Skip to main content

Advertisement

SpringerLink
Log in

XGBoost-based multiparameters from dual-energy computed tomography for the differentiation of multiple myeloma of the spine from vertebral osteolytic metastases

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

Abstract

Objectives

To evaluate the performance of extreme gradient boosting (XGBoost) combined with multiparameters from dual-energy computed tomography (mpDECT) to differentiate between multiple myeloma (MM) of the spine and vertebral osteolytic metastases (VOM).

Methods

For this retrospective study, 28 patients (83 lesions) with MM of the spine and 23 patients (54 lesions) with VOM who underwent DECT were included. The mpDECT for each lesion, including normalized effective atomic number, slope of the spectral Hounsfield unit curve, CT attenuation, and virtual noncalcium (VNCa), was obtained. Boruta was used to select the key parameters, and then subsequently merged with XGBoost to yield a prediction model. The lesions were divided into the training and testing group in a 3:1 ratio. The highest performance of the univariate analysis was compared with XGBoost using the Delong test.

Results

The mpDECT of MM was significantly lower than that of VOM (all p < 0.05). In univariate analysis, VNCa had the highest area under the receiver operating characteristic curve (AUC) in the training group (0.81) and testing group (0.87). Based on Boruta, 6 parameters of DECT were selected for XGBoost model construction. The XGBoost model achieved an excellent and stable diagnostic performance, as shown in the training group (AUC of 1.0) and testing group (AUC of 0.97), with a sensitivity of 80%, a specificity of 95%, and an accuracy of 88%, which was superior to VNCa (p < 0.05).

Conclusions

XGBoost combined with mpDECT yielded promising performance in differentiating between MM of the spine and VOM.

Key Points

• The multiparameters obtained from dual-energy CT of multiple myeloma differed significantly from those of vertebral osteolytic metastases.

• The virtual noncalcium offered the highest AUC in the univariate analysis to distinguish multiple myeloma from vertebral osteolytic metastases.

• Extreme gradient boosting combined with multiparameters from dual-energy CT had a promising performance to distinguish multiple myeloma from vertebral osteolytic metastases.

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

Similar content being viewed by others

Data Availability

The datasets generated and/or analysed during the current study are not publicly available but are available from the corresponding author on reasonable request.

Abbreviations

AUC:

Area under the receiver operating characteristic curve

DECT:

Dual-energy computed tomography

ICC:

Intraclass correlation coefficient

MM:

Multiple myeloma

MRI:

Magnetic resonance imaging

ROI:

Region of interest

SPECT:

Single photon emission computed tomography

VNCa:

Virtual noncalcium

VOM:

Vertebral osteolytic metastases

XGBoost:

Extreme gradient boosting

References

  1. Lang N, Su M-Y, Yu HJ, Lin M, Hamamura MJ, Yuan H (2013) Differentiation of myeloma and metastatic cancer in the spine using dynamic contrast-enhanced MRI. Magn Reson Imaging 31:1285–1291

    Article  PubMed  PubMed Central  Google Scholar 

  2. Iizuka Y, Iizuka H, Tsutsumi S et al (2009) Diagnosis of a previously unidentified primary site in patients with spinal metastasis: diagnostic usefulness of laboratory analysis, CT scanning and CT-guided biopsy. Eur Spine J 18:1431–1435

    Article  PubMed  PubMed Central  Google Scholar 

  3. Agarwal A, Chirindel A, Shah BA, Subramaniam RM (2013) Evolving role of FDG PET/CT in multiple myeloma imaging and management. AJR Am J Roentgenol 200:884–890

    Article  PubMed  Google Scholar 

  4. Kosmala A, Weng AM, Heidemeier A et al (2018) Multiple myeloma and dual-energy CT: diagnostic accuracy of virtual noncalcium technique for detection of bone marrow infiltration of the spine and pelvis. Radiology 286:205–213

    Article  PubMed  Google Scholar 

  5. D’Oronzo S, Coleman R, Brown J, Silvestris F (2019) Metastatic bone disease: pathogenesis and therapeutic options: Up-date on bone metastasis management. J Bone Oncol 15:004–004

    Article  PubMed  Google Scholar 

  6. Coleman R, Hadji P, Body JJ et al (2020) Bone health in cancer: ESMO Clinical Practice Guidelines. Ann Oncol 31:1650–1663

    Article  CAS  PubMed  Google Scholar 

  7. Kumar SK, Callander NS, Adekola K et al (2020) Multiple myeloma, version 3.2021, NCCN clinical practice guidelines in oncology. J Natl Compr Canc Netw 18:1685–1717

    Article  CAS  PubMed  Google Scholar 

  8. Kosmala A, Bley T, Petritsch B (2019) Imaging of Multiple Myeloma. Rofo 191:805–816

    Article  PubMed  Google Scholar 

  9. King A, Vlantis A, Bhatia K et al (2011) Primary nasopharyngeal carcinoma: diagnostic accuracy of MR imaging versus that of endoscopy and endoscopic biopsy. Radiology 258:531–537

    Article  PubMed  Google Scholar 

  10. Gosangi B, Mandell JC, Weaver MJ et al (2020) Bone marrow edema at dual-energy CT: a game changer in the emergency department. Radiographics 40:859–874

    Article  PubMed  Google Scholar 

  11. Zheng S, Dong Y, Miao Y et al (2014) Differentiation of osteolytic metastases and Schmorl’s nodes in cancer patients using dual-energy CT: advantage of spectral CT imaging. Eur J Radiol 83:1216–1221

    Article  PubMed  Google Scholar 

  12. Mallinson P, Coupal T, McLaughlin P, Nicolaou S, Munk P, Ouellette H (2016) Dual-Energy CT for the Musculoskeletal System. Radiology 281:690–707

    Article  PubMed  Google Scholar 

  13. Wu H, Dong S, Li X et al (2020) Clinical utility of dual-energy CT used as an add-on to 18F FDG PET/CT in the preoperative staging of resectable NSCLC with suspected single osteolytic metastases. Lung Cancer 140:80–86

    Article  PubMed  Google Scholar 

  14. Fervers P, Celik E, Bratke G et al (2021) Radiotherapy response assessment of multiple myeloma: a dual-energy CT approach with virtual non-calcium images. Front Oncol 11:734819

    Article  PubMed  PubMed Central  Google Scholar 

  15. Fehr D, Schmidtlein CR, Hwang S, Deasy JO, Veeraraghavan H (2016) Automatic detection and tracking of longitudinal changes of multiple bone metastases from dual energy CT. Proc IEEE Int Symp Biomed Imaging 2016:168–171

    PubMed  PubMed Central  Google Scholar 

  16. Janssen RJ, Mourao-Miranda J, Schnack HG (2018) Making individual prognoses in psychiatry using neuroimaging and machine learning. Biol Psychiatr-Cogn Neurosci Neuroimaging 3:798–808

    Google Scholar 

  17. Handelman GS, Kok HK, Chandra RV, Razavi AH, Lee MJ, Asadi H (2018) eDoctor: machine learning and the future of medicine. J Intern Med 284:603–619

    Article  CAS  PubMed  Google Scholar 

  18. Chen T, Guestrin C (2016). XGBoost. https://doi.org/10.1145/2939672.2939785:785-794

    Article  Google Scholar 

  19. Klontzas ME, Manikis GC, Nikiforaki K et al (2021) Radiomics and machine learning can differentiate transient osteoporosis from avascular necrosis of the hip. Diagnostics (Basel) 11(9):1686

    Article  PubMed  Google Scholar 

  20. Zhao Y, Chen R, Zhang T et al (2021) MRI-based machine learning in differentiation between benign and malignant breast lesions. Front Oncol 11:552634

    Article  PubMed  PubMed Central  Google Scholar 

  21. Rajkumar SV, Dimopoulos MA, Palumbo A et al (2014) International Myeloma Working Group updated criteria for the diagnosis of multiple myeloma. Lancet Oncol 15:e538–e548

    Article  PubMed  Google Scholar 

  22. Li C, Chen J, Qin G (2019) Partial Youden index and its inferences. J Biopharm Stat 29:385–399

    Article  PubMed  Google Scholar 

  23. Kursa MB, Rudnicki WR (2010) Feature selection with the boruta package. J Stat Softw 36:1–13

    Article  Google Scholar 

  24. Dong Y, Zheng S, Machida H et al (2015) Differential diagnosis of osteoblastic metastases from bone islands in patients with lung cancer by single-source dual-energy CT: advantages of spectral CT imaging. Eur J Radiol 84:901–907

    Article  PubMed  Google Scholar 

  25. Deniffel D, Sauter A, Dangelmaier J, Fingerle A, Rummeny EJ, Pfeiffer D (2019) Differentiating intrapulmonary metastases from different primary tumors via quantitative dual-energy CT based iodine concentration and conventional CT attenuation. Eur J Radiol 111:6–13

    Article  PubMed  Google Scholar 

  26. McCollough CH, Leng SA, Yu LF, Fletcher JG (2015) Dual- and multi-energy CT: principles, technical approaches, and clinical applications. Radiology 276:637–653

    Article  PubMed  Google Scholar 

  27. Wang Y, Chen Y, Zheng H, Huang X, Shan C, Bao Y (2020) Detection of different degree traumatic vertebral bone marrow oedema by virtual non-calcium technique of dual-source dual-energy CT. Clin Radiol 75(2):156-e11

    Article  Google Scholar 

  28. Abdullayev N, Grosse Hokamp N, Lennartz S et al (2019) Improvements of diagnostic accuracy and visualization of vertebral metastasis using multi-level virtual non-calcium reconstructions from dual-layer spectral detector computed tomography. Eur Radiol 29:5941–5949

    Article  CAS  PubMed  Google Scholar 

  29. Issa G, Davis D, Mulligan ME (2018) The ability of dual-energy computed tomography to distinguish normal bone marrow from metastases using bone marrow color maps. J Comput Assist Tomogr 42:552–558

    Article  PubMed  Google Scholar 

  30. Barwick BG, Gupta VA, Vertino PM, Boise LH (2019) Cell of origin and genetic alterations in the pathogenesis of multiple myeloma. Front Immunol 10:1121

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  31. Hall MN, Jagannathan JP, Ramaiya NH, Shinagare AB, Van den Abbeele AD (2010) Imaging of extraosseous myeloma: CT, PET/CT, and MRI features. AJR Am J Roentgenol 195:1057–1065

    Article  PubMed  Google Scholar 

  32. Oliveira MB, Mello FC, Paschoal ME (2016) The relationship between lung cancer histology and the clinicopathological characteristics of bone metastases. Lung Cancer 96:19–24

    Article  PubMed  Google Scholar 

  33. Karatas M, Zengel B, Durusoy R et al (2021) Clinicopathologic features of single bone metastasis in breast cancer. Medicine (Baltimore) 100:e24164

    Article  CAS  PubMed  Google Scholar 

  34. Kursa MB, Jankowski A, Rudnicki WR (2010) Boruta – a system for feature selection. Fund Inform 101:271–285

    Google Scholar 

  35. Ahmed AAM, Deo RC, Ghahramani A et al (2021) LSTM integrated with Boruta-random forest optimiser for soil moisture estimation under RCP4.5 and RCP8.5 global warming scenarios. Stoch Env Res Risk Assess 35:1851–1881

    Article  Google Scholar 

  36. Li W, Yin Y, Quan X, Zhang H (2019) Gene expression value prediction based on XGBoost algorithm. Front Genet 10:1077

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  37. Hou N, Li M, He L et al (2020) Predicting 30-days mortality for MIMIC-III patients with sepsis-3: a machine learning approach using XGboost. J Transl Med 18(1):1–14

    Article  Google Scholar 

  38. Ogunleye A, Wang Q-G (2020) XGBoost model for chronic kidney disease diagnosis. IEEE-Acm Trans Comput Biol Bioinforma 17:2131–2140

    Article  Google Scholar 

Download references

Acknowledgements

We thank the study participants and referring technicians for their participation in this study.

Funding

This study has received funding from the National Natural Science Foundation of China (82071883), the Chongqing Natural Science Foundation (cstc2021jcyj-msxmX0313), Chongqing medical research project of a combination of science and medicine (grant No. 2021MSXM035), 2020 SKY Imaging Research Fund of the Chinese International Medical Foundation (project No. Z-2014–07-2003–24), an open fund from Chongqing Key Laboratory of Translational Research for Cancer Metastasis and Individualized Treatment, Chongqing University of Cancer Hospital.

Author information

Author notes

  1. Jinfang Shi and Haiping Huang contributed equally to the study.

Authors and Affiliations

  1. Department of Radiology, Chongqing Key Laboratory for Intelligent Oncology in Breast Cancer (iCQBC), Chongqing University Cancer Hospital, Shapingba District, No.181 Hanyu Road, Chongqing, 400030, China

    Jinfang Shi, Suqin Xu, Lihong Du, Xiangfei Zeng, Daihong Liu, Xiaoxia Wang & Jiuquan Zhang

  2. Department of Pathology, Chongqing University Cancer Hospital, No.181 Hanyu Road, Shapingba District, Chongqing, 400030, China

    Haiping Huang

  3. School of Medicine, Chongqing University, No.181 Hanyu Road, Shapingba District, Chongqing, 400030, China

    Ying Cao

Authors
  1. Jinfang Shi
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Haiping Huang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Suqin Xu
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Lihong Du
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Xiangfei Zeng
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Ying Cao
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Daihong Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Xiaoxia Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  9. Jiuquan Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to Xiaoxia Wang or Jiuquan Zhang.

Ethics declarations

Guarantor

The scientific guarantor of this publication is Jiuquan Zhang, from the Department of Radiology, Chongqing University Cancer Hospital, Chongqing, P.R. China.

E-mail: zhangjq_radiol@foxmail.com

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

No complex statistical methods were necessary for this paper.

Informed consent

Written informed consent was waived by the Institutional Review Board.

Ethical approval

Institutional Review Board approval was obtained.

Methodology

• Retrospective

• Observational

• Performed at one institution

Additional information

Publisher's note

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

Xiaoxia Wang and Jiuquan Zhang are co-corresponding authors.

Supplementary Information

Below is the link to the electronic supplementary material.

Supplementary file1 (DOCX 542 kb)

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

Shi, J., Huang, H., Xu, S. et al. XGBoost-based multiparameters from dual-energy computed tomography for the differentiation of multiple myeloma of the spine from vertebral osteolytic metastases. Eur Radiol 33, 4801–4811 (2023). https://doi.org/10.1007/s00330-023-09404-7

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00330-023-09404-7

Keywords

Search

Navigation