arXiv subjects

Lei Tian

Publications and source records attributed to Lei Tian.

At least 73 records · Page 4Linked to original sources

arXiv2022

Recovery of Continuous 3D Refractive Index Maps from Discrete Intensity-Only Measurements using Neural Fields

Intensity diffraction tomography (IDT) refers to a class of optical microscopy techniques for imaging the 3D refractive index (RI) distribution of a sample from a set of 2D intensity-only measurements. The reconstruction of artifact-free RI maps is a fundamental challenge in IDT due to the loss of phase information and the missing cone problem. Neural fields (NF) has recently emerged as a new deep learning (DL) approach for learning continuous representations of physical fields. NF uses a coordinate-based neural network to represent the field by mapping the spatial coordinates to the corresponding physical quantities, in our case the complex-valued refractive index values. We present DeCAF as the first NF-based IDT method that can learn a high-quality continuous representation of a RI volume from its intensity-only and limited-angle measurements. The representation in DeCAF is learned directly from the measurements of the test sample by using the IDT forward model, without any ground-truth RI maps. We qualitatively and quantitatively evaluate DeCAF on the simulated and experimental biological samples. Our results show that DeCAF can generate high-contrast and artifact-free RI maps and lead to up to 2.1 times reduction in MSE over existing methods.

eess.IV↗

arXiv2022

High-fidelity intensity diffraction tomography with a non-paraxial multiple-scattering model

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 $\textit{C. elegans}$ worms and live $\textit{C. elegans}$ embryos.

physics.optics↗

arXiv2022

Frequency-Angle Two-Dimensional Reflection Coefficient Modeling Based on Terahertz Channel Measurement

Terahertz (THz) channel propagation characteristics are vital for the design, evaluation, and optimization for THz communication systems. Moreover, reflection plays a significant role in channel propagation. In this letter, the reflection coefficient of the THz channel is researched based on extensive measurement campaigns. Firstly, we set up the THz channel sounder from 220 to 320 GHz with the incident angle ranging from 10° to 80°. Based on the measured propagation loss, the reflection coefficients of five building materials, i.e., glass, tile, aluminium alloy, board, and plasterboard, are calculated separately for frequencies and incident angles. It is found that the lack of THz relative parameters leads to the Fresnel model of non-metallic materials can not fit the measured data well. Thus, we propose a frequency-angle two-dimensional reflection coefficient model by modifying the Fresnel model with the Lorenz and Drude model. The proposed model characterizes the frequency and incident angle for reflection coefficients and shows low root-mean-square error with the measured data. Generally, these results are useful for modeling THz channels.

eess.SP↗

arXiv2022

Adaptive 3D descattering with a dynamic synthesis network

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.

eess.IV↗

arXiv2021

Roadmap on Wavefront Shaping and deep imaging in complex media

The last decade has seen the development of a wide set of tools, such as wavefront shaping, computational or fundamental methods, that allow to understand and control light propagation in a complex medium, such as biological tissues or multimode fibers. A vibrant and diverse community is now working on this field, that has revolutionized the prospect of diffraction-limited imaging at depth in tissues. This roadmap highlights several key aspects of this fast developing field, and some of the challenges and opportunities ahead.

physics.optics↗

arXiv2021

Deep learning in biomedical optics

This article reviews deep learning applications in biomedical optics with a particular emphasis on image formation. The review is organized by imaging domains within biomedical optics and includes microscopy, fluorescence lifetime imaging, in vivo microscopy, widefield endoscopy, optical coherence tomography, photoacoustic imaging, diffuse tomography, and functional optical brain imaging. For each of these domains, we summarize how deep learning has been applied and highlight methods by which deep learning can enable new capabilities for optics in medicine. Challenges and opportunities to improve translation and adoption of deep learning in biomedical optics are also summarized.

physics.optics↗

arXiv2021

Large-scale holographic particle 3D imaging with the beam propagation model

We develop a novel algorithm for large-scale holographic reconstruction of 3D particle fields. Our method is based on a multiple-scattering beam propagation method (BPM) combined with sparse regularization that enables recovering dense 3D particles of high refractive index contrast from a single hologram. We show that the BPM-computed hologram generates intensity statistics closely matching with the experimental measurements and provides up to 9$\times$ higher accuracy than the single-scattering model. To solve the inverse problem, we devise a computationally efficient algorithm, which reduces the computation time by two orders of magnitude as compared to the state-of-the-art multiple-scattering-based technique. We demonstrate superior reconstruction accuracy in both simulations and experiments under different scattering strengths. We show that the BPM reconstruction significantly outperforms the single-scattering method in particular for deep imaging depths and high particle densities.

physics.optics↗

arXiv2021

An Adversarial Human Pose Estimation Network Injected with Graph Structure

Because of the invisible human keypoints in images caused by illumination, occlusion and overlap, it is likely to produce unreasonable human pose prediction for most of the current human pose estimation methods. In this paper, we design a novel generative adversarial network (GAN) to improve the localization accuracy of visible joints when some joints are invisible. The network consists of two simple but efficient modules, Cascade Feature Network (CFN) and Graph Structure Network (GSN). First, the CFN utilizes the prediction maps from the previous stages to guide the prediction maps in the next stage to produce accurate human pose. Second, the GSN is designed to contribute to the localization of invisible joints by passing message among different joints. According to GAN, if the prediction pose produced by the generator G cannot be distinguished by the discriminator D, the generator network G has successfully obtained the underlying dependence of human joints. We conduct experiments on three widely used human pose estimation benchmark datasets, LSP, MPII and COCO, whose results show the effectiveness of our proposed framework.

cs.CV↗

arXiv2021

Physical model simulator-trained neural network for computational 3D phase imaging of multiple-scattering samples

Recovering 3D phase features of complex, multiple-scattering biological samples traditionally sacrifices computational efficiency and processing time for physical model accuracy and reconstruction quality. This trade-off hinders the rapid analysis of living, dynamic biological samples that are often of greatest interest to biological research. Here, we overcome this bottleneck by combining annular intensity diffraction tomography (aIDT) with an approximant-guided deep learning framework. Using a novel physics model simulator-based learning strategy trained entirely on natural image datasets, we show our network can robustly reconstruct complex 3D biological samples of arbitrary size and structure. This approach highlights that large-scale multiple-scattering models can be leveraged in place of acquiring experimental datasets for achieving highly generalizable deep learning models. We devise a new model-based data normalization pre-processing procedure for homogenizing the sample contrast and achieving uniform prediction quality regardless of scattering strength. 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's capabilities on experimental measurements of epithelial buccal cells and Caenorhabditis elegans worms. We highlight the robustness of this approach by evaluating dynamic samples on a living worm video, and we emphasize our approach's generalizability by recovering algae samples evaluated with different experimental setups. To assess the prediction quality, we develop a novel quantitative evaluation metric and show that our predictions are consistent with our experimental measurements and multiple-scattering physics.

eess.IV↗

arXiv2021

Acousto-optic Ptychography

Acousto-optic imaging (AOI) enables optical-contrast imaging deep inside scattering samples via localized ultrasound-modulation of scattered light. While AOI allows optical investigations at depths, its imaging resolution is inherently limited by the ultrasound wavelength, prohibiting microscopic investigations. Here, we propose a novel computational imaging approach that allows to achieve optical diffraction-limited imaging using a conventional AOI system. We achieve this by extracting diffraction-limited imaging information from 'memory-effect' speckle-correlations in the conventionally detected ultrasound-modulated scattered-light fields. Specifically, we identify that since speckle correlations allow to estimate the Fourier-magnitude of the field inside the ultrasound focus, scanning the ultrasound focus enables robust diffraction-limited reconstruction of extended objects using ptychography, i.e. we exploit the ultrasound focus as the scanned spatial-gate 'probe' required for ptychographic phase-retrieval. Moreover, we exploit the short speckle decorrelation-time in dynamic media, which is usually considered a hurdle for wavefront-shaping based approaches, for improved ptychographic reconstruction. We experimentally demonstrate non-invasive imaging of targets that extend well beyond the memory-effect range, with a 40-times resolution improvement over conventional AOI, surpassing the performance of state-of-the-art approaches.

physics.optics↗

arXiv2020

Domain Adaptation by Class Centroid Matching and Local Manifold Self-Learning

Domain adaptation has been a fundamental technology for transferring knowledge from a source domain to a target domain. The key issue of domain adaptation is how to reduce the distribution discrepancy between two domains in a proper way such that they can be treated indifferently for learning. In this paper, we propose a novel domain adaptation approach, which can thoroughly explore the data distribution structure of target domain.Specifically, we regard the samples within the same cluster in target domain as a whole rather than individuals and assigns pseudo-labels to the target cluster by class centroid matching. Besides, to exploit the manifold structure information of target data more thoroughly, we further introduce a local manifold self-learning strategy into our proposal to adaptively capture the inherent local connectivity of target samples. An efficient iterative optimization algorithm is designed to solve the objective function of our proposal with theoretical convergence guarantee. In addition to unsupervised domain adaptation, we further extend our method to the semi-supervised scenario including both homogeneous and heterogeneous settings in a direct but elegant way. Extensive experiments on seven benchmark datasets validate the significant superiority of our proposal in both unsupervised and semi-supervised manners.

cs.CV↗

arXiv2020

Single-Shot 3D Widefield Fluorescence Imaging with a Computational Miniature Mesoscope

Fluorescence imaging is indispensable to biology and neuroscience. The need for large-scale imaging in freely behaving animals has further driven the development in miniaturized microscopes (miniscopes). However, conventional microscopes / miniscopes are inherently constrained by their limited space-bandwidth-product, shallow depth-of-field, and the inability to resolve 3D distributed emitters. Here, we present a Computational Miniature Mesoscope (CM$^2$) that overcomes these bottlenecks and enables single-shot 3D imaging across an 8 $\times$ 7-mm$^2$ field-of-view and 2.5-mm depth-of-field, achieving 7-$μ$m lateral resolution and better than 200-$μ$m axial resolution. Notably, the CM$^2$ has a compact lightweight design that integrates a microlens array for imaging and an LED array for excitation in a single platform. Its expanded imaging capability is enabled by computational imaging that augments the optics by algorithms. We experimentally validate the mesoscopic 3D imaging capability on volumetrically distributed fluorescent beads and fibers. We further quantify the effects of bulk scattering and background fluorescence on phantom experiments.

physics.optics↗

arXiv2020

Displacement-agnostic coherent imaging through scatter with an interpretable deep neural network

Coherent imaging through scatter is a challenging task in computational imaging. Both model-based and data-driven approaches have been explored to solve the inverse scattering problem. In our previous work, we have shown that a deep learning approach can make high-quality and highly generalizable predictions through unseen diffusers. Here, we propose a new deep neural network (DNN) model that is agnostic to a broader class of perturbations including scatterer change, displacements, and system defocus up to 10X depth of field. In addition, we develop a new analysis framework for interpreting the mechanism of our DNN model and visualizing its generalizability based on an unsupervised dimension reduction technique. We show that our DNN can unmix the scattering-specific information and extract the object-specific information so as to achieve generalization under different scattering conditions. Our work paves the way to a highly robust and interpretable deep learning approach to imaging through scattering media.

physics.optics↗

arXiv2020

Diffuser-based computational imaging funduscope

Poor access to eye care is a major global challenge that could be ameliorated by low-cost, portable, and easy-to-use diagnostic technologies. Diffuser-based imaging has the potential to enable inexpensive, compact optical systems that can reconstruct a focused image of an object over a range of defocus errors. Here, we present a diffuser-based computational funduscope that reconstructs important clinical features of a model eye. Compared to existing diffuser-imager architectures, our system features an infinite-conjugate design by relaying the ocular lens onto the diffuser. This offers shift-invariance across a wide field-of-view (FOV) and an invariant magnification across an extended depth range. Experimentally, we demonstrate fundus image reconstruction over a 33$^{\circ}$ FOV and robustness to $\pm$4D refractive error using a constant point-spread-function. Combined with diffuser-based wavefront sensing, this technology could enable combined ocular aberrometry and funduscopic screening through a single diffuser sensor.

physics.med-ph↗

arXiv2020

SIMBA: Scalable Inversion in Optical Tomography using Deep Denoising Priors

Two features desired in a three-dimensional (3D) optical tomographic image reconstruction algorithm are the ability to reduce imaging artifacts and to do fast processing of large data volumes. Traditional iterative inversion algorithms are impractical in this context due to their heavy computational and memory requirements. We propose and experimentally validate a novel scalable iterative mini-batch algorithm (SIMBA) for fast and high-quality optical tomographic imaging. SIMBA enables high-quality imaging by combining two complementary information sources: the physics of the imaging system characterized by its forward model and the imaging prior characterized by a denoising deep neural net. SIMBA easily scales to very large 3D tomographic datasets by processing only a small subset of measurements at each iteration. We establish the theoretical fixed-point convergence of SIMBA under nonexpansive denoisers for convex data-fidelity terms. We validate SIMBA on both simulated and experimentally collected intensity diffraction tomography (IDT) datasets. Our results show that SIMBA can significantly reduce the computational burden of 3D image formation without sacrificing the imaging quality.

eess.IV↗

arXiv2019

High-speed in vitro intensity diffraction tomography

We demonstrate a label-free, scan-free {\it intensity} diffraction tomography technique utilizing annular illumination (aIDT) to rapidly characterize large-volume 3D refractive index distributions in vitro. By optimally matching the illumination geometry to the microscope pupil, our technique reduces the data requirement by 60$\times$ to achieve high-speed 10 Hz volume rates. Using 8 intensity images, we recover $\sim350\times100\times20μ$m$^3$ volumes with near diffraction-limited lateral resolution of 487 nm and axial resolution of 3.4 $μ$m. Our technique's large volume rate and high resolution enables 3D quantitative phase imaging of complex living biological samples across multiple length scales. We demonstrate aIDT's capabilities on unicellular diatom microalgae, epithelial buccal cell clusters with native bacteria, and live \emph{Caenorhabditis elegans} specimens. Within these samples, we recover macro-scale cellular structures, subcellular organelles, and dynamic micro-organism tissues with minimal motion artifacts. Quantifying such features has significant utility in oncology, immunology, and cellular pathophysiology, where these morphological features are evaluated for changes in the presence of disease, parasites, and new drug treatments. Finally, we simulate our aIDT system to highlight the accuracy and sensitivity of our technique. aIDT shows promise as a powerful high-speed, label-free computational microscopy technique applications where natural imaging is required to evaluate environmental effects on a sample in real-time. We provide example datasets and an open source implementation of aIDT at \href{https://github.com/bu-cisl/IDT-using-Annular-Illumination}{https://github.com/bu-cisl/IDT-using-Annular-Illumination}.

physics.optics↗

arXiv2019

Inverse scattering for reflection intensity phase microscopy

Reflection phase imaging provides label-free, high-resolution characterization of biological samples, typically using interferometric-based techniques. Here, we investigate reflection phase microscopy from intensity-only measurements under diverse illumination. We evaluate the forward and inverse scattering model based on the first Born approximation for imaging scattering objects above a glass slide. Under this design, the measured field combines linear forward-scattering and height-dependent nonlinear back-scattering from the object that complicates object phase recovery. Using only the forward-scattering, we derive a linear inverse scattering model and evaluate this model's validity range in simulation and experiment using a standard reflection microscope modified with a programmable light source. Our method provides enhanced contrast of thin, weakly scattering samples that complement transmission techniques. This model provides a promising development for creating simplified intensity-based reflection quantitative phase imaging systems easily adoptable for biological research.

q-bio.QM↗

arXiv2019

Stochastic Sparse Learning with Momentum Adaptation for Imprecise Memristor Networks

Memristor based neural networks have great potentials in on-chip neuromorphic computing systems due to the fast computation and low-energy consumption. However, the imprecise properties of existing memristor devices generally result in catastrophic failures for the network in-situ training, which significantly impedes their engineering applications. In this work, we design a novel learning scheme that integrates stochastic sparse updating with momentum adaption (SSM) to efficiently train the imprecise memristor networks with high classification accuracy. The SSM scheme consists of: (1) a stochastic and discrete learning method to make weight updates sparse; (2) a momentum based gradient algorithm to eliminate training noises and distill robust updates; (3) a network re-initialization method to mitigate the device-to-device variation; (4) an update compensation strategy to further stabilize the weight programming process. With the SSM scheme, experiments show that the classification accuracy on multilayer perceptron (MLP) and convolutional neural network (CNN) improves from 26.12% to 90.07% and from 65.98% to 92.38%, respectively. Meanwhile, the total numbers of weight updating pulses decrease 90% and 40% in MLP and CNN, respectively, and the convergence rates are both 3x faster. The SSM scheme provides a high-accuracy, low-power, and fast-convergence solution for the in-situ training of imprecise memristor networks, which is crucial to future neuromorphic intelligence systems.

cs.ET↗