Premium
Deep learning with domain adaptation for accelerated projection‐reconstruction MR
Author(s) -
Han Yoseob,
Yoo Jaejun,
Kim Hak Hee,
Shin Hee Jung,
Sung Kyunghyun,
Ye Jong Chul
Publication year - 2018
Publication title -
magnetic resonance in medicine
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.696
H-Index - 225
eISSN - 1522-2594
pISSN - 0740-3194
DOI - 10.1002/mrm.27106
Subject(s) - streaking , computer science , artificial intelligence , trajectory , artifact (error) , compressed sensing , projection (relational algebra) , deep learning , domain (mathematical analysis) , iterative reconstruction , computer vision , sampling (signal processing) , pattern recognition (psychology) , adaptation (eye) , algorithm , mathematics , physics , mathematical analysis , filter (signal processing) , astronomy , optics
Purpose The 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. Methods The 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. Results The 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. Conclusion We 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.