TY - JOUR
T1 - Self-supervised learning of physics-guided reconstruction neural networks without fully sampled reference data
AU - Yaman, Burhaneddin
AU - Hosseini, Seyed Amir Hossein
AU - Moeller, Steen
AU - Ellermann, Jutta
AU - Uğurbil, Kâmil
AU - Akçakaya, Mehmet
N1 - Publisher Copyright:
© 2020 International Society for Magnetic Resonance in Medicine
PY - 2020/12/1
Y1 - 2020/12/1
N2 - Purpose: To develop a strategy for training a physics-guided MRI reconstruction neural network without a database of fully sampled data sets. Methods: Self-supervised learning via data undersampling (SSDU) for physics-guided deep learning reconstruction partitions available measurements into two disjoint sets, one of which is used in the data consistency (DC) units in the unrolled network and the other is used to define the loss for training. The proposed training without fully sampled data is compared with fully supervised training with ground-truth data, as well as conventional compressed-sensing and parallel imaging methods using the publicly available fastMRI knee database. The same physics-guided neural network is used for both proposed SSDU and supervised training. The SSDU training is also applied to prospectively two-fold accelerated high-resolution brain data sets at different acceleration rates, and compared with parallel imaging. Results: Results on five different knee sequences at an acceleration rate of 4 shows that the proposed self-supervised approach performs closely with supervised learning, while significantly outperforming conventional compressed-sensing and parallel imaging, as characterized by quantitative metrics and a clinical reader study. The results on prospectively subsampled brain data sets, in which supervised learning cannot be used due to lack of ground-truth reference, show that the proposed self-supervised approach successfully performs reconstruction at high acceleration rates (4, 6, and 8). Image readings indicate improved visual reconstruction quality with the proposed approach compared with parallel imaging at acquisition acceleration. Conclusion: The proposed SSDU approach allows training of physics-guided deep learning MRI reconstruction without fully sampled data, while achieving comparable results with supervised deep learning MRI trained on fully sampled data.
AB - Purpose: To develop a strategy for training a physics-guided MRI reconstruction neural network without a database of fully sampled data sets. Methods: Self-supervised learning via data undersampling (SSDU) for physics-guided deep learning reconstruction partitions available measurements into two disjoint sets, one of which is used in the data consistency (DC) units in the unrolled network and the other is used to define the loss for training. The proposed training without fully sampled data is compared with fully supervised training with ground-truth data, as well as conventional compressed-sensing and parallel imaging methods using the publicly available fastMRI knee database. The same physics-guided neural network is used for both proposed SSDU and supervised training. The SSDU training is also applied to prospectively two-fold accelerated high-resolution brain data sets at different acceleration rates, and compared with parallel imaging. Results: Results on five different knee sequences at an acceleration rate of 4 shows that the proposed self-supervised approach performs closely with supervised learning, while significantly outperforming conventional compressed-sensing and parallel imaging, as characterized by quantitative metrics and a clinical reader study. The results on prospectively subsampled brain data sets, in which supervised learning cannot be used due to lack of ground-truth reference, show that the proposed self-supervised approach successfully performs reconstruction at high acceleration rates (4, 6, and 8). Image readings indicate improved visual reconstruction quality with the proposed approach compared with parallel imaging at acquisition acceleration. Conclusion: The proposed SSDU approach allows training of physics-guided deep learning MRI reconstruction without fully sampled data, while achieving comparable results with supervised deep learning MRI trained on fully sampled data.
KW - accelerated imaging
KW - convolutional neural networks
KW - deep learning
KW - image reconstruction
KW - parallel imaging
KW - self-supervised learning
UR - http://www.scopus.com/inward/record.url?scp=85087296101&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85087296101&partnerID=8YFLogxK
U2 - 10.1002/mrm.28378
DO - 10.1002/mrm.28378
M3 - Article
C2 - 32614100
AN - SCOPUS:85087296101
SN - 0740-3194
VL - 84
SP - 3172
EP - 3191
JO - Magnetic resonance in medicine
JF - Magnetic resonance in medicine
IS - 6
ER -