isotropic imaging

Comparison of software-corrected (SSAI-3D) and hardware-corrected (mesoSPIM) axial image of mouse brain from light-sheet microscopy.

Comparison of software-corrected (SSAI-3D) and hardware-corrected (multiview confocal) axial image of mitochondria from confocal microscopy.

Three-dimensional subcellular imaging is essential for biomedical research, but the diffraction limit of optical microscopy compromises axial resolution, hindering accurate three-dimensional 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 noise and linear shift-invariant point-spread functions) are often invalid. Here, we introduce SSAI-3D, a weakly physics-informed, domain-shift-resistant framework for robust isotropic three-dimensional imaging. SSAI-3D enables robust axial deblurring by generating a diverse, noise-resilient, sample-informed training dataset and sparsely fine-tuning a large pre-trained blind deblurring network. SSAI-3D is 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 three-dimensional heterogeneous biological tissues with unknown blurring and noise across different microscopy systems.