Registration Evaluation by De-enhancing CT Images

  • Manh Ha Luu
  • Hassan Boulkhrif
  • Adriaan Moelker
  • Theo van WalsumEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10883)


Image registration is relevant for many medical procedures. For CT-guided ablation procedures, integrating the lesion location from diagnostic contrast-enhanced CT (CECT) images in interventional CT images may provide better guidance for the interventional radiologist. The main requirement for such methods is to accurately align the lesion location. This, in general, can not be measured, and often surrogates are used for the assessment. In this work, we present a method that permits the assessment of the accuracy of the lesion localization, i.e. assessing the value that is relevant for clinical practice. To this end, we developed a method that virtually removes the contrast agent from an interventional CT image, use this image for the registration, and use the original CECT image for the assessment. For the experimental evaluation, imaging data of 20 subjects (33 lesions) were used, and the registration accuracy of a publicly available registration method was assessed using this method.



Theo van Walsum was supported by ITEA project 13031: Benefit.


  1. 1.
    Fischer, B., Modersitzki, J.: Ill-posed medicine-an introduction to image registration. Inverse Prob. 24, 034008 (2008)MathSciNetCrossRefGoogle Scholar
  2. 2.
    Rohlfing, T.: Image similarity and tissue overlaps as surrogates for image registration accuracy: widely used but unreliable. IEEE Trans. Med. Imaging. 31(2), 153–163 (2012)CrossRefGoogle Scholar
  3. 3.
    Luu, H.M., Klink, C., Niessen, W., Moelker, A., van Walsum, T.: An automatic registration method for pre- and post-interventional CT images for assessing treatment success in liver RFA treatment. Med. Phys. 42(9), 5559–5567 (2015)CrossRefGoogle Scholar
  4. 4.
    Luu, H.M., Klink, C., Niessen, W., Moelker, A., Walsum, T.V.: Non-rigid registration of liver CT images for CT-guided ablation of liver tumors. PLOS ONE 11(9), e0161600 (2016)CrossRefGoogle Scholar
  5. 5.
    Laura, C., Drechsler, K., Wesarg, S., Bale, R.: Accurate physics-based registration for the outcome validation of minimal invasive interventions and open liver surgeries. IEEE Trans. Biomed. Eng. PP(99), 1 (2016)Google Scholar
  6. 6.
    Rieder, C., Wirtz, S., Strehlow, J., Zidowitz, S., Bruners, P., Isfort, P., Mahnken, A.H., Peitgen, H.O.: Automatic alignment of pre- and post-interventional liver CT images for assessment of radiofrequency ablation, vol. 8316, pp. 83163E–83163E-8 (2012)Google Scholar
  7. 7.
    Wang, B., Ying, C.A.O.: Liver medical image registration based on biomechanical model. Multimed. Tools Appl. 76, 1–18 (2016)Google Scholar
  8. 8.
    Nielsen, M.S., Østergaard, L.R., Carl, J.: A new method to validate thoracic CT-CT deformable image registration using auto-segmented 3D anatomical landmarks. Acta Oncol. 54(9), 1515–1520 (2015)CrossRefGoogle Scholar
  9. 9.
    Nie, K., Chuang, C., Kirby, N., Braunstein, S., Pouliot, J.: Site-specific deformable imaging registration algorithm selection using patient-based simulated deformations. Med. Phys. 40(4), 041911 (2013)CrossRefGoogle Scholar
  10. 10.
    Klein, S., Staring, M., Murphy, K., Viergever, M., Pluim, J.P.W.: Elastix: a toolbox for intensity-based medical image registration. IEEE Trans. Med. Imaging 29(1), 196–205 (2010)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG, part of Springer Nature 2018

Authors and Affiliations

  • Manh Ha Luu
    • 1
    • 2
  • Hassan Boulkhrif
    • 3
  • Adriaan Moelker
    • 3
  • Theo van Walsum
    • 1
    Email author
  1. 1.Biomedical Imaging Group Rotterdam Departments of Radiology & Nuclear Medicine and Medical InformaticsErasmus MC – University Medical Center RotterdamRotterdamThe Netherlands
  2. 2.AVITECH – University of Technology and Engineering, VNUHanoiVietnam
  3. 3.Department of Radiology & Nuclear MedicineErasmus MC – University Medical Center RotterdamRotterdamThe Netherlands

Personalised recommendations