Skip to main content
SpringerLink
Log in

Prediction of lumbar vertebral strength of elderly men based on quantitative computed tomography images using machine learning

  • Original Article
  • Published:
Osteoporosis International Aims and scope Submit manuscript

Abstract

Summary

The parameters extracted from quantitative computed tomography (QCT) images were used to predict vertebral strength through machine learning models, and the highly accurate prediction indicated that it may be a promising approach to assess fracture risk in clinics.

Introduction

Vertebral fracture is common in elderly populations. The main factor contributing to vertebral fracture is the reduced vertebral strength. This study aimed to predict vertebral strength based on clinical QCT images by using machine learning.

Methods

Eighty subjects with QCT data of lumbar spine were randomly selected from the MrOS cohorts. L1 vertebral strengths were computed by QCT-based finite element analysis. A total of 58 features of each L1 vertebral body were extracted from QCT images, including grayscale distribution, grayscale values of 39 partitioned regions, BMDQCT, structural rigidity, axial rigidity, and BMDQCTAmin. Feature selection and dimensionality reduction were used to simplify the 58 features. General regression neural network and support vector regression models were developed to predict vertebral strength. Performance of prediction models was quantified by the mean squared error, the coefficient of determination, the mean bias, and the SD of bias.

Results

The 58 parameters were simplified to five features (grayscale value of the 60% percentile, grayscale values of three specific partitioned regions, and BMDQCTAmin) and nine principal components (PCs). High accuracy was achieved by using the five features or the nine PCs to predict vertebral strength.

Conclusions

This study provided an effective approach to predict vertebral strength and showed that it may have great potential in clinical applications for noninvasive assessment of vertebral fracture risk.

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

Access this article

Log in via an institution

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

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4

Similar content being viewed by others

References

  1. Matsumoto T, Ohnishi I, Bessho M, Imai K, Ohashi S, Nakamura K (2009) Prediction of vertebral strength under loading conditions occurring in activities of daily living using a computed tomography-based nonlinear finite element method. Spine 34(14):1464–1469. https://doi.org/10.1097/BRS.0b013e3181a55636

  2. Dall'Ara E, Schmidt R, Pahra D, Varga P, Chevalier Y, Patsch J, Kainberger F, Zysset P (2010) A nonlinear finite element model validation study based on a novel experimental technique for inducing anterior wedge-shape fractures in human vertebral bodies in vitro. J Biomech 43(12):2374–2380. https://doi.org/10.1016/j.jbiomech.2010.04.023

    Article  CAS  PubMed  Google Scholar 

  3. Borgstrom F, Olafsson G, Strom O, Tillman JB, Wardlaw D, Boonen S, Miltenburger C (2013) The impact of different health dimensions on overall quality of life related to kyphoplasty and non-surgical management. Osteoporosis Int 24(7):1991–1999. https://doi.org/10.1007/s00198-012-2237-x

  4. Song LJ, Wang LL, Ning L, Fan SW, Zhao X, Chen YL, Li ZZ, Hu ZA (2018) A modification and validation of quantitative morphometry classification system for osteoporotic vertebral compressive fractures in mainland Chinese. Osteoporosis Int 29(11):2495–2504. https://doi.org/10.1007/s00198-018-4641-3

  5. Papanastassiou ID, Filis A, Gerochristou MA, Vrionis FD (2014) Controversial issues in kyphoplasty and vertebroplasty in osteoporotic vertebral fractures. Biomed Res Int 2014(934206):1–12. https://doi.org/10.1155/2014/934206

    Article  CAS  Google Scholar 

  6. Lochmuller EM, Burklein D, Kuhn V, Glaser C, Muller R, Gluer CC, Eckstein F (2002) Mechanical strength of the thoracolumbar spine in the elderly: prediction from in situ dual-energy X-ray absorptiometry, quantitative computed tomography (QCT), upper and lower limb peripheral QCT, and quantitative ultrasound. Bone 31(1):77–84. https://doi.org/10.1016/S8756-3282(02)00792-5

  7. Keaveny TM, Donley DW, Hoffmann PF, Mitlak BH, Glass EV, San Martin JA (2007) Effects of teriparatide and alendronate on vertebral strength as assessed by finite element modeling of QCT scans in women with osteoporosis. J Bone Miner Res 22(1):149–157. https://doi.org/10.1359/JBMR.061011

  8. Wang X, Sanyal A, Cawthon PM, Palermo L, Jekir M, Christensen J, Ensrud KE, Cummings SR, Orwoll E, Black DM, Keaveny TM, Mros OFM (2012) Prediction of new clinical vertebral fractures in elderly men using finite element analysis of CT scans. J Bone Miner Res 27(4):808–816. https://doi.org/10.1002/jbmr.1539

    Article  PubMed  PubMed Central  Google Scholar 

  9. Kopperdahl DL, Aspelund T, Hoffmann PF, Sigurdsson S, Siggeirsdottir K, Harris TB, Gudnason V, Keaveny TM (2014) Assessment of incident spine and hip fractures in women and men using finite element analysis of CT scans. J Bone Miner Res 29(3):570–580. https://doi.org/10.1002/jbmr.2069

  10. Luo YH, Ahmed S, Leslie WD (2018) Automation of a DXA-based finite element tool for clinical assessment of hip fracture risk. Comput Meth Prog Bio 155:75–83. https://doi.org/10.1016/j.cmpb.2017.11.020

  11. Gong H, Zhang M, Fan YB, Kwok WL, Leung PC (2012) Relationships between femoral strength evaluated by nonlinear finite element analysis and BMD, material distribution and geometric morphology. Ann Biomed Eng 40(7):1575–1585. https://doi.org/10.1007/s10439-012-0514-7

    Article  PubMed  Google Scholar 

  12. Yi C, Wang MY, Wei J, Wang J, Wang L, Cheng XG (2017) Preoperative QCT assessment of femoral head for assessment of femoral head bone loss. Exp Ther Med 13(4):1470–1474. https://doi.org/10.3892/etm.2017.4136

    Article  PubMed  PubMed Central  Google Scholar 

  13. Mirzaei M, Zeinali A, Razmjoo A, Nazemi M (2009) On prediction of the strength levels and failure patterns of human vertebrae using quantitative computed tomography (QCT)-based finite element method. J Biomech 42(11):1584–1591. https://doi.org/10.1016/j.jbiomech.2009.04.042

    Article  PubMed  Google Scholar 

  14. Luo YH, Yang HJ (2019) Comparison of femur stiffness measured from DXA and QCT for assessment of hip fracture risk. J Bone Miner Metab 37(2):342–350. https://doi.org/10.1007/s00774-018-0926-z

  15. Crawford RP, Cann CE, Keaveny TM (2003) Finite element models predict in vitro vertebral body compressive strength better than quantitative computed tomography. Bone 33(4):744–750. https://doi.org/10.1016/S8756-3282(03)00210-2

    Article  PubMed  Google Scholar 

  16. Bachmann KN, Bruno AG, Bredella MA, Schorr M, Lawson EA, Gill CM, Singhal V, Meenaghan E, Gerweck AV, Eddy KT, Ebrahimi S, Koman SL, Greenblatt JM, Keane RJ, Weigel T, Dechant E, Misra M, Klibanski A, Bouxsein ML, Miller KK (2016) Vertebral strength and estimated fracture risk across the BMI spectrum in women. J Bone Miner Res 31(2):281–288. https://doi.org/10.1002/jbmr.2697

  17. Bruno AG, Broe KE, Zhang XC, Samelson EJ, Meng CA, Manoharan R, D'Agostino J, Cupples LA, Kiel DP, Bouxsein ML (2014) Vertebral size, bone density, and strength in men and women matched for age and areal spine BMD. J Bone Miner Res 29(3):562–569. https://doi.org/10.1002/jbmr.2067

  18. Taylor M, Perilli E, Martelli S (2017) Development of a surrogate model based on patient weight, bone mass and geometry to predict femoral neck strains and fracture loads. J Biomech 55:121–127. https://doi.org/10.1016/j.jbiomech.2017.02.022

    Article  PubMed  Google Scholar 

  19. Yang CC, Nagarajan MB, Huber MB, Carballidogamio J, Bauer JS, Baum T, Eckstein F, Lochmüller E, Majumdar S, Link TM (2014) Improving bone strength prediction in human proximal femur specimens through geometrical characterization of trabecular bone microarchitecture and support vector regression. J Electron Imaging 23(1):013013. https://doi.org/10.1117/1.JEI.23.1.013013

    Article  PubMed  PubMed Central  Google Scholar 

  20. Murphy KP (2012) Machine learning: a probabilistic perspective. MIT Press, Massachusetts

    Google Scholar 

  21. Nagarajan MB, Checefsky WA, Abidin AZ, Tsai H, Wang XX, Hobbs SK, Bauer JS, Baum T, Wismuller A (2015) Characterizing trabecular bone structure for assessing vertebral fracture risk on volumetric quantitative computed tomography. Proc SPIE Int Soc Opt Eng 9417(3):297–308. https://doi.org/10.1117/12.2082059

    Article  Google Scholar 

  22. Panda BN, Bahubalendruni MVAR, Biswal BB (2015) A general regression neural network approach for the evaluation of compressive strength of FDM prototypes. Neural Comput Appl 26(5):1129–1136. https://doi.org/10.1007/s00521-014-1788-5

    Article  Google Scholar 

  23. Harvey NC, Oden A, Orwoll E, Lapidus J, Kwok T, Karlsson MK, Rosengren BE, Ljunggren Ö, Cooper C, McCloskey E, Kanis JA, Ohlsson C, Mellström D, Johansson H (2018) Falls predict fractures independently of FRAX probability: a meta-analysis of the Osteoporotic Fractures in Men (MrOS) study. J Bone Miner Res 33(3):510–516. https://doi.org/10.1002/jbmr.3331

    Article  PubMed  Google Scholar 

  24. Orwoll ES, Marshall LM, Nielson CM, Cummings SR, Lapidus J, Cauley JA, Ensrud K, Lane N, Hoffmann PR, Kopperdahl DL, Keaveny TM, Osteoporotic Fractures in Men Study Group (2009) Finite element analysis of the proximal femur and hip fracture risk in older men. J Bone Miner Res 24(3):475–483. https://doi.org/10.1359/JBMR.081201

    Article  PubMed  Google Scholar 

  25. Yang L, Burton AC, Bradburn M, Nielson CM, Orwoll ES, Eastell R, Osteoporotic Fractures in Men (MrOS) Study Group (2012) Distribution of bone density in the proximal femur and its association with hip fracture risk in older men: the Osteoporotic Fractures in Men (MrOS) Study. J Bone Miner Res 27(11):2314–2324. https://doi.org/10.1002/jbmr.1693

    Article  PubMed  PubMed Central  Google Scholar 

  26. Yoo TK, Kim SK, Kim DW, Choi JY, Lee WH, Oh E, Park EC (2013) Osteoporosis risk prediction for bone mineral density assessment of postmenopausal women using machine learning. Yonsei Med J 54(6):1321–1330. https://doi.org/10.3349/ymj.2013.54.6.1321

    Article  PubMed  PubMed Central  Google Scholar 

  27. Johnell O, Kanis JA (2006) An estimate of the worldwide prevalence and disability associated with osteoporotic fractures. Osteoporosis Int 17(12):1726–1733. https://doi.org/10.1007/s00198-006-0172-4

  28. Van Der Klift M, De Laet CEDH, McCloskey EV, Hofman A, Pols HAP (2002) The incidence of vertebral fractures in men and women: the Rotterdam Study. J Bone Miner Res 17(6):1051–1056. https://doi.org/10.1359/jbmr.2002.17.6.1051

    Article  PubMed  Google Scholar 

  29. Cooper C, Atkinson EJ, O'Fallon WM, Melton LJ (1992) Incidence of clinically diagnosed vertebral fractures: a population-based study in Rochester, Minnesota, 1985-1989. J Bone Miner Res 7(2):221–227. https://doi.org/10.1002/jbmr.5650070214

    Article  CAS  PubMed  Google Scholar 

  30. Keaveny TM, Hoffmann PF, Singh M, Palermo L, Bilezikian JP, Greenspan SL, Black DM (2008) Femoral bone strength and its relation to cortical and trabecular changes after treatment with PTH, alendronate, and their combination as assessed by finite element analysis of quantitative CT scans. J Bone Miner Res 23(12):1974–1982. https://doi.org/10.1359/jbmr.080805

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  31. Christiansen BA, Kopperdahl DL, Kiel DP, Keaveny TM, Bouxsein ML (2011) Mechanical contributions of the cortical and trabecular compartments contribute to differences in age-related changes in vertebral body strength in men and women assessed by QCT-based finite element analysis. J Bone Miner Res 26(5):974–983. https://doi.org/10.1002/jbmr.287

    Article  PubMed  PubMed Central  Google Scholar 

  32. Chalhoub D, Orwoll ES, Cawthon PM, Ensrud KE, Boudreau R, Greenspan S, Newman AB, Zmuda J, Bauer D, Cummings S, Cauley JA, St OFMM (2016) Areal and volumetric bone mineral density and risk of multiple types of fracture in older men. Bone 92:100–106. https://doi.org/10.1016/j.bone.2016.08.014

  33. Eswaran SK, Gupta A, Keaveny TM (2007) Locations of bone tissue at high risk of initial failure during compressive loading of the human vertebral body. Bone 41(4):733–739. https://doi.org/10.1016/j.bone.2007.05.017

  34. Riggs BL, Melton LJ, Robb RA, Camp JJ, Atkinson EJ, Oberg AL, Rouleau PA, McCollough CH, Khosla S, Bouxsein ML (2006) Population-based analysis of the relationship of whole bone strength indices and fall-related loads to age- and sex-specific patterns of hip and wrist fractures. J Bone Miner Res 21(2):315–323. https://doi.org/10.1359/JBMR.051022

    Article  PubMed  Google Scholar 

  35. Buckley JM, Loo K, Motherway J (2007) Comparison of quantitative computed tomography-based measures in predicting vertebral compressive strength. Bone 40(3):767–774. https://doi.org/10.1016/j.bone.2006.10.025

    Article  PubMed  Google Scholar 

  36. Bouxsein ML, Melton LJ, Riggs BL, Muller J, Atkinson EJ, Oberg AL, Robb RA, Camp JJ, Rouleau PA, McCollough CH, Khosla S (2006) Age- and sex-specific differences in the factor of risk for vertebral fracture: a population-based study using QCT. J Bone Miner Res 21(9):1475–1482. https://doi.org/10.1359/JBMR.060606

    Article  PubMed  Google Scholar 

  37. Leslie WD, Lix LM (2014) Comparison between various fracture risk assessment tools. Osteoporosis Int 25(1):1–21. https://doi.org/10.1007/s00198-013-2409-3

    Article  CAS  Google Scholar 

  38. Keaveny TM, Kopperdahl DL, Melton LJ, Hoffmann PF, Amin S, Riggs BL, Khosla S (2010) Age-dependence of femoral strength in white women and men. J Bone Miner Res 25(5):994–1001. https://doi.org/10.1359/jbmr.091033

    Article  PubMed  Google Scholar 

  39. Roberts BJ, Kopperdahl D, Thrall E, Muller JA, Keaveny TM, Bouxsein ML (2009) Prediction of femoral strength in a sideways fall configuration using QCT-based finite element analysis. Bone 44(S1):S72. https://doi.org/10.1016/j.bone.2009.01.158

    Article  Google Scholar 

  40. Keyak JH (2001) Improved prediction of proximal femoral fracture load using nonlinear finite element models. Med Eng Phys 23(3):165–173. https://doi.org/10.1016/s1350-4533(01)00045-5

    Article  CAS  PubMed  Google Scholar 

  41. Crawford RP, Brouwers JEM, Keaveny TM (2004) Accurate prediction of vertebral strength using voxel-based non-linear finite element models. Trans Orthop Res Soc 29:1123

    Google Scholar 

  42. Moro M, Hecker AT, Bouxsein ML, Myers ER (1995) Failure load of thoracic vertebrae correlates with lumbar bone mineral density measured by DXA. Calcif Tissue Int 56(3):206–209. https://doi.org/10.1007/BF00298611

    Article  CAS  PubMed  Google Scholar 

  43. Dall'Ara E, Pahr D, Varga P, Kainberger F, Zysset P (2012) QCT-based finite element models predict human vertebral strength in vitro significantly better than simulated DEXA. Osteoporosis Int 23(2):563–572. https://doi.org/10.1007/s00198-011-1568-3

    Article  CAS  Google Scholar 

  44. Imai K, Ohnishi I, Bessho M, Nakamura K (2006) Nonlinear finite element model predicts vertebral bone strength and fracture site. Spine 31(16):1789–1794. https://doi.org/10.1097/01.brs.0000225993.57349.df

  45. Graeff C, Chevalier Y, Charlebois M, Varga P, Pahr D, Nickelsen TN, Morlock MM, Gluer CC, Zysset PK (2009) Improvements in vertebral body strength under teriparatide treatment assessed in vivo by finite element analysis: results from the EUROFORS study. J Bone Miner Res 24(10):1672–1680. https://doi.org/10.1359/JBMR.090416

    Article  CAS  PubMed  Google Scholar 

Download references

Acknowledgments

We wish to acknowledge the Osteoporotic Fractures in Men (MrOS) study. We are grateful to all of the participants in this study as well as all of the technicians who performed the scans.

Funding

This work is supported by the National Natural Science foundation of China (Nos. 11432016, 11872095, 11702110), the Natural Science foundation of Jilin Province (Nos. 20160101297JC, 20170519008JH, and 20170520093JH), and the Graduate Innovation Fund of Jilin University (No. 101832018C194).

Author information

Authors and Affiliations

  1. Department of Engineering Mechanics, Jilin University, Nanling Campus, Changchun, 130025, People’s Republic of China

    M. Zhang, H. Gong & K. Zhang

  2. Department of Biomedical Engineering, The Hong Kong Polytechnic University, Hong Hum, Kowloon, Hong Kong SAR, People’s Republic of China

    M. Zhang

Authors
  1. M. Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. H. Gong
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. K. Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. M. Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to H. Gong.

Ethics declarations

Conflicts of interest

None.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Zhang, M., Gong, H., Zhang, K. et al. Prediction of lumbar vertebral strength of elderly men based on quantitative computed tomography images using machine learning. Osteoporos Int 30, 2271–2282 (2019). https://doi.org/10.1007/s00198-019-05117-0

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00198-019-05117-0

Keywords

Search

Navigation