4.7 Article

Physics-Based Deep Learning for Imaging Neuronal Activity via Two-Photon and Light Field Microscopy

Related references

Note: Only part of the references are listed.
Article Neurosciences

Comparing synthetic refocusing to deconvolution for the extraction of neuronal calcium transients from light fields

Carmel L. Howe et al.

Summary: Light-field microscopy enables fast and efficient volumetric imaging of neuronal activity with calcium indicators. This study compared the capabilities of two light-field reconstruction algorithms for calcium fluorescence imaging and found that both algorithms can resolve calcium signals in three dimensions. However, increasing the iteration number of the deconvolution algorithm improved spatial confinement but reduced tSNR.

NEUROPHOTONICS (2022)

Article Neurosciences

Residual RAKI: A hybrid linear and non-linear approach for scan-specific k-space deep learning

Chi Zhang et al.

Summary: This article presents an improved MRI reconstruction method, called rRAKI, which utilizes a combination of linear and non-linear approaches to achieve machine learning reconstruction. The rRAKI method improves image quality and preserves time-varying dynamics compared to conventional parallel imaging and other existing methods.

NEUROIMAGE (2022)

Article Computer Science, Hardware & Architecture

ClarifyNet: A high-pass and low-pass filtering based CNN for single image dehazing

Onkar Susladkar et al.

Summary: In this paper, a novel end-to-end trainable convolutional neural network architecture called ClarifyNet is proposed for single image dehazing. ClarifyNet utilizes low-pass and high-pass filters to extract different types of information and employs a shared-encoder and multi-decoder model structure. By utilizing a weighted loss function, complementary features are extracted and propagated. Experimental results show that ClarifyNet achieves high scores on multiple datasets.

JOURNAL OF SYSTEMS ARCHITECTURE (2022)

Article Biochemical Research Methods

Incorporating the image formation process into deep learning improves network performance

Yue Li et al.

Summary: Richardson-Lucy Network (RLN) combines traditional Richardson-Lucy iteration with deep learning for improved deconvolution. RLN is more generalizable, offers fewer artifacts, and requires less computing time. Compared to purely data-driven networks, RLN contains only roughly 16,000 parameters, enabling faster processing.

NATURE METHODS (2022)

Proceedings Paper Acoustics

A General Deep Learning Model for Ultrasound Localization Microscopy

Renxian Wang et al.

Summary: By utilizing microbubbles and ultrasound localization microscopy (ULM), the diffraction limit of ultrasound imaging can be overcome. Accurate localization of microbubbles remains challenging, and a deep learning-based ULM framework is proposed to address this issue.

2022 IEEE INTERNATIONAL ULTRASONICS SYMPOSIUM (IEEE IUS) (2022)

Article Engineering, Electrical & Electronic

Shift-Invariant-Subspace Discretization and Volume Reconstruction for Light Field Microscopy

Herman Verinaz-Jadan et al.

Summary: Light Field Microscopy (LFM) is an imaging technique that captures 3D spatial information with a single 2D image. However, conventional 3D reconstruction algorithms for LFM suffer from computational cost, resolution, and artifact issues. In this work, novel techniques are proposed to improve reconstruction performance by using discretization, shift-invariant subspaces, and singular value decomposition (SVD) to reduce computational time, as well as iterative approaches with additional priors for artifact-free 3D reconstruction.

IEEE TRANSACTIONS ON COMPUTATIONAL IMAGING (2022)

Article Biochemical Research Methods

Real-time volumetric reconstruction of biological dynamics with light-field microscopy and deep learning

Zhaoqiang Wang et al.

Summary: Combining a view-channel-depth neural network with light-field microscopy allows for artifact-free three-dimensional image sequences with uniform spatial resolution and high reconstruction throughput, enabling imaging of dynamic spatiotemporal patterns in samples at high speeds.

NATURE METHODS (2021)

Article Biochemical Research Methods

Deep learning-enhanced light-field imaging with continuous validation

Nils Wagner et al.

Summary: The study introduces a framework for artificial intelligence-enhanced microscopy, combining a hybrid light-field light-sheet microscope and deep learning-based volume reconstruction. High-quality three-dimensional reconstructions at video-rate throughput are achieved using high-resolution two-dimensional light-sheet images as training data.

NATURE METHODS (2021)

Article Engineering, Electrical & Electronic

Learning to Reconstruct Confocal Microscopy Stacks From Single Light Field Images

Josue Page Vizcaino et al.

Summary: A novel deep learning approach, LFMNet, is introduced for reconstructing confocal microscopy stacks from single light field images rapidly and accurately, enabling imaging of highly dynamic and light-sensitive events, as well as in closed-loop systems where reducing latency is crucial.

IEEE TRANSACTIONS ON COMPUTATIONAL IMAGING (2021)

Article Optics

Learned SPARCOM: unfolded deep super-resolution microscopy

Gili Dardikman-Yoffe et al.

OPTICS EXPRESS (2020)

Article Engineering, Electrical & Electronic

3D Localization for Light-Field Microscopy via Convolutional Sparse Coding on Epipolar Images

Pingfan Song et al.

IEEE TRANSACTIONS ON COMPUTATIONAL IMAGING (2020)

Article Optics

Phase-space deconvolution for light field microscopy

Zhi Lu et al.

OPTICS EXPRESS (2019)

Article Optics

Artifact-free deconvolution in light field microscopy

Anca Stefanoiu et al.

OPTICS EXPRESS (2019)

Article Biochemistry & Molecular Biology

Ultrafast Two-Photon Imaging of a High-Gain Voltage Indicator in Awake Behaving Mice

Vincent Villette et al.

Review Neurosciences

A Guide to Emerging Technologies for Large-Scale and Whole-Brain Optical Imaging of Neuronal Activity

Siegfried Weisenburger et al.

ANNUAL REVIEW OF NEUROSCIENCE, VOL 41 (2018)

Proceedings Paper Computer Science, Artificial Intelligence

ISTA-Net: Interpretable Optimization-Inspired Deep Network for Image Compressive Sensing

Jian Zhang et al.

2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) (2018)

Article Biochemical Research Methods

Video rate volumetric Ca2+ imaging across cortex using seeded iterative demixing (SID) microscopy

Tobias Noebauer et al.

NATURE METHODS (2017)

Proceedings Paper Computer Science, Artificial Intelligence

Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network

Christian Ledig et al.

30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017) (2017)

Article Engineering, Electrical & Electronic

Principles of Light Field Imaging Briefly revisiting 25 years of research

Ivo Ihrke et al.

IEEE SIGNAL PROCESSING MAGAZINE (2016)

Article Biochemical Research Methods

Simultaneous whole-animal 3D imaging of neuronal activity using light-field microscopy

Robert Prevedel et al.

NATURE METHODS (2014)

Article Optics

Wave optics theory and 3-D deconvolution for the light field microscope

Michael Broxton et al.

OPTICS EXPRESS (2013)

Article Geochemistry & Geophysics

Estimation of the Equivalent Number of Looks in Polarimetric Synthetic Aperture Radar Imagery

Stian Normann Anfinsen et al.

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING (2009)

Article Computer Science, Artificial Intelligence

A Fast Iterative Shrinkage-Thresholding Algorithm for Linear Inverse Problems

Amir Beck et al.

SIAM JOURNAL ON IMAGING SCIENCES (2009)

Article Computer Science, Software Engineering

Light field microscopy

Marc Levoy et al.

ACM TRANSACTIONS ON GRAPHICS (2006)

Article Mathematics, Applied

An iterative thresholding algorithm for linear inverse problems with a sparsity constraint

I Daubechies et al.

COMMUNICATIONS ON PURE AND APPLIED MATHEMATICS (2004)