News

CISL at Optica Imaging Congress 2023

August 20th, 2023in Conference

Hao Wang
Wide-field, high-resolution reflection-mode Fourier ptychographic microscopy
* best student paper award 1st place

Jiabei Zhu
3D Phase Imaging from Intensity Measurements with Non-Paraxial Multiple Scattering Model
* best student paper award 1st place
* featured in Optica news.

 

Qianwan Yang
Advancing Computational Miniature Mesoscope With Simulator-Based Deep Learning Reconstruction
* featured in Optica news.

 

Guorong Hu
Caustic Illumination-based HiLo Microscopy

Lei Tian
Computational 3D Phase Imaging by Intensity Diffraction Tomography * invited

Lei Tian
Computational Miniature Mesoscope: augmenting miniature optics with algorithms for large-scale 3D fluorescence imaging * invited

Shiyi defended PhD!

July 10th, 2023in People

Congratulations, Dr. Cheng!

=============================

Title:                    Augmenting Label-free Imaging Modalities with Deep Learning based Digital Staining
Presenter:          Shiyi Cheng
Date:                    Monday, July 10th, 2023
Time:                   11:00 am to 1:00 pm
Location:             8 Saint Mary's Street, Room 339
Advisor:              Professor Lei Tian
Chair:                   Professor Ari Trachtenberg
Committee:        Professor Lei Tian, Professor Eshed Ohn-Bar, Professor David A. Boas, Professor Irving Bigio, Professor Ji-Xin Cheng.

Abstract:

Label-free imaging techniques provide valuable insights into biological samples and processes in their native states, eliminating the need for labor-intensive and potentially disruptive processes of physical staining. However, these methods often lack structural and molecular specific information. To overcome this limitation, recent advances in deep learning based digital staining techniques have shown the ability to virtually introduce digital labels or stains into label-free images, which enables extracting rich information that would typically require physical staining. The integration of label-free imaging and digital staining holds great potential for significantly expanding the toolkit for biomedical imaging, facilitating improved analysis, and enhancing our understanding of biomedical sciences at both the cellular and tissue level. In this thesis, I explore supervised and semi-supervised methodologies for digital staining and their applications in augmenting label-free imaging, with a focus on imaging cytometry and human brain imaging.

In the first part of the thesis, I present a novel integration of multi-contrast dark-field reflectance microscopy and digital staining by supervised deep learning. This method enables multiplexed immunofluorescence labeling of subcellular features and single cell cytometry. By leveraging the rich structural information and sensitivity of reflectance microscopy, the digital staining method accurately predicts subcellular features and achieves up to 3 times improvement in prediction accuracy over the state-of-the-art techniques. Additionally, the method accurately reproduces single-cell level structural phenotypes related to cell cycles. The multiplexed digital labeling enables multi-parametric single-cell profiling across a large cell population.

In the second part, I developed a novel semi-supervised digital staining technique for serial sectioning OCT (S-OCT) for 3D histological imaging of human brain tissue. The deep learning model integrates unpaired image translation, a biophysical model, and unsupervised cross-modality image registration. The digital staining model enables the translation of S-OCT images to Gallyas silver staining, provides consistent staining quality across different samples, and enhances contrast across cortical layer boundaries, enabling reliable layer differentiation. Importantly, the integration of S-OCT and digital staining allows volumetric histological imaging while preserving complex 3D geometry on centimeter-scale brain tissue blocks. In addition, our pilot study demonstrates promising results on other anatomical regions acquired from different S-OCT systems.

In summary, I investigated deep-learning-based digital staining techniques for augmenting two types of label-free imaging modalities. I showcased two important applications in the field of single-cell immunofluorescence microscopy and mesoscale 3D histological human brain imaging. I expect two major potential impacts from my thesis work. First, the integration of digital staining techniques with multi-contrast microscopy can potentially enhance the throughput of single-cell imaging cytometry and phenotyping. Second, the integration of digital staining techniques with S-OCT can potentially enable high-throughput human brain imaging, facilitating comprehensive studies on the brain's structure and function. Through this exploration, this thesis advances the digital staining technique and its applications for various biomedical disciplines.

 

Joe, Qianwan, Jiabei, Hao present at Optica FiO conference

October 23rd, 2022in Conference

J. Zhu*, H. Wang*, L. Tian, “Non-paraxial multiple scattering model for intensity diffraction tomography”, Optica Frontier in Optics, Oct. 2022.
J. Greene*, Y. Xue*, J. Alido*, A. Matlock*, G. Hu*, K. Kilic, I. Davison, L. Tian, “Pupil engineering in miniscopes for extended depth-of-field neural imaging”, Optica Frontier in Optics, Oct. 2022.
Q. Yang*, Y. Xue*, G. Hu*, L. Tian, “Computational Miniature Mesoscope with deep learning reconstruction”, Optica Frontier in Optics, Oct. 2022. * Emil Wolf Outstanding Student Paper Award
H. Wang*, W. Tahir*, L. Tian, “Adaptive volumetric descattering in digital holography”, Optica Frontier in Optics, Oct. 2022.

Yunzhe defended PhD Dissertation!

September 28th, 2022in Graduation, People

Title:                 Robust Deep Learning for Computational Imaging through Random Optics 

Presenter:        Yunzhe Li

Date:                 Monday, September 26, 2022

Time:                12:00 pm to 2:00 pm

Location:          8 Saint Mary's Street, Room 339

Advisor:           Professor Lei Tian, ECE

Chair:                Professor Eshed Ohn-Bar, ECE

Committee:     Professor Lei Tian, ECE; Professor Vivek Goyal, ECE; Professor Luca Dal Negro, ECE; Professor Roberto Paiella, ECE.

Abstract:  Light scattering is a pervasive phenomenon that poses outstanding challenges in both coherent and incoherent imaging systems. The output of a coherent light scattered from a complex medium exhibits a seemingly random speckle pattern that scrambles the useful information of the object. To date, there is no simple solution for inverting such complex scattering. Advancing the solution of inverse scattering problems could provide important insights into applications across many areas, such as deep tissue imaging, non-line-of-sight imaging, and imaging in degraded environment. On the other hand, in incoherent systems, the randomness of scattering medium could be exploited to build lightweight, compact, and low-cost lensless imaging systems that are applicable in miniaturized biomedical and scientific imaging. The imaging capability of such computational imaging systems, however, are largely limited by the ill-posed or ill-conditioned inverse problems, which typically causes imaging artifacts and degradation of the image resolution. Therefore, mitigating this issue by developing modern algorithms is essential for pushing the limits of such lensless computational imaging systems.

In this thesis, I focus on the problem of imaging through random optics and present two novel deep-learning (DL) based methodologies to overcome the challenges in coherent and incoherent systems: 1) no simple solution for inverse scattering problem and lack of robustness to scattering variations; and 2) ill-posed problem for diffuser-based lensless imaging.

In the first part, I demonstrate the novel use of a deep neural network (DNN) to solve the inverse scattering problem in a coherent imaging system. I propose a statistical `one-to-all' deep learning technique that encapsulates a wide range of statistical variations for the model to be resilient to speckle decorrelations. I push the limit of robustness against a broad class of perturbations including scatterer change, displacements, and system defocus up to 10X depth of field.

In the second part, I consider the utility of the random light scattering to build a diffuser-based computational lensless imaging system and present a generally applicable novel DL framework to achieve fast and noise-robust color image reconstruction. I developed a diffuser-based computational funduscope that reconstructs important clinical features of a model eye. Experimentally, I demonstrated fundus image reconstruction over a large field-of-view (FOV) and robustness to refractive error using a constant point-spread-function. Next, I present a physics simulator-trained, adaptive DL framework to achieve fast and noise-robust color imaging. The physics simulator incorporates optical system modeling, the simulation of mixed Poisson-Gaussian noise, and color filter array induced artifacts in color sensors. The learning framework includes an adaptive multi-channel L2-regularized inversion module and a channel-attention enhancement network module. Both simulation and experiments show consistently better reconstruction accuracy and robustness to various noise levels under different light conditions compared with traditional L2-regularized reconstructions.

Overall, this thesis investigated two major classes of problems in imaging through random optics. In the first part of the thesis, my work explored a novel DL-based approach for solving the inverse scattering problem and paves the way to a scalable and robust deep learning approach to imaging through scattering media. In the second part of the thesis, my work developed a broadly applicable adaptive learning-based framework for ill-conditioned image reconstruction and a physics-based simulation model for computational color imaging.

Chang and Qianwan present posters at Sculpted Light in the Brain

June 28th, 2022in Conference

Voltage imaging is an evolving tool to continuously image neuronal activities for large number of neurons. Recently, a high-speed low-light two-photon voltage imaging framework was developed, which enabled kilohertz-scanning on population-level neurons in the awake behaving animal. However, with a high frame rate and a large field-of-view (FOV), shot noise dominates pixel-wise measurements and the neuronal signals are difficult to be identified in the single-frame raw measurement. Another issue is that although deep-learning-based methods has exhibited promising results in image denoising, the traditional supervised learning is not applicable to this problem as the lack of ground-truth “clean” (high SNR) measurements. To address these issues, we developed a self-supervised deep learning framework for voltage imaging denoising (DeepVID) without the need for any ground-truth data. Inspired by previous self-supervised algorithms, DeepVID infers the underlying fluorescence signal based on the independent temporal and spatial statistics of the measurement that is attributed to shot noise. DeepVID reduced the frame-to-frame variably of the image and achieved a 15-fold improvement in SNR when comparing denoised and raw image data.

 

Conventional microscopes are inherently constrained by its space-bandwidth product, which means compromises must be made to obtain either a low spatial resolution or a narrow field-of-view. Computational Miniature Mesoscope (CM2) is a novel fluorescence imaging device that overcomes this bottleneck by jointly designing the optics and algorithm. The CM2 platform achieves single-shot large-scale volumetric imaging with single cell resolution on a compact platform. Here, we demonstrate CM2 V2 – an advanced CM2 system that integrates novel hardware improvements and a new deep learning reconstruction framework. On the hardware side, the platform features a 3D-printed freeform illuminator that achieves ~80% excitation efficiency – a ~3X improvement over our V1 design, and a hybrid emission filter design that improves the measurement contrast by >5X. On the computational side, the new proposed computational pipeline, termed CM2Net, is fueled by simulated realistic field varying data to perform fast and reliable 3D reconstruction. As compared to the model-based deconvolution in our V1 system, CM2Net achieves ~8X better axial localization and ~1400X faster reconstruction speed. The trained CM2Net is validated by imaging phantom objects with embedded fluorescent particles. We experimentally demonstrate the CM2Net offers 6um lateral, and 24um axial resolution in a 7mm FOV and 800um depth range. We anticipate that this simple and low-cost computational miniature imaging system may be applied to a wide range of large-scale 3D fluorescence imaging and wearable in-vivo neural recordings on mice and other small animals.