Recovering 3D phase features of complex biological samples traditionally sacrifices computational efficiency and processing time for physical model accuracy and reconstruction quality. Here, we overcome this challenge using an approximant-guided deep learning framework in a high-speed intensity diffraction tomography system. Applying a physics model simulator-based learning strategy trained entirely on natural image datasets, we show our network can robustly reconstruct complex 3D biological samples. To achieve highly efficient training and prediction, we implement a lightweight 2D network structure that utilizes a multi-channel input for encoding the axial information. We demonstrate this framework on experimental measurements of weakly scattering epithelial buccal cells and strongly scattering
We propose a novel intensity diffraction tomography (IDT) reconstruction algorithm based on the split-step non-paraxial (SSNP) model for recovering the 3D refractive index (RI) distribution of multiple-scattering biological samples. High-quality IDT reconstruction requires high-angle illumination to encode both low- and high- spatial frequency information of the 3D biological sample. We show that our SSNP model can more accurately compute multiple scattering from high-angle illumination compared to paraxial approximation-based multiple-scattering models. We apply this SSNP model to both sequential and multiplexed IDT techniques. We develop a unified reconstruction algorithm for both IDT modalities that is highly computationally efficient and is implemented by a modular automatic differentiation framework. We demonstrate the capability of our reconstruction algorithm on both weakly scattering buccal epithelial cells and strongly scattering live
- Award ID(s):
- 1846784
- NSF-PAR ID:
- 10370015
- Publisher / Repository:
- Optical Society of America
- Date Published:
- Journal Name:
- Optics Express
- Volume:
- 30
- Issue:
- 18
- ISSN:
- 1094-4087; OPEXFF
- Page Range / eLocation ID:
- Article No. 32808
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
more » « less
C. elegans worms. We benchmark the network’s performance against a state-of-the-art multiple-scattering model-based iterative reconstruction algorithm. We highlight the network’s robustness by reconstructing dynamic samples from a living worm video. We further emphasize the network’s generalization capabilities by recovering algae samples imaged from different experimental setups. To assess the prediction quality, we develop a quantitative evaluation metric to show that our predictions are consistent with both multiple-scattering physics and experimental measurements. -
null (Ed.)Intensity Diffraction Tomography (IDT) is a new computational microscopy technique providing quantitative, volumetric, large field-of-view (FOV) phase imaging of biological samples. This approach uses computationally efficient inverse scattering models to recover 3D phase volumes of weakly scattering objects from intensity measurements taken under diverse illumination at a single focal plane. IDT is easily implemented in a standard microscope equipped with an LED array source and requires no exogenous contrast agents, making the technology widely accessible for biological research.Here, we discuss model and learning-based approaches for complex 3D object recovery with IDT. We present two model-based computational illumination strategies, multiplexed IDT (mIDT) [1] and annular IDT (aIDT) [2], that achieve high-throughput quantitative 3D object phase recovery at hardware-limited 4Hz and 10Hz volume rates, respectively. We illustrate these techniques on living epithelial buccal cells and Caenorhabditis elegans worms. For strong scattering object recovery with IDT, we present an uncertainty quantification framework for assessing the reliability of deep learning-based phase recovery methods [3]. This framework provides per-pixel evaluation of a neural network predictions confidence level, allowing for efficient and reliable complex object recovery. This uncertainty learning framework is widely applicable for reliable deep learning-based biomedical imaging techniques and shows significant potential for IDT.more » « less
-
more » « less
Abstract Mapping 3D plasma membrane topology in live cells can bring unprecedented insights into cell biology. Widefield-based super-resolution methods such as 3D-structured illumination microscopy (3D-SIM) can achieve twice the axial ( ~ 300 nm) and lateral ( ~ 100 nm) resolution of widefield microscopy in real time in live cells. However, twice-resolution enhancement cannot sufficiently visualize nanoscale fine structures of the plasma membrane. Axial interferometry methods including fluorescence light interference contrast microscopy and its derivatives (e.g., scanning angle interference microscopy) can determine nanoscale axial locations of proteins on and near the plasma membrane. Thus, by combining super-resolution lateral imaging of 2D-SIM with axial interferometry, we developed multi-angle-crossing structured illumination microscopy (MAxSIM) to generate multiple incident angles by fast, optoelectronic creation of diffraction patterns. Axial localization accuracy can be enhanced by placing cells on a bottom glass substrate, locating a custom height-controlled mirror (HCM) at a fixed axial position above the glass substrate, and optimizing the height reconstruction algorithm for noisy experimental data. The HCM also enables imaging of both the apical and basal surfaces of a cell. MAxSIM with HCM offers high-fidelity nanoscale 3D topological mapping of cell plasma membranes with near-real-time ( ~ 0.5 Hz) imaging of live cells and 3D single-molecule tracking.
-
more » « less
We present a tomographic imaging technique, termed Deep Prior Diffraction Tomography (DP-DT), to reconstruct the 3D refractive index (RI) of thick biological samples at high resolution from a sequence of low-resolution images collected under angularly varying illumination. DP-DT processes the multi-angle data using a phase retrieval algorithm that is extended by a deep image prior (DIP), which reparameterizes the 3D sample reconstruction with an untrained, deep generative 3D convolutional neural network (CNN). We show that DP-DT effectively addresses the missing cone problem, which otherwise degrades the resolution and quality of standard 3D reconstruction algorithms. As DP-DT does not require pre-captured data or pre-training, it is not biased towards any particular dataset. Hence, it is a general technique that can be applied to a wide variety of 3D samples, including scenarios in which large datasets for supervised training would be infeasible or expensive. We applied DP-DT to obtain 3D RI maps of bead phantoms and complex biological specimens, both in simulation and experiment, and show that DP-DT produces higher-quality results than standard regularization techniques. We further demonstrate the generality of DP-DT, using two different scattering models, the first Born and multi-slice models. Our results point to the potential benefits of DP-DT for other 3D imaging modalities, including X-ray computed tomography, magnetic resonance imaging, and electron microscopy.
