Advertisement

An Automated Cobb Angle Estimation Method Using Convolutional Neural Network with Area Limitation

  • Kailai Zhang
  • Nanfang Xu
  • Guosheng Yang
  • Ji WuEmail author
  • Xiangling Fu
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11769)

Abstract

Cobb angle measurement is the gold standard for the idiopathic scoliosis assessment, and the measurement result is very important for the surgical planning and medical curing. Currently, the Cobb angle is measured manually by physicians. They find the four landmarks on each vertebra and calculate the Cobb angle by rules, which is time-consuming and unreliable. In this paper, we apply the convolutional neural network (CNN) to find the landmarks automatically based on anterior-posterior view X-rays, then output the Cobb angle results. The X-rays always have too much noise, which has a strong influence on the landmark estimation. Addressing this problem, we first detect each vertebra bounding box to provide an area limitation. Then we use the CNN with an enhancement module to find the landmarks on detected vertebra bounding boxes, which can remove the noise in the background. Our experiment results show that our two-stage framework achieves precise landmark location and small error on Cobb angle estimation. Therefore our method can provide reliable assistance for the physicians.

Keywords

Cobb angle Convolutional neural network Area limitation 

References

  1. 1.
    Glassman, S., Bridwell, K., Berven, S., Horton, W., Schwab, F.: The impact of positive sagittal balance in adult spinal deformity. Spine J. 4(5–supp–S), S113–S114 (2004). P90CrossRefGoogle Scholar
  2. 2.
    Cobb, J.: Outline for the study of scoliosis. Instr. Course Lect. 5, 261–275 (1948)Google Scholar
  3. 3.
    Anitha, H., Prabhu, G.K.: Automatic quantification of spinal curvature in scoliotic radiograph using image processing. J. Med. Syst. 36(3), 1943–1951 (2012)CrossRefGoogle Scholar
  4. 4.
    Sardjono, T.A., et al.: Automatic cobb angle determination from radiographic images. Spine 38(20), E1256–E1262 (2013)CrossRefGoogle Scholar
  5. 5.
    Sun, H., Zhen, X., Bailey, C., Rasoulinejad, P., Yin, Y., Li, S.: Direct estimation of spinal cobb angles by structured multi-output regression. In: Niethammer, M., et al. (eds.) IPMI 2017. LNCS, vol. 10265, pp. 529–540. Springer, Cham (2017).  https://doi.org/10.1007/978-3-319-59050-9_42CrossRefGoogle Scholar
  6. 6.
    Wu, H., Bailey, C., Rasoulinejad, P., Li, S.: Automatic landmark estimation for adolescent idiopathic scoliosis assessment using BoostNet. In: Descoteaux, M., Maier-Hein, L., Franz, A., Jannin, P., Collins, D.L., Duchesne, S. (eds.) MICCAI 2017. LNCS, vol. 10433, pp. 127–135. Springer, Cham (2017).  https://doi.org/10.1007/978-3-319-66182-7_15CrossRefGoogle Scholar
  7. 7.
    Wu, H., Bailey, C., Rasoulinejad, P., Li, S.: Automated comprehensive adolescent idiopathic scoliosis assessment using MVC-Net. Med. Image Anal. 48, 1–11 (2018)CrossRefGoogle Scholar
  8. 8.
    He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)Google Scholar
  9. 9.
    Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234–241. Springer, Cham (2015).  https://doi.org/10.1007/978-3-319-24574-4_28CrossRefGoogle Scholar
  10. 10.
    He, K., Gkioxari, G., Dollár, P., Girshick, R.: Mask R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2961–2969 (2017)Google Scholar
  11. 11.
    Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39(6), 1137–1149 (2017)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Kailai Zhang
    • 1
  • Nanfang Xu
    • 3
  • Guosheng Yang
    • 4
  • Ji Wu
    • 1
    • 2
    Email author
  • Xiangling Fu
    • 4
  1. 1.Department of Electronic EngineeringTsinghua UniversityBeijingChina
  2. 2.Institute for Precision MedicineTsinghua UniversityBeijingChina
  3. 3.Peking University Third HospitalBeijingChina
  4. 4.School of Software EngineeringBeijing University of Posts and TelecommunicationsBeijingChina

Personalised recommendations