Advertisement

Perthes Disease Classification Using Shape and Appearance Modelling

  • Adrian K. DavisonEmail author
  • Timothy F. Cootes
  • Daniel C. Perry
  • Weisang Luo
  • Medical Student Annotation Collaborative
  • Claudia Lindner
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11404)

Abstract

We propose to use statistical shape and appearance modelling to classify the proximal femur in hip radiographs of children into Legg-Calvé-Perthes disease and healthy. Legg-Calvé-Perthes disease affects the femoral head with avascular necrosis, which causes large shape deformities during the growth-stage of the child. Further, the dead or dying bone of the femoral head is prominent visually in radiographic images, leading to a distinction between healthy bone and bone where necrosis is present. Currently, there is little to no research into analysing the shape and appearance of hips affected by Perthes disease from radiographic images. Our research demonstrates how the radiographic shape, texture and overall appearance of a proximal femur affected by Perthes disease differs and how this can be used for identifying cases with the disease. Moreover, we present a radiograph-based fully automatic Perthes classification system that achieves state-of-the-art results with an area under the receiver operator characteristic (ROC) curve of 98%.

Keywords

Computer-aided diagnosis Perthes disease Random forests Radiographs Paediatrics Shape modelling Appearance modelling 

Notes

Acknowledgements

A. K. Davison was funded by Arthritis Research UK as part of the ORCHiD project. C. Lindner was funded by the Engineering and Physical Sciences Research Council, UK (EP/M012611/1) and by the Medical Research Council, UK (MR/S00405X/1). Manual landmark annotations were provided by the Medical Student Annotation Collaborative (Grace Airey, Evan Araia, Aishwarya Avula, Emily Gargan, Mihika Joshi, Muhammad Khan, Kantida Koysombat, Jason Lee, Sophie Munday, and Allen Roby).

References

  1. 1.
    Perry, D.C.: The epidemiology and etiology of Perthes’ disease. In: Koo, K.-H., Mont, M.A., Jones, L.C. (eds.) Osteonecrosis, pp. 419–425. Springer, Heidelberg (2014).  https://doi.org/10.1007/978-3-642-35767-1_58CrossRefGoogle Scholar
  2. 2.
    Hall, A., Barker, D.: The age distribution of Legg-Perthes disease: an analysis using Sartwell’s incubation period model. Am. J. Epidemiol. 120(4), 531–536 (1984)CrossRefGoogle Scholar
  3. 3.
    Wiig, O., Terjesen, T., Svenningsen, S., Lie, S.: The epidemiology and aetiology of Perthes disease in Norway: a nationwide study of 425 patients. J. Bone Joint Surg. Br. 88(9), 1217–1223 (2006).  https://doi.org/10.1302/0301-620X.88B9.17400CrossRefGoogle Scholar
  4. 4.
    Hunter, J.: (iv) Legg Calvé Perthes’ disease. Curr. Orthop. 18(4), 273–283 (2004).  https://doi.org/10.1016/j.cuor.2004.06.001CrossRefGoogle Scholar
  5. 5.
    Waldenstrom, H.: The first stages of coxa plana. Acta Orthop. Scand. 5(1–4), 1–34 (1934)CrossRefGoogle Scholar
  6. 6.
    Joseph, B.: Natural history of early onset and late-onset Legg-Calve-Perthes disease. J. Pediatr. Orthop. 31(Suppl. 2), S152–S155 (2011).  https://doi.org/10.1097/BPO.0b013e318223b423CrossRefGoogle Scholar
  7. 7.
    Catterall, A.: Natural history, classification, and x-ray signs in Legg-Calvé-Perthes’ disease. Acta Orthop. Belg. 46(4), 346–351 (1980)Google Scholar
  8. 8.
    Salter, R., Thompson, G.: Legg-Calvé-Perthes disease: the prognostic significance of the subchondral fracture and a two-group classification of the femoral head involvement. J. Bone Joint Surg. Am. 66(4), 479–489 (1984)CrossRefGoogle Scholar
  9. 9.
    Herring, J., Neustadt, J., Williams, J., Early, J., Browne, R.: The lateral pillar classification of Legg-Calvé-Perthes disease. J. Pediatr. Orthop. 12(2), 143–150 (1992)CrossRefGoogle Scholar
  10. 10.
    Stulberg, S., Cooperman, D., Wallensten, R.: The natural history of Legg-Calvé-Perthes disease. J. Bone Joint Surg. Am. 763(7), 1095–1108 (1981)CrossRefGoogle Scholar
  11. 11.
    Mouravliansky, N., Matsopoulos, G., Nikita, K., Uzunoglu, N., Pistevos, G.: An image processing technique for the quantitative analysis of hip disorder in Perthes’ disease. In: Proceedings of 18th Annual International Conference of the IEEE Engineering in Medicine and Biology Society - EMBC 1996, vol. 3, pp. 1103–1104. IEEE (1996).  https://doi.org/10.1109/IEMBS.1996.652728
  12. 12.
    Chan, E., Farnsworth, C., Koziol, J., Hosalkar, H., Sah, R.: Statistical shape modeling of proximal femoral shape deformities in Legg-Calvé-Perthes disease and slipped capital femoral epiphysis. Osteoarthritis Cartilage 31(3), 443–449 (2013).  https://doi.org/10.1016/j.joca.2012.12.007CrossRefGoogle Scholar
  13. 13.
    Cootes, T., Taylor, C., Cooper, D., Graham, J.: Active shape models - their training and application. Comput. Vis. Image Understand. 61(1), 38–59 (1995).  https://doi.org/10.1006/cviu.1995.1004CrossRefGoogle Scholar
  14. 14.
    Cootes, T., Edwards, G., Taylor, C.: Active appearance models. IEEE Trans. Pattern Anal. Mach. Intell. 23(6), 681–685 (2001).  https://doi.org/10.1109/34.927467CrossRefGoogle Scholar
  15. 15.
    Breiman, L.: Random forests. Mach. Learn. 45(1), 5–32 (2001).  https://doi.org/10.1023/A:1010933404324CrossRefzbMATHGoogle Scholar
  16. 16.
    Lindner, C., Thiagarajah, S., Wilkinson, J., The arcOGEN Consortium, Wallis, G., Cootes, T.: Fully automatic segmentation of the proximal femur using random forest regression voting. IEEE Trans. Med. Imaging 32(8), 1462–1472 (2013),  https://doi.org/10.1109/TMI.2013.2258030CrossRefGoogle Scholar
  17. 17.
    Lindner, C., Bromiley, P., Ionita, M., Cootes, T.: Robust and accurate shape model matching using random forest regression-voting. IEEE Trans. Pattern Anal. Mach. Intell. 37(9), 1862–1874 (2015).  https://doi.org/10.1109/TPAMI.2014.2382106CrossRefGoogle Scholar
  18. 18.
    Sarkalkan, N., Weinans, H., Zadpoor, A.: Statistical shape and appearance models of bones. Bone 60, 129–140 (2014).  https://doi.org/10.1016/j.bone.2013.12.006CrossRefGoogle Scholar
  19. 19.
    Waarsing, J., Rozendaal, R., Verhaar, J., Bierma-Zeinstra, S., Weinans, H.: A statistical model of shape and density of the proximal femur in relation to radiological and clinical OA of the hip. Osteoarthritis Cartilage 18(6), 787–794 (2010).  https://doi.org/10.1016/j.joca.2010.02.003CrossRefGoogle Scholar
  20. 20.
    Whitmarsh, T., et al.: A statistical model of shape and bone mineral density distribution of the proximal femur for fracture risk assessment. In: Fichtinger, G., Martel, A., Peters, T. (eds.) MICCAI 2011. LNCS, vol. 6892, pp. 393–400. Springer, Heidelberg (2011).  https://doi.org/10.1007/978-3-642-23629-7_48CrossRefGoogle Scholar
  21. 21.
    Thomson, J., O’Neill, T., Felson, D., Cootes, T.: Automated shape and texture analysis for detection of osteoarthritis from radiographs of the knee. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9350, pp. 127–134. Springer, Cham (2015).  https://doi.org/10.1007/978-3-319-24571-3_16CrossRefGoogle Scholar
  22. 22.
    Adeshina, S., Cootes, T., Adams, J.: Automatic assessment of bone age using statistical models of appearance and random forest regression voting. In: Proceedings of 13th International Conference on Electronics, Computer and Computation - ICECCO, pp. 1–6. IEEE (2017).  https://doi.org/10.1109/ICECCO.2017.8333314

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Adrian K. Davison
    • 1
    Email author
  • Timothy F. Cootes
    • 1
  • Daniel C. Perry
    • 2
    • 3
  • Weisang Luo
    • 3
  • Medical Student Annotation Collaborative
    • 2
    • 3
  • Claudia Lindner
    • 1
  1. 1.Centre for Imaging SciencesThe University of ManchesterManchesterUK
  2. 2.University of LiverpoolLiverpoolUK
  3. 3.Alder Hey Children’s HospitalLiverpoolUK

Personalised recommendations