arrow
返回

Diffraction tomography with a deep image prior

delete2020-04-16
delete96
delete
OA
AI
K
Kevin C. Zhou *
R
Roarke Horstmeyer
DOI:10.1364/OE.379200delete
delete原文链接
delete原文求助
delete分享
delete收藏
摘要

摘要

En 中文
We present a tomographic imaging technique, termed Deep Prior Diffraction Tomography (DP-DT), to reconstruct the 3D refractive index (RI) of thick biological samples at high resolution from a sequence of low-resolution images collected under angularly varying illumination. DP-DT processes the multi-angle data using a phase retrieval algorithm that is extended by a deep image prior (DIP), which reparameterizes the 3D sample reconstruction with an untrained, deep generative 3D convolutional neural network (CNN). We show that DP-DT effectively addresses the missing cone problem, which otherwise degrades the resolution and quality of standard 3D reconstruction algorithms. As DP-DT does not require pre-captured data or pre-training, it is not biased towards any particular dataset. Hence, it is a general technique that can be applied to a wide variety of 3D samples, including scenarios in which large datasets for supervised training would be infeasible or expensive. We applied DP-DT to obtain 3D RI maps of bead phantoms and complex biological specimens, both in simulation and experiment, and show that DP-DT produces higher-quality results than standard regularization techniques. We further demonstrate the generality of DP-DT, using two different scattering models, the first Born and multi-slice models. Our results point to the potential benefits of DP-DT for other 3D imaging modalities, including X-ray computed tomography, magnetic resonance imaging, and electron microscopy. (C) 2020 Optical Society of America under the terms of the OSA Open Access Publishing Agreement
Keyword:
INVERSE PROBLEMS
LEARNING APPROACH
NEURAL-NETWORKS
RECONSTRUCTION
INTENSITY
MICROSCOPY
FIELD

期刊

Optics Express 封面图
Optics Express
IF:
3.3
论文数:
6.1W
被引数:
14.3W

机构

D
Duke University
学者数:
6.3W
论文数: 5.7W
被引数: 6.5W
引用论文

引用论文

On the use of deep learning for computational imaging关于将深度学习用于计算成像
errOPTICA
IF8.5
err2019-07-25
err611
errOAAI
errBarbastathis, George; Ozcan, Aydogan; Situ, Guohai
err分享
err收藏
Simplified approach to diffraction tomography in optical microscopy
err2009-07-20
err53
errOAAI
errFiolka, Reto; Wicker, Kai; Heintzmann, Rainer; Stemmer, Andreas
err分享
err收藏
Optical diffraction tomography for high resolution live cell imaging用于高分辨率活细胞成像的光学衍射层析成像
err2009-01-02
err542
errOAAI
errSung, Yongjin; Choi, Wonshik; Fang-Yen, Christopher; Badizadegan, Kamran; Dasari, Ramachandra R.; Feld, Michael S.
err分享
err收藏
Design and simulation of a snapshot multi-focal interferometric microscope
err2018-10-05
err5
errOAAI
errHe, Kuan; Huang, Xiang; Wang, Xiaolei; Yoo, Seunghwan; Ruiz, Pablo; Gdor, Itay; Ferrier, Nicola J.; Scherer, Norbert; Hereld, Mark; Katsaggelos, Aggelos K.; Cossairt, Oliver
err分享
err收藏
Learning approach to optical tomography
errOPTICA
IF8.5
err2015-05-28
err302
errOAAI
errKamilov, Ulugbek S.; Papadopoulos, Ioannis N.; Shoreh, Morteza H.; Goy, Alexandre; Vonesch, Cedric; Unser, Michael; Psaltis, Demetri
err分享
err收藏
学者 查看更多内容