期刊
JOURNAL OF IMAGING
卷 4, 期 11, 页码 -出版社
MDPI
DOI: 10.3390/jimaging4110128
关键词
machine learning; deep learning; image reconstruction; tomography
资金
- Netherlands Organisation for Scientific Research (NWO) [639.073.506, 016.Veni.192.235]
- Center for Advanced Mathematics for Energy Research Applications (CAMERA) - Advanced Scientific Computing Research (ASCR)
- Center for Advanced Mathematics for Energy Research Applications (CAMERA) - Basic Energy Sciences (BES) branches of the Office of Science, US Department of Energy
In many applications of tomography, the acquired data are limited in one or more ways due to unavoidable experimental constraints. In such cases, popular direct reconstruction algorithms tend to produce inaccurate images, and more accurate iterative algorithms often have prohibitively high computational costs. Using machine learning to improve the image quality of direct algorithms is a recently proposed alternative, for which promising results have been shown. However, previous attempts have focused on using encoder-decoder networks, which have several disadvantages when applied to large tomographic images, preventing wide application in practice. Here, we propose the use of the Mixed-Scale Dense convolutional neural network architecture, which was specifically designed to avoid these disadvantages, to improve tomographic reconstruction from limited data. Results are shown for various types of data limitations and object types, for both simulated data and large-scale real-world experimental data. The results are compared with popular tomographic reconstruction algorithms and machine learning algorithms, showing that Mixed-Scale Dense networks are able to significantly improve reconstruction quality even with severely limited data, and produce more accurate results than existing algorithms.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据