Skip to main content

MR imaging of thymomas: a combined radiomics nomogram to predict histologic subtypes

European Radiology volume 31, pages 447–457 (2021)Cite this article

Abstract

Objectives

Accurately predicting the WHO classification of thymomas is urgently needed to optimize individualized therapeutic strategies. We aimed to develop and validate a combined radiomics nomogram for personalized prediction of histologic subtypes in patients with thymomas.

Methods

A total of 182 thymoma patients were divided into training (n = 128) and test (n = 54) cohorts. Radiomics features were extracted from T2-weighted, T2-weighted fat suppression, and diffusion-weighted images to establish a radiomics signature in the training cohort. Multivariate logistic regression analysis was used to develop a combined radiomics nomogram that incorporated clinical, conventional MR imaging variables, apparent diffusion coefficient (ADC) value, and radiomics signature. The efficacy of clinical, conventional MR imaging, or ADC model was also evaluated respectively. The performances of different models were compared by receiver operating characteristic analysis and Delong test. The discrimination, calibration, and clinical usefulness of the combined radiomics nomogram were assessed.

Results

The radiomics signature, consisting of 14 features, achieved favorable predictive efficacy in differentiating low-risk from high-risk thymomas, outperforming clinical, conventional MR imaging, and ADC models. The combined radiomics nomogram incorporating tumor shape, ADC value, and radiomics signature yielded the best performance (training cohort: area under the curve [AUC] = 0.946, test cohort: AUC = 0.878). The calibration curve and decision curve analysis indicated the clinical utility of the combined radiomics nomogram.

Conclusions

The radiomics signature is a useful tool that can be used to predict histologic subtypes of thymomas. The combined radiomics nomogram improved the individualized subtype prediction in patients with thymomas.

Key Points

• Fourteen robust features were selected to develop a radiomics signature for preoperative prediction of thymoma subtype.

• MRI-based radiomics signature can differentiate low-risk thymomas from high-risk thymomas with favorable predictive efficacy compared with clinical, conventional MR imaging, and ADC models.

• Combined radiomics nomogram based on tumor shape, ADC value, and radiomics signature could improve the individualized subtype prediction in patients with thymomas.

This is a preview of subscription content, access via your institution.

Access options

Buy single article

Instant access to the full article PDF.

43,34 €

Price includes VAT (Finland)
Tax calculation will be finalised during checkout.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5

Abbreviations

ADC:

Apparent diffusion coefficient

DCA:

Decision curve analysis

FS:

Fat suppression

ICC:

Inter- and intra-class correlation coefficient

LASSO:

Least absolute shrinkage and selection operator

OR:

Odds ratio

References

  1. Priola AM, Priola SM, Cardinale L, Cataldi A, Fava C (2006) The anterior mediastinum: diseases. Radiol Med 111:312–342

    CAS  Article  Google Scholar 

  2. Marx A, Chan JK, Coindre JM et al (2015) The 2015 World Health Organization classification of tumors of the Thymus: continuity and changes. J Thorac Oncol 10:1383–1395

    CAS  Article  Google Scholar 

  3. Jeong YJ, Lee KS, Kim J, Shim YM, Han J, Kwon OJ (2004) Does CT of thymic epithelial tumors enable us to differentiate histologic subtypes and predict prognosis? AJR Am J Roentgenol 183:283–289

    Article  Google Scholar 

  4. Girard N, Ruffini E, Marx A, Faivre-Finn C, Peters S (2015) Thymic epithelial tumours: ESMO clinical practice guidelines for diagnosis, treatment and follow-up. Ann Oncol 26(Suppl 5):v40–v55

    Article  Google Scholar 

  5. Henschke CI, Lee IJ, Wu N et al (2006) CT screening for lung cancer: prevalence and incidence of mediastinal masses. Radiology 239:586–590

    Article  Google Scholar 

  6. Marom EM (2010) Imaging thymoma. J Thorac Oncol 5:S296–S303

    Article  Google Scholar 

  7. Roden AC (2017) Evolution of classification of thymic epithelial tumors in the era of Dr Thomas V. Colby. Arch Pathol Lab Med 141:232–246

    Article  Google Scholar 

  8. Benveniste MF, Rosado-de-Christenson ML, Sabloff BS, Moran CA, Swisher SG, Marom EM (2011) Role of imaging in the diagnosis, staging, and treatment of thymoma. Radiographics 31:1847–1861 discussion 1861-1843

    Article  Google Scholar 

  9. Carter BW, Benveniste MF, Truong MT, Marom EM (2015) State of the art: MR imaging of thymoma. Magn Reson Imaging Clin N Am 23:165–177

    Article  Google Scholar 

  10. Priola AM, Gned D, Veltri A, Priola SM (2016) Chemical shift and diffusion-weighted magnetic resonance imaging of the anterior mediastinum in oncology: current clinical applications in qualitative and quantitative assessment. Crit Rev Oncol Hematol 98:335–357

    Article  Google Scholar 

  11. Abdel Razek AA, Khairy M, Nada N (2014) Diffusion-weighted MR imaging in thymic epithelial tumors: correlation with World Health Organization classification and clinical staging. Radiology 273:268–275

    Article  Google Scholar 

  12. Priola AM, Priola SM, Giraudo MT et al (2016) Diffusion-weighted magnetic resonance imaging of thymoma: ability of the apparent diffusion coefficient in predicting the World Health Organization (WHO) classification and the Masaoka-Koga staging system and its prognostic significance on disease-free survival. Eur Radiol 26:2126–2138

    Article  Google Scholar 

  13. Lambin P, Rios-Velazquez E, Leijenaar R et al (2012) Radiomics: extracting more information from medical images using advanced feature analysis. Eur J Cancer 48:441–446

    Article  Google Scholar 

  14. Gillies RJ, Kinahan PE, Hricak H (2016) Radiomics: images are more than pictures, they are data. Radiology 278:563–577

    Article  Google Scholar 

  15. Huang YQ, Liang CH, He L et al (2016) Development and validation of a radiomics nomogram for preoperative prediction of lymph node metastasis in colorectal cancer. J Clin Oncol 34:2157–2164

    Article  Google Scholar 

  16. Ding J, Xing Z, Jiang Z et al (2018) CT-based radiomic model predicts high grade of clear cell renal cell carcinoma. Eur J Radiol 103:51–56

    Article  Google Scholar 

  17. Zhu X, Dong D, Chen Z et al (2018) Radiomic signature as a diagnostic factor for histologic subtype classification of non-small cell lung cancer. Eur Radiol 28:2772–2778

    Article  Google Scholar 

  18. Ma W, Zhao Y, Ji Y et al (2019) Breast cancer molecular subtype prediction by mammographic radiomic features. Acad Radiol 26:196–201

    Article  Google Scholar 

  19. Sauerbrei W, Boulesteix AL, Binder H (2011) Stability investigations of multivariable regression models derived from low- and high-dimensional data. J Biopharm Stat 21:1206–1231

    Article  Google Scholar 

  20. Shinohara RT, Sweeney EM, Goldsmith J et al (2014) Statistical normalization techniques for magnetic resonance imaging. Neuroimage Clin 6:9–19

    Article  Google Scholar 

  21. Liang W, Yang P, Huang R et al (2019) A combined nomogram model to preoperatively predict histologic grade in pancreatic neuroendocrine tumors. Clin Cancer Res 25:584–594

    Article  Google Scholar 

  22. Okumura M, Ohta M, Tateyama H et al (2002) The World Health Organization histologic classification system reflects the oncologic behavior of thymoma: a clinical study of 273 patients. Cancer 94:624–632

    Article  Google Scholar 

  23. Berghmans T, Durieux V, Holbrechts S et al (2018) Systemic treatments for thymoma and thymic carcinoma: a systematic review. Lung Cancer 126:25–31

    Article  Google Scholar 

  24. Falkson CB, Bezjak A, Darling G et al (2009) The management of thymoma: a systematic review and practice guideline. J Thorac Oncol 4:911–919

    Article  Google Scholar 

  25. Sadohara J, Fujimoto K, Muller NL et al (2006) Thymic epithelial tumors: comparison of CT and MR imaging findings of low-risk thymomas, high-risk thymomas, and thymic carcinomas. Eur J Radiol 60:70–79

    Article  Google Scholar 

  26. Birkhahn M, Mitra AP, Cote RJ (2007) Molecular markers for bladder cancer: the road to a multimarker approach. Expert Rev Anticancer Ther 7:1717–1727

    CAS  Article  Google Scholar 

  27. Sparano JA, Gray RJ, Makower DF et al (2015) Prospective validation of a 21-gene expression assay in breast cancer. N Engl J Med 373:2005–2014

    CAS  Article  Google Scholar 

  28. Kang D, Park JE, Kim YH et al (2018) Diffusion radiomics as a diagnostic model for atypical manifestation of primary central nervous system lymphoma: development and multicenter external validation. Neuro Oncol 20:1251–1261

    Article  Google Scholar 

  29. Li B, Xin YK, Xiao G et al (2019) Predicting pathological subtypes and stages of thymic epithelial tumors using DWI: value of combining ADC and texture parameters. Eur Radiol 29:5330–5340

    Article  Google Scholar 

  30. Liang W, Xu L, Yang P et al (2018) Novel Nomogram for preoperative prediction of early recurrence in intrahepatic cholangiocarcinoma. Front Oncol 8:360

    Article  Google Scholar 

Download references

Acknowledgments

We would like to thank Dr. Xiao-Cheng Wei and Dr. Min Li in GE Healthcare China for providing technical support regarding the MR imaging examination of the thorax.

Funding

This study has received funding by the Science and Technology Innovation Development Foundation of Tangdu Hospital (no. 2017LCYJ004).

Author information

Author notes

  1. Gang Xiao and Yu-Chuan Hu contributed equally to this work.

Affiliations

  1. Department of Radiology, Tangdu Hospital, Fourth Military Medical University, Xi’an, 710038, Shaanxi, People’s Republic of China

    Gang Xiao, Yu-Chuan Hu, Xiao-Yan Qu, Wei-Cheng Rong, Wei-Qiang Yan, Qiang Tian, Yu Han, Wen Wang & Guang-Bin Cui

  2. Functional and Molecular Imaging Key Lab of Shaanxi Province, Xi’an, Shaanxi, People’s Republic of China

    Gang Xiao, Yu-Chuan Hu, Wei-Cheng Rong, Wei-Qiang Yan, Qiang Tian, Yu Han, Wen Wang & Guang-Bin Cui

  3. GE Healthcare, Beijing, People’s Republic of China

    Jia-Liang Ren

  4. Student Brigade, Fourth Military Medical University, 169 Changle Road, Xi’an, 710032, Shaanxi, People’s Republic of China

    Peng Qin & Jia-Cheng Han

  5. Department of Thoracic Surgery, Tangdu Hospital, Fourth Military Medical University, Xi’an, Shaanxi, People’s Republic of China

    Wu-Ping Wang

  6. Department of Pathology, Tangdu Hospital, Fourth Military Medical University, Xi’an, Shaanxi, People’s Republic of China

    Shu-Mei Wang & Jiao Ma

Authors
  1. Gang Xiao
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Yu-Chuan Hu
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Jia-Liang Ren
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Peng Qin
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Jia-Cheng Han
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Xiao-Yan Qu
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Wei-Cheng Rong
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Wei-Qiang Yan
    View author publications

    You can also search for this author in PubMed Google Scholar

  9. Qiang Tian
    View author publications

    You can also search for this author in PubMed Google Scholar

  10. Yu Han
    View author publications

    You can also search for this author in PubMed Google Scholar

  11. Wu-Ping Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  12. Shu-Mei Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  13. Jiao Ma
    View author publications

    You can also search for this author in PubMed Google Scholar

  14. Wen Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  15. Guang-Bin Cui
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to Wen Wang or Guang-Bin Cui.

Ethics declarations

Guarantor

The scientific guarantor of this publication is Guang-Bin Cui.

Conflict of interest

One of the authors of this manuscript (Jia-Liang Ren) is an employee of GE Healthcare. The remaining authors declare no relationships with any companies whose products or services may be related to the subject matter of the article.

Statistics and biometry

Gang Xiao and Jia-Liang Ren kindly provided statistical advice for this manuscript.

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

Some study subjects or cohorts have been previously reported in European Radiology: Li B, Xin YK, Xiao G et al (2019) Predicting pathological subtypes and stages of thymic epithelial tumors using DWI value of combining ADC and texture parameters. European Radiology 29:5330–5340.

Methodology

• retrospective

• diagnostic or prognostic study

• performed at one institution

Additional information

Publisher’s note

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

Electronic supplementary material

ESM 1

(DOCX 2057 kb)

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Xiao, G., Hu, YC., Ren, JL. et al. MR imaging of thymomas: a combined radiomics nomogram to predict histologic subtypes. Eur Radiol 31, 447–457 (2021). https://doi.org/10.1007/s00330-020-07074-3

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00330-020-07074-3

Keywords

  • Thymoma
  • Magnetic resonance imaging
  • Nomograms
  • Machine learning