Skip to main content
SpringerLink
Log in

Differentiation of benign versus malignant indistinguishable vertebral compression fractures by different machine learning with MRI-based radiomic features

  • Musculoskeletal
  • Published:
European Radiology Aims and scope Submit manuscript

A Commentary to this article was published on 26 May 2023

Abstract

Objectives

To explore an optimal machine learning (ML) model trained on MRI-based radiomic features to differentiate benign from malignant indistinguishable vertebral compression fractures (VCFs).

Methods

This retrospective study included patients within 6 weeks of back pain (non-traumatic) who underwent MRI and were diagnosed with benign and malignant indistinguishable VCFs. The two cohorts were retrospectively recruited from the Affiliated Hospital of Qingdao University (QUH) and Qinghai Red Cross Hospital (QRCH). Three hundred seventy-six participants from QUH were divided into the training (n = 263) and validation (n = 113) cohort based on the date of MRI examination. One hundred three participants from QRCH were used to evaluate the external generalizability of our prediction models. A total of 1045 radiomic features were extracted from each region of interest (ROI) and used to establish the models. The prediction models were established based on 7 different classifiers.

Results

These models showed favorable efficacy in differentiating benign from malignant indistinguishable VCFs. However, our Gaussian naïve Bayes (GNB) model attained higher AUC and accuracy (0.86, 87.61%) than the other classifiers in validation cohort. It also remains the high accuracy and sensitivity for the external test cohort.

Conclusions

Our GNB model performed better than the other models in the present study, suggesting that it may be more useful for differentiating indistinguishable benign form malignant VCFs.

Key Points

• The differential diagnosis of benign and malignant indistinguishable VCFs based on MRI is rather difficult for spine surgeons or radiologists.

• Our ML models facilitate the differential diagnosis of benign and malignant indistinguishable VCFs with improved diagnostic efficacy.

• Our GNB model had the high accuracy and sensitivity for clinical application.

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

Abbreviations

AUC:

Area under the ROC curve

DT:

Decision tree

FN:

False negative

FP:

False positive

FS:

Fat suppression

GB:

Gradient-boosting decision tree

GLCM:

Gray level co-occurrence matrix

GLRLM:

Gray level run length matrix

GLSZM:

Gray level size zone matrix

GNB:

Gaussian naïve Bayes

ICCs:

Inter- and intraclass correlation coefficients

KNN:

K-nearest neighbor

LD:

Linear discriminant

LR:

Logistic regression

ML:

Machine learning

MLP:

Multilayer Perceptron

MRI:

Magnetic resonance imaging

PACS:

Picture archiving and communication system

PET/CT:

Positron emission tomography/computed tomography

ROC:

Receiver operating characteristic

ROI:

Region of interest

ROI:

Region of interest

T2WI:

T2-weighted imaging

TN:

True negative

TP:

True positive

VCFs:

Vertebral compression fractures

References

  1. Cicala D, Briganti F, Casale L et al (2013) Atraumatic vertebral compression fractures: differential diagnosis between benign osteoporotic and malignant fractures by MRI. Musculoskelet Surg 97(Suppl 2):S169-179

    Article  PubMed  Google Scholar 

  2. Arevalo-Perez J, Peck KK, Lyo JK et al (2015) Differentiating benign from malignant vertebral fractures using T1 -weighted dynamic contrast-enhanced MRI. J Magn Reson Imaging 42:1039–1047

    Article  PubMed  PubMed Central  Google Scholar 

  3. Chee CG, Yoon MA, Kim KW et al (2021) Combined radiomics-clinical model to predict malignancy of vertebral compression fractures on CT. Eur Radiol 31:6825–6834

    Article  PubMed  Google Scholar 

  4. Li K, Huang L, Lang Z et al (2019) Reliability and validity of different MRI sequences in improving the accuracy of differential diagnosis of benign and malignant vertebral fractures: a meta-analysis. AJR Am J Roentgenol 213:427–436

    Article  PubMed  Google Scholar 

  5. Shanbhogue K, Tong A, Smereka P et al (2021) Accelerated single-shot T2-weighted fat-suppressed (FS) MRI of the liver with deep learning-based image reconstruction: qualitative and quantitative comparison of image quality with conventional T2-weighted FS sequence. Eur Radiol 31:8447–8457

    Article  CAS  PubMed  Google Scholar 

  6. Sung JK, Jee WH, Jung JY et al (2014) Differentiation of acute osteoporotic and malignant compression fractures of the spine: use of additive qualitative and quantitative axial diffusion-weighted MR imaging to conventional MR imaging at 3.0 T. Radiology 271:488–498

    Article  PubMed  Google Scholar 

  7. Tokuda O, Hayashi N, Taguchi K, Matsunaga N (2005) Dynamic contrast-enhanced perfusion MR imaging of diseased vertebrae: analysis of three parameters and the distribution of the time-intensity curve patterns. Skeletal Radiol 34:632–638

    Article  PubMed  Google Scholar 

  8. Jung HS, Jee WH, McCauley TR, Ha KY, Choi KH (2003) Discrimination of metastatic from acute osteoporotic compression spinal fractures with MR imaging. Radiographics 23:179–187

    Article  PubMed  Google Scholar 

  9. Grassi R, Lombardi G, Reginelli A et al (2007) Coccygeal movement: assessment with dynamic MRI. Eur J Radiol 61:473–479

    Article  PubMed  Google Scholar 

  10. Muto M, Perrotta V, Guarnieri G et al (2008) Vertebroplasty and kyphoplasty: friends or foes? Radiol Med 113:1171–1184

    Article  CAS  PubMed  Google Scholar 

  11. An HS, Andreshak TG, Nguyen C, Williams A, Daniels D (1995) Can we distinguish between benign versus malignant compression fractures of the spine by magnetic resonance imaging? Spine (Phila Pa 1976) 20:1776–1782

    Article  CAS  PubMed  Google Scholar 

  12. Ishiyama M, Fuwa S, Numaguchi Y, Kobayashi N, Saida Y (2010) Pedicle involvement on MR imaging is common in osteoporotic compression fractures. AJNR Am J Neuroradiol 31:668–673

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  13. Theodorou DJ (2001) The intravertebral vacuum cleft sign. Radiology 221:787–788

    Article  CAS  PubMed  Google Scholar 

  14. Nie P, Yang G, Wang N et al (2021) Additional value of metabolic parameters to PET/CT-based radiomics nomogram in predicting lymphovascular invasion and outcome in lung adenocarcinoma. Eur J Nucl Med Mol Imag 48:217–230

    Article  Google Scholar 

  15. Frighetto-Pereira L, Rangayyan RM, Metzner GA, de Azevedo-Marques PM, Nogueira-Barbosa MH (2016) Shape, texture and statistical features for classification of benign and malignant vertebral compression fractures in magnetic resonance images. Comput Biol Med 73:147–156

    Article  PubMed  Google Scholar 

  16. Mauch JT, Carr CM, Cloft H, Diehn FE (2018) Review of the imaging features of benign osteoporotic and malignant vertebral compression fractures. AJNR Am J Neuroradiol 39:1584–1592

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  17. Wennmann M, Thierjung H, Bauer F et al (2022) Repeatability and reproducibility of ADC measurements and MRI signal intensity measurements of bone marrow in monoclonal plasma cell disorders: a prospective bi-institutional multiscanner, multiprotocol study. Invest Radiol 57:272–281

    Article  CAS  PubMed  Google Scholar 

  18. Wennmann M, Bauer F, Klein A et al (2022) In vivo repeatability and multiscanner reproducibility of MRI radiomics features in patients with monoclonal plasma cell disorders: a prospective bi-institutional study. Invest Radiol 58:253–264

  19. Da-Ano R, Visvikis D, Hatt M (2020) Harmonization strategies for multicenter radiomics investigations. Phys Med Biol 65:24tr02

    Article  CAS  PubMed  Google Scholar 

  20. Fatania K, Mohamud F, Clark A et al (2022) Intensity standardization of MRI prior to radiomic feature extraction for artificial intelligence research in glioma-a systematic review. Eur Radiol 32:7014–7025

    Article  PubMed  PubMed Central  Google Scholar 

  21. Wennmann M, Klein A, Bauer F et al (2022) Combining deep learning and radiomics for automated, objective, comprehensive bone marrow characterization from whole-body MRI: a multicentric feasibility study. Invest Radiol 57:752–763

Download references

Funding

This study has received funding from the National Natural Science Foundation of China (81871804, 82100940) and National Key Research and Development Project (CN) (2019YFC0121400). None of these funding sources had any role in the study design; the collection, analysis, and interpretation of data; the writing of the report; or the decision to submit the paper for publication.

Author information

Author notes

  1. Hao Zhang and Genji Yuan are co-first authors and have contributed equally to this project and manuscript preparation.

Authors and Affiliations

  1. Department of Spinal Surgery, The Affiliated Hospital of Qingdao University, No. 59 Haier Road, Qingdao, 266000, Shandong, China

    Hao Zhang, Chao Wang, Kai Zhu, Jianwei Guo, Mingrui Chen, Houchen Liu, Yan Wang & Xuexiao Ma

  2. College of Computer Science and Technology, Qingdao University, Qingdao, Shandong, China

    Genji Yuan

  3. Department of Nuclear Medicine, The Affiliated Hospital of Qingdao University, No. 59 Haier Road, Qingdao, 266000, Shandong, China

    Guangjie Yang

  4. Department of Spinal Surgery, Qinghai Red Cross Hospital, Xining, Qinghai, China

    Hongshun Zhao

Authors
  1. Hao Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Genji Yuan
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Chao Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Hongshun Zhao
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Kai Zhu
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Jianwei Guo
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Mingrui Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Houchen Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  9. Guangjie Yang
    View author publications

    You can also search for this author in PubMed Google Scholar

  10. Yan Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  11. Xuexiao Ma
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to Guangjie Yang, Yan Wang or Xuexiao Ma.

Ethics declarations

Guarantor

The scientific guarantor of this publication is Xuexiao Ma.

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 (Guangjie Yang) 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

No.

Methodology

• retrospective

• case–control study

• multicentre study

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

Zhang, H., Yuan, G., Wang, C. et al. Differentiation of benign versus malignant indistinguishable vertebral compression fractures by different machine learning with MRI-based radiomic features. Eur Radiol 33, 5069–5076 (2023). https://doi.org/10.1007/s00330-023-09678-x

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00330-023-09678-x

Keywords

Search

Navigation