Variational Shape Completion for Virtual Planning of Jaw Reconstructive Surgery

  • Amir H. AbdiEmail author
  • Mehran Pesteie
  • Eitan Prisman
  • Purang Abolmaesumi
  • Sidney Fels
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11768)


The premorbid geometry of the mandible is of significant relevance in jaw reconstructive surgeries and occasionally unknown to the surgical team. In this paper, an optimization framework is introduced to train deep models for completion (reconstruction) of the missing segments of the bone based on the remaining healthy structure. To leverage the contextual information of the surroundings of the dissected region, the voxel-weighted Dice loss is introduced. To address the non-deterministic nature of the shape completion problem, we leverage a weighted multi-target probabilistic solution which is an extension to the conditional variational autoencoder (CVAE). This approach considers multiple targets as acceptable reconstructions, each weighted according to their conformity with the original shape. We quantify the performance gain of the proposed method against similar algorithms, including CVAE, where we report statistically significant improvements in both deterministic and probabilistic paradigms. The probabilistic model is also evaluated on its ability to generate anatomically relevant variations for the missing bone. As a unique aspect of this work, the model is tested on real surgical cases where the clinical relevancy of its reconstructions and their compliance with surgeon’s virtual plan are demonstrated as necessary steps towards clinical adoption.


Conditional variational autoencoder 3D shape completion V-Net Mandible reconstruction 

Supplementary material

490279_1_En_26_MOESM1_ESM.pdf (215 kb)
Supplementary material 1 (pdf 215 KB)


  1. 1.
    Abdi, A.H., et al.: AnatomyGen: deep anatomy generation from dense representation with applications in mandible synthesis. Technical report (2019)Google Scholar
  2. 2.
    Achlioptas, P., et al.: Representation learning and adversarial generation of 3D point clouds. 2(3), 4 arXiv preprint arXiv:1707.02392 (2017)
  3. 3.
    Brinkley, J.F., et al.: The FaceBase consortium: a comprehensive resource for craniofacial researchers. Development 143(14), 2677–2688 (2016). www.facebase.orgCrossRefGoogle Scholar
  4. 4.
    Hidalgo, D.A.: Fibula free flap: a new method of mandible reconstruction. Plast. Reconstr. Surg. 84(1), 71–79 (1989)CrossRefGoogle Scholar
  5. 5.
    Milletari, F., et al.: V-Net: fully convolutional neural networks for volumetric medical image segmentation. In: 2016 Fourth International Conference on 3D Vision (3DV). IEEE (2016)Google Scholar
  6. 6.
    Nash, C., Williams, C.K.I.: The shape variational autoencoder: a deep generative model of part-segmented 3D objects. Comput. Graph. Forum 36(5), 1–12 (2017)CrossRefGoogle Scholar
  7. 7.
    Ravikumar, N., Gooya, A., Çimen, S., Frangi, A.F., Taylor, Z.A.: A multi-resolution T-mixture model approach to robust group-wise alignment of shapes. In: Ourselin, S., Joskowicz, L., Sabuncu, M.R., Unal, G., Wells, W. (eds.) MICCAI 2016. LNCS, vol. 9902, pp. 142–149. Springer, Cham (2016). Scholar
  8. 8.
    Siegel, R.L., et al.: Cancer statistics. CA Cancer J. Clin. 67(1), 7–30 (2017)CrossRefGoogle Scholar
  9. 9.
    Sohn, K., et al.: Learning structured output representation using deep conditional generative models. In: Cortes, C., et al. (ed.) Advances in Neural Information Processing Systems, vol. 28, pp. 3483–3491. Curran Associates, Inc. (2015)Google Scholar
  10. 10.
    Stranix, J.T., et al.: A virtual surgical planning algorithm for delayed maxillomandibular reconstruction. Plast. Reconstr. Surg. 143(4), 1197–1206 (2019) CrossRefGoogle Scholar
  11. 11.
    Wu, J., et al.: Learning a probabilistic latent space of object shapes via 3D generative-adversarial modeling. In: Advances in Neural Information Processing Systems, pp. 82–90 (2016)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Amir H. Abdi
    • 1
    Email author
  • Mehran Pesteie
    • 1
  • Eitan Prisman
    • 1
  • Purang Abolmaesumi
    • 1
  • Sidney Fels
    • 1
  1. 1.University of British ColumbiaVancouverCanada

Personalised recommendations