Osteoporosis International

, Volume 20, Issue 2, pp 323–333 | Cite as

Using Radon transform of standard radiographs of the hip to differentiate between post-menopausal women with and without fracture of the proximal femur

  • H. F. Boehm
  • J. Lutz
  • M. Körner
  • W. Mutschler
  • M. Reiser
  • K.-J. Pfeifer
Original Article



Texture features based on the Radon transform were extracted from clinical radiographs of the hip in post-menopausal women. The novel algorithm allowed us to identify patients with fracture of the proximal femur and may provide an alternative to measuring bone mineral density in predicting the fracture-risk in osteoporosis, especially where densitometry is regionally unavailable.


The aim of this study is to introduce an algorithm for differentiation between patients with and without fracture of the hip using parameters based on the Radon transform (RT) and applied to standard radiographs of the proximal femur and to compare the results with bone mineral density (BMD).


The study comprised 50 post-menopausal women (78.6 ± 11.5 years of age), including 25 patients with hip fracture and 25 age-matched controls. We obtained lumbar and femoral BMD and standard femoral radiographs. In the radiographs we analysed trabecular patterns of the hip in a region-of-interest of 57 x 29 mm using the RT. From the histogram-representation of the RT, we extracted several characteristic parameters. By ROC and discriminant-analysis, we assessed the statistical power of both methods.


For correct differentiation between fracture and non-fracture cases by femoral BMD, area-under-the-curve (AUC) was 0.78; AUC for the RT-based parameters ranged from 0.73 to 0.8. By combination of densitometric and textural information in a multivariate model the fracture status of 84% of subjects was predicted correctly, identification of fracture cases rose to 88%.


Identification of fracture patients by RT applied to femoral radiographs was feasible and seemed to have a discriminative potential comparable to that of standard densitometry. In the future, the new method may provide an alternative to DXA or in conjunction with conventional densitometry may enhance the detection of patients with elevated risk of hip fracture.


Fracture risk In vivo Osteoporosis Proximal femur Radiographic texture analysis Radon transform 


  1. 1.
    Fitzpatrick P, Kirke PN, Daly L et al (2001) Predictors of first hip fracture and mortality post fracture in older women. Ir J Med Sci 170:49–53PubMedCrossRefGoogle Scholar
  2. 2.
    Hreybe H, Salamoun M, Badra M et al (2004) Hip fractures in Lebanese patients: determinants and prognosis. J Clin Densitom 7:368–375PubMedCrossRefGoogle Scholar
  3. 3.
    Pande I, Scott DL, O’Neill TW et al (2006) Quality of life, morbidity, and mortality after low trauma hip fracture in men. Ann Rheum Dis 65:87–92PubMedCrossRefGoogle Scholar
  4. 4.
    WHO (1994) Assessment of fracture risk and its application to screening for postmenopausal osteoporosis: report of a WHO study group. WHO Technical Report Series 843Google Scholar
  5. 5.
    Rivadeneira F, Zillikens MC, De Laet CE et al (2007) Femoral neck BMD is a strong predictor of hip fracture susceptibility in elderly men and women because it detects cortical bone instability: the rotterdam study. J Bone Miner Res 22(11):1781–1790PubMedCrossRefGoogle Scholar
  6. 6.
    Alonso CG, Curiel MD, Carranza FH, Cano RP, Perez AD (2000) Femoral bone mineral density, neck-shaft angle and mean femoral neck width as predictors of hip fracture in men and women. Multicenter Project for Research in Osteoporosis. Osteoporos Int 11:714–720PubMedCrossRefGoogle Scholar
  7. 7.
    Eckstein F, Lochmüller EM, Lill CA et al (2002) Bone strength at clinically relevant sites displays substantial heterogeneity and is best predicted from site-specific bone densitometry. J Bone Miner Res 17:162–171PubMedCrossRefGoogle Scholar
  8. 8.
    Kanis JA, Oden A, Johnell O et al (2007) The use of clinical risk factors enhances the performance of BMD in the prediction of hip and osteoporotic fractures in men and women. Osteoporos Int 18(8):1033–1046PubMedCrossRefGoogle Scholar
  9. 9.
    Johnell O, Kanis JA, Oden A et al (2005) Predictive value of BMD for hip and other fractures. J Bone Miner Res 20(7):1185–1194PubMedCrossRefGoogle Scholar
  10. 10.
    Cummings SR, Cawthon PM, Ensrud KE et al (2006) BMD and risk of hip and nonvertebral fractures in older men: a prospective study and comparison with older women. J Bone Miner Res 21(10):1550–1556PubMedCrossRefGoogle Scholar
  11. 11.
    McBroom R, Hayes W, Edwards W et al (1985) Prediction of vertebral body compressive fracture using quantitative computed tomography. J Bone Joint Surg 67(8):1206–1214PubMedGoogle Scholar
  12. 12.
    Mosekilde L, Mosekilde L, Danielson C (1987) Biomechanical competence of vertebral trabecular bone in relation to ash density and age in normal individuals. Bone 8:79–85PubMedCrossRefGoogle Scholar
  13. 13.
    Cortet B, Marchandise X (2001) Bone microarchitecture and mechanical resistance. Joint Bone Spine 68:297–305CrossRefGoogle Scholar
  14. 14.
    Lang T, Augat P, Majumdar S et al (1998) Noninvasive assessment of bone density and structure using computed tomography and magnetic resonance. Bone 22:149S–153SPubMedCrossRefGoogle Scholar
  15. 15.
    Krug R, Banerjee S, Han ET et al (2005) Feasibility of in vivo structural analysis of high-resolution magnetic resonance images of the proximal femur. Osteoporos Int 16:1307–1314PubMedCrossRefGoogle Scholar
  16. 16.
    Link TM, Majumdar S, Augat P et al (1998) In vivo high-resolution MRI of the calcaneus: differences in trabecular structure in osteoporosis patients. J Bone Miner Res 13:1175–1182PubMedCrossRefGoogle Scholar
  17. 17.
    Singh M, Nagrath AR, Maini PS (1970) Changes in trabecular pattern of the upper end of the femur as an index of osteoporosis. J Bone Joint Surg Am 52(3):457–467PubMedGoogle Scholar
  18. 18.
    Gregory JS, Alison Stewart A, Undril PE et al (2004) Identification of hip fracture patients from radiographs using Fourier analysis of the trabecular structure: a cross-sectional study. BMC Med Imaging 4(1):4PubMedCrossRefGoogle Scholar
  19. 19.
    Pulkkinen P, Jämsä T, Lochmüller EM et al. (2007) Experimental hip fracture load can be predicted from plain radiography by combined analysis of trabecular bone structure and bone geometry. Osteo Int 2007 Sep 22 [Epub ahead of print]Google Scholar
  20. 20.
    Boehm HF, Raeth C, Monetti R et al (2003) Application of the standard Hough-transform to high-resolution MRI of human trabecular bone to predict mechanical strength. Proceedings of the SPIE 5032:470–480CrossRefGoogle Scholar
  21. 21.
    Boehm HF, Link TM, Monetti R et al (2005) Performance of linear and nonlinear texture measures in 2D and 3D for monitoring architectural changes in osteoporosis using computer-generated models of trabecular bone. Proc SPIE 5747:249–257CrossRefGoogle Scholar
  22. 22.
    Sklansky J (1978) On the Hough technique for curve detection. IEEE Transactions on computers 27(10):923–926CrossRefGoogle Scholar
  23. 23.
    Stockman GC, Agrawala AK (1977) Equivalence of Hough curve detection to template matching. Commun ACM 20(11):820–822CrossRefGoogle Scholar
  24. 24.
    Pontzer H, Lieberman DE, Momin E et al (2006) Trabecular bone in the bird knee responds with high sensitivity to changes in load orientation. J Exp Biol 209:57–65PubMedCrossRefGoogle Scholar
  25. 25.
    Hiriyannaiah HP (1997) X-ray computed tomography for medical imaging. IEEE Signal Proc 14(2):42–58CrossRefGoogle Scholar
  26. 26.
    DeLong ER, DeLong DM, Clarke-Pearson DL (1988) Comparing the areas under two or more correlated receiver operating characteristic curves: a parametric approach. Biometrics 44:837–845PubMedCrossRefGoogle Scholar
  27. 27.
    Huberty C (1994) Applied discriminant-analysis. Wiley, New YorkGoogle Scholar
  28. 28.
    Eriksson L, Johansson E, Muller M et al (2000) On the selection of the training set in environmental QSAR analysis when compounds are clustered. J Chemometrics 14:599–616CrossRefGoogle Scholar
  29. 29.
    Stone M (1977) An asymptotic equivalence of choice of model by cross-validation and akaike’s criterion. J R Stat Soc 38:44–47Google Scholar
  30. 30.
    White J, Harris SS, Dallal GE et al (2003) Precision of single vs bilateral hip bone mineral density scans. J Clin Densitom 6:159–162PubMedCrossRefGoogle Scholar
  31. 31.
    Hans D, Duboeuf F, Schott AM et al (1997) Effects of a new positioner on the precision of hip bone mineral density measurements. J Bone Miner Res 12:1289–1294PubMedCrossRefGoogle Scholar
  32. 32.
    Faulkner KG, Genant HK McClung M (1995) Bilateral comparison of femoral bone density and hip axis length from single and fan beam DXA scans. Calcif Tissue Int 56:26–31PubMedCrossRefGoogle Scholar
  33. 33.
    Parkkari J, Kannus P, Palvanen M et al (1999) Majority of hip fractures occur as a result of a fall and impact on the greater trochanter of the femur: a prospective controlled hip fracture study with 206 consecutive patients. Calcif Tissue Int 65(3):183–187PubMedCrossRefGoogle Scholar
  34. 34.
    Greenspan SL, Myers ER, Kiel DP et al (1998) Fall direction, bone mineral density, and function: risk factors for hip fracture in frail nursing home elderly. Am J Med 104(6):539–545PubMedCrossRefGoogle Scholar
  35. 35.
    Shepherd JA, Fan B, Lu Y (2007) Comparison of BMD precision for Prodigy and Delphi spine and femur scans. Osteoporos Int 17(9):1303–1308CrossRefGoogle Scholar
  36. 36.
    Odgaard A, Kabel J, van Rietbergen B et al (1997) Fabric and elastic principal directions of cancellous bone are closely related. J Biomech 30(11–12):1191–1193Google Scholar
  37. 37.
    Steel SA, Baker AJ, Saunderson JR (1998) An assessment of the radiation dose to patients and staff from a Lunar Expert-XL fan beam densitometer. Physiol Meas 19(1):17–26PubMedCrossRefGoogle Scholar
  38. 38.
    Wall BF, Hart D (1997) Revised radiation doses for typical X-ray examinations. Report on a recent review of doses to patients from medical X-ray examinations in the UK by NRPB. National Radiological Protection Board. Br J Radiol 70(833):437–439PubMedGoogle Scholar
  39. 39.
    Buck AM, Price RI, Sweetman IM, Oxnard CE (2002) An investigation of thoracic and lumbar cancellous vertebral architecture using power-spectral analysis of plain radiographs. J Anat 200:445–456PubMedCrossRefGoogle Scholar
  40. 40.
    Wigderowitz CA, Abel EW, Rowley DI (1997) Evaluation of cancellous structure in the distal radius using spectral analysis. Clin Orthop 152–161Google Scholar
  41. 41.
    Wigderowitz CA, Paterson CR, Dashti H et al (2000) Prediction of bone strength from cancellous structure of the distal radius: can we improve on DXA? Osteoporos Int 11:840–846PubMedCrossRefGoogle Scholar
  42. 42.
    Benhamou CL, Poupon S, Lespessailles E et al (2001) Fractal analysis of radiographic trabecular bone texture and bone mineral density: two complementary parameters related to osteoporotic fractures. J Bone Miner Res 16(4):697–704PubMedCrossRefGoogle Scholar
  43. 43.
    Lespessailles E, Gadois C, Lemineur G et al (2007) Bone texture analysis on direct digital radiographic images: precision study and relationship with bone mineral density at the os calcis. Calcif Tissue Int 80(2):97–102PubMedCrossRefGoogle Scholar
  44. 44.
    Pothuaud L, Lespessailles E, Harba R et al (1998) Fractal analysis of trabecular bone texture on radiographs: discriminant-value in postmenopausal osteoporosis. Osteoporos Int 8(6):618–625PubMedCrossRefGoogle Scholar
  45. 45.
    Boehm HF, Vogel T, Panteleon A et al (2007) Differentiation between post-menopausal women with and without hip fractures: enhanced evaluation of clinical DXA by topological analysis of the mineral distribution in the scan images. Osteoporos Int 18(6):779–787PubMedCrossRefGoogle Scholar

Copyright information

© International Osteoporosis Foundation and National Osteoporosis Foundation 2008

Authors and Affiliations

  • H. F. Boehm
    • 1
  • J. Lutz
    • 1
  • M. Körner
    • 1
  • W. Mutschler
    • 2
  • M. Reiser
    • 1
  • K.-J. Pfeifer
    • 1
  1. 1.Department of RadiologyUniversity of MunichMunichGermany
  2. 2.Department of Trauma SurgeryUniversity of MunichMunichGermany

Personalised recommendations