Radiogenomics of lower-grade gliomas: machine learning–based MRI texture analysis for predicting 1p/19q codeletion status

  • Burak KocakEmail author
  • Emine Sebnem Durmaz
  • Ece Ates
  • Ipek Sel
  • Saime Turgut Gunes
  • Ozlem Korkmaz Kaya
  • Amalya Zeynalova
  • Ozgur Kilickesmez



To evaluate the potential value of the machine learning (ML)–based MRI texture analysis for predicting 1p/19q codeletion status of lower-grade gliomas (LGG), using various state-of-the-art ML algorithms.

Materials and methods

For this retrospective study, 107 patients with LGG were included from a public database. Texture features were extracted from conventional T2-weighted and contrast-enhanced T1-weighted MRI images, using LIFEx software. Training and unseen validation splits were created using stratified 10-fold cross-validation technique along with minority over-sampling. Dimension reduction was done using collinearity analysis and feature selection (ReliefF). Classifications were done using adaptive boosting, k-nearest neighbours, naive Bayes, neural network, random forest, stochastic gradient descent, and support vector machine. Friedman test and pairwise post hoc analyses were used for comparison of classification performances based on the area under the curve (AUC).


Overall, the predictive performance of the ML algorithms were statistically significantly different, χ2(6) = 26.7, p < 0.001. There was no statistically significant difference among the performance of the neural network, naive Bayes, support vector machine, random forest, and stochastic gradient descent, adjusted p > 0.05. The mean AUC and accuracy values of these five algorithms ranged from 0.769 to 0.869 and from 80.1 to 84%, respectively. The neural network had the highest mean rank with mean AUC and accuracy values of 0.869 and 83.8%, respectively.


The ML-based MRI texture analysis might be a promising non-invasive technique for predicting the 1p/19q codeletion status of LGGs. Using this technique along with various ML algorithms, more than four-fifths of the LGGs can be correctly classified.

Key Points

• More than four-fifths of the lower-grade gliomas can be correctly classified with machine learning–based MRI texture analysis. Satisfying classification outcomes are not limited to a single algorithm.

• A few-slice-based volumetric segmentation technique would be a valid approach, providing satisfactory predictive textural information and avoiding excessive segmentation duration in clinical practice.

• Feature selection is sensitive to different patient data set samples so that each sampling leads to the selection of different feature subsets, which needs to be considered in future works.


Artificial intelligence Machine learning Radiomics Glioma Mutation 



Area under the curve


Grey-level co-occurrence matrix


Grey-level run-length matrix


Grey-level zone length matrix


Lower-grade glioma


Machine learning


Magnetic resonance imaging


Neighbourhood grey-level difference matrix


Standard deviation






The Cancer Imaging Archive


World Health Organisation


Funding information

The authors state that this work has not received any funding.

Compliance with ethical standards


The scientific guarantor of this publication is Burak Kocak, MD.

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 (Burak Kocak, MD) has significant statistical expertise.

Informed consent

Written informed consent was not required for this study because all patients included in this study are publicly and freely available for scientific purposes.

Ethical approval

Institutional Review Board approval was not required because all patients included in this study are publicly and freely available for scientific purposes.

Study subjects or cohorts overlap

Imaging data of 25 patients were partially used in the authors’ previous work in a completely different context. Previous work has been submitted to another journal.


• Retrospective

• Diagnostic or prognostic study

• Based on public data

Supplementary material

330_2019_6492_MOESM1_ESM.docx (512 kb)
ESM 1 Part A: Acquisition parameters. Part B: Details of extracted radiomic features. Part C: Data handling. Part D: Receiver operating characteristic (ROC) curves for each model and sample (DOCX 512 kb)


  1. 1.
    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. CrossRefGoogle Scholar
  2. 2.
    Gillies RJ, Kinahan PE, Hricak H (2016) Radiomics: images are more than pictures, they are data. Radiology 278:563–577. CrossRefPubMedGoogle Scholar
  3. 3.
    Koçak B, Durmaz EŞ, Ateş E, Kılıçkesmez Ö (2019) Radiomics with artificial intelligence: a practical guide for beginners. Diagn Interv Radiol. CrossRefGoogle Scholar
  4. 4.
    Cuccarini V, Erbetta A, Farinotti M et al (2016) Advanced MRI may complement histological diagnosis of lower grade gliomas and help in predicting survival. J Neurooncol 126:279–288. CrossRefPubMedGoogle Scholar
  5. 5.
    Cancer Genome Atlas Research Network, Brat DJ, Verhaak RG et al (2015) Comprehensive, integrative genomic analysis of diffuse lower-grade gliomas. N Engl J Med 372:2481–2498.
  6. 6.
    Chen B, Liang T, Yang P et al (2016) Classifying lower grade glioma cases according to whole genome gene expression. Oncotarget 7:74031–74042. CrossRefPubMedPubMedCentralGoogle Scholar
  7. 7.
    Louis DN, Perry A, Reifenberger G et al (2016) The 2016 World Health Organization classification of tumors of the central nervous system: a summary. Acta Neuropathol 131:803–820. CrossRefGoogle Scholar
  8. 8.
    Eckel-Passow JE, Lachance DH, Molinaro AM et al (2015) Glioma groups based on 1p/19q, IDH, and TERT promoter mutations in tumors. N Engl J Med 372:2499–2508. CrossRefPubMedPubMedCentralGoogle Scholar
  9. 9.
    Ino Y, Betensky RA, Zlatescu MC et al (2001) Molecular subtypes of anaplastic oligodendroglioma: implications for patient management at diagnosis. Clin Cancer Res 7:839–845Google Scholar
  10. 10.
    Kaloshi G, Benouaich-Amiel A, Diakite F et al (2007) Temozolomide for low-grade gliomas: predictive impact of 1p/19q loss on response and outcome. Neurology 68:1831–1836. CrossRefGoogle Scholar
  11. 11.
    Reifenberger J, Reifenberger G, Liu L, James CD, Wechsler W, Collins VP (1994) Molecular genetic analysis of oligodendroglial tumors shows preferential allelic deletions on 19q and 1p. Am J Pathol 145:1175–1190Google Scholar
  12. 12.
    Theeler BJ, Yung WKA, Fuller GN, De Groot JF (2012) Moving toward molecular classification of diffuse gliomas in adults. Neurology 79:1917–1926. CrossRefPubMedPubMedCentralGoogle Scholar
  13. 13.
    Woehrer A, Hainfellner JA (2015) Molecular diagnostics: techniques and recommendations for 1p/19q assessment. CNS Oncol 4:295–306. CrossRefPubMedPubMedCentralGoogle Scholar
  14. 14.
    Sanai N, Martino J, Berger MS (2012) Morbidity profile following aggressive resection of parietal lobe gliomas. J Neurosurg 116:1182–1186. CrossRefPubMedGoogle Scholar
  15. 15.
    Tate MC, Kim CY, Chang EF, Polley MY, Berger MS (2011) Assessment of morbidity following resection of cingulate gyrus gliomas. Clinical article. J Neurosurg 114:640–647. CrossRefGoogle Scholar
  16. 16.
    Megyesi JF, Kachur E, Lee DH et al (2004) Imaging correlates of molecular signatures in oligodendrogliomas. Clin Cancer Res 10:4303–4306. CrossRefGoogle Scholar
  17. 17.
    Patel SH, Poisson LM, Brat DJ et al (2017) T2-FLAIR mismatch, an imaging biomarker for IDH and 1p/19q status in lower-grade gliomas: a TCGA/TCIA project. Clin Cancer Res 23:6078–6085. CrossRefGoogle Scholar
  18. 18.
    Broen MPG, Smits M, Wijnenga MMJ et al (2018) The T2-FLAIR mismatch sign as an imaging marker for non-enhancing IDH-mutant, 1p/19q-intact lower-grade glioma: a validation study. Neuro Oncol 20:1393–1399. CrossRefGoogle Scholar
  19. 19.
    Han Y, Xie Z, Zang Y et al (2018) Non-invasive genotype prediction of chromosome 1p/19q co-deletion by development and validation of an MRI-based radiomics signature in lower-grade gliomas. J Neurooncol 140:297–306. CrossRefPubMedGoogle Scholar
  20. 20.
    Lu CF, Hsu FT, Hsieh KL et al (2018) Machine learning-based radiomics for molecular subtyping of gliomas. Clin Cancer Res 24:4429–4436. CrossRefGoogle Scholar
  21. 21.
    Akkus Z, Ali I, Sedlář J et al (2017) Predicting deletion of chromosomal arms 1p/19q in low-grade gliomas from MR images using machine intelligence. J Digit Imaging 30:469–476. CrossRefPubMedPubMedCentralGoogle Scholar
  22. 22.
    Clark K, Vendt B, Smith K et al (2013) The Cancer Imaging Archive (TCIA): maintaining and operating a public information repository. J Digit Imaging 26:1045–1057. CrossRefPubMedPubMedCentralGoogle Scholar
  23. 23.
    Erickson B, Akkus Z, Sedlar J, Korfiatis P (2017) Data from LGG-1p19qDeletion. Cancer Imaging Arch.
  24. 24.
    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. CrossRefPubMedGoogle Scholar
  25. 25.
    Shafiq-Ul-Hassan M, Zhang GG, Latifi K et al (2017) Intrinsic dependencies of CT radiomic features on voxel size and number of gray levels. Med Phys 44:1050–1062. CrossRefPubMedPubMedCentralGoogle Scholar
  26. 26.
    Nioche C, Orlhac F, Boughdad S et al (2018) LIFEx: a freeware for radiomic feature calculation in multimodality imaging to accelerate advances in the characterization of tumor heterogeneity. Cancer Res 78:4786–4789. CrossRefPubMedGoogle Scholar
  27. 27.
    Demšar J, Curk T, Erjavec A et al (2013) Orange: data mining toolbox in Python. J Mach Learn Res 14:2349–2353Google Scholar
  28. 28.
    Demšar J (2006) Statistical comparisons of classifiers over multiple data sets. J Mach Learn Res 7:1–30Google Scholar
  29. 29.
    Zhou H, Chang K, Bai HX et al (2019) Machine learning reveals multimodal MRI patterns predictive of isocitrate dehydrogenase and 1p/19q status in diffuse low- and high-grade gliomas. J Neurooncol 142:299–307. CrossRefPubMedPubMedCentralGoogle Scholar
  30. 30.
    Zhou H, Vallières M, Bai HX et al (2017) MRI features predict survival and molecular markers in diffuse lower-grade gliomas. Neuro Oncol 19:862–870. CrossRefGoogle Scholar
  31. 31.
    Lewis MA, Ganeshan B, Barnes A et al (2019) Filtration-histogram based magnetic resonance texture analysis (MRTA) for glioma IDH and 1p19q genotyping. Eur J Radiol 113:116–123. CrossRefPubMedGoogle Scholar
  32. 32.
    Kuthuru S, Deaderick W, Bai H et al (2018) A visually interpretable, dictionary-based approach to imaging-genomic modeling, with low-grade glioma as a case study. Cancer Inform 17:1176935118802796. CrossRefPubMedPubMedCentralGoogle Scholar
  33. 33.
    Bahrami N, Hartman SJ, Chang YH et al (2018) Molecular classification of patients with grade II/III glioma using quantitative MRI characteristics. J Neurooncol 139:633–642. CrossRefGoogle Scholar
  34. 34.
    Zwanenburg A, Leger S, Vallières M, Löck S (2016) Image biomarker standardisation initiative - feature definitions. arXiv:1612.07003Google Scholar

Copyright information

© European Society of Radiology 2019

Authors and Affiliations

  1. 1.Department of RadiologyIstanbul Training and Research HospitalIstanbulTurkey
  2. 2.Department of RadiologyBuyukcekmece Mimar Sinan State HospitalIstanbulTurkey
  3. 3.Department of Radiology, Koc University School of MedicineKoc University HospitalIstanbulTurkey
  4. 4.Department of Radiology, Cerrahpasa Medical FacultyIstanbul University-CerrahpasaIstanbulTurkey

Personalised recommendations