Abstract
The extraction of spines from medical records in a fast yet accurate way is a challenging task, especially for large data sets. Addressing this issue, we present a framework based on convolutional neural networks for the reconstruction of the spinal shape and curvature, making statistical assessments feasible on epidemiological scale. Our method uses a two-step strategy. First, anchor vertebrae and the spinal centerline in between them get extracted. Second, the centerlines are transformed into a common coordinate system to enable comparisons and statistical assessments across subjects. Our networks were trained on 103 subjects, where we achieved accuracies of 3.3 mm on average, taking at most 1 s per record, which eases the handling of even very large cohorts. Without any further training, we validated our model on study data of about 3400 subjects with only 10 cases of failure, which demonstrates the robustness of our method with respect to the natural variability in spinal shape and curvature. A thorough statistical analysis of the results underpins the importance of our work. Specifically, we show that the spinal curvature is significantly influenced by the body mass index of a subject. Moreover, we show that the same findings arise when Cobb angles are considered instead of direct curvature measures. To this end, we propose a generalization of classical Cobb angles that can be evaluated algorithmically and can also serve as a useful (visual) tool for physicians in everyday clinical practice.
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
References
Castro-Mateos, I., Pozo, J.M., Pereañez, M., Lekadir, K., Lazary, A., Frangi, A.F.: Statistical interspace models (SIMS): application to robust 3D spine segmentation. IEEE Trans. Med. Imag. 34(8), 1663–1675 (2015)
Han, Z., Wei, B., Mercado, A., et al.: Spine-GAN: semantic segmentation of multiple spinal structures. Med. Imag. Anal. 50, 23–35 (2018)
Hille, G., Saalfeld, S., Serowy, S., Tönnies, K.: Vertebral body segmentation in wide range clinical routine spine MRI data. Comput. Methods Prog. Biomed. 155, 93–99 (2018)
Korez, R., Likar, B., Pernuš, F., Vrtovec, T.: Model-based segmentation of vertebral bodies from MR images with 3D CNNs. In: Ourselin, S., Joskowicz, L., Sabuncu, M.R., Unal, G., Wells, W. (eds.) MICCAI 2016. LNCS, vol. 9901, pp. 433–441. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46723-8_50
Litjens, G.J.S., Kooi, T., Bejnordi, B.E., et al.: A survey on deep learning in medical image analysis. Med. Image Anal. 42, 60–88 (2017)
Mann, H.B., Whitney, D.R.: On a test of whether one of two random variables is stochastically larger than the other. Ann. Math. Statist. 18, 50–60 (1947)
Milletari, F., Navab, N., Ahmadi, S.: V-NET: fully convolutional neural networks for volumetric medical image segmentation. In: International Conference on 3D Vision (2016)
Pak, C.W., Thomas, J.: Visual analytics. IEEE Comput. Graph Appl. 24(5), 20–21 (2004)
Rak, M., Steffen, J., Meyer, A., et al.: Combining convolutional neural networks and star convex cuts for fast whole spine vertebra segmentation in MRI. Comput. Methods Programs Biomed. 177, 47–56 (2019)
Rak, M., Tönnies, K.D.: On computerized methods for spine analysis in MRI. Int. J. CARS 11(8), 1445–1465 (2016)
Robbins, H., Monro, S.: A stochastic approximation method. Ann. Math. Stat. 22, 400–407 (1951)
Tönnies, K.D., Gloger, O., Rak, M., et al.: Image analysis in epidemiological applications. it (2015)
Völzke, H.: Study of health in pomerania (ship). Bundesgesundheitsblatt - Gesundheitsforschung - Gesundheitsschutz (2012)
Yan, Y.Z., Li, Q.P., Wu, C.C., et al.: Rate of presence of 11 thoracic vertebrae and 6 lumbar vertebrae in asymptomatic Chinese adult volunteers. J. Orthop. Surg. Res. 13, 124 (2018)
Zukić, D., Vlasák, A., Egger, J., et al.: Robust detection and segmentation for diagnosis of vertebral diseases using routine mr images. Comput Graph Forum (2014)
Acknowledgments
We thank all parties and participants of the Study of Health in Pomerania. This work is funded by the EU and the federal state of Saxony-Anhalt, Germany (ZS/2016/08/80388 and ZS/2016/04/78123) as part of the initiative ‘Sachsen-Anhalt WISSENSCHAFT Schwerpunkte’. This work was conducted within the context of the International Graduate School MEMoRIAL at Otto von Guericke University Magdeburg, Germany, kindly supported by the ESF under the program ‘Sachsen-Anhalt WISSENSCHAFT Internationalisierung’ (ZS/2016/08/80646). We thank the NVIDIA Corporation for donating the Titan Xp used for this research.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Ernst, P., Hille, G., Hansen, C., Tönnies, K., Rak, M. (2019). A CNN-Based Framework for Statistical Assessment of Spinal Shape and Curvature in Whole-Body MRI Images of Large Populations. In: Shen, D., et al. Medical Image Computing and Computer Assisted Intervention – MICCAI 2019. MICCAI 2019. Lecture Notes in Computer Science(), vol 11767. Springer, Cham. https://doi.org/10.1007/978-3-030-32251-9_1
Download citation
DOI: https://doi.org/10.1007/978-3-030-32251-9_1
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-32250-2
Online ISBN: 978-3-030-32251-9
eBook Packages: Computer ScienceComputer Science (R0)
