Advertisement

Direct Automated Quantitative Measurement of Spine via Cascade Amplifier Regression Network

  • Shumao Pang
  • Stephanie Leung
  • Ilanit Ben Nachum
  • Qianjin Feng
  • Shuo Li
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11071)

Abstract

Automated quantitative measurement of the spine (i.e., multiple indices estimation of heights, widths, areas, and so on for the vertebral body and disc) is of the utmost importance in clinical spinal disease diagnoses, such as osteoporosis, intervertebral disc degeneration, and lumbar disc herniation, yet still an unprecedented challenge due to the variety of spine structure and the high dimensionality of indices to be estimated. In this paper, we propose a novel cascade amplifier regression network (CARN), which includes the CARN architecture and local shape-constrained manifold regularization (LSCMR) loss function, to achieve accurate direct automated multiple indices estimation. The CARN architecture is composed of a cascade amplifier network (CAN) for expressive feature embedding and a linear regression model for multiple indices estimation. The CAN consists of cascade amplifier units (AUs), which are used for selective feature reuse by stimulating effective feature and suppressing redundant feature during propagating feature map between adjacent layers, thus an expressive feature embedding is obtained. During training, the LSCMR is utilized to alleviate overfitting and generate realistic estimation by learning the multiple indices distribution. Experiments on MR images of 195 subjects show that the proposed CARN achieves impressive performance with mean absolute errors of 1.2496 ± 1.0624 mm, 1.2887 ± 1.0992 mm, and 1.2692 ± 1.0811 mm for estimation of 15 heights of discs, 15 heights of vertebral bodies, and total indices respectively. The proposed method has great potential in clinical spinal disease diagnoses.

Keywords

Spine Deep learning Manifold regularization Disc height measurement Vertebral body height measurement 

Notes

Acknowledgements

This work was supported by China Scholarship Council (No. 201708440350), National Natural Science Foundation of China (No. U1501256), and Science and Technology Project of Guangdong Province (No. 2015B010131011).

References

  1. 1.
    McCloskey, E., Johansson, H., Oden, A., Kanis, J.A.: Fracture risk assessment. Clin. Biochem. 45(12), 887–893 (2012)CrossRefGoogle Scholar
  2. 2.
    Tatoń, G., Rokita, E., Korkosz, M., Wróbel, A.: The ratio of anterior and posterior vertebral heights reinforces the utility of DXA in assessment of vertebrae strength. Calcif. Tissue Int. 95(2), 112–121 (2014)CrossRefGoogle Scholar
  3. 3.
    Jarman, J.P., Arpinar, V.E., Baruah, D., Klein, A.P., Maiman, D.J., Muftuler, L.T.: Intervertebral disc height loss demonstrates the threshold of major pathological changes during degeneration. Eur. Spine J. 24(9), 1944–1950 (2014)CrossRefGoogle Scholar
  4. 4.
    Salamat, S., Hutchings, J., Kwong, C., Magnussen, J., Hancock, M.J.: The relationship between quantitative measures of disc height and disc signal intensity with Pfirrmann score of disc degeneration. SpringerPlus 5(1), 829 (2016)CrossRefGoogle Scholar
  5. 5.
    Tunset, A., Kjaer, P., Chreiteh, S.S., Jensen, T.S.: A method for quantitative measurement of lumbar intervertebral disc structures: an intra- and inter-rater agreement and reliability study. Chiropr. Man. Ther. 21(1), 26 (2013)CrossRefGoogle Scholar
  6. 6.
    Videman, T., Battié, M.C., Gibbons, L.E., Gill, K.: Aging changes in lumbar discs and vertebrae and their interaction: a 15-year follow-up study. Spine J. 14(3), 469–478 (2014)CrossRefGoogle Scholar
  7. 7.
    Zhen, X., Zhang, H., Islam, A., Bhaduri, M., Chan, I., Li, S.: Direct and simultaneous estimation of cardiac four chamber volumes by multioutput sparse regression. Med. Image Anal. 36, 184–196 (2017)CrossRefGoogle Scholar
  8. 8.
    Xue, W., Lum, A., Mercado, A., Landis, M., Warrington, J., Li, S.: Full quantification of left ventricle via deep multitask learning network respecting intra- and inter-task relatedness. In: Descoteaux, M., Maier-Hein, L., Franz, A., Jannin, P., Collins, D.L., Duchesne, S. (eds.) MICCAI 2017. LNCS, vol. 10435, pp. 276–284. Springer, Cham (2017).  https://doi.org/10.1007/978-3-319-66179-7_32CrossRefGoogle Scholar
  9. 9.
    Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. CoRR abs/1409.1556 (2014)Google Scholar
  10. 10.
    Pang, S., et al.: Hippocampus segmentation based on local linear mapping. Sci. Rep. 7, 45501 (2017)CrossRefGoogle Scholar
  11. 11.
    Huang, G., Liu, Z., van der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, July 2017Google Scholar
  12. 12.
    Liu, G., Lin, Z., Yu, Y.: Multi-output regression on the output manifold. Pattern Recognit. 42(11), 2737–2743 (2009)CrossRefGoogle Scholar
  13. 13.
    Liu, W., He, J., Chang, S.F.: Large graph construction for scalable semi-supervised learning. In: Proceedings of the 27th International Conference on Machine Learning (ICML-2010), pp. 679–686 (2010)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  1. 1.Guangdong Provincial Key Laboratory of Medical Image Processing, School of Biomedical EngineeringSouthern Medical UniversityGuangzhouChina
  2. 2.Department of Medical ImagingWestern UniversityLondonCanada
  3. 3.Digital Imaging Group of LondonLondonCanada

Personalised recommendations