scholarly journals Deep learning enables structured illumination microscopy with low light levels and enhanced speed

2020 ◽  
Vol 11 (1) ◽  
Author(s):  
Luhong Jin ◽  
Bei Liu ◽  
Fenqiang Zhao ◽  
Stephen Hahn ◽  
Bowei Dong ◽  
...  
2019 ◽  
Author(s):  
Luhong Jin ◽  
Bei Liu ◽  
Fenqiang Zhao ◽  
Stephen Hahn ◽  
Bowei Dong ◽  
...  

AbstractUsing deep learning to augment structured illumination microscopy (SIM), we obtained a fivefold reduction in the number of raw images required for super-resolution SIM, and generated images under extreme low light conditions (100X fewer photons). We validated the performance of deep neural networks on different cellular structures and achieved multi-color, live-cell super-resolution imaging with greatly reduced photobleaching.


2020 ◽  
Vol 8 (8) ◽  
pp. 1350 ◽  
Author(s):  
Chang Ling ◽  
Chonglei Zhang ◽  
Mingqun Wang ◽  
Fanfei Meng ◽  
Luping Du ◽  
...  

2021 ◽  
Author(s):  
ZAFRAN HUSSAIN SHAH ◽  
Marcel Müller ◽  
TUNG-CHENG WANG ◽  
Philip Scheidig ◽  
Axel Schneider ◽  
...  

Author(s):  
Miguel A. Boland ◽  
Edward A. K. Cohen ◽  
Seth R. Flaxman ◽  
Mark A. A. Neil

Structured Illumination Microscopy (SIM) is a widespread methodology to image live and fixed biological structures smaller than the diffraction limits of conventional optical microscopy. Using recent advances in image up-scaling through deep learning models, we demonstrate a method to reconstruct 3D SIM image stacks with twice the axial resolution attainable through conventional SIM reconstructions. We further demonstrate our method is robust to noise and evaluate it against two-point cases and axial gratings. Finally, we discuss potential adaptions of the method to further improve resolution. This article is part of the Theo Murphy meeting issue ‘Super-resolution structured illumination microscopy (part 1)’.


Author(s):  
Nihar Das ◽  
Nisarg Sharma ◽  
Vaishnavi Shebare ◽  
Parth Dawda ◽  
Prajakta Gourkhede ◽  
...  

With the ever-growing field of microscopy there is pretty much a necessity of high - resolution microscopic images. A microscope may have powerful magnifying lenses, but if the resolution is poor, the magnified image is just blur and no useful insights can be gained from such images. Traditional techniques like Structured Illumination Microscopy (SIM) are not feasible enough for proper use and current solutions based on deep learning assume that the input image is noise free. Based on our research and existing applications related to deep learning-based image enhancement, our proposed solution of deep learning based General Adversarial Network (GAN), will help jointly denoise and super-resolved microscopy images. Thus, this project has competitive applications in different research areas including biomedical microscopy, medical diagnosis, astronomical research, surveillance or investigation, etc., and many other areas as well.


Author(s):  
Doron Shterman ◽  
Gilad Feinberg ◽  
Shai Tsesses ◽  
Yochai Blau ◽  
Guy Bartal

Author(s):  
Yongbing Zhang ◽  
Xu Chen ◽  
Bowen Li ◽  
Shaowei Jiang ◽  
Terrance Zhang ◽  
...  

Sign in / Sign up

Export Citation Format

Share Document