Open AccessImage reconstruction with a deep convolutional neural network in high-density super-resolution microscopy
Author(s) -
Bowen Yao,
Wen Li,
Wenhui Pan,
Zhigang Yang,
Danni Chen,
Jia Li,
Junle Qu
Publication year - 2020
Publication title -
optics express
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.394
H-Index - 271
ISSN - 1094-4087
DOI - 10.1364/oe.392358
Subject(s) - convolutional neural network , computer science , pixel , robustness (evolution) , iterative reconstruction , artificial intelligence , microscopy , optics , image quality , residual , image resolution , full width at half maximum , convolution (computer science) , computer vision , superresolution , algorithm , artificial neural network , image (mathematics) , physics , biochemistry , chemistry , gene
An accurate and fast reconstruction algorithm is crucial for the improvement of temporal resolution in high-density super-resolution microscopy, particularly in view of the challenges associated with live-cell imaging. In this work, we design a deep network based on a convolutional neural network to take advantage of its enhanced ability in high-density molecule localization, and introduce a residual layer into the network to reduce noise. The proposed scheme also incorporates robustness against variations of both the full width at half maximum (FWHM) and the pixel size. We validate our algorithm on both simulated and experimental data by achieving performance improvement in terms of loss value and image quality, and demonstrate live-cell imaging with temporal resolution of 0.5 seconds by recovering mitochondria dynamics.