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.
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.
Authors: Kerstin Hammernik; Teresa Klatzer; Erich Kobler; Michael P Recht; Daniel K Sodickson; Thomas Pock; Florian Knoll Journal: Magn Reson Med Date: 2017-11-08 Impact factor: 4.668
Authors: Morteza Mardani; Enhao Gong; Joseph Y Cheng; Shreyas S Vasanawala; Greg Zaharchuk; Lei Xing; John M Pauly Journal: IEEE Trans Med Imaging Date: 2018-07-23 Impact factor: 10.048
Authors: Seyed Amir Hossein Hosseini; Burhaneddin Yaman; Steen Moeller; Mingyi Hong; Mehmet Akçakaya Journal: IEEE J Sel Top Signal Process Date: 2020-06-17 Impact factor: 6.856
Authors: Omer Burak Demirel; Burhaneddin Yaman; Logan Dowdle; Steen Moeller; Luca Vizioli; Essa Yacoub; John Strupp; Cheryl A Olman; Kamil Ugurbil; Mehmet Akcakaya Journal: Annu Int Conf IEEE Eng Med Biol Soc Date: 2021-11
Authors: Allard A Hendriksen; Minna Bührer; Laura Leone; Marco Merlini; Nicola Vigano; Daniël M Pelt; Federica Marone; Marco di Michiel; K Joost Batenburg Journal: Sci Rep Date: 2021-06-04 Impact factor: 4.379