Advertisement

Vertebral body insufficiency fractures: detection of vertebrae at risk on standard CT images using texture analysis and machine learning

  • Urs J. Muehlematter
  • Manoj Mannil
  • Anton S. Becker
  • Kerstin N. Vokinger
  • Tim Finkenstaedt
  • Georg Osterhoff
  • Michael A. Fischer
  • Roman Guggenberger
Computed Tomography

Abstract

Purpose

To evaluate the diagnostic performance of bone texture analysis (TA) combined with machine learning (ML) algorithms in standard CT scans to identify patients with vertebrae at risk for insufficiency fractures.

Materials and methods

Standard CT scans of 58 patients with insufficiency fractures of the spine, performed between 2006 and 2013, were analyzed retrospectively. Every included patient had at least two CT scans. Intact vertebrae in a first scan that either fractured (“unstable”) or remained intact (“stable”) in the consecutive scan were manually segmented on mid-sagittal reformations. TA features for all vertebrae were extracted using open-source software (MaZda). In a paired control study, all vertebrae of the study cohort “cases” and matched controls were classified using ROC analysis of Hounsfield unit (HU) measurements and supervised ML techniques. In a within-subject vertebra comparison, vertebrae of the cases were classified into “unstable” and “stable” using identical techniques.

Results

One hundred twenty vertebrae were included. Classification of cases/controls using ROC analysis of HU measurements showed an AUC of 0.83 (95% confidence interval [CI], 0.77–0.88), and ML-based classification showed an AUC of 0.97 (CI, 0.97–0.98). Classification of unstable/stable vertebrae using ROC analysis showed an AUC of 0.52 (CI, 0.42–0.63), and ML-based classification showed an AUC of 0.64 (CI, 0.61–0.67).

Conclusion

TA combined with ML allows to identifying patients who will suffer from vertebral insufficiency fractures in standard CT scans with high accuracy. However, identification of single vertebra at risk remains challenging.

Key Points

• Bone texture analysis combined with machine learning allows to identify patients at risk for vertebral body insufficiency fractures on standard CT scans with high accuracy.

• Compared to mere Hounsfield unit measurements on CT scans, application of bone texture analysis combined with machine learning improve fracture risk prediction.

• This analysis has the potential to identify vertebrae at risk for insufficiency fracture and may thus increase diagnostic value of standard CT scans.

Keywords

Spine Machine learning Osteoporosis Tomography, X-ray computed 

Abbreviations

ANN

Artificial neural networks

BMD

Bone mineral density

CCC

Concordance correlation coefficient

DXA

Dual-energy X-ray absorptiometry

FEA

Finite element analysis

GLCM

Gray-level co-occurrence matrix

GLRLM

Gray-level run-length matrix

HR-pQCT

High-resolution peripheral quantitative computed tomography

IH

Image histogram

ML

Machine learning

MLP

Multi-layer perceptron

RF

Random forest

ROI

Region of interest

SVM

Support vector machine

TA

Texture analysis

TLJ

Thoracic-lumbar junction

Notes

Funding

The authors state that this work has not received any funding.

Compliance with ethical standards

Guarantor

The scientific guarantor of this publication is Roman Guggenberger.

Conflict of interest

The authors of this manuscript declare no relationships with any companies, whose products or services may be related to the subject matter of the article.

Statistics and biometry

One of the authors has significant statistical expertise.

Informed consent

Written informed consent was waived by the Institutional Review Board.

Ethical approval

Institutional Review Board approval was obtained.

Study subjects or cohorts overlap

The control cohort used in the present study (58 patients) is part of a study population of a previously published study establishing normative values for CT-based texture analysis of vertebral bodies. Mannil M, Eberhard M, Becker AS, et al (2017) Normative values for CT-based texture analysis of vertebral bodies in dual X-ray absorptiometry-confirmed, normally mineralized subjects. Skeletal Radiology 46:1541–1551.  https://doi.org/10.1007/s00256-017-2728-0).

Methodology

• retrospective

• case-control study

• performed at one institution

Supplementary material

330_2018_5846_MOESM1_ESM.docx (20 kb)
ESM 1 (DOCX 20 kb)

References

  1. 1.
    Sambrook P, Cooper C (2006) Osteoporosis. Lancet 367:2010–2018.  https://doi.org/10.1016/S0140-6736(06)68891-0 CrossRefGoogle Scholar
  2. 2.
    Kim DH, Vaccaro AR (2006) Osteoporotic compression fractures of the spine; current options and considerations for treatment. Spine J 6:479–487.  https://doi.org/10.1016/j.spinee.2006.04.013 CrossRefPubMedGoogle Scholar
  3. 3.
    NIH Consensus Development Panel on Osteoporosis Prevention, Diagnosis, and Therapy (2001) Osteoporosis prevention, diagnosis, and therapy. JAMA 285:785–795.  https://doi.org/10.1001/jama.285.6.785 CrossRefGoogle Scholar
  4. 4.
    Johnell O, Kanis JA (2006) An estimate of the worldwide prevalence and disability associated with osteoporotic fractures. Osteoporos Int 17:1726–1733.  https://doi.org/10.1007/s00198-006-0172-4 CrossRefPubMedPubMedCentralGoogle Scholar
  5. 5.
    Johnell O, Kanis J (2005) Epidemiology of osteoporotic fractures. Osteoporos Int 16:S3–S7.  https://doi.org/10.1007/s00198-004-1702-6 CrossRefPubMedGoogle Scholar
  6. 6.
    Delmas PD, van de Langerijt L, Watts NB et al (2005) Underdiagnosis of vertebral fractures is a worldwide problem: the IMPACT study. J Bone Miner Res 20:557–563.  https://doi.org/10.1359/JBMR.041214 CrossRefPubMedGoogle Scholar
  7. 7.
    Silva BC, Leslie WD, Resch H et al (2014) Trabecular bone score: a noninvasive analytical method based upon the DXA image. J Bone Miner Res 29:518–530.  https://doi.org/10.1002/jbmr.2176 CrossRefPubMedGoogle Scholar
  8. 8.
    Burns JE, Yao J, Summers RM (2017) Vertebral body compression fractures and bone density: automated detection and classification on CT images. Radiology 284:788–797.  https://doi.org/10.1148/radiol.2017162100
  9. 9.
    Schreiber JJ, Anderson PA, Rosas HG, Buchholz AL, Au AG (2011) Hounsfield units for assessing bone mineral density and strength: a tool for osteoporosis management. J Bone Joint Surg 93:1057–1063.  https://doi.org/10.2106/JBJS.J.00160
  10. 10.
    Krug R, Burghardt AJ, Majumdar S, Link TM (2010) High-resolution imaging techniques for the assessment of osteoporosis. Radiol Clin North Am 48:601–621.  https://doi.org/10.1016/j.rcl.2010.02.015 CrossRefPubMedCentralPubMedGoogle Scholar
  11. 11.
    Damilakis J, Maris TG, Karantanas AH (2007) An update on the assessment of osteoporosis using radiologic techniques. Eur Radiol 17:1591–1602.  https://doi.org/10.1007/s00330-006-0511-z CrossRefPubMedGoogle Scholar
  12. 12.
    Imai K, Ohnishi I, Bessho M, Nakamura K (2006) Nonlinear finite element model predicts vertebral bone strength and fracture site. Spine (Phila Pa 1976) 31:1789–1794Google Scholar
  13. 13.
    Schwaiger BJ, Kopperdahl DL, Nardo L et al (2017) Vertebral and femoral bone mineral density and bone strength in prostate cancer patients assessed in phantomless PET/CT examinations. Bone 101:62–69.  https://doi.org/10.1016/j.bone.2017.04.008 CrossRefPubMedCentralPubMedGoogle Scholar
  14. 14.
    Lubner MG, Smith AD, Sandrasegaran K, Sahani DV, Pickhardt PJ (2017) CT texture analysis: definitions, applications, biologic correlates, and challenges. Radiographics 37:1483–1503.  https://doi.org/10.1148/rg.2017170056
  15. 15.
    Rachidi M, Marchadier A, Gadois C, Lespessailles E, Chappard C, Benhamou CL (2008) Laws’ masks descriptors applied to bone texture analysis: an innovative and discriminant tool in osteoporosis. Skeletal Radiol 37:541–548.  https://doi.org/10.1007/s00256-008-0463-2
  16. 16.
    Thevenot J, Hirvasniemi J, Pulkkinen P et al (2014) Assessment of risk of femoral neck fracture with radiographic texture parameters: a retrospective study. Radiology 272:184–191CrossRefPubMedGoogle Scholar
  17. 17.
    Zou Z, Yang J, Megalooikonomou V, Jennane R, Cheng E, Ling H (2016) Trabecular bone texture classification using wavelet leaders. Proc. SPIE 9788, Medical Imaging 2016: Biomedical Applications in Molecular, Structural, and Functional Imaging, 97880E.  https://doi.org/10.1117/12.2216452
  18. 18.
    Mannil M, Eberhard M, Becker AS et al (2017) Normative values for CT-based texture analysis of vertebral bodies in dual X-ray absorptiometry-confirmed, normally mineralized subjects. Skeletal Radiol 46:1541–1551.  https://doi.org/10.1007/s00256-017-2728-0 CrossRefPubMedGoogle Scholar
  19. 19.
    Tabari A, Torriani M, Miller KK, Klibanski A, Kalra MK, Bredella MA (2016) Anorexia nervosa: analysis of trabecular texture with CT. Radiology 283:178–185Google Scholar
  20. 20.
    Torres C, Hammond I (2016) Computed tomography and magnetic resonance imaging in the differentiation of osteoporotic fractures from neoplastic metastatic fractures. J Clin Densitom 19:63–69.  https://doi.org/10.1016/j.jocd.2015.08.008 CrossRefPubMedGoogle Scholar
  21. 21.
    Genant HK, Wu CY, van Kuijk C, Nevitt MC (2009) Vertebral fracture assessment using a semiquantitative technique. J Bone Miner Res 8:1137–1148.  https://doi.org/10.1002/jbmr.5650080915 CrossRefGoogle Scholar
  22. 22.
    Szczypiński PM, Strzelecki M, Materka A, Klepaczko A (2009) MaZda—a software package for image texture analysis. Comput Methods Programs Biomed 94:66–76.  https://doi.org/10.1016/j.cmpb.2008.08.005 CrossRefPubMedGoogle Scholar
  23. 23.
    Andresen R, Radmer S, Banzer D (1998) Bone mineral density and spongiosa architecture in correlation to vertebral body insufficiency fractures. Acta Radiol 39:538–542CrossRefPubMedGoogle Scholar
  24. 24.
    Ito M, Ikeda K, Nishiguchi M et al (2005) Multi-detector row CT imaging of vertebral microstructure for evaluation of fracture risk. J Bone Miner Res 20:1828–1836.  https://doi.org/10.1359/JBMR.050610 CrossRefPubMedGoogle Scholar
  25. 25.
    Issever AS, Link TM, Kentenich M et al (2010) Assessment of trabecular bone structure using MDCT: comparison of 64- and 320-slice CT using HR-pQCT as the reference standard. Eur Radiol 20:458–468.  https://doi.org/10.1007/s00330-009-1571-7 CrossRefPubMedGoogle Scholar
  26. 26.
    Kuhn M (2008) Building predictive models in R using the caret package. J Stat Softw 28.  https://doi.org/10.18637/jss.v028.i05
  27. 27.
    Gevrey M, Dimopoulos I, Lek S (2003) Review and comparison of methods to study the contribution of variables in artificial neural network models. Ecol Modell 160:249–264Google Scholar
  28. 28.
    DeLong ER, DeLong DM, Clarke-Pearson DL (1988) Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach. Biometrics 44:837–845CrossRefGoogle Scholar
  29. 29.
    Lin LI-K (1989) A concordance correlation coefficient to evaluate reproducibility. Biometrics 45:255–268.  https://doi.org/10.2307/2532051
  30. 30.
    Erickson BJ, Korfiatis P, Akkus Z, Kline TL (2017) Machine learning for medical imaging. Radiographics 37:505–515.  https://doi.org/10.1148/rg.2017160130 CrossRefPubMedCentralPubMedGoogle Scholar
  31. 31.
    Valentinitsch A, Patsch J, Mueller D et al (2010) Texture analysis in quantitative osteoporosis assessment. In: Biomedical imaging: from nano to macro, 2010 IEEE International Symposium on. IEEE, pp 1361–1364Google Scholar
  32. 32.
    Boivin GY, Chavassieux PM, Santora AC, Yates J, Meunier PJ (2000) Alendronate increases bone strength by increasing the mean degree of mineralization of bone tissue in osteoporotic women. Bone 27:687–694Google Scholar
  33. 33.
    Guggenbuhl P, Bodic F, Hamel L, Baslé MF, Chappard D (2006) Texture analysis of X-ray radiographs of iliac bone is correlated with bone micro-CT. Osteoporos Int 17:447–454.  https://doi.org/10.1007/s00198-005-0007-8
  34. 34.
    Chappard D, Guggenbuhl P, Legrand E, Baslé MF, Audran M (2005) Texture analysis of X-ray radiographs is correlated with bone histomorphometry. J Bone Miner Metab 23:24–29.  https://doi.org/10.1007/s00774-004-0536-9
  35. 35.
    Kimmel DB, Recker RR, Gallagher JC, Vaswani AS, Aloia JF (1990) A comparison of iliac bone histomorphometric data in post-menopausal osteoporotic and normal subjects. Bone Miner 11:217–235Google Scholar
  36. 36.
    Reddy TK, Kumaravel N (2010) Wavelet based texture analysis and classification of bone lesions from dental CT. Int J Med Eng Inf 2:319–327Google Scholar
  37. 37.
    Rohlmann A, Zander T, Bergmann G (2006) Spinal loads after osteoporotic vertebral fractures treated by vertebroplasty or kyphoplasty. Eur Spine J 15:1255–1264.  https://doi.org/10.1007/s00586-005-0018-3 CrossRefPubMedGoogle Scholar
  38. 38.
    Paul R, Alahamri S, Malla S, Quadri GJ (2017) Make your bone great again: a study on osteoporosis classification. Available via http://arxiv.org/abs/1707.05385. Accessed 02 Jan 2018
  39. 39.
    Wagner S, Stäbler A, Sittek H et al (2005) Diagnosis of osteoporosis: visual assessment on conventional versus digital radiographs. Osteoporos Int 16:1815–1822.  https://doi.org/10.1007/s00198-005-1937-x CrossRefPubMedGoogle Scholar
  40. 40.
    Ngo VQ, Dinh TN (2016) Bone texture characterization based on Contourlet and Gabor tranforms. Int J Comput Theory Eng 8:177–181.  https://doi.org/10.7763/IJCTE.2016.V8.1040 CrossRefGoogle Scholar

Copyright information

© European Society of Radiology 2018

Authors and Affiliations

  1. 1.Institute of Diagnostic and Interventional RadiologyUniversity Hospital ZurichZurichSwitzerland
  2. 2.University Hospital of ZurichZurichSwitzerland
  3. 3.University of ZurichZurichSwitzerland
  4. 4.Department of TraumaUniversity Hospital ZurichZurichSwitzerland
  5. 5.Department of RadiologyUniversity Hospital Balgrist, University of ZurichZurichSwitzerland

Personalised recommendations