Skip to main content

Advertisement

SpringerLink
Log in

Diagnostic value of machine learning-based computed tomography texture analysis for differentiating multiple myeloma from osteolytic metastatic bone lesions in the peripheral skeleton

  • Scientific Article
  • Published:
Skeletal Radiology Aims and scope Submit manuscript

Abstract

Objectives

To report the diagnostic performance of machine learning-based CT texture analysis for differentiating multiple myeloma from osteolytic metastatic bone lesions in the peripheral skeleton.

Methods

We retrospectively evaluated 172 patients with multiple myeloma (n = 70) and osteolytic metastatic bone lesions (n = 102) in the peripheral skeleton. Two radiologists individually used two-dimensional manual segmentation to extract texture features from non-contrast CT. In total, 762 radiomic features were extracted. Dimension reduction was performed in three stages: inter-observer agreement analysis, collinearity analysis, and feature selection. Data were randomly divided into training (n = 120) and test (n = 52) groups. Eight machine learning algorithms were used for model development. The primary performance metrics were the area under the receiver operating characteristic curve and accuracy.

Results

In total, 476 of the 762 texture features demonstrated excellent interobserver agreement. The number of features was reduced to 22 after excluding those with strong collinearity. Of these features, six were included in the machine learning algorithms using the wrapper-based classifier-specific technique. When all eight machine learning algorithms were considered for differentiating multiple myeloma from osteolytic metastatic bone lesions in the peripheral skeleton, the area under the receiver operating characteristic curve and accuracy were 0.776–0.932 and 78.8–92.3%, respectively. The k-nearest neighbors model performed the best, with the area under the receiver operating characteristic curve and accuracy values of 0.902 and 92.3%, respectively.

Conclusion

Machine learning-based CT texture analysis is a promising method for discriminating multiple myeloma from osteolytic metastatic bone lesions.

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

Similar content being viewed by others

References

  1. Roodman GD. Pathogenesis of myeloma bone disease. J Cell Biochem. 2010;109:283–91.

    CAS  PubMed  Google Scholar 

  2. Panaroni C, Yee AJ, Raje NS. Myeloma and bone disease. Curr Osteoporos Rep. 2017;15:483–98.

    PubMed  Google Scholar 

  3. Hillengass J. Evolving concepts in the diagnosis and staging of multiple myeloma. J Natl Compr Cancer Netw. 2020;18:1770–2.

    CAS  Google Scholar 

  4. Roodman GD. Pathogenesis of myeloma bone disease. Leukemia. 2009;23:435–41.

    CAS  PubMed  Google Scholar 

  5. Terpos E, Dimopoulos MA, Moulopoulos LA. The role of imaging in the treatment of patients with multiple myeloma in 2016. Am Soc Clin Oncol Educ B. 2016;36:407–17.

    Google Scholar 

  6. Macedo F, Ladeira K, Pinho F, et al. Bone metastases: an overview. Oncol Rev. 2017;11:321.

    PubMed  PubMed Central  Google Scholar 

  7. Roodman GD. Mechanisms of bone metastasis. N Engl J Med. 2004;15:1655–64.

    Google Scholar 

  8. Giuliani N, Rizzoli V, Roodman GD. Multiple myeloma bone disease: patho-physiology of osteoblast inhibition. Blood. 2006;108:3992–6.

    CAS  PubMed  Google Scholar 

  9. Terpos E, Ntanasis-Stathopoulos I, Gavriatopoulou M, et al. Pathogenesis of bone disease in multiple myeloma: from bench to bedside. Blood Cancer J. 2018;8:7.

    PubMed  PubMed Central  Google Scholar 

  10. Bernstein ZS, Kim EB, Raje N. Bone disease in multiple myeloma: biologic and clinical implications. Cells. 2022;11(15):2308.

    CAS  PubMed  PubMed Central  Google Scholar 

  11. Clézardin P, Coleman R, Puppo M, et al. Bone metastasis: mechanisms, therapies, and biomarkers. Physiol Rev. 2021;101(3):797–855.

    PubMed  Google Scholar 

  12. Chandra H, Chandra S, Verma SK. Multiple myeloma or metastatic carcinoma breast: diagnostic dilemma in a case presenting with lytic bony lesion. Breast Dis. 2015;35:199–201.

    PubMed  Google Scholar 

  13. Tomono H, Fujioka S, Kato K, Yoshida K, Nimura Y. Multiple myeloma mimicking bone metastasis from breast cancer: report of a case. Surg Today. 1998;28:1304–6.

    CAS  PubMed  Google Scholar 

  14. Hough B, Brufsky A, Lentzsch S. Metastatic breast cancer or multiple myeloma? Camouflage by lytic lesions. J Oncol. 2010;2010:7–9.

    Google Scholar 

  15. Kang YM, Lee HJ, Kim S-J. Metastatic breast cancer with osteolytic skull lesions suspected to be multiple myeloma. Korean J Clin Oncol. 2017;13:152–5.

    Google Scholar 

  16. Hsu Y-T, Chang K-C. Breast cancer with extensive bone metastasis mimicking myeloma. Clin Case Reports. 2017;5:203–4.

    Google Scholar 

  17. Zhang H, Lv J, Lv C, Zhang H. Presentation of multiple myeloma mimicking bone metastasis from colon adenocarcinoma: a case report and literature review. Mol Clin Oncol. 2016;4:31–4.

    CAS  PubMed  Google Scholar 

  18. Merrild EH, Baerentzen S, Bouchelouche K, Buus S. Vertebral myeloma mimicking prostatic carcinoma metastasis in 68Ga-PSMA PET/CT. Clin Nucl Med. 2017;42:790–2.

    PubMed  Google Scholar 

  19. Shah E, Azhar W, Saleem S. A trail to diagnosis-finding the primary lesions of bone metastasis. Cureus. e2022;44:1–6

  20. Nagao T, Bando K, Iura A, et al. Malignant paraganglioma mimicking multiple myeloma. Rinsho Ketsueki Japan. 2022;63:1373–8.

    Google Scholar 

  21. Mutlu U, Balci A, Özsan GH, Özkal S, Şeyhanli A, Özgül HA. Computed tomography characteristics of multiple myeloma and other osteolytic metastatic bone lesions. Acta Radiol. 2021;62:1639–47.

    PubMed  Google Scholar 

  22. Varghese BA, Cen SY, Hwang DH, et al. Texture analysis of imaging: what radiologists need to know. AJR Am J Roentgenol. 2019;212:520–8.

    PubMed  Google Scholar 

  23. Gillies RJ, Kinahan PE, Hricak H. Radiomics: images are more than pictures, they are data. Radiology. 2016;278:563–77.

    PubMed  Google Scholar 

  24. Wang S, Summers RM. Machine learning and radiology. Med Image Anal. 2012;16:933–51.

    CAS  PubMed  PubMed Central  Google Scholar 

  25. Kocak B, Kus EA, Yardimci AH, Bektas CT, Kilickesmez O. Machine learning in radiomic renal mass characterization: fundamentals, applications, challenges, and future directions. AJR Am J Roentgenol. 2020;215:920–8.

    PubMed  Google Scholar 

  26. Gitto S, Cuocolo R, Albano D, et al. MRI radiomics-based machine-learning classification of bone chondrosarcoma. Eur J Radiol. 2020;128:109043.

    PubMed  Google Scholar 

  27. Basara Akin I, Ozgul H, Simsek K, Altay C, Secil M, Balci P. Texture analysis of ultrasound images to differentiate simple fibroadenomas from complex fibroadenomas and benign phyllodes tumors. J Ultrasound Med. 2020;39:1993–2003.

    PubMed  Google Scholar 

  28. Jin Z, Wang Y, Wang Y, Mao Y, Zhang F. Application of 18F-FDG PET-CT images based radiomics in identifying vertebral multiple myeloma and bone metastases. Front Med. 2022;9:1–12.

    Google Scholar 

  29. Baykara M, Yıldırım M. Differentiation of multiple myeloma and metastases with apparent diffusion coefficient map histogram analysis. North Clin Istanb. 2022;9:256–60.

    PubMed  PubMed Central  Google Scholar 

  30. Tagliafico AS, Cea M, Rossi F, et al. Differentiating diffuse from focal pattern on computed tomography in multiple myeloma: added value of a radiomics approach. Eur J Radiol. 2019;121:108739.

    PubMed  Google Scholar 

  31. Park H, Lee S, Lee J, et al. Detecting multiple myeloma infiltration of the bone marrow on CT scans in patients with osteopenia : feasibility of radiomics analysis. Diagnostics. 2022;12:923.

    PubMed  PubMed Central  Google Scholar 

  32. Rajkumar SV, Dimopoulos MA, Palumbo A, et al. International myeloma working group updated criteria for the diagnosis of multiple myeloma. Lancet Oncol. 2014;15:e538–48.

    PubMed  Google Scholar 

  33. Koçak B, Durmaz EŞ, Ateş E, Kılıçkesmez Ö. Radiomics with artificial intelligence: a practical guide for beginners. Diagn Interv Radiol. 2019;25:485–95.

    PubMed  PubMed Central  Google Scholar 

  34. Dormann CF, Elith J, Bacher S, et al. Collinearity: a review of methods to deal with it and a simulation study evaluating their performance. Ecography. 2013;36:27–46.

    Google Scholar 

  35. Bermejo P, Gamez JA, Puerta JM. Improving incremental wrapper-based subset selection via replacement and early stopping. Int J Pattern Recognit Artif Intell. 2011;25:605–25.

    Google Scholar 

  36. Frank E, Hall MA, Witten IH. The WEKA workbench. Online appendix for “data mining: practical machine learning tools and techniques”. Data Min Pract Mach Learn Tools Tech. 2016. https://www.cs.waikato.ac.nz/ml/weka/Witten_et_al_2016_appendix.pdf. Accessed 12 Dec 2022.

  37. Mwangi B, Tian TS, Soares JC. A review of feature reduction techniques in neuroimaging. Neuroinformatics. 2014;12:229–44.

    PubMed  PubMed Central  Google Scholar 

  38. Varma S, Simon R. Bias in error estimation when using cross-validation for model selection. BMC Bioinformatics. 2006;7:91.

    PubMed  PubMed Central  Google Scholar 

  39. Rajkumar SV. Multiple myeloma: 2020 update on diagnosis, risk-stratification and management. Am J Hematol. 2020;95:548–67.

    CAS  PubMed  Google Scholar 

  40. Deng C, Han D, Zhang X, Lv Z, Li D. Differential performances in lesions and radio-tracer of 18F-FDG PET/CT between multiple myeloma and unknown osteolytic metastasis. Curr Med Imaging. 2022. https://doi.org/10.2174/1573405618666220516120230.

  41. Vicentini JRT, Bredella MA. Whole body imaging in musculoskeletal oncology: when, why, and how. Skeletal Radiol. 2022;52(3):281–95. https://doi.org/10.1007/s00256-022-04112-7.

    Article  PubMed  Google Scholar 

  42. Li X, Wu N, Zhang W, Liu Y, Ming Y. Differential diagnostic value of 18F-FDG PET/CT in osteolytic lesions. J Bone Oncol. 2020;24:100302.

    PubMed  PubMed Central  Google Scholar 

  43. Lecouvet FE, Van Nieuwenhove S, Jamar F, Lhommel R, Guermazi A, Pasoglou VP. Whole-body MR imaging: the novel, “intrinsically hybrid,” approach to metastases, myeloma, lymphoma, in bones and beyond. PET Clin. 2018;13:505–22.

    PubMed  Google Scholar 

  44. Matteucci F, Paganelli G, Martinelli G, Cerchione C. PET/CT in multiple myeloma: beyond FDG. Front Oncol. 2021;10:622501.

    PubMed  PubMed Central  Google Scholar 

  45. Ganeshan B, Miles KA. Quantifying tumour heterogeneity with CT. Cancer Imaging. 2013;13:140–9.

    PubMed  PubMed Central  Google Scholar 

  46. Mutlu İN, Koçak B, Ateş Kuş E, Baykara Ulusan M, Kılıçkesmez Ö. Machine learning-based computed tomography texture analysis of lytic bone lesions needing biopsy: a preliminary study. Istanbul Med J. 2021;22:223–31.

    Google Scholar 

  47. Ng F, Kozarski R, Ganeshan B, Goh V. Assessment of tumor heterogeneity by CT texture analysis: can the largest cross-sectional area be used as an alternative to whole tumor analysis? Eur J Radiol. 2013;82:342–8.

    PubMed  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Radiology, Kemalpaşa State Hospital, Kırovası Küme Street, Kemalpaşa, 35730, Izmir, Turkey

    Hakan Abdullah Özgül

  2. Department of Radiology, Dokuz Eylul University, Faculty of Medicine, Izmir, Turkey

    Işıl Başara Akin & Ali Balci

  3. Department of Radiology, Yozgat State Hospital, Yozgat, Turkey

    Uygar Mutlu

Authors
  1. Hakan Abdullah Özgül
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Işıl Başara Akin
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Uygar Mutlu
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Ali Balci
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Hakan Abdullah Özgül.

Ethics declarations

Conflict of Interest

The authors declare that they have no conflict of interest.

Additional information

Publisher’s note

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

The English in this document has been checked by at least two professional editors, both native speakers of English. For a certificate, please see: http://www.textcheck.com/certificate/DmpUp8.

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

Özgül, H.A., Akin, I.B., Mutlu, U. et al. Diagnostic value of machine learning-based computed tomography texture analysis for differentiating multiple myeloma from osteolytic metastatic bone lesions in the peripheral skeleton. Skeletal Radiol 52, 1703–1711 (2023). https://doi.org/10.1007/s00256-023-04333-4

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00256-023-04333-4

Keywords

Search

Navigation