Statistical Shape Model to 3D Ultrasound Registration for Spine Interventions Using Enhanced Local Phase Features

  • Ilker Hacihaliloglu
  • Abtin Rasoulian
  • Robert N. Rohling
  • Purang Abolmaesumi
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8150)


Accurate registration of ultrasound images to statistical shape models is a challenging problem in percutaneous spine injection procedures due to the typical imaging artifacts inherent to ultrasound. In this paper we propose a robust and accurate registration method that matches local phase bone features extracted from ultrasound images to a statistical shape model. The local phase information for enhancing the bone surfaces is obtained using a gradient energy tensor filter, which combines advantages of the monogenic scale-space and Gaussian scale-space filters, resulting in an improved simultaneous estimation of phase and orientation information. A novel statistical shape model was built by separating the pose statistics from the shape statistics. This model is then registered to the local phase bone surfaces using an iterative expectation maximization registration technique. Validation on 96 in vivo clinical scans obtained from eight patients resulted in a root mean square registration error of 2 mm (SD: 0.4 mm), which is below the clinically acceptable threshold of 3.5 mm. The improvement achieved in registration accuracy using the new features was also significant (p < 0.05) compared to state of the art local phase image processing methods.


Ultrasound local phase spinal injection gradient energy tensor image registration statistical shape model 


  1. 1.
    Frymoyer, J.D.: Back pain and sciatica. N. England J. Med. 318, 291–300 (1988)CrossRefGoogle Scholar
  2. 2.
    Osterman, M.J.K., Martin, J.A.: Epidural and spinal anesthesia use during labor: 27-state reporting area, 2008. Nat. Vital Statistics Reports, vol. 59(5). NCHS, Hyattsville (2011)Google Scholar
  3. 3.
    Rasoulian, A., Abolmaesumi, P., Mousavi, P.: Feature-based multi-body rigid registration of CT and US images of lumbar spine. Med. Phys. 39(6), 3154–3167 (2012)CrossRefGoogle Scholar
  4. 4.
    Foroughi, P., Boctor, E., Swatrz, M.J., Taylor, R.H., Fichtinger, G.: US bone segmentation using dynamic programming. In: IEEE Ultrasonics Symp., pp. 2523–2252 (2007)Google Scholar
  5. 5.
    Mulet-Parada, M., Noble, J.A.: 2D+T boundary detection in echocardiography. Med. Im. Anal. 4(1), 21–30 (2000)CrossRefGoogle Scholar
  6. 6.
    Hacihaliloglu, I., Abugharbieh, R., Hodgson, A., Rohling, R.N.: Automatic adaptive parameterization in local phase feature-based bone segmentation in US. Ultr. in Med. Biol. 37(10), 1689–1703 (2011)Google Scholar
  7. 7.
    Gill, S., Abolmaesumi, P., Fichtinger, G., Boisvert, J., Pichora, D., Borshneck, D., Mousavi, P.: Biomechanically constrained groupwise US to CT registration of the lumbar spine. Med. Im. Anal. 16(3), 662–674 (2010)CrossRefGoogle Scholar
  8. 8.
    Khallaghi, S., Mousavi, P., Borschneck, D., Fichtinger, G., Abolmaesumi, P.: Biomechanically constrained groupwise statistical shape model to ultrasound registration of the lumbar spine. In: Taylor, R.H., Yang, G.-Z. (eds.) IPCAI 2011. LNCS, vol. 6689, pp. 47–54. Springer, Heidelberg (2011)CrossRefGoogle Scholar
  9. 9.
    Winter, S., Pechlivanis, I., Dekomien, C., Igel, C., Schmieder, K.: Toward registration of 3D ultrasound and CT images of the spine in clinical praxis: design and evaluation of a data acquisition protocol. Ultr. in Med. Biol. 35(11), 1773–1782 (2009)CrossRefGoogle Scholar
  10. 10.
    Rasoulian, A., Rohling, R.N., Abolmaesumi, P.: A statistical multi vertebrae shape+pose model for segmentation of CT images. SPIE Medical Imaging, 86710–86716 (2013)Google Scholar
  11. 11.
    Rahmatullah, B., Papageorghiou, A.T., Noble, J.A.: Integration of local and global features for anatomical object detection in US. In: Ayache, N., Delingette, H., Golland, P., Mori, K. (eds.) MICCAI 2012, Part III. LNCS, vol. 7512, pp. 402–409. Springer, Heidelberg (2012)CrossRefGoogle Scholar
  12. 12.
    Felsberg, M.: The GET operator. LiTH-ISY-R, No. 2633 (2004)Google Scholar
  13. 13.
    Rasoulian, A., Rohling, R.N., Abolmaesumi, P.: Group-wise registration of point sets for statistical shape models. IEEE Trans. Med. Imag. 31(11), 2025–2034 (2012)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Ilker Hacihaliloglu
    • 1
  • Abtin Rasoulian
    • 1
  • Robert N. Rohling
    • 1
    • 2
  • Purang Abolmaesumi
    • 1
  1. 1.Department of Electrical EngineeringUniversity of British ColumbiaVancouverCanada
  2. 2.Department of Mechanical EngineeringUniversity of British ColumbiaVancouverCanada

Personalised recommendations