Skip to main content

Advertisement

SpringerLink
Log in

MRI-based radiomics assessment of the imminent new vertebral fracture after vertebral augmentation

  • Original Article
  • Published:
European Spine Journal Aims and scope Submit manuscript

Abstract

Background

Imminent new vertebral fracture (NVF) is highly prevalent after vertebral augmentation (VA). An accurate assessment of the imminent risk of NVF could help to develop prompt treatment strategies.

Purpose

To develop and validate predictive models that integrated the radiomic features and clinical risk factors based on machine learning algorithms to evaluate the imminent risk of NVF.

Materials and methods

In this retrospective study, a total of 168 patients with painful osteoporotic vertebral compression fractures treated with VA were evaluated. Radiomic features of L1 vertebrae based on lumbar T2-weighted images were obtained. Univariate and LASSO-regression analyses were applied to select the optimal features and construct radiomic signature. The radiomic signature and clinical signature were integrated to develop a predictive model by using machine learning algorithms including LR, RF, SVM, and XGBoost. Receiver operating characteristic curve and calibration curve analyses were used to evaluate the predictive performance of the models.

Results

The radiomic-XGBoost model with the highest AUC of 0.93 of the training cohort and 0.9 of the test cohort among the machine learning algorithms. The combined-XGBoost model with the best performance with an AUC of 0.9 in the training cohort and 0.9 in the test cohort. The radiomic-XGBoost model and combined-XGBoost model achieved better performance to assess the imminent risk of NVF than that of the clinical risk factors alone (p < 0.05).

Conclusion

Radiomic and machine learning modeling based on T2W images of preoperative lumbar MRI had an excellent ability to evaluate the imminent risk of NVF after VA.

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
Fig. 5
Fig. 6
Fig. 7
Fig. 8

Similar content being viewed by others

Abbreviations

OVCF:

Osteoporotic vertebral compression fracture

NVF:

New vertebral fracture

VA:

Vertebral augmentation

ROI:

Regions of interest

ICC:

Intra-class correlation coefficients

ROC:

Receiver operating characteristic

AUC:

Area under the receiver operating characteristic curve

LR:

Logistic regression

RF:

Random forest

SVM:

Support vector machine

XGBoost:

Extreme gradient boosting

References

  1. Compston JE, McClung MR, Leslie WD (2019) Osteoporos Lancet 393(10169):364–376

    Article  CAS  Google Scholar 

  2. Johnell O, Kanis JA (2006) An estimate of the worldwide prevalence and disability associated with osteoporotic fractures. Osteoporos Int 17(12):1726–1733

    Article  CAS  PubMed  Google Scholar 

  3. Hopkins RB, Burke N, Von Keyserlingk C et al (2016) The current economic burden of illness of osteoporosis in Canada. Osteoporos Int 27(10):3023–1732

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  4. Burge R, Dawson-Hughes B, Solomon DH et al (2007) Incidence and economic burden of osteoporosis-related fractures in the United States, 2005–2025. J Bone Miner Res 22(3):465–475

    Article  PubMed  Google Scholar 

  5. Lin X, Xiong D, Peng YQ et al (2015) Epidemiology and management of osteoporosis in the People’s Republic of China: current perspectives. Clin Interv Aging 10:1017–1033

    PubMed  PubMed Central  Google Scholar 

  6. Yang EZ, Xu JG, Huang GZ et al (2016) Percutaneous vertebroplasty versus conservative treatment in aged patients with acute osteoporotic vertebral compression fractures: a prospective randomized controlled clinical study. Spine 41(8):653–660

    Article  PubMed  Google Scholar 

  7. Hoshino M, Takahashi S, Yasuda H et al (2019) Balloon kyphoplasty versus conservative treatment for acute osteoporotic vertebral fractures with poor prognostic factors: propensity score matched analysis using data from two prospective multicenter studies. Spine 44(2):110–117

    Article  PubMed  Google Scholar 

  8. Rho YJ, Choe WJ, Chun YI (2012) Risk factors predicting the new symptomatic vertebral compression fractures after percutaneous vertebroplasty or kyphoplasty. Eur Spine J 21(5):905–911

    Article  PubMed  Google Scholar 

  9. Lee BG, Choi JH, Kim DY et al (2019) Risk factors for newly developed osteoporotic vertebral compression fractures following treatment for osteoporotic vertebral compression fractures. Spine J 19(2):301–305

    Article  PubMed  Google Scholar 

  10. Roux C, Briot K (2017) Imminent fracture risk. Osteoporos Int 28(6):1765–1769

    Article  CAS  PubMed  Google Scholar 

  11. Johansson H, Siggeirsdóttir K, Harvey NC et al (2017) Imminent risk of fracture after fracture. Osteoporos Int 28(3):775–780

    Article  CAS  PubMed  Google Scholar 

  12. Park SM, Ahn SH, Kim HY et al (2020) Incidence and mortality of subsequent vertebral fractures: analysis of claims data of the Korea National Health Insurance Service from 2007 to 2016. Spine J 20(2):225–233

    Article  PubMed  Google Scholar 

  13. Bliuc D, Nguyen ND, Milch VE et al (2009) Mortality risk associated with low-trauma osteoporotic fracture and subsequent fracture in men and women. JAMA 301(5):513–521

    Article  CAS  PubMed  Google Scholar 

  14. Scapicchio C, Gabelloni M, Barucci A et al (2021) A deep look into radiomics. Radiol Med 126(10):1296–1311

    Article  PubMed  PubMed Central  Google Scholar 

  15. Muehlematter UJ, Mannil M, Becker AS et al (2019) Vertebral body insufficiency fractures: detection of vertebrae at risk on standard CT images using texture analysis and machine learning. Eur Radiol 29(5):2207–2217

    Article  PubMed  Google Scholar 

  16. Burian E, Subburaj K, Mookiah M et al (2019) Texture analysis of vertebral bone marrow using chemical shift encoding-based water-fat MRI: a feasibility study. Osteoporos Int 30(6):1265–1274

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  17. Jiang YW, Xu XJ, Wang R et al (2022) Radiomics analysis based on lumbar spine CT to detect osteoporosis. Eur Radiol 32(11):8019–8026

    Article  PubMed  PubMed Central  Google Scholar 

  18. Rastegar S, Vaziri M, Qasempour Y et al (2020) Radiomics for classification of bone mineral loss: a machine learning study. Diagn Interv Imaging 101(9):599–610

    Article  CAS  PubMed  Google Scholar 

  19. He L, Liu Z, Liu C et al (2021) Radiomics based on lumbar spine magnetic resonance imaging to detect osteoporosis. Acad Radiol 28(6):e165–e171

    Article  PubMed  Google Scholar 

  20. Zaworski C, Cheah J, Koff MF et al (2021) MRI-based texture analysis of trabecular bone for opportunistic screening of skeletal fragility. J Clin Endocrinol Metab 106(8):2233–2241

    Article  PubMed  Google Scholar 

  21. Grigoryan M, Guermazi A, Roemer FW et al (2003) Recognizing and reporting osteoporotic vertebral fractures. Eur Spine J 12(Suppl 2):S104–S112

    Article  PubMed  PubMed Central  Google Scholar 

  22. Nieuwenhuijse MJ, van Rijswijk CS, van Erkel AR et al (2012) The intravertebral cleft in painful long-standing osteoporotic vertebral compression fractures treated with percutaneous vertebroplasty: diagnostic assessment and clinical significance. Spine 37(11):974–981

    Article  PubMed  Google Scholar 

  23. Garfin SR, Yuan HA, Reiley MA (2001) New technologies in spine: kyphoplasty and vertebroplasty for the treatment of painful osteoporotic compression fractures. Spine 26(14):1511–1515

    Article  CAS  PubMed  Google Scholar 

  24. Toth E, Banefelt J, Åkesson K et al (2020) History of previous fracture and imminent fracture risk in Swedish women aged 55 to 90 years presenting with a fragility fracture. J Bone Miner Res 35(5):861–868

    Article  PubMed  Google Scholar 

  25. LeBoff MS, Greenspan SL, Insogna KL et al (2022) The clinician’s guide to prevention and treatment of osteoporosis. Osteoporos Int 33(10):2049–2102

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  26. Zhong BY, He SC, Zhu HD et al (2017) Risk prediction of new adjacent vertebral fractures after PVP for patients with vertebral compression fractures: development of a prediction model. Cardiovasc Interv Radiol 40(2):277–284

    Article  Google Scholar 

  27. Söreskog E, Ström O, Spångéus A et al (2020) Risk of major osteoporotic fracture after first, second and third fracture in Swedish women aged 50 years and older. Bone 134:115286

    Article  PubMed  Google Scholar 

  28. Li Q, Long X, Wang Y et al (2021) Development and validation of a nomogram for predicting the probability of new vertebral compression fractures after vertebral augmentation of osteoporotic vertebral compression fractures. BMC Musculoskelet Disord 22(1):957

    Article  PubMed  PubMed Central  Google Scholar 

  29. Xue Z, Huo J, Sun X et al (2022) Using radiomic features of lumbar spine CT images to differentiate osteoporosis from normal bone density. BMC Musculoskelet Disord 23(1):336

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  30. Sollmann N, Becherucci EA, Boehm C et al (2022) Texture analysis using CT and chemical shift encoding-based water-fat MRI Can improve differentiation between patients with and without osteoporotic vertebral fractures. Front Endocrinol 1:778537

    Article  Google Scholar 

  31. Perrier-Cornet J, Omorou AY, Fauny M et al (2019) Opportunistic screening for osteoporosis using thoraco–abdomino–pelvic CT-scan assessing the vertebral density in rheumatoid arthritis patients. Osteoporos Int 30(6):1215–1222

    Article  CAS  PubMed  Google Scholar 

  32. Jang S, Graffy PM, Ziemlewicz TJ et al (2019) Opportunistic osteoporosis screening at routine abdominal and thoracic CT: normative L1 trabecular attenuation values in more than 20000 adults. Radiology 291(2):360–367

    Article  PubMed  Google Scholar 

  33. Lee SJ, Graffy PM, Zea RD et al (2018) Future osteoporotic fracture risk related to lumbar vertebral trabecular attenuation measured at routine body CT. J Bone Miner Res 33(5):860–867

    Article  CAS  PubMed  Google Scholar 

  34. Gerety EL, Hopper MA, Bearcroft PW (2017) The reliability of measuring the density of the L1 vertebral body on CT imaging as a predictor of bone mineral density. Clin Radiol 72(2):177.e9-177.e15

    Article  PubMed  Google Scholar 

  35. Salzmann SN, Shirahata T, Yang J et al (2019) Regional bone mineral density differences measured by quantitative computed tomography: does the standard clinically used L1–L2 average correlate with the entire lumbosacral spine. Spine J 19(4):695–702

    Article  PubMed  Google Scholar 

  36. Dieckmeyer M, Junker D, Ruschke S et al (2020) Vertebral bone marrow heterogeneity using texture analysis of chemical shift encoding-based mri: variations in age, sex, and anatomical location. Front Endocrinol 11:555931

    Article  Google Scholar 

  37. Maciel JG, Araújo IM, Trazzi LC et al (2020) Association of bone mineral density with bone texture attributes extracted using routine magnetic resonance imaging. Clinics 75:e1766

    Article  PubMed  PubMed Central  Google Scholar 

  38. Geusens P, Bours S, Wyers CE et al (2019) Fracture liaison programs. Best Pract Res Clin Rheumatol 33(2):278–289

    Article  PubMed  Google Scholar 

Download references

Funding

This project is provided by Guangzhou Science, Technology and Innovation Commission (Grand No. 202002030209), Guangzhou Municipal Health and Family Planning Commission (Grand No. 20201A010090).

Author information

Author notes

  1. Jinhui Cai, Chen Shen and Tingqian Yang have contributed equally to this work.

Authors and Affiliations

  1. Department of Radiology, The Seventh Affiliated Hospital, Sun Yat-Sen University, 628 Zhenyuan Road, Xinhu Street, Guangming New District, Shenzhen, 518107, Guangdong, China

    Jinhui Cai, Tingqian Yang, Yang Jiang & Qingyu Liu

  2. Department of Radiology, The Fourth Affiliated Hospital of Guangzhou Medical University, 1 Guangming East Road, Zengjiang Street, Zengcheng District, Guangzhou, 511300, Guangdong, China

    Jinhui Cai, Chen Shen, Haoyi Ye, Yaoqin Ruan & Zhifeng Liu

  3. Department of Spine Surgery, The Fourth Affiliated Hospital of Guangzhou Medical University, Guangzhou, 511300, China

    Xuemin Zhu

Authors
  1. Jinhui Cai
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Chen Shen
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Tingqian Yang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Yang Jiang
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Haoyi Ye
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Yaoqin Ruan
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Xuemin Zhu
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Zhifeng Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  9. Qingyu Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

JC, CS and TY contributed equally as co-first authors because they are the guarantors of this work and take responsibility for the integrity of the data and the accuracy of the data analysis. ZL and QL contributed equally as co-corresponding authors because they designed this study and take responsibility for the integrity and reliability of the entire study and revised the manuscript.

Corresponding authors

Correspondence to Zhifeng Liu or Qingyu Liu.

Ethics declarations

Conflict of interest

No conflict of interest.

Additional information

Publisher's Note

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

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Cai, J., Shen, C., Yang, T. et al. MRI-based radiomics assessment of the imminent new vertebral fracture after vertebral augmentation. Eur Spine J 32, 3892–3905 (2023). https://doi.org/10.1007/s00586-023-07887-y

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00586-023-07887-y

Keywords

Search

Navigation