scholarly journals Parametric Comparison between Sparsity-Based and Deep Learning-Based Image Reconstruction of Super-Resolution Fluorescence Microscopy

2021 ◽  
Author(s):  
Yun Chen ◽  
Junjie Chen
Keyword(s):  
Deep Learning ◽  
Image Reconstruction ◽  
Fluorescence Microscopy ◽  
Super Resolution

scholarly journals Applications, Promises, and Pitfalls of Deep Learning for Fluorescence Image Reconstruction

2018 ◽  
Author(s):  
Chinmay Belthangady ◽  
Loic A. Royer
Keyword(s):  
Deep Learning ◽  
Image Reconstruction ◽  
Super Resolution ◽  
Training Data ◽  
Structured Illumination ◽  
Fluorescence Image ◽  
Important Addition ◽  
Review State ◽  
Image Details ◽  
Field Imaging

Deep Learning is a recent and important addition to the computational toolbox available for image reconstruction in fluorescence microscopy. We review state-of-the-art applications such as image restoration, super-resolution, and light-field imaging, and discuss how the latest Deep Learning research can be applied to other image reconstruction tasks such as structured illumination, spectral deconvolution, and sample stabilisation. Despite its successes, Deep Learning also poses significant challenges, has often misunderstood capabilities, and overlooked limits. We will address key questions, such as: What are the challenges in obtaining training data? Can we discover structures not present in the training data? And, what is the danger of inferring unsubstantiated image details?

scholarly journals Deep learning enables cross-modality super-resolution in fluorescence microscopy

2018 ◽  
Vol 16 (1) ◽  
pp. 103-110 ◽  
Author(s):  
Hongda Wang ◽  
Yair Rivenson ◽  
Yiyin Jin ◽  
Zhensong Wei ◽  
Ronald Gao ◽  
...  
Keyword(s):  
Deep Learning ◽  
Fluorescence Microscopy ◽  
Super Resolution

scholarly journals Design Principles for Autonomous Illumination Control in Localization Microscopy

2018 ◽  
Author(s):  
Marcel Štefko ◽  
Baptiste Ottino ◽  
Kyle M. Douglass ◽  
Suliana Manley
Keyword(s):  
Deep Learning ◽  
Control System ◽  
Fluorescence Microscopy ◽  
A Priori ◽  
Super Resolution ◽  
Density Estimator ◽  
Localization Microscopy ◽  
Extended Range ◽  
Self Tuning ◽  
Fine Tune

Super-resolution fluorescence microscopy improves spatial resolution, but this comes at a loss of image throughput and presents unique challenges in identifying optimal acquisition parameters. Microscope automation routines can offset these drawbacks, but thus far have required user inputs that presume a priori knowledge about the sample. Here, we develop a flexible illumination control system for localization microscopy comprised of two interacting components that require no sample-specific inputs: a self-tuning controller and a deep learning molecule density estimator that is accurate over an extended range. This system obviates the need to fine-tune parameters and demonstrates the design of modular illumination control for localization microscopy.

scholarly journals Low power super resolution fluorescence microscopy by lifetime modification and image reconstruction

2014 ◽  
Vol 22 (10) ◽  
pp. 12327 ◽  
Author(s):  
Richard J. Marsh ◽  
Siân Culley ◽  
Angus J. Bain
Keyword(s):  
Image Reconstruction ◽  
Fluorescence Microscopy ◽  
Low Power ◽  
Super Resolution

scholarly journals Applications, Promises, and Pitfalls of Deep Learning for Fluorescence Image Reconstruction

2019 ◽  
Author(s):  
Chinmay Belthangady ◽  
Loic A. Royer
Keyword(s):  
Deep Learning ◽  
Image Reconstruction ◽  
Super Resolution ◽  
Training Data ◽  
Structured Illumination ◽  
Fluorescence Image ◽  
Important Addition ◽  
Review State ◽  
Image Details ◽  
Field Imaging

Deep Learning is a recent and important addition to the computational toolbox available for image reconstruction in fluorescence microscopy. We review state-of-the-art applications such as image restoration, super-resolution, and light-field imaging, and discuss how the latest Deep Learning research can be applied to other image reconstruction tasks such as structured illumination, spectral deconvolution, and sample stabilisation. Despite its successes, Deep Learning also poses significant challenges, has often misunderstood capabilities, and overlooked limits. We will address key questions, such as: What are the challenges in obtaining training data? Can we discover structures not present in the training data? And, what is the danger of inferring unsubstantiated image details?

Cross-Modality Deep Learning Achieves Super-Resolution in Fluorescence Microscopy

2019 ◽  
Author(s):  
Hongda Wang ◽  
Yair Rivenson ◽  
Yiyin Jin ◽  
Zhensong Wei ◽  
Ronald Gao ◽  
...  
Keyword(s):  
Deep Learning ◽  
Fluorescence Microscopy ◽  
Super Resolution

scholarly journals Convolutional Neural Networks Using Skip Connections with Layer Groups for Super-Resolution Image Reconstruction Based on Deep Learning

2020 ◽  
Vol 10 (6) ◽  
pp. 1959
Author(s):  
Hyeongyeom Ahn ◽  
Changhoon Yim
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Image Reconstruction ◽  
Convolutional Neural Networks ◽  
Input Data ◽  
Signal To Noise Ratio ◽  
Super Resolution ◽  
Resolution Image ◽  
Hidden Layer ◽  
Layer Groups

In this paper, we propose a deep learning method with convolutional neural networks (CNNs) using skip connections with layer groups for super-resolution image reconstruction. In the proposed method, entire CNN layers for residual data processing are divided into several layer groups, and skip connections with different multiplication factors are applied from input data to these layer groups. With the proposed method, the processed data in hidden layer units tend to be distributed in a wider range. Consequently, the feature information from input data is transmitted to the output more robustly. Experimental results show that the proposed method yields a higher peak signal-to-noise ratio and better subjective quality than existing methods for super-resolution image reconstruction.

Sign in / Sign up

Export Citation Format

Share Document