Resection-Based Demons Regularization for Breast Tumor Bed Propagation

  • Marek WodzinskiEmail author
  • Andrzej Skalski
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11040)


A tumor resection introduces a problem of missing data into the image registration process. The state-of-the-art methods fail while attempting to recover the real deformations when the structure of interest is missing. In this work, we propose an empirical, greedy regularization term which promotes the tumor contraction. The proposed method is simple but very effective. It is based on a priori medical knowledge about the scar localization to promote the direction of the tumor propagation. The proposed method is compared to the Demons algorithm using both the artificially generated data with a known ground-truth and a real, medical data. A relative tumor volume reduction, a Hausdorff distance between the tumor beds, a RMSE between the deformation fields, and a visual inspection are used as the evaluation methods. The proposed method models the tumor resection accurately in the target data and improves the potential dose distribution for the radiotherapy planning.


Image registration Missing data Demons Cancer surgery Breast cancer 



This work was funded by the Ministry of Science and Higher Education in Poland (Dean’s Grant no. and Statutory Activity no. We would like to thank P. Kedzierawski, I. Ciepiela and T. Kuszewski for providing the real, medical CT data and the tumor outlines.


  1. 1.
    Fornefett, M., Rohr, K., Stiehl, H.: Radial basis functions with compact support for elastic registration of medical images. Image Vis. Comput. 19(1–2), 87–96 (2001)CrossRefGoogle Scholar
  2. 2.
    Periaswamy, S., Farid, H.: Medical image registration with partial data. Med. Image Anal. 10(3 Spec. Iss.), 452–464 (2006)CrossRefGoogle Scholar
  3. 3.
    Pock, T., Urschler, M., Zach, C., Beichel, R., Bischof, H.: A duality based algorithm for TV-L1-optical-flow image registration. In: Ayache, N., Ourselin, S., Maeder, A. (eds.) MICCAI 2007. LNCS, vol. 4792, pp. 511–518. Springer, Heidelberg (2007). Scholar
  4. 4.
    Kirova, Y., et al.: How to boost the breast tumor bed? A multidisciplinary approach in eight steps. Int. J. Radiat. Oncol. Biol. Phys. 72(2), 494–500 (2008)CrossRefGoogle Scholar
  5. 5.
    Kirova, Y., et al.: Improving the definition of tumor bed boost with the use of surgical clips and image registration in breast cancer patients. Int. J. Radiat. Oncol. Biol. Phys. 78(5), 1352–1355 (2010)CrossRefGoogle Scholar
  6. 6.
    Risholm, P., et al.: Validation of a non-rigid registration framework that accommodates tissue resection. In: Medical Imaging 2010: Image Processing - SPIE, pp. 1–11 (2010)Google Scholar
  7. 7.
    Nithiananthan, S., et al.: Extra-dimensional Demons: a method for incorporating missing tissue in deformable image registration. Med. Phys. 39(9), 5718–5731 (2012)CrossRefGoogle Scholar
  8. 8.
    Bach, M., et al.: Atlas-based segmentation of pathological MR brain images using a model of lesion growth. IEEE Trans. Med. Imaging 23(10), 1301–1314 (2004)CrossRefGoogle Scholar
  9. 9.
    Wodzinski, M., et al.: Improving oncoplastic breast tumor bed localization for radiotherapy planning using image registration algorithms. Phys. Med. Biol. 63(3), 035024 (2018)CrossRefGoogle Scholar
  10. 10.
    Van Aarle, W., et al.: Fast and flexible X-ray tomography using the ASTRA toolbox. Opt. Express 24(22), 25129–25147 (2016)CrossRefGoogle Scholar
  11. 11.
    Reaungamornrat, S., et al.: MIND Demons: symmetric diffeomorphic deformable registration of MR and CT for image-guided spine surgery. IEEE Trans. Med. Imaging 35(11), 2413–2424 (2016)CrossRefGoogle Scholar
  12. 12.
    Lu, H., et al.: Multi-modal diffeomorphic demons registration based on point-wise mutual information, pp. 372–375 (2010)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  1. 1. Department of Measurement and ElectronicsAGH University of Science and TechnologyKrakowPoland

Personalised recommendations