Abstract
Magnetic resonance (MR) images are often acquired as multi-slice volumes to reduce scan time and motion artifacts while improving signal-to-noise ratio. These slices often are thicker than their in-plane resolution and sometimes are acquired with gaps between slices. Such thick-slice image volumes (possibly with gaps) can impact the accuracy of volumetric analysis and 3D methods. While many super-resolution (SR) methods have been proposed to address thick slices, few have directly addressed the slice gap scenario. Furthermore, data-driven methods are sensitive to domain shift due to the variability of resolution, contrast in acquisition, pathology, and differences in anatomy. In this work, we propose a self-supervised SR technique to address anisotropic MR images with and without slice gap. We compare against competing methods and validate in both signal recovery and downstream task performance on two open-source datasets and show improvements in all respects. Our code publicly available at https://gitlab.com/iacl/smore.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Du, J., et al.: Super-resolution reconstruction of single anisotropic 3D MR images using residual convolutional neural network. Neurocomputing 392, 209–220 (2020)
Han, S.: Cerebellum parcellation from magnetic resonance imaging using deep learning. PhD thesis, Johns Hopkins University, Baltimore, MD (2022)
Han, S., Remedios, S., Carass, A., Schär, M., Prince, J.L.: MR slice profile estimation by learning to match internal patch distributions. In: Feragen, A., Sommer, S., Schnabel, J., Nielsen, M. (eds.) IPMI 2021. LNCS, vol. 12729, pp. 108–119. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-78191-0_9
Han, S., Remedios, S.W., Schär, M., Carass, A., Prince, J.L.: ESPRESO: an algorithm to estimate the slice profile of a single magnetic resonance image. Magn. Reson. Imaging 98, 155–163 (2023)
Huo, Y., Xu, Z., Xiong, Y., Aboud, K., Parvathaneni, P., Bao, S., Bermudez, C., Resnick, S.M., Cutting, L.E., Landman, B.A.: 3D whole brain segmentation using spatially localized atlas network tiles. Neuroimage 194, 105–119 (2019)
Iglesias, J.E., et al.: SynthSR: a public AI tool to turn heterogeneous clinical brain scans into high-resolution T1-weighted images for 3D morphometry. Sci. Adv. 9(5), eadd3607 (2023)
Krishnan, A.P., Upendra, R.R., Pramanik, A., Song, Z., Carano, R.A., Initiative, A.D.N.: Multimodal super resolution with dual domain loss and gradient guidance. In: Simulation and Synthesis in Medical Imaging: 7th International Workshop, SASHIMI 2022, Held in Conjunction with MICCAI 2022, Singapore, September 18, 2022, Proceedings, pp. 91–100. Springer (2022). https://doi.org/10.1007/978-3-031-16980-9_9
LaMontagne, P.J., et al.: OASIS-3: longitudinal neuroimaging, clinical, and cognitive dataset for normal aging and alzheimer disease. medRxiv (2019)
Lesjak, Ž, et al.: A novel public MR image dataset of multiple sclerosis patients with lesion segmentations based on multi-rater consensus. Neuroinformatics 16, 51–63 (2018)
Lim, B., Son, S., Kim, H., Nah, S., Mu Lee, K.: Enhanced deep residual networks for single image super-resolution. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 136–144 (2017)
Lu, Z., et al.: Two-stage self-supervised cycle-consistency transformer network for reducing slice gap in MR images. IEEE J. Biomed. Health Inform. 27(7), 3337–3348 (2023)
Martin, J., Ong, F., Ma, J., Tamir, J.I., Lustig, M., Grissom, W.A.: SigPy.RF: comprehensive open-source RF pulse design tools for reproducible research. In: Proceedings of the International Society for Magnetic Resonance in Medicine. ISMRM Annual Meeting, vol. 1045 (2020)
Peng, C., Zhou, S.K., Chellappa, R.: DA-VSR: domain adaptable volumetric super-resolution for medical images. In: de Bruijne, M., et al. (eds.) MICCAI 2021. LNCS, vol. 12906, pp. 75–85. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-87231-1_8
Remedios, S.W., et al.: Cautions in anisotropy: thick slices and slice gaps in 2D magnetic resonance acquisition tarnish volumetrics. Int. J. Multiple Sclerosis Care 25, 55 (2023)
Remedios, S.W., Han, S., Dewey, B.E., Pham, D.L., Prince, J.L., Carass, A.: Joint image and label self-super-resolution. In: Svoboda, D., Burgos, N., Wolterink, J.M., Zhao, C. (eds.) SASHIMI 2021. LNCS, vol. 12965, pp. 14–23. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-87592-3_2
Remedios, S.W., et al.: Deep filter bank regression for super-resolution of anisotropic MR brain images. In: Medical Image Computing and Computer Assisted Intervention-MICCAI 2022: 25th International Conference, Singapore, September 18–22, 2022, Proceedings, Part VI, pp. 613–622. Springer, Cham (2022). https://doi.org/10.1007/978-3-031-16446-0_58
Shi, W., et al.: Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1874–1883 (2016)
Smith, L.N., Topin, N.: Super-convergence: very fast training of neural networks using large learning rates. In: Artificial Intelligence and Machine Learning for Multi-domain Operations Applications, vol. 11006, pp. 369–386. SPIE (2019)
Wu, Q., et al.: IREM: high-resolution magnetic resonance image reconstruction via implicit neural representation. In: de Bruijne, M., et al. (eds.) MICCAI 2021. LNCS, vol. 12906, pp. 65–74. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-87231-1_7
Yu, J., Fan, Y., Yang, J., Xu, N., Wang, X., Huang, T.S.: Wide activation for efficient and accurate image super-resolution. arXiv preprint arXiv:1808.08718 (2018)
Zhang, H., et al.: Self-supervised arbitrary scale super-resolution framework for anisotropic MRI. arXiv preprint arXiv:2305.01360 (2023)
Zhao, C., Dewey, B.E., Pham, D.L., Calabresi, P.A., Reich, D.S., Prince, J.L.: SMORE: a self-supervised anti-aliasing and super-resolution algorithm for MRI using deep learning. IEEE Trans. Med. Imaging 40(3), 805–817 (2020)
Zhao, C., et al.: Applications of a deep learning method for anti-aliasing and super-resolution in MRI. Magn. Reson. Imaging 64, 132–141 (2019)
Acknowledgements
This material is supported by the National Science Foundation Graduate Research Fellowship under Grant No. DGE-1746891 (Remedios). Development is partially supported by NIH ORIP grant R21 OD030163 (Pham). This work also received support from National Multiple Sclerosis Society RG-1907-34570 (Pham), FG-2008-36966 (Dewey), CDMRP W81XWH2010912 (Prince), and the Department of Defense in the Center for Neuroscience and Regenerative Medicine. The opinions and assertions expressed herein are those of the authors and do not reflect the official policy or position of the Uniformed Services University of the Health Sciences or the Department of Defense.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Remedios, S.W. et al. (2023). Self-Supervised Super-Resolution for Anisotropic MR Images with and Without Slice Gap. In: Wolterink, J.M., Svoboda, D., Zhao, C., Fernandez, V. (eds) Simulation and Synthesis in Medical Imaging. SASHIMI 2023. Lecture Notes in Computer Science, vol 14288. Springer, Cham. https://doi.org/10.1007/978-3-031-44689-4_12
Download citation
DOI: https://doi.org/10.1007/978-3-031-44689-4_12
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-44688-7
Online ISBN: 978-3-031-44689-4
eBook Packages: Computer ScienceComputer Science (R0)