An official website of the United States government
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 C. elegans worms and live C. elegans embryos.
more »
« less
Model and learning-based computational 3D phase microscopy with intensity diffraction tomography
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
- PAR ID:
- 10209664
- Date Published:
- Journal Name:
- 2020 28th European Signal Processing Conference (EUSIPCO)
- Page Range / eLocation ID:
- 760 to 764
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
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 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.more » « less
-
We present deep-ultraviolet Fourier ptychography (DUV-FP) for high-resolution chemical imaging of biological specimens in their native state without exogenous stains. This approach uses a customized 265-nm DUV LED array for angle-varied illumination, leveraging the unique DUV absorption properties of biomolecules at this wavelength region. We implemented a robust feature-domain optimization framework to overcome common challenges in Fourier ptychographic reconstruction, including vignetting, pupil aberrations, stray light problems, intensity variations, and other systematic errors. By using a 0.12 numerical aperture low-resolution objective lens, our DUV-FP prototype can resolve the 345-nm linewidth on a resolution target, demonstrating at least a four-fold resolution gain compared to the captured raw images. Testing on various biospecimens demonstrates that DUV-FP significantly enhances absorption-based chemical contrast and reveals detailed structural and molecular information. To further address the limitations of conventional FP in quantitative phase imaging, we developed a spatially coded DUV-FP system. This platform enables true quantitative phase imaging of biospecimens with DUV light, overcoming the non-uniform phase response inherent in traditional microscopy techniques. The demonstrated advancements in high-resolution, label-free chemical imaging may accelerate developments in digital pathology, potentially enabling rapid, on-site analysis of biopsy samples in clinical settings.more » « less
-
Illumination uniformity is critical for widefield optical microscopy, especially for high-throughput and accurate quantitative imaging of biological specimens. While traditional Köhler illumination improves uniformity, it often fails to deliver homogeneous intensity across large fields of view. Existing optical and computational correction techniques remain inadequate for a broad range of quantitative imaging applications. Here, we implement a novel illumination device that we call the “effective uniform colorlight integration device” (EUCLID), quantifying improvements in two widefield imaging modalities that require uniform illumination. For both imaging modalities, we demonstrate significantly improved precision of quantitative measurements compared to traditional Köhler illumination. The EUCLID device, which can also provide uniform spectral mixing, can be readily adapted to many other widefield imaging modalities to enhance imaging accuracy and reliability, with low cost and ease of implementation.more » « less
-
Abstract Deep learning has been broadly applied to imaging in scattering applications. A common framework is to train a descattering network for image recovery by removing scattering artifacts. To achieve the best results on a broad spectrum of scattering conditions, individual “expert” networks need to be trained for each condition. However, the expert’s performance sharply degrades when the testing condition differs from the training. An alternative brute-force approach is to train a “generalist” network using data from diverse scattering conditions. It generally requires a larger network to encapsulate the diversity in the data and a sufficiently large training set to avoid overfitting. Here, we propose an adaptive learning framework, termed dynamic synthesis network (DSN), which dynamically adjusts the model weights and adapts to different scattering conditions. The adaptability is achieved by a novel “mixture of experts” architecture that enables dynamically synthesizing a network by blending multiple experts using a gating network. We demonstrate the DSN in holographic 3D particle imaging for a variety of scattering conditions. We show in simulation that our DSN provides generalization across a continuum of scattering conditions. In addition, we show that by training the DSN entirely on simulated data, the network can generalize to experiments and achieve robust 3D descattering. We expect the same concept can find many other applications, such as denoising and imaging in scattering media. Broadly, our dynamic synthesis framework opens up a new paradigm for designing highly adaptive deep learning and computational imaging techniques.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript
- Conference Paper:
- https://doi.org/10.23919/Eusipco47968.2020.9287407
