Automatic Craniomaxillofacial Landmark Digitization via Segmentation-Guided Partially-Joint Regression Forest Model

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9351)


Craniomaxillofacial (CMF) deformities involve congenital and acquired deformities of the head and face. Landmark digitization is a critical step in quantifying CMF deformities. In current clinical practice, CMF landmarks have to be manually digitized on 3D models, which is time-consuming. To date, there is no clinically acceptable method that allows automatic landmark digitization, due to morphological variations among different patients and artifacts of cone-beam computed tomography (CBCT) images. To address these challenges, we propose a segmentation-guided partially-joint regression forest model that can automatically digitizes CMF landmarks. In this model, a regression voting strategy is first adopted to localize landmarks by aggregating evidences from context locations, thus potentially relieving the problem caused by image artifacts near the landmark. Second, segmentation is also utilized to resolve inconsistent landmark appearances that are caused by morphological variations among different patients, especially on the teeth. Third, a partially-joint model is proposed to separately localize landmarks based on coherence of landmark positions to improve digitization reliability. The experimental results show that the accuracy of automatically digitized landmarks using our approach is clinically acceptable.


Random Forest Vote Weight CBCT Image Landmark Position Digitization Error 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


  1. 1.
    Cheng, E., Chen, J., Yang, J., Deng, H., Wu, Y., Megalooikonomou, V., Gable, B., Ling, H.: Automatic dent-landmark detection in 3-d cbct dental volumes. In: 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC, pp. 6204–6207 (2011)Google Scholar
  2. 2.
    Cootes, T.F., Ionita, M.C., Lindner, C., Sauer, P.: Robust and accurate shape model fitting using random forest regression voting. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part VII. LNCS, vol. 7578, pp. 278–291. Springer, Heidelberg (2012)CrossRefGoogle Scholar
  3. 3.
    Criminisi, A., Robertson, D., Konukoglu, E., Shotton, J., Pathak, S., White, S., Siddiqui, K.: Regression forests for efficient anatomy detection and localization in computed tomography scans. Medical Image Analysis 17(8), 1293–1303 (2013)CrossRefGoogle Scholar
  4. 4.
    Gao, Y., Shen, D.: Context-aware anatomical landmark detection: Application to deformable model initialization in prostate ct images. In: Wu, G., Zhang, D., Zhou, L. (eds.) MLMI 2014. LNCS, vol. 8679, pp. 165–173. Springer, Heidelberg (2014)Google Scholar
  5. 5.
    Keustermans, J., Smeets, D., Vandermeulen, D., Suetens, P.: Automated cephalometric landmark localization using sparse shape and appearance models. In: Suzuki, K., Wang, F., Shen, D., Yan, P. (eds.) MLMI 2011. LNCS, vol. 7009, pp. 249–256. Springer, Heidelberg (2011)CrossRefGoogle Scholar
  6. 6.
    Lindner, C., Thiagarajah, S., Wilkinson, J.M., Consortium, T., Wallis, G., Cootes, T.: Fully automatic segmentation of the proximal femur using random forest regression voting. IEEE Transactions on Medical Imaging 32(8), 1462–1472 (2013)CrossRefGoogle Scholar
  7. 7.
    Lou, L., Lagravere, M.O., Compton, S., Major, P.W., Flores-Mir, C.: Accuracy of measurements and reliability of landmark identification with computed tomography (ct) techniques in the maxillofacial area: a systematic review. Oral Surgery, Oral Medicine, Oral Pathology, Oral Radiology, and Endodontology 104(3), 402–411 (2007)CrossRefGoogle Scholar
  8. 8.
    Wang, L., Chen, K.C., Gao, Y., Shi, F., Liao, S., Li, G., Shen, S.G., Yan, J., Lee, P.K., Chow, B., et al.: Automated bone segmentation from dental cbct images using patch-based sparse representation and convex optimization. Medical Physics 41(4), 043503 (2014)Google Scholar
  9. 9.
    Shahidi, S., Bahrampour, E., Soltanimehr, E., Zamani, A., Oshagh, M., Moattari, M., Mehdizadeh, A.: The accuracy of a designed software for automated localization of craniofacial landmarks on cbct images. BMC Medical Imaging 14(1), 32 (2014)CrossRefGoogle Scholar
  10. 10.
    Xia, J.J., Gateno, J., Teichgraeber, J.F.: A new clinical protocol to evaluate cranio-maxillofacial deformity and to plan surgical correction. Journal of Oral and Maxillofacial Surgery: Official Journal of the American Association of Oral and Maxillofacial Surgeons 67(10), 2093 (2009)CrossRefGoogle Scholar
  11. 11.
    Zhang, J., Liang, J., Zhao, H.: Local energy pattern for texture classification using self-adaptive quantization thresholds. IEEE Transactions on Image Processing 22(1), 31–42 (2013)MathSciNetCrossRefGoogle Scholar
  12. 12.
    Zhang, S., Zhan, Y., Dewan, M., Huang, J., Metaxas, D.N., Zhou, X.S.: Towards robust and effective shape modeling: Sparse shape composition. Medical Image Analysis 16(1), 265–277 (2012)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  1. 1.Department of Radiology and BRICUNC at Chapel HillChapel HillUSA
  2. 2.Department of Computer ScienceUNC at Chapel HillChapel HillUSA
  3. 3.Houston Methodist HospitalHoustonUSA
  4. 4.Weill Medical CollegeCornell UniversityNew YorkUSA

Personalised recommendations