期刊
MAGNETIC RESONANCE IN MEDICINE
卷 80, 期 3, 页码 1189-1205出版社
WILEY
DOI: 10.1002/mrm.27106
关键词
compressed sensing; convolutional neural network; deep learning; domain adaptation; projection reconstruction MRI
资金
- National Institute of Biomedical Imaging and Bioengineering [EB01705, EB01785]
- National Research Foundation of Korea [NRF-2016R1A2B3008104, NRF-2013M3A9B2076548]
- NIH Blueprint Initiative for Neuroscience Research [U01MH093765]
- National Institutes of Health [P41EB015896]
- NIBIB [K99/R00EB012107]
- National Research Foundation of Korea [2016R1A2B3008104, 2013M3A9B2076548] Funding Source: Korea Institute of Science & Technology Information (KISTI), National Science & Technology Information Service (NTIS)
PurposeThe radial k-space trajectory is a well-established sampling trajectory used in conjunction with magnetic resonance imaging. However, the radial k-space trajectory requires a large number of radial lines for high-resolution reconstruction. Increasing the number of radial lines causes longer acquisition time, making it more difficult for routine clinical use. On the other hand, if we reduce the number of radial lines, streaking artifact patterns are unavoidable. To solve this problem, we propose a novel deep learning approach with domain adaptation to restore high-resolution MR images from under-sampled k-space data. MethodsThe proposed deep network removes the streaking artifacts from the artifact corrupted images. To address the situation given the limited available data, we propose a domain adaptation scheme that employs a pre-trained network using a large number of X-ray computed tomography (CT) or synthesized radial MR datasets, which is then fine-tuned with only a few radial MR datasets. ResultsThe proposed method outperforms existing compressed sensing algorithms, such as the total variation and PR-FOCUSS methods. In addition, the calculation time is several orders of magnitude faster than the total variation and PR-FOCUSS methods. Moreover, we found that pre-training using CT or MR data from similar organ data is more important than pre-training using data from the same modality for different organ. ConclusionWe demonstrate the possibility of a domain-adaptation when only a limited amount of MR data is available. The proposed method surpasses the existing compressed sensing algorithms in terms of the image quality and computation time.
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