Skip to main content
SpringerLink
Log in

Kurtosis is An MRI Radiomics Feature Predictor of Poor Prognosis in Patients with GBM

  • General and Applied Physics
  • Published:
Brazilian Journal of Physics Aims and scope Submit manuscript

Abstract

Glioblastoma multiforme (GBM) is the most lethal and aggressive brain tumor. Magnetic resonance imaging (MRI) is currently used to diagnose and monitoring it. Radiomic features extracted from MRI are being used for correlations with the disease prognosis. A methodology to extract MRI radiomics features in a radiotherapy planning workflow, to assess features related to GBM poor prognosis patients, is presented. One hundred five radiomics features were extracted from T1 post-contrast MRIs of 43 GBM patients. The progression-free survival (PFS) time of all patients was also achieved. These patients were separated into two groups: PFS within 3 months (class value = 1) and PFS higher than 3 months (class value = 0). A machine learning model was built to predict the poor prognosis of patients using a random forest algorithm optimized for class = 1 classification, i. e. optimized for the recall score. Kurtosis was ranked as the most important feature for this classification. The final model presents a recall score of 1.00 ± 0.0 and an area under a receiver operating characteristic curve (AUROC) of 0.81 ± 0.04. The model used a kurtosis threshold value at 2.69 ± 0.03 for classification. The kurtosis values achieved for the PFS within 3 months indicate that these tumors are composed of almost the same amount of necrose, neoangiogenesis, edema, and/or tumor cells. In conclusion, a relation between the radiomics analysis of kurtosis in MRI with GBM’s poor prognosis was found, and the developed model may help guide the patient’s clinical management.

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

Similar content being viewed by others

References

  1. A. Chaddad, M.J. Kucharczyk, P. Daniel, S. Sabri, B.J. Jean-Claude, T. Niazi et al., Radiomics in glioblastoma: current status and challenges facing clinical implementation. Front. Oncol. 9, 1–9 (2019). https://doi.org/10.3389/fonc.2019.00374

    Article  Google Scholar 

  2. R. Stupp, M.E. Hegi, W.P. Mason, M.J. van den Bent, M.J. Taphoorn, R.C. Janzer et al., Effects of radiotherapy with concomitant and adjuvant temozolomide versus radiotherapy alone on survival in glioblastoma in a randomised phase III study: 5-year analysis of the EORTC-NCIC trial. Lancet Oncol. 10, 459–66 (2009). https://doi.org/10.1016/S1470-2045(09)70025-7

    Article  Google Scholar 

  3. C. Adamson, O.O. Kanu, A.I. Mehta, C. Di, N. Lin, A.K. Mattox et al., Glioblastoma multiforme: a review of where we have been and where we are going. Expert Opin. Investig. Drugs. 18, 1061–83 (2009). https://doi.org/10.1517/13543780903052764

    Article  Google Scholar 

  4. A. Sottoriva, I. Spiteri, S.G.M. Piccirillo, A. Touloumis, V.P. Collins, J.C. Marioni et al., Intratumor heterogeneity in human glioblastoma reflects cancer evolutionary dynamics. Proc. Natl. Acad. Sci. 110, 4009–14 (2013). https://doi.org/10.1073/pnas.1219747110

    Article  ADS  Google Scholar 

  5. S. Moton, M. Elbanan, P.O. Zinn, R.R. Colen, Imaging genomics of glioblastoma. Top. Magn. Reson. Imaging. 24, 155–63 (2015). https://doi.org/10.1097/RMR.0000000000000052

    Article  Google Scholar 

  6. R.J. Gillies, A.R. Anderson, R.A. Gatenby, D.L. Morse, The biology underlying molecular imaging in oncology: from genome to anatome and back again. Clin. Radiol. 65, 517–21 (2010). https://doi.org/10.1016/j.crad.2010.04.005

    Article  Google Scholar 

  7. H.J.W.L. Aerts, E.R. Velazquez, R.T.H. Leijenaar, C. Parmar, P. Grossmann, S. Cavalho et al., Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach. Nat. Commun. 5, (2014). https://doi.org/10.1038/ncomms5006

  8. P. Lambin, R.G.P.M. Van Stiphout, M.H.W. Starmans, E. Rios-Velazquez, G. Nalbantov, H.J.W.L. Aerts et al., Predicting outcomes in radiation oncology-multifactorial decision support systems. Nat. Rev. Clin. Oncol. 10, 27–40 (2013). https://doi.org/10.1038/nrclinonc.2012.196

    Article  Google Scholar 

  9. H. Sotoudeh, O. Shafaat, J.D. Bernstock, M.D. Brooks, G.A. Elsayed, J.A. Chen et al., Artificial intelligence in the management of glioma: era of personalized medicine. Front. Oncol. 9, (2019). https://doi.org/10.3389/fonc.2019.00768

  10. C.A. Sarkiss, I.M. Germano, Machine learning in neuro-oncology: can data analysis from 5346 patients change decision-making paradigms? World Neurosurg. 124, 287–94 (2019). https://doi.org/10.1016/j.wneu.2019.01.046

    Article  Google Scholar 

  11. D. Assefa, H. Keller, C. Ḿnard, N. Laperriere, R.J. Ferrari, I. Yeung, Robust texture features for response monitoring of glioblastoma multiforme on T1 -weighted and T2 -FLAIR MR images: a preliminary investigation in terms of identification and segmentation. Med. Phys. 37, 1722–36 (2010). https://doi.org/10.1118/1.3357289

    Article  Google Scholar 

  12. S. Bauer, T. Fejes, J. Slotboom, R. Wiest, L.-P. Nolte, M. Reyes, Segmentation of brain tumor images based on integrated hierarchical classification and regularization. MICCAI BraTS Work. 10–3 (2012)

  13. K. Li-Chun Hsieh, C.-Y. Chen, C.-M. Lo, Quantitative glioma grading using transformed gray-scale invariant textures of MRI. Comput. Biol. Med. 83, 102–8 (2017). https://doi.org/10.1016/j.compbiomed.2017.02.012

    Article  Google Scholar 

  14. J. Wu, Z. Qian, L. Tao, J. Yin, S. Ding, Y. Zhang et al., Resting state fMRI feature-based cerebral glioma grading by support vector machine. Int. J. Comput. Assist. Radiol. Surg. 10, 1167–74 (2015). https://doi.org/10.1007/s11548-014-1111-z

    Article  Google Scholar 

  15. Q. Tian, L.-F. Yan, X. Zhang, X. Zhang, Y.-C. Hu, Y. Han et al., Radiomics strategy for glioma grading using texture features from multiparametric MRI. J. Magn. Reson. Imaging. 48, 1518–28 (2018). https://doi.org/10.1002/jmri.26010

    Article  Google Scholar 

  16. P.A. Eliat, D. Olivié, S. Saïkali, B. Carsin, H. Saint-Jalmes, J.D. De Certaines, Can dynamic contrast-enhanced magnetic resonance imaging combined with texture analysis differentiate malignant glioneuronal tumors from other glioblastoma? Neurol. Res. Int. (2012). https://doi.org/10.1155/2012/195176

  17. E.I. Zacharaki, S. Wang, S. Chawla, D.S. Yoo, R. Wolf, E.R. Melhem et al., Classification of brain tumor type and grade using MRI texture and shape in a machine learning scheme. Magn. Reson. Med. 62, 1609–18 (2009). https://doi.org/10.1002/mrm.22147

    Article  Google Scholar 

  18. M. Zhou, L. Hall, D. Goldgof, R. Russo, Y. Balagurunathan, R. Gillies et al., Radiologically defined ecological dynamics and clinical outcomes in glioblastoma multiforme: Preliminary results. Transl. Oncol. 7, 5–13 (2014). https://doi.org/10.1593/tlo.13730

    Article  Google Scholar 

  19. A. Chaddad, S. Sabri, T. Niazi, B. Abdulkarim, Prediction of survival with multi-scale radiomic analysis in glioblastoma patients. Med. Biol. Eng. Comput. 56, 2287–300 (2018). https://doi.org/10.1007/s11517-018-1858-4

    Article  Google Scholar 

  20. S.S.F. Yip, H.J.W.L. Aerts, Applications and limitations of radiomics. Phys. Med. Biol. 61, R150-66 (2016). https://doi.org/10.1088/0031-9155/61/13/R150

    Article  ADS  Google Scholar 

  21. J.J.M. van Griethuysen, A. Fedorov, C. Parmar, A. Hosny, N. Aucoin, V. Narayan et al., Computational radiomics system to decode the radiographic phenotype. Cancer Res. 77, e104-7 (2017). https://doi.org/10.1158/0008-5472.CAN-17-0339

    Article  Google Scholar 

  22. S.S. Shapiro, M.B. Wilk, An analysis of variance test for normality (complete samples). Biometrika. 52, 591 (1965). https://doi.org/10.2307/2333709

    Article  MathSciNet  MATH  Google Scholar 

  23. F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel et al., Scikit-learn: machine learning in python. J. Mach. Learn. Res. 12, 2825–30 (2011)

    MathSciNet  MATH  Google Scholar 

  24. C.H.B. Liu, B.P. Chamberlain, D.A. Little, Â. Cardoso, Generalising random forest parameter optimisation to include stability and cost. p. 102–13 (2017). https://doi.org/10.1007/978-3-319-71273-4_9

  25. M. Wehenkel, A. Sutera, C. Bastin, P. Geurts, C. Phillips, Random forests based group importance scores and their statistical interpretation: application for Alzheimer’s disease. Front. Neurosci. 12, (2018). https://doi.org/10.3389/fnins.2018.00411

  26. G. James, D. Witten, T. Hastie, R. Tibshirani, An Introduction to statistical learning. vol. 103. New York, NY: Springer New York. (2013). https://doi.org/10.1007/978-1-4614-7138-7

  27. H. He, Y. Ma, editors. Imbalanced Learning. Wiley. (2013). https://doi.org/10.1002/9781118646106

  28. S. Bae, Y.S. Choi, S.S. Ahn, J.H. Chang, S.G. Kang, E.H. Kim et al., Radiomic MRI phenotyping of glioblastoma: improving survival prediction. Radiology 289, 797–806 (2018). https://doi.org/10.1148/radiol.2018180200

    Article  Google Scholar 

  29. X. Chen, M. Fang, D. Dong, L. Liu, X. Xu, X. Wei et al., Development and validation of a MRI-based radiomics prognostic classifier in patients with primary glioblastoma multiforme. Acad. Radiol. 26, 1292–300 (2019). https://doi.org/10.1016/j.acra.2018.12.016

    Article  Google Scholar 

  30. M.W. McDonald, H.-K.G. Shu, W.J. Curran, I.R. Crocker, Pattern of failure after limited margin radiotherapy and temozolomide for glioblastoma. Int. J. Radiat. Oncol. 79, 130–6 (2011). https://doi.org/10.1016/j.ijrobp.2009.10.048

  31. B.J. Gebhardt, M.C. Dobelbower, W.H. Ennis, A.K. Bag, J.M. Markert, J.B. Fiveash, Patterns of failure for glioblastoma multiforme following limited-margin radiation and concurrent temozolomide. Radiat. Oncol. 9, 130 (2014). https://doi.org/10.1186/1748-717X-9-130

    Article  Google Scholar 

  32. M.C. Dobelbower, O.L. Burnett III., R.A. Nordal, L.B. Nabors, J.M. Markert, M.D. Hyatt et al., Patterns of failure for glioblastoma multiforme following concurrent radiation and temozolomide. J. Med. Imaging Radiat. Oncol. 55, 77–81 (2011). https://doi.org/10.1111/j.1754-9485.2010.02232.x

    Article  Google Scholar 

  33. H. Um, F. Tixier, D. Bermudez, J.O. Deasy, R.J. Young, H. Veeraraghavan, Impact of image preprocessing on the scanner dependence of multi-parametric MRI radiomic features and covariate shift in multi-institutional glioblastoma datasets. Phys. Med. Biol. 64, (2019). https://doi.org/10.1088/1361-6560/ab2f44

  34. S. Narang, M. Lehrer, D. Yang, J. Lee, A. Rao, Radiomics in glioblastoma: current status, challenges and potential opportunities. Transl. Cancer Res. 5, 383–97 (2016). https://doi.org/10.21037/tcr.2016.06.31

  35. J. Pyyry, W. Keranen, Varian APIs. First Edit. (2018)

Download references

Funding

This study was financed in part by the Coordenação de Aperfeiçoamento de Pessoal de Nível Superior—Brasil (CAPES)—Finance Code 001.

Author information

Author notes

  1. PedroHenrique de Marco Borges and JéssicaCaroline Lizar contributed equally for this manuscript.

Authors and Affiliations

  1. Physics Department, Faculty of Philosophy, Sciences and Letters at Ribeirão Preto, University of São Paulo, Av. Bandeirantes 3900, Monte Alegre, Ribeirão Preto, SP, 14040-901, Brazil

    Pedro Henrique de Marco Borges, Jéssica Caroline Lizar & Juliana Fernandes Pavoni

  2. Ribeirão Preto Medical School Hospital and Clinics, University of São Paulo, Ribeirão Preto, SP, Brazil

    Alexandre Ciuffi Correa Faustino, Gustavo Viani Arruda & Juliana Fernandes Pavoni

Authors
  1. Pedro Henrique de Marco Borges
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Jéssica Caroline Lizar
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Alexandre Ciuffi Correa Faustino
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Gustavo Viani Arruda
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Juliana Fernandes Pavoni
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Juliana Fernandes Pavoni.

Ethics declarations

Competing Interests

The authors declare no competing interests.

Additional information

Publisher's Note

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

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

de Marco Borges, P.H., Lizar, J.C., Faustino, A.C.C. et al. Kurtosis is An MRI Radiomics Feature Predictor of Poor Prognosis in Patients with GBM. Braz J Phys 51, 1035–1042 (2021). https://doi.org/10.1007/s13538-021-00912-9

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s13538-021-00912-9

Keywords

Search

Navigation