DeepSTORM3D: dense 3D localization microscopy and PSF design by deep learning

Nature Methods, Journal Year: 2020, Volume and Issue: 17(7), P. 734 - 740

Published: June 15, 2020

Language: Английский

---

Design of task-specific optical systems using broadband diffractive neural networks

Light Science & Applications, Journal Year: 2019, Volume and Issue: 8(1)

Published: Dec. 2, 2019

Deep learning has been transformative in many fields, motivating the emergence of various optical computing architectures. Diffractive network is a recently introduced framework that merges wave optics with deep-learning methods to design neural networks. Diffraction-based all-optical object recognition systems, designed through this and fabricated by 3D printing, have reported recognize hand-written digits fashion products, demonstrating inference generalization sub-classes data. These previous diffractive approaches employed monochromatic coherent light as illumination source. Here, we report broadband simultaneously processes continuum wavelengths generated temporally incoherent source all-optically perform specific task learned using deep learning. We experimentally validated success architecture designing, fabricating testing seven different multi-layer, systems transform wavefront THz pulse realize (1) series tuneable, single-passband dual-passband spectral filters (2) spatially controlled wavelength de-multiplexing. Merging native or engineered dispersion material deep-learning-based strategy, networks help us engineer light-matter interaction 3D, diverging from intuitive analytical create task-specific components can deterministic tasks statistical for machine

Language: Английский

---

Three-dimensional virtual refocusing of fluorescence microscopy images using deep learning

Nature Methods, Journal Year: 2019, Volume and Issue: 16(12), P. 1323 - 1331

Published: Nov. 4, 2019

Language: Английский

---

Single-particle spectroscopy for functional nanomaterials

Nature, Journal Year: 2020, Volume and Issue: 579(7797), P. 41 - 50

Published: March 4, 2020

Language: Английский

---

Deep learning enables fast and dense single-molecule localization with high accuracy

Nature Methods, Journal Year: 2021, Volume and Issue: 18(9), P. 1082 - 1090

Published: Sept. 1, 2021

Language: Английский

---

Deep Learning in Image Cytometry: A Review

Cytometry Part A, Journal Year: 2018, Volume and Issue: 95(4), P. 366 - 380

Published: Dec. 19, 2018

Artificial intelligence, deep convolutional neural networks, and learning are all niche terms that increasingly appearing in scientific presentations as well the general media. In this review, we focus on how it is applied to microscopy image data of cells tissue samples. Starting with an analogy neuroscience, aim give reader overview key concepts understanding differs from more classical approaches for extracting information data. We increase these methods, while highlighting considerations regarding input requirements, computational resources, challenges, limitations. do not provide a full manual applying methods your own data, but rather review previously published articles cytometry, guide readers toward further reading specific networks including new yet cytometry © 2018 The Authors. Cytometry Part A by Wiley Periodicals, Inc. behalf International Society Advancement Cytometry.

Language: Английский

---

Plug-and-Play Algorithms for Large-Scale Snapshot Compressive Imaging

2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Journal Year: 2020, Volume and Issue: unknown, P. 1444 - 1454

Published: June 1, 2020

Snapshot compressive imaging (SCI) aims to capture the high-dimensional (usually 3D) images using a 2D sensor (detector) in single snapshot. Though enjoying advantages of low-bandwidth, low-power and low-cost, applying SCI large-scale problems (HD or UHD videos) our daily life is still challenging. The bottleneck lies reconstruction algorithms; they are either too slow (iterative optimization algorithms) not flexible encoding process (deep learning based end-to-end networks). In this paper, we develop fast algorithms for on plug-and-play (PnP) framework. addition widely used PnP-ADMM method, further propose PnP-GAP (generalized alternating projection) algorithm with lower computational workload prove {global convergence} under hardware constraints. By employing deep denoising priors, first time show that PnP can recover color video (3840×1644×48 PNSR above 30dB) from snapshot measurement. Extensive results both simulation real datasets verify superiority proposed algorithm.

Language: Английский

---

Super-resolution Microscopy with Single Molecules in Biology and Beyond–Essentials, Current Trends, and Future Challenges

Journal of the American Chemical Society, Journal Year: 2020, Volume and Issue: 142(42), P. 17828 - 17844

Published: Oct. 9, 2020

Single-molecule super-resolution microscopy has developed from a specialized technique into one of the most versatile and powerful imaging methods nanoscale over past two decades. In this perspective, we provide brief overview historical development field, fundamental concepts, methodology required to obtain maximum quantitative information, current state art. Then, will discuss emerging perspectives areas where innovation further improvement are needed. Despite tremendous progress, full potential single-molecule is yet be realized, which enabled by research ahead us.

Language: Английский

---

Three-dimensional residual channel attention networks denoise and sharpen fluorescence microscopy image volumes

Nature Methods, Journal Year: 2021, Volume and Issue: 18(6), P. 678 - 687

Published: May 31, 2021

Language: Английский

---

Terahertz pulse shaping using diffractive surfaces

Nature Communications, Journal Year: 2021, Volume and Issue: 12(1)

Published: Jan. 4, 2021

Abstract Recent advances in deep learning have been providing non-intuitive solutions to various inverse problems optics. At the intersection of machine and optics, diffractive networks merge wave-optics with design task-specific elements all-optically perform tasks such as object classification vision. Here, we present a network, which is used shape an arbitrary broadband pulse into desired optical waveform, forming compact passive engineering system. We demonstrate synthesis different pulses by designing layers that collectively engineer temporal waveform input terahertz pulse. Our results direct shaping spectrum, where amplitude phase wavelengths are independently controlled through device, without need for external pump. Furthermore, physical transfer approach presented illustrate pulse-width tunability replacing part existing network newly trained layers, demonstrating its modularity. This learning-based framework can find broad applications e.g., communications, ultra-fast imaging spectroscopy.

Language: Английский

---