Abstract
This paper summarizes our approaches and results for the three tasks of the Learn2Reg 2021 MICCAI Grand Challenge focused on the registration of: (1) intra-patient abdominal CT and MR images, (2) intra-patient expiration and inspiration lung CT scans, and (3) inter-patient brain MR images. These registration tasks have multiple challenges including dealing with multi-modal scans, estimating large deformations, lack of training data, and missing data. For Task 1, we first segmented four organs in both CT and MRI and, second, used them in a two-stage deformable registration pipeline. Our approach has achieved a Dice coefficient of 0.71. For Task 2, we handled missing data in the expiration CT by using a pairwise geodesic density registration algorithm that excludes data outside the lungs. Our approach has achieved a target registration error of 2.3 mm. For Task 3, we modified the VoxelMorph architecture to give more degrees of freedom to the registration model and used it to register brain MRI across patients. Our approach has achieved a Dice coefficient of 0.78. Overall, our team has won second place out of 35 submissions from 15 teams.
W. Shao and S. Vesal—Equal contribution as first authors.
G. Sonn and M. Rusu—Equal contribution as senior authors.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Balakrishnan, G., Zhao, A., Sabuncu, M.R., Guttag, J., Dalca, A.V.: VoxelMorph: a learning framework for deformable medical image registration. IEEE Trans. Med. Imaging 38(8), 1788–1800 (2019)
Clark, K., et al.: The Cancer Imaging Archive (TCIA): maintaining and operating a public information repository. J. Digit. Imaging 26(6), 1045–1057 (2013)
Dalca, A.V., Balakrishnan, G., Guttag, J., Sabuncu, M.R.: Unsupervised learning for fast probabilistic diffeomorphic registration. In: Frangi, A.F., Schnabel, J.A., Davatzikos, C., Alberola-López, C., Fichtinger, G. (eds.) MICCAI 2018. LNCS, vol. 11070, pp. 729–738. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-00928-1_82
Hering, A., et al.: Learn2Reg: comprehensive multi-task medical image registration challenge, dataset and evaluation in the era of deep learning. arXiv preprint arXiv:2112.04489 (2021)
Shao, W., et al.: Geodesic density regression for correcting 4DCT pulmonary respiratory motion artifacts. Med. Image Anal. 72, 102140 (2021)
Vesal, S., Gu, M., Kosti, R., Maier, A., Ravikumar, N.: Adapt everywhere: unsupervised adaptation of point-clouds and entropy minimization for multi-modal cardiac image segmentation. IEEE Trans. Med. Imaging 40(7), 1838–1851 (2021)
Acknowledgments
This work was supported by the Department of Radiology and the Department of Urology at Stanford University.
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 Springer Nature Switzerland AG
About this paper
Cite this paper
Shao, W. et al. (2022). The Learn2Reg 2021 MICCAI Grand Challenge (PIMed Team). In: Aubreville, M., Zimmerer, D., Heinrich, M. (eds) Biomedical Image Registration, Domain Generalisation and Out-of-Distribution Analysis. MICCAI 2021. Lecture Notes in Computer Science(), vol 13166. Springer, Cham. https://doi.org/10.1007/978-3-030-97281-3_24
Download citation
DOI: https://doi.org/10.1007/978-3-030-97281-3_24
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-97280-6
Online ISBN: 978-3-030-97281-3
eBook Packages: Computer ScienceComputer Science (R0)
