Roberto Souza^{1}, M Louis Lauzon^{1}, Marina Salluzzi^{1}, Letícia Rittner^{2}, and Richard Frayne^{1}

^{1}University of Calgary, Calgary, AB, Canada, ^{2}University of Campinas, Campinas, Brazil

Machine learning is a new frontier for magnetic resonance (MR) image reconstruction, but progress is hampered by a lack of benchmark datasets. Our datasets provides ~200 GB of brain MR data (both raw and reconstructed data) acquired with different acquisition parameters on different scanners from different vendors and different magnetic field intensities. The fastMRI initiative (https://fastmri.org/), also provides raw data but otherwise is complementary. For instance, fastMRI provides raw k-space data corresponding to 2D acquisitions, while our dataset is composed of 3D acquisitions (i.e., with our data, you can under-sample in two directions).

The authors would like to thank NVidia for providing a Titan V GPU, Amazon Web Services for access to cloud-based GPU services, FAPESP CEPID-BRAINN (2013/07559-3) and CAPES PVE (88881.062158/2014-01). R.S. was supported by an NSERC CREATE I3T Award and the T. Chen Fong Fellowship in Medical Imaging from the University of Calgary. R.F. holds the Hopewell Professorship of Brain Imaging at the University of Calgary. L.R. thanks CNPq (308311/2016-7).

^{1}C. Qin, J.
Schlemper, J. Caballero, A. N. Price, J. V. Hajnal, and D. Rueckert,
“Convolutional recurrent neural networks for dynamic MR image reconstruction,”
IEEE Transactions on Medical Imaging, vol. 38, no. 1, pp. 280–290, 2019.

^{2}T. M. Quan, T.
Nguyen-Duc, and W.-K. Jeong, “Compressed sensing MRI reconstruction using a
generative adversarial network with a cyclic loss,” IEEE Transactions on
Medical Imaging, vol. 37, no. 6, pp. 1488– 1497, 2018.

^{3}J. Schlemper, J.
Caballero, J. Hajnal, A. Price, and D. Rueckert, “A deep cascade of
convolutional neural networks for dynamic MR image reconstruction,” IEEE
Transactions on Medical Imaging, vol. 37, no. 2, pp. 491–503, 2018.

^{4}L. Xiang, Y. Chen,
W. Chang, Y. Zhan, W. Lin, Q. Wang, and D. Shen, “Deep learning based
multi-modal fusion for fast MR reconstruction,” IEEE Transactions on Biomedical
Engineering, 2018.

^{5}G. Yang, S. Yu, H.
Dong, G. Slabaugh, P. L. Dragotti, X. Ye, F. Liu, S. Arridge, J. Keegan, and Y.
Guo, “DAGAN: Deep de-aliasing generative adversarial networks for fast
compressed sensing MRI reconstruction,” IEEE Transactions on Medical Imaging,
vol. 37, no. 6, pp. 1310–1321, 2018.

^{6}P. Zhang, F. Wang,
W. Xu, and Y. Li, “Multi-channel generative adversarial network for parallel
magnetic resonance image reconstruction in k-space,” in International
Conference on Medical Image Computing and Computer-Assisted Intervention
(MICCAI). Springer, 2018, pp. 180–188.

^{7}B. Zhu, J. Z. Liu,
S. F. Cauley, B. R. Rosen, and M. S. Rosen, “Image reconstruction by
domain-transform manifold learning,” Nature, vol. 555, no. 7697, p. 487, 2018.

^{8}T. Eo, Y. Jun, T.
Kim, J. Jang, H.-J. Lee, and D. Hwang, “Kiki-net: crossdomain convolutional
neural networks for reconstructing undersampled magnetic resonance images,”
Magnetic Resonance in Medicine, vol. 80, no. 5, pp. 2188–2201, 2018.

^{9}J. Sun, H. Li, Z.
Xu et al., “Deep ADMM-net for compressive sensing MRI,” in Advances in Neural
Information Processing Systems, 2016, pp. 10–18.

^{10}S. Wang, Z. Su, L.
Ying, X. Peng, S. Zhu, F. Liang, D. Feng, and D. Liang, “Accelerating magnetic
resonance imaging via deep learning,” in IEEE International Symposium on
Biomedical Imaging (ISBI). IEEE, 2016, pp. 514–517.

^{11}K. Hammernik, T.
Klatzer, E. Kobler, M. P. Recht, D. K. Sodickson, T. Pock, and F. Knoll,
“Learning a variational network for reconstruction of accelerated MRI data,”
Magnetic Resonance in Medicine, vol. 79, no. 6, pp. 3055–3071, 2018.

^{12}Y. Han, J. Yoo, H.
Kim, H. Shin, K. Sung, and J. Ye, “Deep learning with domain adaptation for
accelerated projection-reconstruction MR,” Magnetic resonance in medicine, vol.
80, no. 3, pp. 1189–1205, 2018.

^{13}K. Zeng, Y. Yang,
G. Xiao, and Z. Chen, “A very deep densely connected network for compressed
sensing mri,” IEEE Access, vol. 7, pp. 85 430– 85 439, 2019.

^{14}M. Mardani, E. Gong, J. Y. Cheng, S. S. Vasanawala, G. Zaharchuk, L. Xing, and J. M. Pauly, “Deep generative adversarial neural networks for compressive sensing MRI,” IEEE Transactions on Medical Imaging, vol. 38, no. 1, pp. 167–179, 2019.

^{15}R. Souza, R. M.
Lebel, and R. Frayne, “A hybrid, dual domain, cascade of convolutional neural
networks for magnetic resonance image reconstruction,” in Proceedings of The
2nd International Conference on Medical Imaging with Deep Learning, ser.
Proceedings of Machine Learning Research, vol. 102. London, United Kingdom:
PMLR, 08–10 Jul 2019, pp. 437–446.

^{16}J. Zbontar, F.
Knoll, A. Sriram, M. J. Muckley, M. Bruno, A. Defazio, M. Parente, K. J. Geras,
J. Katsnelson, H. Chandarana et al., “fastMRI: An open dataset and benchmarks
for accelerated MRI,” arXiv preprint arXiv:1811.08839, 2018.

^{17}R. Souza, O.
Lucena, J. Garrafa, D. Gobbi, M. Saluzzi, S. Appenzeller, L. Rittner, R.
Frayne, and R. Lotufo, “An open, multi-vendor, multifield-strength brain MR
dataset and analysis of publicly available skull stripping methods agreement,”
NeuroImage, 2017.

^{18}E. G. Larsson, D.
Erdogmus, R. Yan, J. C. Principe, and J. R. Fitzsimmons, “Snr-optimality of
sum-of-squares reconstruction for phased-array magnetic resonance imaging,”
Journal of Magnetic Resonance, vol. 163, no. 1, pp. 121–123, 2003.

^{19}A. Mason, J. Rioux,
S. Clarke, A. Costa, M. Schmidt, V. Keough, T. Huynh, and S. Beyea, “Comparison
of objective image quality metrics to expert radiologists’ scoring of
diagnostic quality of MR images.” IEEE transactions on medical imaging, 2019.

^{20}MER Jones, R Frayne, RM Lebel. Image quality impact of randomized sampling trajectories: implications for compressed sensing and a correction strategy Image quality impact of randomized sampling trajectories: implications for compressed sensing and a correction strategy. International Society of Magnetic Resonance in Medicine Annual Meeting, 22-27 April 2017, Honolulu, Hawaii, USA

Table 1. Summary of the reconstructed portion of the CC
dataset.
The dataset is composed of images of older healthy adults (29–80 years) scanned
between 2009 and 2016. All reconstructed images are publicly available and a
subset of these have corresponding segmentation masks for the brain and
hippocampus.

Figure 1 Sample images acquired on scanners from different
vendors and at different magnetic field intensities of the CC dataset

Table
2 Summary of the raw k-space data. The 32-channel and
the phantom are not made publicly available to assess model generalizability to
unseen data as part of the challenge.

Figure
2 Sample 12-channel data. Note that the data is
partially collected in the slice-encoding direction.

Figure 3 Sample 32-channel data.
Note that the data is partially collected in the slice-encoding direction.