Abstract
Registration of Magnetic Resonance Imaging (MRI) scans containing pathologies is challenging due to tissue appearance changes, and still an unsolved problem. In this paper, we present our implementation of the Quadratic Penalty Deformable Image Registration (QPDIR) algorithm for the Brain Tumor Sequence Registration (BraTS-Reg) Challenge 2022. The QPDIR algorithm is an intensity-based algorithm which turns computation of deformation field to an optimization problem of minimizing terms of image dissimilarity and regularization. The terms are computed based on processing exhaustive search among image blocks and the optimization is performed using a gradient-free quadratic penalty method. The whole optimization problem is decomposed to several sub-problems and each of them can be solved by straightforward block coordinate decent iteration. The data set of the BraTS-Reg Challenge 2022 has 160 cases. For each case, pre-operative images and follow-up images of 4 different modalities including t1, t1ce, flair and t2 are provided. For each case, we apply QPDIR to register image pairs of each modality to produce the deformation field, and then add the deformation field to landmarks, and merge the predict landmarks of each modality together to compute the final predict landmarks of the case. During the validation phrase, our method produces the average median absolute error(MAE) of 4.425, the average Robustness of 0.734 and the average negative numbers of Jacobi Determinant of 87960.95. The testing phase rank of our method is at 7. Detailed study of case ID 142 are shown in the paper.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Avants, B.B., Epstein, C.L., Grossman, M., Gee, J.C.: Symmetric diffeomorphic image registration with cross-correlation: evaluating automated labeling of elderly and neurodegenerative brain. Med. Image Anal. 12(1), 26–41 (2008)
Avants, B.B., Tustison, N.J., Song, G., Cook, P.A., Klein, A., Gee, J.C.: A reproducible evaluation of ants similarity metric performance in brain image registration. Neuroimage 54(3), 2033–2044 (2011)
Baheti, B., et al.: The brain tumor sequence registration challenge: establishing correspondence between pre-operative and follow-up MRI scans of diffuse glioma patients. arXiv preprint arXiv:2112.06979 (2021)
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)
Beg, M.F., Miller, M.I., Trouvé, A., Younes, L.: Computing large deformation metric mappings via geodesic flows of diffeomorphisms. Int. J. Comput. Vision 61(2), 139–157 (2005)
Castillo, E.: Quadratic penalty method for intensity-based deformable image registration and 4dct lung motion recovery. Med. Phys. 46(5), 2194–2203 (2019)
Chen, J., Frey, E.C., He, Y., Segars, W.P., Li, Y., Du, Y.: TransMorph: transformer for unsupervised medical image registration. arXiv preprint arXiv:2111.10480 (2021)
Chung, J., Gulcehre, C., Cho, K., Bengio, Y.: Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv preprint arXiv:1412.3555 (2014)
Fan, J., Cao, X., Yap, P.T., Shen, D.: BIRNet: brain image registration using dual-supervised fully convolutional networks. Med. Image Anal. 54, 193–206 (2019)
Guéziec, A., Ayache, N.: Smoothing and matching of 3-D space curves. In: Sandini, G. (ed.) ECCV 1992. LNCS, vol. 588, pp. 620–629. Springer, Heidelberg (1992). https://doi.org/10.1007/3-540-55426-2_66
Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)
Kim, Y., Denton, C., Hoang, L., Rush, A.M.: Structured attention networks. arXiv preprint arXiv:1702.00887 (2017)
Levin, D.: The approximation power of moving least-squares. Math. Comput. 67(224), 1517–1531 (1998)
Lipton, Z.C.: The mythos of model interpretability: in machine learning, the concept of interpretability is both important and slippery. Queue 16(3), 31–57 (2018)
Mahapatra, D.: Gan based medical image registration. arXiv preprint arXiv:1805.02369 (2018)
Mahapatra, D., Sedai, S., Garnavi, R.: Elastic registration of medical images with gans. arXiv preprint arXiv:1805.02369 7 (2018)
Nocedal, J., Wright, S.J.: Numerical Optimization. Springer, New York (1999). https://doi.org/10.1007/978-0-387-40065-5
Oh, S., Kim, S.: Deformable image registration in radiation therapy. Radiat. Oncol. J. 35(2), 101 (2017)
Rister, B., Horowitz, M.A., Rubin, D.L.: Volumetric image registration from invariant keypoints. IEEE Trans. Image Process. 26(10), 4900–4910 (2017)
Shen, Z., Vialard, F.X., Niethammer, M.: Region-specific diffeomorphic metric mapping. Adv. Neural Inf. Process. Syst. 32, 1–11 (2019)
Thirion, J.P.: Image matching as a diffusion process: an analogy with Maxwell’s demons. Med. Image Anal. 2(3), 243–260 (1998)
Vaswani, A., et al.: Attention is all you need (2017)
Vercauteren, T., Pennec, X., Perchant, A., Ayache, N.: Diffeomorphic demons: efficient non-parametric image registration. Neuroimage 45(1), S61–S72 (2009)
Acknowledgment
This research was partially supported by National Science Foundation under Grant 2015254. We thank our colleague Yaying Shi for providing comments about using ML/DL methods for this task. We appreciate Dr. Edward Castillo for sharing his idea with us, and we thank the reviewers for their insights.
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
Yan, K., Yan, Y. (2023). Applying Quadratic Penalty Method for Intensity-Based Deformable Image Registration on BraTS-Reg Challenge 2022. In: Bakas, S., et al. Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries. BrainLes 2022. Lecture Notes in Computer Science, vol 14092. Springer, Cham. https://doi.org/10.1007/978-3-031-44153-0_1
Download citation
DOI: https://doi.org/10.1007/978-3-031-44153-0_1
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-44152-3
Online ISBN: 978-3-031-44153-0
eBook Packages: Computer ScienceComputer Science (R0)