Deep learning with domain adaptation for accelerated projection‐reconstruction MR

• Published in: Magnetic resonance in medicine Vol. 80; no. 3; pp. 1189 - 1205
• Main Authors: Han, Yoseob, Yoo, Jaejun, Kim, Hak Hee, Shin, Hee Jung, Sung, Kyunghyun, Ye, Jong Chul
• Format: Journal Article
• Language: English
• Published: United States Wiley Subscription Services, Inc 01-09-2018
• Subjects: Adaptation; Algorithms; compressed sensing; Computed tomography; convolutional neural network; Datasets; Deep learning; domain adaptation; Image quality; Image reconstruction; Image restoration; Magnetic resonance imaging; Medical imaging; projection reconstruction MRI; Training; Trajectories; deep learning; compressed sensing; domain adaptation; projection reconstruction MRI; convolutional neural network
• ISSN: 0740-3194; 1522-2594
• DOI: 10.1002/mrm.27106

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.