Classifying brain metastases by their primary site of origin using a radiomics approach based on texture analysis: a feasibility study



To examine the capability of MRI texture analysis to differentiate the primary site of origin of brain metastases following a radiomics approach.


Sixty-seven untreated brain metastases (BM) were found in 3D T1-weighted MRI of 38 patients with cancer: 27 from lung cancer, 23 from melanoma and 17 from breast cancer. These lesions were segmented in 2D and 3D to compare the discriminative power of 2D and 3D texture features. The images were quantized using different number of gray-levels to test the influence of quantization. Forty-three rotation-invariant texture features were examined. Feature selection and random forest classification were implemented within a nested cross-validation structure. Classification was evaluated with the area under receiver operating characteristic curve (AUC) considering two strategies: multiclass and one-versus-one.


In the multiclass approach, 3D texture features were more discriminative than 2D features. The best results were achieved for images quantized with 32 gray-levels (AUC = 0.873 ± 0.064) using the top four features provided by the feature selection method based on the p-value. In the one-versus-one approach, high accuracy was obtained when differentiating lung cancer BM from breast cancer BM (four features, AUC = 0.963 ± 0.054) and melanoma BM (eight features, AUC = 0.936 ± 0.070) using the optimal dataset (3D features, 32 gray-levels). Classification of breast cancer and melanoma BM was unsatisfactory (AUC = 0.607 ± 0.180).


Volumetric MRI texture features can be useful to differentiate brain metastases from different primary cancers after quantizing the images with the proper number of gray-levels.

Key Points

• Texture analysis is a promising source of biomarkers for classifying brain neoplasms.

• MRI texture features of brain metastases could help identifying the primary cancer.

• Volumetric texture features are more discriminative than traditional 2D texture features.

This is a preview of subscription content, log in to check access.

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



Analysis of variance


Area under receiver operating characteristic curve


Brain metastases


Confusion matrix




Gray-level co-occurrence matrix


Gray-level run-length matrix


Gray-level size zone matrix


Leave-group-out cross-validation


Number of gray-levels


Neighborhood gray-tone difference matrix


Random Forest


Texture analysis


  1. 1.

    Gavrilovic IT, Posner JB (2005) Brain metastases: epidemiology and pathophysiology. J Neurooncol 75:5–14

    Article  Google Scholar 

  2. 2.

    Stelzer KJ (2013) Epidemiology and prognosis of brain metastases. Surg Neurol Int 4:S192–S202

    Article  Google Scholar 

  3. 3.

    Soffietti R, Cornu P, Delattre JY et al (2006) EFNS Guidelines on diagnosis and treatment of brain metastases: report of an EFNS Task Force. Eur J Neurol 13:674–681

    CAS  Article  Google Scholar 

  4. 4.

    Kaal ECA, Taphoorn MJB, Vecht CJ (2005) Symptomatic management and imaging of brain metastases. J Neurooncol 75:15–20

    Article  Google Scholar 

  5. 5.

    Nayak L, Lee EQ, Wen PY (2012) Epidemiology of brain metastases. Curr Oncol Rep 14:48–54

    Article  Google Scholar 

  6. 6.

    Bartelt S, Lutterbach J (2003) Brain metastases in patients with cancer of unknown primary. J Neurooncol 64:249–253

    Article  Google Scholar 

  7. 7.

    Agazzi S, Pampallona S, Pica A et al (2004) The origin of brain metastases in patients with an undiagnosed primary tumor. Acta Neurochir (Wien) 146:153–157

    CAS  Article  Google Scholar 

  8. 8.

    Pekmezci M, Perry A (2013) Neuropathology of brain metastases. Surg Neurol Int 4:245

    Article  Google Scholar 

  9. 9.

    Zakaria R, Das K, Bhojak M et al (2014) The role of magnetic resonance imaging in the management of brain metastases: diagnosis to prognosis. Cancer Imaging 14:1–8

    Google Scholar 

  10. 10.

    Bekaert L, Emery E, Levallet G, Lechapt-Zalcman E (2017) Histopathologic diagnosis of brain metastases: current trends in management and future considerations. Brain Tumor Pathol 34:8–19

    CAS  Article  Google Scholar 

  11. 11.

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

    Article  Google Scholar 

  12. 12.

    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 

  13. 13.

    Yip SSF, Aerts HJWL (2016) Applications and limitations of radiomics. Phys Med Biol 61:R150–R166

    CAS  Article  Google Scholar 

  14. 14.

    Kumar V, Gu Y, Basu S et al (2012) Radiomics: the process and the challenges. Magn Reson Imaging 30:1234–1248

    Article  Google Scholar 

  15. 15.

    Castellano G, Bonilha L, Li LM, Cendes F (2004) Texture analysis of medical images. Clin Radiol 59:1061–1069

    CAS  Article  Google Scholar 

  16. 16.

    Kassner A, Thornhill RE (2010) Texture analysis: a review of neurologic MR imaging applications. AJNR Am J Neuroradiol 31:809–816

    CAS  Article  Google Scholar 

  17. 17.

    Mahmoud-Ghoneim D, Toussaint G, Constans JM, De Certaines JD (2003) Three dimensional texture analysis in MRI: a preliminary evaluation in gliomas. Magn Reson Imaging 21:983–987

    Article  Google Scholar 

  18. 18.

    Fetit AE, Novak J, Peet AC, Arvanitis TN (2015) Three-dimensional textural features of conventional MRI improve diagnostic classification of childhood brain tumors. NMR Biomed 28:1174–1184

    Article  Google Scholar 

  19. 19.

    Zacharaki EI, Wang S, Chawla S et al (2009) Classification of brain tumor type and grade using MRI texture and shape in a machine learning scheme. Magn Reson Med 62:1609–1618

    Article  Google Scholar 

  20. 20.

    Georgiadis P, Cavouras D, Kalatzis I et al (2009) Enhancing the discrimination accuracy between metastases, gliomas and meningiomas on brain MRI by volumetric textural features and ensemble pattern recognition methods. Magn Reson Imaging 27:120–130

    Article  Google Scholar 

  21. 21.

    Larroza A, Moratal D, Paredes-Sánchez A et al (2015) Support vector machine classification of brain metastasis and radiation necrosis based on texture analysis in MRI. J Magn Reson Imaging 42:1362–1368

    Article  Google Scholar 

  22. 22.

    Li Z, Mao Y, Li H et al (2016) Differentiating brain metastases from different pathological types of lung cancers using texture analysis of T1 postcontrast MR. Magn Reson Med 76:1410–1419

    Article  Google Scholar 

  23. 23.

    Fink KR, Fink JR (2013) Imaging of brain metastases. Surg Neurol Int 4:S209–S219

    Article  Google Scholar 

  24. 24.

    Larroza A, Bodí V, Moratal D (2016) Texture analysis in magnetic resonance imaging: review and considerations for future applications. In: Assessment of cellular and organ function and dysfunction using direct and derived MRI methodologies. InTech, Rijeka, Croatia, pp 75–106

    Google Scholar 

  25. 25.

    Leite M, Rittner L, Appenzeller S et al (2015) Etiology-based classification of brain white matter hyperintensity on magnetic resonance imaging. J Med Imaging 2:14002

    Article  Google Scholar 

  26. 26.

    Mahmoud-Ghoneim D, Alkaabi MK, De Certaines JD, Goettsche F-M (2008) The impact of image dynamic range on texture classification of brain white matter. BMC Med Imaging 8:1–8

    Article  Google Scholar 

  27. 27.

    Depeursinge A, Foncubierta-Rodriguez A, Van De Ville D, Müller H (2014) Three-dimensional solid texture analysis in biomedical imaging: review and opportunities. Med Image Anal 18:176–196

    Article  Google Scholar 

  28. 28.

    Ellingson BM, Bendszus M, Boxerman J et al (2015) Consensus recommendations for a standardized Brain Tumor Imaging Protocol in clinical trials. Neuro Oncol 17:1188–1198

    Article  Google Scholar 

  29. 29.

    Mayerhoefer ME, Breitenseher MJ, Kramer J et al (2005) Texture analysis for tissue discrimination on T1-weighted MR images of the knee joint in a multicenter study: Transferability of texture features and comparison of feature selection methods and classifiers. J Magn Reson Imaging 22:674–680

    Article  Google Scholar 

  30. 30.

    Waugh SA, Lerski RA, Bidaut L, Thompson AM (2011) The influence of field strength and different clinical breast MRI protocols on the outcome of texture analysis using foam phantoms. Med Phys 38:5058–5066

    Article  Google Scholar 

  31. 31.

    Chan TF, Vese LA (2001) Active contours without edges. IEEE Trans Image Process 10:266–277

    CAS  Article  Google Scholar 

  32. 32.

    Collewet G, Strzelecki M, Mariette F (2004) Influence of MRI acquisition protocols and image intensity normalization methods on texture classification. Magn Reson Imaging 22:81–91

    CAS  Article  Google Scholar 

  33. 33.

    Gibbs P, Turnbull LW (2003) Textural analysis of contrast-enhanced MR images of the breast. Magn Reson Med 50:92–98

    Article  Google Scholar 

  34. 34.

    Vallières M, Freeman CR, Skamene SR, El Naqa I (2015) A radiomics model from joint FDG-PET and MRI texture features for the prediction of lung metastases in soft-tissue sarcomas of the extremities. Phys Med Biol 60:5471–5496

    Article  Google Scholar 

  35. 35.

    Kuhn M, Johnson K (2013) Data pre-processing. In: Applied predictive modeling, 1st ed. Springer, New York, NY, pp 27–59

    Google Scholar 

  36. 36.

    Fernández-Delgado M, Cernadas E, Barro S et al (2014) Do we need hundreds of classifiers to solve real world classification problems? J Mach Learn Res 15:3133–3181

    Google Scholar 

  37. 37.

    Caruana R, Karampatziakis N, Yessenalina A (2008) An empirical evaluation of supervised learning in high dimensions. In: Proceedings of the 25th international conference on Machine learning - ICML ’08. ACM Press, Helsinki, Finland, pp 96–103

  38. 38.

    Kuhn M, Johnson K (2013) Over-fitting and model tuning. In: Applied predictive modeling, 1st ed. Springer, New York, NY, pp 61–92

    Google Scholar 

  39. 39.

    Kuhn M, Johnson K (2013) An introduction to feature selection. In: Applied predictive modeling, 1st ed. Springer, New York, NY, pp 487–519

    Google Scholar 

  40. 40.

    Ambroise C, McLachlan GJ (2002) Selection bias in gene extraction on the basis of microarray gene-expression data. Proc Natl Acad Sci U S A 99:6562–6566

    CAS  Article  Google Scholar 

  41. 41.

    Provost F, Domingos P (2003) Tree induction for probability-based ranking. Mach Learn 52:199–215

    Article  Google Scholar 

  42. 42.

    Kuhn M (2008) Building predictive models in R using the caret package. J Stat Softw 28:1–26

    Article  Google Scholar 

  43. 43.

    Ortiz-Ramon R, Larroza A, Arana E, Moratal D (2017) Identifying the primary site of origin of MRI brain metastases from lung and breast cancer following a 2D radiomics approach. In: 2017 I.E. 14th International Symposium on Biomedical Imaging (ISBI 2017). Melbourne, VIC, pp 1213–1216

  44. 44.

    Ortiz-Ramon R, Larroza A, Arana E, Moratal D (2017) A radiomics evaluation of 2D and 3D MRI texture features to classify brain metastases from lung cancer and melanoma. In: 2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). Seogwipo, pp 493–496

  45. 45.

    Béresová M, Larroza A, Arana E, et al (2017) 2D and 3D texture analysis to differentiate brain metastases on MR images: proceed with caution. MAGMA 1–10

  46. 46.

    Ahmed A, Gibbs P, Pickles M, Turnbull L (2013) Texture analysis in assessment and prediction of chemotherapy response in breast cancer. J Magn Reson Imaging 38:89–101

    Article  Google Scholar 

  47. 47.

    Chen W, Giger ML, Li H et al (2007) Volumetric texture analysis of breast lesions on contrast-enhanced magnetic resonance images. Magn Reson Med 58:562–571

    Article  Google Scholar 

Download references


This work has been partially funded by the Spanish Ministerio de Economía y Competitividad (MINECO) and FEDER funds under Grant BFU2015-64380-C2-2-R.

Rafael Ortiz-Ramón was supported by grant ACIF/2015/078 from the Conselleria d’Educació, Investigació, Cultura i Esport of the Valencian Community (Spain).

Andrés Larroza was supported by grant FPU12/01140 from the Spanish Ministerio de Educación, Cultura y Deporte (MECD).

Author information



Corresponding author

Correspondence to David Moratal.

Ethics declarations


The scientific guarantor of this publication is David Moratal.

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 (David Moratal) has significant statistical expertise.

Informed consent

Written informed consent was obtained from all subjects (patients) in this study.

Ethical approval

Institutional Review Board approval was obtained.


• retrospective

• diagnostic or prognostic study

• performed at one institution

Electronic supplementary material


(DOCX 34 kb)

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Ortiz-Ramón, R., Larroza, A., Ruiz-España, S. et al. Classifying brain metastases by their primary site of origin using a radiomics approach based on texture analysis: a feasibility study. Eur Radiol 28, 4514–4523 (2018).

Download citation


  • Neoplasms, Unknown primary
  • Magnetic resonance imaging
  • Image processing, Computer-assisted
  • Biomarkers
  • Feasibility studies