Bone Age Assessment Using the Classifying Generalized Hough Transform

  • Ferdinand Hahmann
  • Inga Berger
  • Heike Ruppertshofen
  • Thomas Deserno
  • Hauke Schramm
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8142)


A theoretical description and experimental validation of the Classifying Generalized Hough Transform (CGHT) is presented. This general image classification technique is based on a discriminative training procedure that jointly estimates concurrent class-dependent shape models for usage in a GHT voting procedure. The basic approach is extended by a coarse-to-fine classification strategy and a simple classifier combination technique for a combined decision on several regions of interest in a given image. The framework is successfully applied to the task of automatic bone age assessment and produces comparable results to other state-of-the-art techniques on a public database. For the most difficult age range of 9 to 16 years the automatic system achieves a mean error of 0.8 years compared to the average rating of two physicians. Unlike most other image classification techniques, the trained CGHT models can be visually interpreted, unveiling the most relevant anatomical structures for class discrimination.


Training Image Skeletal Maturity Vote Procedure Shape Variability Combine Decision 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Aja-Fernández, S., de Luis-Garcıa, R., Martın-Fernandez, M.A., Alberola-López, C.: A computational tw3 classifier for skeletal maturity assessment. A computing with words approach. Journal of Biomedical Informatics 37(2), 99–107 (2004)CrossRefGoogle Scholar
  2. 2.
    Ballard, D.: Generalizing the Hough transform to detect arbitrary shapes. Pattern Recognition 13(2), 111–122 (1981)CrossRefzbMATHGoogle Scholar
  3. 3.
    Beyerlein, P.: Discriminative model combination. In: ICASSP, pp. 481–484 (1998)Google Scholar
  4. 4.
    Bocchi, L., Ferrara, F., Nicoletti, I., Valli, G.: An artificial neural network architecture for skeletal age assessment. In: ICIP, pp. 1077–1080 (2003)Google Scholar
  5. 5.
    Brunk, M., Ruppertshofen, H., Schmidt, S., Beyerlein, P., Schramm, H.: Bone age classification using the discriminative generalized hough transform. In: BVM, pp. 284–288 (2011)Google Scholar
  6. 6.
    Chang, C.H., Hsieh, C.W., Jong, T.L., Tiu, C.M.: A fully automatic computerized bone age assessment procedure based on phalange ossification analysis. In: IPPR, pp. 463–468 (2003)Google Scholar
  7. 7.
    Greulich, W.W., Pyle, S.I.: Radiographic atlas of skeletal development of the hand and wrist. The American Journal of the Medical Sciences 238(3), 393 (1959)CrossRefGoogle Scholar
  8. 8.
    Harmsen, M., Fischer, B., Schramm, H., Seidl, T., Deserno, T.M.: Support vector machine classification based on correlation prototypes applied to bone age assessment. IEEE Transaction on Information Technology in Biomedicine (2012)Google Scholar
  9. 9.
    Hsieh, C., Jong, T., Chou, Y., Tiu, C.: Computerized geometric features of carpal bone for bone age estimation. Chinese Medical Journal 120(9), 767–770 (2007)Google Scholar
  10. 10.
    Kim, H.-J., Kim, W.-Y.: Computerized bone age assessment using DCT and LDA. In: Gagalowicz, A., Philips, W. (eds.) MIRAGE 2007. LNCS, vol. 4418, pp. 440–448. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  11. 11.
    Klakow, D.: Log-linear interpolation of language models. In: ICSLP (1998)Google Scholar
  12. 12.
    Martin, D.D., Deusch, D., Schweizer, R., Binder, G., Thodberg, H.H., Ranke, M.B.: Clinical application of automated greulich-pyle bone age determination in children with short stature. Pediatric Radiology 39(6), 598–607 (2009)CrossRefGoogle Scholar
  13. 13.
    Pietka, E., Gertych, A., Pospiech, S., Cao, F., Huang, H., Gilsanz, V.: Computer-assisted bone age assessment: Image preprocessing and epiphyseal/metaphyseal roi extraction. IEEE Transactions on Medical Imaging 20(8), 715–729 (2001)CrossRefGoogle Scholar
  14. 14.
    Ruppertshofen, H.: Automatic Modeling of Anatomical Variability for Object Localization in Medical Images. Ph.D. thesis, Otto-von-Guericke University Magdeburg (2013)Google Scholar
  15. 15.
    Ruppertshofen, H., Schramm, H.: The classifying generalized hough transform. German Patent Submission (2011)Google Scholar
  16. 16.
    Ruppertshofen, H., Bülow, T., von Berg, J., Schmidt, S., Beyerlein, P., Salah, Z., Rose, G., Schramm, H.: A multi-dimensional model for localization of highly variable objects. In: SPIE, vol. 8314, p. 88 (2012)Google Scholar
  17. 17.
    Tanner, J., Healy, M., Goldstein, H., Cameron, N.: Assessment of skeletal maturity and prediction of adult height (tw3). WB Saunders, London (2001)Google Scholar
  18. 18.
    Thodberg, H.H., Kreiborg, S., Juul, A., Pedersen, K.D.: The bonexpert method for automated determination of skeletal maturity. IEEE Transactions on Medical Imaging 28(1), 52–66 (2009)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Ferdinand Hahmann
    • 1
  • Inga Berger
    • 1
  • Heike Ruppertshofen
    • 2
  • Thomas Deserno
    • 3
  • Hauke Schramm
    • 1
  1. 1.University of Applied Sciences KielGermany
  2. 2.Philips Technologie GmbHGermany
  3. 3.Department of Medical InformaticsRWTH Aachen UniversityGermany

Personalised recommendations