Abstract
Cardiac magnetic resonance (CMR) imaging is the most accurate imaging modality for cardiac function analysis. However respiration misalignment can negatively impact the accuracy of the cardiac wall 3D segmentation and the assessment of cardiac function. A learning based misalignment correction method is needed, in order to build an end-to-end accurate cardiac function analysis pipeline. To this end, we proposed an unsupervised misalignment correction network to solve this challenge problem. We validated the proposed framework on synthetic and real CMR segmented images, and the result prove the efficiency of misalignment correction and the improvement with the corrected CMR image. Experimental results using our approach show that it: 1) could more efficiently correct the misalignment of CMR images compared with the traditional optimization process. 2) incorporated an unsupervised loss named “intersection distance” loss to guide the network output to the accurate correction prediction. 3) is the first to use the unsupervised learning based method for Cardiac MR slices’ misalignment problem and achieved more accurate results.
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
Biffi, C., et al.: 3D high-resolution cardiac segmentation reconstruction from 2D views using conditional variational autoencoders. In: 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019), pp. 1643–1646. IEEE (2019)
Cavalcante, J.L., Lalude, O.O., Schoenhagen, P., Lerakis, S.: Cardiovascular magnetic resonance imaging for structural and valvular heart disease interventions. JACC: Cardiovasc. Interv. 9(5), 399–425 (2016)
Chandler, A.G., et al.: Correction of misaligned slices in multi-slice cardiovascular magnetic resonance using slice-to-volume registration. J. Cardiovasc. Magn. Reson. 10(1), 1–9 (2008)
Fonseca, C.G., et al.: The cardiac atlas project-an imaging database for computational modeling and statistical atlases of the heart. Bioinformatics 27(16), 2288–2295 (2011)
Glorot, X., Bordes, A., Bengio, Y.: Deep sparse rectifier neural networks. In: Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics, pp. 315–323 (2011)
Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv:1502.03167 (2015)
Lötjönen, J., Pollari, M., Kivistö, S., Lauerma, K.: Correction of movement artifacts from 4-D cardiac short- and long-axis MR data. In: Barillot, C., Haynor, D.R., Hellier, P. (eds.) MICCAI 2004. LNCS, vol. 3217, pp. 405–412. Springer, Heidelberg (2004). https://doi.org/10.1007/978-3-540-30136-3_50
Metaxas, D.N., Yan, Z.: Chapter 12 - deformable models, sparsity and learning-based segmentation for cardiac MRI based analytics. In: Zhou, S.K., Rueckert, D., Fichtinger, G. (eds.) Handbook of Medical Image Computing and Computer Assisted Intervention, pp. 273–292. Academic Press (2020)
Moriyama, I.M., Krueger, D.E., Stamler, J.: Cardiovascular diseases in the United States, vol. 10. Harvard University Press (1971)
Pazos-López, P., et al.: Value of CMR for the differential diagnosis of cardiac masses. JACC: Cardiovasc. Imaging 7(9), 896–905 (2014)
Ruijsink, B., et al.: Fully automated, quality-controlled cardiac analysis from CMR: validation and large-scale application to characterize cardiac function. Cardiovasc. Imaging 13(3), 684–695 (2020)
Scheffler, K., Lehnhardt, S.: Principles and applications of balanced SSFP techniques. Eur. Radiol. 13(11), 2409–2418 (2003)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)
Sinclair, M., Bai, W., Puyol-Antón, E., Oktay, O., Rueckert, D., King, A.P.: Fully automated segmentation-based respiratory motion correction of multiplanar cardiac magnetic resonance images for large-scale datasets. In: Descoteaux, M., Maier-Hein, L., Franz, A., Jannin, P., Collins, D.L., Duchesne, S. (eds.) MICCAI 2017. LNCS, vol. 10434, pp. 332–340. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-66185-8_38
Villard, B., Zacur, E., Dall’Armellina, E., Grau, V.: Correction of slice misalignment in multi-breath-hold cardiac MRI scans. In: Mansi, T., McLeod, K., Pop, M., Rhode, K., Sermesant, M., Young, A. (eds.) STACOM 2016. LNCS, vol. 10124, pp. 30–38. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-52718-5_4
Wilkins, E., et al.: European cardiovascular disease statistics 2017 (2017)
Yang, D., Huang, Q., Mikael, K., Al’Aref, S., Axel, L., Metaxas, D.: MRI-based characterization of left ventricle dyssynchrony with correlation to CRT outcomes. In: 2020 IEEE 17th International Symposium on Biomedical Imaging (ISBI), pp. 1–4. IEEE (2020)
Yang, D., Wu, P., Tan, C., Pohl, K.M., Axel, L., Metaxas, D.: 3D motion modeling and reconstruction of left ventricle wall in cardiac MRI. In: Pop, M., Wright, G.A. (eds.) FIMH 2017. LNCS, vol. 10263, pp. 481–492. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-59448-4_46
Zakkaroff, C., Radjenovic, A., Greenwood, J., Magee, D.: Stack alignment transform for misalignment correction in cardiac MR cine series. Technical report. Citeseer (2012)
Zhuang, X.: Challenges and methodologies of fully automatic whole heart segmentation: a review. J. Healthc. Eng. 4, 371–407 (2013)
Zhuang, X., Shen, J.: Multi-scale patch and multi-modality atlases for whole heart segmentation of MRI. Med. Image Anal. 31, 77–87 (2016)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 Springer Nature Switzerland AG
About this paper
Cite this paper
Chang, Q. et al. (2022). An Unsupervised 3D Recurrent Neural Network for Slice Misalignment Correction in Cardiac MR Imaging. In: Puyol Antón, E., et al. Statistical Atlases and Computational Models of the Heart. Multi-Disease, Multi-View, and Multi-Center Right Ventricular Segmentation in Cardiac MRI Challenge. STACOM 2021. Lecture Notes in Computer Science(), vol 13131. Springer, Cham. https://doi.org/10.1007/978-3-030-93722-5_16
Download citation
DOI: https://doi.org/10.1007/978-3-030-93722-5_16
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-93721-8
Online ISBN: 978-3-030-93722-5
eBook Packages: Computer ScienceComputer Science (R0)
