Super-resolution quantitative phase imaging of out-of-focus images based on deep learning

AbstractSpatial light modulators have become an essential tool for advanced microscopy, enabling breakthroughs in 3D, phase, and super-resolution imaging. However, continuous spatial-light modulation that is capable of capturing sub-millisecond microscopic motion without diffraction artifacts and polarization dependence is challenging. Here we present a photothermal spatial light modulator (PT-SLM) enabling fast phase imaging for nanoscopic 3D reconstruction. The PT-SLM can generate a step-like wavefront change, free of diffraction artifacts, with a high transmittance and a modulation efficiency independent of light polarization. We achieve a phase-shift > π and a response time as short as 70 µs with a theoretical limit in the sub microsecond range. We used the PT-SLM to perform quantitative phase imaging of sub-diffractional species to decipher the 3D nanoscopic displacement of microtubules and study the trajectory of a diffusive microtubule-associated protein, providing insights into the mechanism of protein navigation through a complex microtubule network.

Download Full-text

Auto-focusing and quantitative phase imaging using deep learning for the incoherent illumination microscopy system

Optics Express ◽

10.1364/oe.434014 ◽

2021 ◽

Author(s):

Hao Ding ◽

Fajing Li ◽

Zhang Meng ◽

Shaoteng Feng ◽

Jun Ma ◽

...

Keyword(s):

Deep Learning ◽

Phase Imaging ◽

Quantitative Phase Imaging ◽

Quantitative Phase ◽

Auto Focusing

Download Full-text

Single-shot higher-order transport-of-intensity quantitative phase imaging using deep learning

Applied Optics ◽

10.1364/ao.435538 ◽

2021 ◽

Vol 60 (28) ◽

pp. 8802

Author(s):

Naru Yoneda ◽

Shunsuke Kakei ◽

Koshi Komuro ◽

Aoi Onishi ◽

Yusuke Saita ◽

...

Keyword(s):

Deep Learning ◽

Higher Order ◽

Phase Imaging ◽

Single Shot ◽

Quantitative Phase Imaging ◽

Quantitative Phase

Download Full-text

Rapid and label-free identification of individual bacterial pathogens exploiting three-dimensional quantitative phase imaging and deep learning

10.1101/596486 ◽

2019 ◽

Cited By ~ 2

Author(s):

Geon Kim ◽

Daewoong Ahn ◽

Minhee Kang ◽

YoungJu Jo ◽

Donghun Ryu ◽

...

Keyword(s):

Refractive Index ◽

Deep Learning ◽

Infectious Diseases ◽

Bacterial Pathogens ◽

Bacterial Species ◽

Three Dimensional ◽

Phase Imaging ◽

Label Free ◽

Quantitative Phase Imaging ◽

Quantitative Phase

ABSTRACTFor appropriate treatments of infectious diseases, rapid identification of the pathogens is crucial. Here, we developed a rapid and label-free method for identifying common bacterial pathogens as individual bacteria by using three-dimensional quantitative phase imaging and deep learning. We achieved 95% accuracy in classifying 19 bacterial species by exploiting the rich information in three-dimensional refractive index tomograms with a convolutional neural network classifier. Extensive analysis of the features extracted by the trained classifier was carried out, which supported that our classifier is capable of learning species-dependent characteristics. We also confirmed that utilizing three-dimensional refractive index tomograms was crucial for identification ability compared to two-dimensional imaging. This method, which does not require time-consuming culture, shows high feasibility for diagnosing patients with infectious diseases who would benefit from immediate and adequate antibiotic treatment.

Download Full-text

Quantitative Phase Imaging Using Deep Learning-Based Holographic Microscope

Frontiers in Physics ◽

10.3389/fphy.2021.651313 ◽

2021 ◽

Vol 9 ◽

Author(s):

Jianglei Di ◽

Ji Wu ◽

Kaiqiang Wang ◽

Ju Tang ◽

Ying Li ◽

...

Keyword(s):

Neural Network ◽

Deep Learning ◽

Dry Mass ◽

Learning Technologies ◽

Digital Holographic Microscopy ◽

Phase Imaging ◽

Quantitative Phase Imaging ◽

Quantitative Phase ◽

Living Mouse ◽

Digital Holograms

Digital holographic microscopy enables the measurement of the quantitative light field information and the visualization of transparent specimens. It can be implemented for complex amplitude imaging and thus for the investigation of biological samples including tissues, dry mass, membrane fluctuation, etc. Currently, deep learning technologies are developing rapidly and have already been applied to various important tasks in the coherent imaging. In this paper, an optimized structural convolution neural network PhaseNet is proposed for the reconstruction of digital holograms, and a deep learning-based holographic microscope using above neural network is implemented for quantitative phase imaging. Living mouse osteoblastic cells are quantitatively measured to demonstrate the capability and applicability of the system.

Download Full-text

Fast photothermal spatial light modulation for quantitative phase imaging at the nanoscale

10.21203/rs.3.rs-38429/v1 ◽

2020 ◽

Author(s):

Hadrien Robert ◽

Łukasz Bujak ◽

Kristýna Holanová ◽

Milan Vala ◽

Piliarik Marek

Keyword(s):

Super Resolution ◽

Light Polarization ◽

Spatial Light Modulators ◽

Phase Imaging ◽

Light Modulation ◽

Quantitative Phase Imaging ◽

Light Modulator ◽

Quantitative Phase ◽

Light Modulators ◽

Spatial Light Modulation

Abstract Spatial light modulators have become an essential tool for advanced microscopy enabling breakthroughs in 3D, phase, or super-resolution imaging. However, continuous spatial-light modulation without diffraction artifacts, polarization dependence, and able to capture sub-ms microscopic motion is challenging. Here we present a photothermal spatial light modulator (PT-SLM) enabling the fast wavefront shaping free of diffraction artifacts, having a high transmissivity and modulation efficiency independent of light polarization. It is based on the microscopic heating of a thin layer of thermo-optic material confined between the photothermal heat-source and a transparent heatsink. We achieve a phase-shift > π with a response time as short as 70 µs with a theoretical limit in the sub-µs range. The combination of the PT-SLM with an interferometric scattering microscope (iSCAT) allowed us to perform quantitative phase imaging of sub-diffractional scatterers and decipher the 3D nanoscopic displacement of microtubules matching closely with control data from atomic force microscopy.

Download Full-text