Automatic Multi-modal Cervical Spine Image Atlas Segmentation

Using Adaptive Stochastic Gradient Descent
  • Ibraheem Al-DhamariEmail author
  • Sabine Bauer
  • Dietrich Paulus
Conference paper
Part of the Informatik aktuell book series (INFORMAT)


A personalized medicine has been advanced in different fields of medicine to combat, control and prevent a number of diseases. In personalized medicine, products are customized and only suitable for a specific patient. In spinal surgery, medical images are taken into account to implant spinal devices with the aim of minimizing the risk of insufficient implant fit. A model of the spine is generated from these images and used in biomechanic framework to simulate the effect of the customized implant on a specific patient.

To generate such a model, an efficient and practical segmentation method is needed which is proposed in this paper. The large deformation of human spine and the touching boundaries of neighboring vertebrae make the problem of spine segmentation very challenging. The classical segmentation methods e.g. thresholding or region growing fail to separate different vertebrae. The state of the art methods using shape models require a long time for training and testing. A new method for automatic multi-modal cervical spine segmentation is proposed in this paper. The proposed method requires only a few seconds to segment a specific vertebra or the whole cervical spine. It is provided as Slicer 3D plug-in which is free and open-source. The public datasets available fail to provide high quality MRI cervical spine images. Another contribution of this study is providing a high quality multi-modal cervical spine public and free dataset.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Bauer S, Paulus D. Computational simulation as an innovative approach in personalized medicine. in Innovations in Spinal Deformities and Postural Disorders; 2017.Google Scholar
  2. 2.
    Gonzale R, Woods R. Digital image processing. Prentice-Hall, USA; 2006.Google Scholar
  3. 3.
    Hajnal H Hill. Medical image registration. CRC Press; 2001.Google Scholar
  4. 4.
    Al-Dhamari I, Bauer S, Paulus D, et al. ACIR: automatic cochlea image registration. Proc SPIE. 2017;10133(10):47–67.Google Scholar
  5. 5.
    Klein, Pluim, Staring, et al. Adaptive stochastic gradient descent optimisation for image registration. Int Jo Comput Vis. 2009;81(3):227–239.Google Scholar
  6. 6.
    Mattes, Haynor, Vesselle, et al. Non-rigid multimodality image registration. Proc SPIEs. 2001; p. 1609–1620.Google Scholar
  7. 7.
    Klein, Staring, Murphy, et al. elastix: a toolbox for intensity-based medical image registration. IEEE Trans Med Imaging. 2010;29(1):196–205.Google Scholar
  8. 8.
    Qiao, van Lew, Lelieveldt, et al. Fast automatic step Size Estimation for Gradient Descent Optimization of Image Registration. IEEE Trans Med Imaging. 2016;35(2):391–403.Google Scholar
  9. 9.
    Qiao Y, Sun Z, Lelieveldt B, et al. A stochastic quasi-newton method for non-rigid image registration. Proc MICCAI. 2015;9350(1):297–304.Google Scholar
  10. 10.
    Dice, R L. Measures of the amount of ecologic association between species. Ecology. 1945;26(3):297–302.Google Scholar
  11. 11.
    Hausdorff F. Grundzüge der mengenlehre. Leipzig: Veit; 1914.Google Scholar

Copyright information

© Springer-Verlag GmbH Deutschland 2018

Authors and Affiliations

  • Ibraheem Al-Dhamari
    • 1
    Email author
  • Sabine Bauer
    • 1
  • Dietrich Paulus
    • 1
  1. 1.Medizinische Tekchnik Institut (MTI)Koblenz and Landau UniversityMainzDeutschland

Personalised recommendations