Skip to main content

Advertisement

Log in

Statistical Shape and Appearance Models in Osteoporosis

  • Biomechanics (M Silva and P Zysset, Section Editors)
  • Published:
Current Osteoporosis Reports Aims and scope Submit manuscript

Abstract

Statistical models (SMs) of shape (SSM) and appearance (SAM) have been acquiring popularity in medical image analysis since they were introduced in the early 1990s. They have been primarily used for segmentation, but they are also a powerful tool for 3D reconstruction and classification. All these tasks may be required in the osteoporosis domain, where fracture detection and risk estimation are key to reducing the mortality and/or morbidity of this bone disease. In this article, we review the different applications of SSMs and SAMs in the context of osteoporosis, and it concludes with a discussion of their advantages and disadvantages for this application.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1

Similar content being viewed by others

References

Papers of particular interest, published recently, have been highlighted as: • Of importance

  1. Sambrook P, Cooper C. Osteoporosis. Lancet. 2006;367:2010–8.

    Article  CAS  PubMed  Google Scholar 

  2. Cummings SR, Melton LJ. Epidemiology and outcomes of osteoporotic fractures. Lancet. 2002;359:1761–7.

    Article  PubMed  Google Scholar 

  3. Williams AL, Al-Busaidi A, Sparrow PJ, Adams JE, Whitehouse RW. Under-reporting of osteoporotic vertebral fractures on computed tomography. Eur J Radiol. 2009;69:179–83.

    Article  PubMed  Google Scholar 

  4. Rachner TD, Khosla S, Hofbauer LC. Osteoporosis: now and the future. Lancet. 2011;377:1276–87.

    Article  CAS  PubMed Central  PubMed  Google Scholar 

  5. Blake GM, Fogelman I. The clinical role of dual energy X-ray absorptiometry. Eur J Radiol. 2009;71:406–14.

    Article  PubMed  Google Scholar 

  6. Adams JE. Quantitative computed tomography. Eur J Radiol. 2009;71:415–24.

    Article  PubMed  Google Scholar 

  7. Wesarg S, Hosseini ASG, Erdt M, Kafchitsas K, Khan MF. Segmental assessment and visualization of trabecular bone mineral density in vertebrae. In Eurographics Workshop on Visual Computing for Biology and Medicine: 2010; p. 1–3.

  8. Schmid J, Kim J, Magnenat-Thalmann N. Robust statistical shape models for MRI bone segmentation in presence of small field of view. Med Image Anal. 2011;15:155–68.

    Article  PubMed  Google Scholar 

  9. Neubert A, Fripp J, Engstrom C, Schwarz R, Lauer L, Salvado O, et al. Automated detection, 3D segmentation and analysis of high resolution spine MR images using statistical shape models. Phys Med Biol. 2012;57:8357.

    Article  CAS  PubMed  Google Scholar 

  10. Pilgram R, Walch CA, Blauth M, Jaschke W, Schubert R, Kuhn V. Knowledge-based femur detection in conventional radiographs of the pelvis. Comp Biol Med. 2008;38:535–44.

    Article  Google Scholar 

  11. Pilgram R, Walch C, Kuhn V, Schubert R, Staudinger R. Proximal femur segmentation in conventional pelvic x ray. Med Phys. 2008;35:2463.

    Article  PubMed  Google Scholar 

  12. Lindner C, Thiagarajah S, Wilkinson JM, Wallis GA, Cootes TF. Accurate fully automatic femur segmentation in pelvic radiographs using regression voting. Med Image Comput Comput Assist Interv. 2012;15(Pt 3):353–60.

    CAS  PubMed  Google Scholar 

  13. Lindner C, Thiagarajah S, Wilkinson JM, Wallis GA, Cootes TF. Development of a fully automatic shape model matching (FASMM) system to derive statistical shape models from radiographs: application to the accurate capture and global representation of proximal femur shape. Osteoarthr Cartil. 2013;21(10):1537–44.

    Article  CAS  PubMed  Google Scholar 

  14. Fritscher KD, Grunerbl A, Schubert R. 3D image segmentation using combined shape-intensity prior models. Int J Comp Assist Radiol Surg. 2007;1:341–50.

    Article  Google Scholar 

  15. Whitmarsh T, Humbert L, De Craene M, Del Rio Barquero LM, Frangi AF. Reconstructing the 3D shape and bone mineral density distribution of the proximal femur from dual-energy X-ray absorptiometry. Med Imaging. 2011;30:2101–14.

    Article  Google Scholar 

  16. Ahmad O, Ramamurthi K, Wilson KE, Engelke K, Prince RL, Taylor RH. Volumetric DXA (VXA): a new method to extract 3D information from multiple in vivo DXA images. J Bone Miner Res. 2010;25:2744–51.

    Article  PubMed  Google Scholar 

  17. Schumann S, Tannast M, Nolte L-P, Zheng G. Validation of statistical shape model based reconstruction of the proximal femur, a morphology study. Med Eng Phys. 2010;32:638–44.

    Article  PubMed  Google Scholar 

  18. Zheng G, Gollmer S, Schumann S, Dong X, Feilkas T, Gonzalez Ballester MA. A 2D/3D correspondence building method for reconstruction of a patient-specific 3D bone surface model using point distribution models and calibrated X-ray images. Med Image Anal. 2009;13:883–99.

    Article  PubMed  Google Scholar 

  19. Kurazume R, Nakamura K, Okada T, Sato Y, Sugano N, Koyama T, et al. 3D reconstruction of a femoral shape using a parametric model and two 2D fluoroscopic images. Comp Vis Image Underst. 2009;113:202–11.

    Article  Google Scholar 

  20. Baka N, Kaptein BL, de Bruijne M, van Walsum T, Giphart JE, Niessen WJ, et al. 2D–3D shape reconstruction of the distal femur from stereo X-ray imaging using statistical shape models. Med Image Anal. 2011;15:840–50.

    Article  CAS  PubMed  Google Scholar 

  21. Fritscher K, Grunerbl A, Hanni M, Suhm N, Hengg C, Schubert R. Trabecular bone analysis in CT and X-ray images of the proximal femur for the assessment of local bone quality. Med Imaging. 2009;28:1560–75.

    Article  Google Scholar 

  22. Whitmarsh T, Fritscher KD, Humbert L, Barquero LM, Roth T, Kammerlander C, 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, editors. Medical Image Computing and Computer-Assisted Intervention– MICCAI. Berlin Heidelberg: Springer, volume 6892 2011. p.393–400. First method that uses a reconstructed QCT instead of a real one for fracture prediction.

  23. Schuler B, Fritscher KD, Kuhn V, Eckstein F, Schubert R. Using a statistical appearance model to predict the fracture load of the proximal femur. Med Imaging. 2009;72610W–10.

  24. Schuler B, Fritscher KD, Kuhn V, Eckstein F, Link TM, Schubert R. Assessment of the individual fracture risk of the proximal femur by using statistical appearance models. Med Phys. 2010;37:25602571.

    Article  Google Scholar 

  25. Bryan R, Nair PB, Taylor M. Use of a statistical model of the whole femur in a large scale, multi-model study of femoral neck fracture risk. J Biomech. 2009;42:2171–6.

    Article  PubMed  Google Scholar 

  26. Smyth PP, Taylor CJ, Adams JE. Automatic measurement of vertebral shape using active shape models. Image Vis Comput J. 1997;15:575–81.

    Article  Google Scholar 

  27. Roberts MG, Cootes TF, Adams JE. Linking sequences of active appearance sub-models via constraints: an application in automated vertebral morphometry. In British Machine Vision Conference. 2003;1–10.

  28. Roberts M, Cootes TF, Adams JE. Vertebral morphometry: semiautomatic determination of detailed shape from dual-energy X-ray absorptiometry images using active appearance models. Investig Radiol. 2006;41:849–59.

    Article  Google Scholar 

  29. Roberts MG, Cootes TF, Pacheco E, Oh T, Adams JE. Segmentation of lumbar vertebrae using part-based graphs and active appearance models. Med Image Comput Comput Assist Interv. 2009;12:1017–24.

    PubMed  Google Scholar 

  30. Roberts MG, Cootes TF, Adams JE. Automatic location of vertebrae on DXA images using random forest regression. Med Image Comp Comp Assist Interv. 2012;15:361–8.

    CAS  Google Scholar 

  31. Long LR, Thoma GR. Use of shape models to search digitized spine X-rays. In Computer-Based Medical Systems, 2000. CBMS 2000. Proceedings. 13th IEEE Symposium: 2000; p. 255–60.

  32. Zamora G, Sari-Sarraf H, Long LR. Hierarchical segmentation of vertebrae from X-ray images. Med Imaging. 2003;12:631–42.

    Google Scholar 

  33. Roberts M, Cootes TF, Adams JE. Vertebral shape: automatic measurement with dynamically sequenced active appearance models. Med Image Comp Comp Assist Interv. 2005;8(Pt 2):733–40.

    CAS  Google Scholar 

  34. Roberts MG, Cootes TF, Adams JE. Automatic segmentation of lumbar vertebrae on digitised radiographs using linked active appearance models. Med Image Underst Anal. 2006;2:120–4.

    Google Scholar 

  35. Iglesias JE, de Bruijne M. Semiautomatic segmentation of vertebrae in lateral X-rays using a conditional shape model. Acad Radiol. 2007;14:1156–65.

    Article  PubMed  Google Scholar 

  36. Aouache M, Hussain A, Samad SA, Hamzaini AH, Ariffin AK. Osteoporosis presence verification using mace filter based statistical models of appearance with application to cervical X-ray images. In 4th Kuala Lumpur International Conference on Biomedical Engineering: 2008; p. 607–10.

  37. Guglielmi G, Palmieri F, Placentino MG, D’Errico F, Stoppino LP. Assessment of osteoporotic vertebral fractures using specialized workflow software for 6-point morphometry. Eur J Radiol. 2009;70:142–8.

    Article  PubMed  Google Scholar 

  38. Mysling P, Petersen K, Nielsen M, Lillholm M. A unifying framework for automatic and semiautomatic segmentation of vertebrae from radiographs using sample-driven active shape models. Machine Vision and Applications, 2012; p. 1–14. This was the first multi-object/resolution SSM in osteoporosis.

  39. Howe B, Gururajan A, Sari-Sarraf H, Long LR. Hierarchical segmentation of cervical and lumbar vertebrae using a customized generalized though transform and extensions to active appearance models. Image Analysis and Interpretation, 2004. 6th IEEE Southwest Symposium on: 2004; p. 182–6.

  40. Aslan MS, Abdelmunim H, Farag AA, Arnold B, Mostafa E, Xiang P. A new shape based segmentation framework using statistical and variational methods. 2011 18th IEEE International Conference. Image Process. 2011;717–20.

  41. Al-Helo S, Alomari RS, Chaudhary V, Al-Zoubi MB. Segmentation of lumbar vertebrae from clinical CT using active shape models and GVF-snake. In Engineering in Medicine and Biology Society, EMBC, 2011 Annual International Conference of the IEEE: 2011; p. 8033–6.

  42. Whitmarsh T, Humbert L, Del Rio Barquero LM, Gregorio S, Frangi AF. 3D reconstruction of the lumbar vertebrae from anteroposterior and lateral dual-energy X-ray absorptiometry. Med Image Anal. 2013;4:475–87.

    Article  Google Scholar 

  43. Zheng G, Nolte L-P, Ferguson SJ. Scaled, patient-specific 3D vertebral model reconstruction based on 2D lateral fluoroscopy. Int J Comp Assist Radiol Surg. 2011;6:351–66. Accurate and fast 3D vertebra reconstruction method that handles fractures, thus it can improve fracture detection and prediction.

    Article  Google Scholar 

  44. Lund MT, de Bruijne M, Tanko LB, Nielsen M. Shape regression for vertebra fracture quantification. Med Imaging, 2005;723–31.

  45. De Bruijne M, Lund MT, Tanko LB, Pettersen PC, Nielsen M. Quantitative vertebral morphometry using neighbor-conditional shape models. Med Image Comp Comp Assist Interv. 2006;9(Pt 1):1–8.

    Google Scholar 

  46. De Bruijne M, Lund MT, Tanko LB, Pettersen PC, Nielsen M. Quantitative vertebral morphometry using neighbor-conditional shape models. Med Image Anal. 2007;11:503–12.

    Article  PubMed  Google Scholar 

  47. Roberts MG, Cootes TF, Adams JE. Robust active appearance models with iteratively rescaled kernels. Br Mach Vis Conf. 2007;1:1–10.

    Google Scholar 

  48. Roberts MG, Pacheco EMB, Mohankumar R, Cootes TF, Adams JE. Detection of vertebral fractures in DXA VFA images using statistical models of appearance and a semi-automatic segmentation. Osteoporos Int. 2010;21:2037–46.

    Article  CAS  PubMed  Google Scholar 

  49. De Bruijne M, Pettersen P. Supervised shape analysis for risk assessment in osteoporosis. In Biomedical Imaging (ISBI), IEEE International Symposium: 2008; p. 1581–4.

  50. Seim H, Kainmueller D, Heller M, Lamecker H, Zachow S, Hege H. Automatic segmentation of the pelvic bones from CT data based on a statistical shape model. Visual Comp Biomed. 2008;93–100.

  51. Yao J, Taylor R. Assessing accuracy factors in deformable 2D/3D medical image registration using a statistical pelvis model. In Computer Vision, 2003. Proceedings. Ninth IEEE International Conference: 2003; p. 1329–34.

  52. Lamecker H, Wenckebach TH, Hege H-C. Atlas- based 3D-shape reconstruction from X-ray images. In Pattern Recognition, 2006. ICPR 2006. Int Conf. 2006;1:371–4.

    Google Scholar 

  53. Sadowsky O, Chintalapani G, Taylor RH. Deformable 2D-3D registration of the pelvis with a limited field of view, using shape statistics. Med Image Comp Comp Assist Interv. 2007;10(Pt 2):519–26.

    Google Scholar 

  54. Whitmarsh T, Fritscher KD, Humbert L, Del-Rio Barquero LM, Schubert R, Frangi AF. Hip fracture discrimination using 3D reconstructions from dual-energy X-ray absorptiometry. From Nano to Macro, 2011 I.E. International Symposium. Biomed Imaging. 2011;1189–92.

  55. Gregory JS, Testi D, Stewart A, Undrill PE, Reid DM, Aspden RM. A method for assessment of the shape of the proximal femur and its relationship to osteoporotic hip fracture. Osteoporos Int. 2004;15:5–11.

    Article  CAS  PubMed  Google Scholar 

  56. Goodyear SR, Barr RJ, McCloskey E, Alesci S, Aspden RM, Reid DM, et al. Can we improve the prediction of hip fracture by assessing bone structure using shape and appearance modelling? Bone. 2013;53:188–93.

    Article  CAS  PubMed  Google Scholar 

  57. Baker-LePain JC, Luker KR, Lynch JA, Parimi N, Nevitt MC, et al. Active shape modeling of the hip in the prediction of incident hip fracture. J Bone Miner Res. 2011;26:468–74.

    Article  PubMed Central  PubMed  Google Scholar 

  58. Li W, Kornak J, Harris T, Lu Y, Cheng X, Lang T. Hip fracture risk estimation based on principal component analysis of QCT atlas: a preliminary study. SPIE Med Imaging. 2009;72621M.

  59. Sotoca JM, Inesta JM, Belmonte MA. Hand bone segmentation in radioabsorptiometry images for computerised bone mass assessment. Comp Med Imaging Graph. 2003;27:459–67.

    Article  Google Scholar 

  60. Alien PD, Graham J, Farnell DJJ, Marjanovic EJ, Adams J, Jacobs R, et al. Detecting osteoporosis from dental radiographs using active shape models. Biomed Imaging. 2007;1256–9.

  61. Alien PD, Graham J, Farnell DJJ, Harrison EJ, Jacobs R, Karayianni K, et al. Detecting reduced bone mineral density from dental radiographs using statistical shape models. Inf Technol Biomed. 2007;11:601–10.

    Article  Google Scholar 

  62. Thodberg HH, Rosholm A. Application of the active shape model in a commercial medical device for bone densitometry. Image Vis Comp. 2003;21:1155–61.

    Article  Google Scholar 

  63. Roberts MG, Graham J, Devlin H. Image texture in dental panoramic radiographs as a potential biomarker of osteoporosis. Biomed Eng. 2013;60:2384–92. State-of-the-art method in detecting osteoporosis using SM and images with a low radiation dose to patient.

    Google Scholar 

  64. Roberts MG, Graham J, and Devlin H. Improving the detection of osteoporosis from dental radiographs using active appearance models. From Nano to Macro, 2010 I.E. International Symposium. Biomed Imaging. 2010;440–3.

  65. Devlin H, Allen PD, Graham J, Jacobs R, Karayianni K, Lindh C, et al. Automated osteoporosis risk assessment by dentists: a new pathway to diagnosis. Bone. 2007;40:835–42.

    Article  CAS  PubMed  Google Scholar 

  66. Cootes TF, Taylor CJ, Graham J. Active shape models- their training and applications. Comput Vis Image Underst. 1995;61:38–59.

    Article  Google Scholar 

  67. Heimann T, Meinzer HP. Statistical shape models for 3D medical image segmentation: a review. Med Image Anal. 2009;13:543–63.

    Article  PubMed  Google Scholar 

  68. Sadowsky O, Ramamurthi K, Ellingsen LM, Chintalapani GI, Prince JL, Taylor RH. Atlas-assisted tomography: registration of a deformable atlas to compensate for limited-angle cone-beam trajectory. Nano to Macro, 2006. 3rd IEEE International Symposium. Biomed Imaging. 2006;1244–7.

  69. Tang TSY, Ellis RE. 2D/3D deformable registration using a hybrid atlas. Med Image Comput Comput Assist Interv. 2005;3750:223–30.

    Google Scholar 

  70. Aslan MS, Ali A, Farag AA, Arnold B, Chen D, Xiang P. 3D vertebrae segmentation in CT images with random noises. In Proceedings of the 2010 20th International Conference on Pattern Recognition, IEEE Computer Society: 2010; p. 2290–3.

  71. Gower JC. Generalized procrustes analysis. Psychometrika. 1975;40:33–51.

    Article  Google Scholar 

  72. Hurvitz A, Joskowicz L. Registration of a CT- like atlas to fluoroscopic X-ray images using intensity correspondences. Int J Comp Assist Radiol Surg. 2008;3:493–504.

    Article  Google Scholar 

  73. Kotcheff AC, Taylor CJ. Automatic construction of Eigenshape models by direct optimization. Med Image Anal. 1998;4:303–14.

    Article  Google Scholar 

  74. Cootes TF, Edwards GJ, Taylor CJ. Active appearance models. Pattern Anal Mach Intell. 2001;23:681–5.

    Article  Google Scholar 

  75. Koschan A, Kang S, Paik J, Abidi B, Abidi M. Color active shape models for tracking non-rigid objects. Pattern Recogn Lett. 2003;24:1751–5.

    Article  Google Scholar 

  76. Ahmad OM, Ramamurthi K, Wilson KE, Engelke K, Bouxsein M, Taylor RH. 3D structural measurements of the proximal femur from 2D DXA images using a statistical atlas. Med Imaging. 2009;7260:5–13.

    Google Scholar 

  77. Boykov Y, Veksler O, Zabih R. Fast approximate energy minimization via graph cuts. Pattern Anal Mach Intell. 2001;23:1222–39.

    Article  Google Scholar 

  78. Fleute M, Lavallee S, Desbat L. Integrated approach for matching statistical shape models with intraoperative 2D and 3D data. Med Image Comp Comp Assist Interv. 2002;2:364–72.

    Google Scholar 

  79. Steininger P, Fritscher KD, Kofler G, Schuler B, Hanni M, Schwieger K, et al. Comparison of different metrics for appearance-model-based 2D/3D registration with X-ray images. Bildverarbeitung fur die Medizin. 2008;122–6.

  80. Rosholm A, Hyldstrup L, Baeksgaard L, Grunkin M, Thodberg HH. Estimation of bone mineral density by digital X-ray radiogrammetry: theoretical background and clinical testing. Osteoporos Int. 2001;12:961–9.

    Article  CAS  PubMed  Google Scholar 

  81. Michopoulou SK, Costaridou L, Panagiotopoulos E, Speller R, Panayiotakis G, Todd-Pokropek A. Atlas-based segmentation of degenerated lumbar intervertebral discs from MR images of the spine. Biomed Eng. 2009;56:2225–31.

    Google Scholar 

  82. Zhang B, Sun S, Sun J, Chi Z, Xi Ch. 3D reconstruction method from bi-planar radiography using DLT algorithm: application to the femur. 2010 First International Conference. Pervasive Computing Signal Processing and Applications. 2010;251–54.

  83. Zhang JH, Shi XL, Wang YY, Lv L, Wu J, Zhang YF. Bi-planar radiographic 3D reconstruction of vertebrae using non-stereo corresponding points based on epipolar geometry. In 6th World Congress of Biomechanics (WCB 2010). August 1-6, 2010 Singapore. 2010; p. 1266–9.

  84. Cerrolaza JJ, Villanueva A, Cabeza R. Hierarchical statistical shape models of multi-object anatomical structures: application to brain MRI. Med Imaging. 2012;31:713–24.

    Article  Google Scholar 

Download references

Compliance with Ethics Guidelines

Conflict of Interest

I. Castro-Mateos. J. M. Pozo, J. M. Wilkinson and A. F. Frangi declare that they have no conflicts of interest. T. F. Cootes has begun to collaborate with Optasia-Medical Ltd to develop an automated system for identifying vertebral fractures (funded by MRC and the Wellcome Trust). R Eastell has received grants from Amgen, Department of Health, AstraZeneca, Immunodiagnostic Systems, Canadian Institutes of Health Research, National Osteoporosis Society, ARUK/MRC Centre of Excellence in Musculoskeletal Ageing Research, National Institute for Health Research, Cancer Research UK, MRC/AZ Mechanisms of Diseases Call; personal fees from Novartis, Roche, Alexion, Otsuka, Merck, Johnson & Johnson, SPD Development, Fonterra Brands, Janssen Research, Eli Lilly, Ono Pharma, Immunodiagnostic Systems, Alere (Unipath), Chronos, Amgen, IBMS; is on an advisory board for European Calcified Tissue Society, Efficacy & Mechanism Evaluation Board of the Medical Research Council, Eli Lilly, Roche, IOF CSA outside the submitted work.

Human and Animal Rights and Informed Consent

All studies by the authors involving animal and/or human subjects were performed after approval by the appropriate institutional review boards.When required, written informed consent was obtained from all participants.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Alejandro F. Frangi.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Castro-Mateos, I., Pozo, J.M., Cootes, T.F. et al. Statistical Shape and Appearance Models in Osteoporosis. Curr Osteoporos Rep 12, 163–173 (2014). https://doi.org/10.1007/s11914-014-0206-3

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11914-014-0206-3

Keywords

Navigation