Advertisement

Machine learning-based quantitative texture analysis of conventional MRI combined with ADC maps for assessment of IDH1 mutation in high-grade gliomas

  • Deniz AlisEmail author
  • Omer Bagcilar
  • Yeseren Deniz Senli
  • Mert Yergin
  • Cihan Isler
  • Naci Kocer
  • Civan Islak
  • Osman Kizilkilic
Original Article

Abstract

Purpose

To assess the performance of texture analysis of conventional magnetic resonance imaging (MRI) and apparent diffusion coefficient (ADC) maps in predicting IDH1 status in high-grade gliomas (HGG).

Materials and methods

A total of 142 patients with HGG were included in the study. IDH1 mutation was present in 48 of 142 HGG (33.8%). Patients were randomly divided into the training cohort (n = 96) and the validation cohort (n = 46). Texture features were extracted via regions of interest on axial T2WI FLAIR, post-contrast T1WI, and ADC maps covering the whole volume of the tumors. The training cohort was used to train the random forest classifier, and the diagnostic performance of the pre-trained model was tested on the validation cohort.

Results

The random forest model of conventional MRI sequences and ADC images achieved diagnostic accuracy of 82.2% and 80.4% in predicting IDH1 status in the validation cohorts, respectively. The combined model of T2WI FLAIR, post-contrast T1WI, and ADC images exhibited the highest diagnostic accuracy equating 86.94% in the validation cohort.

Conclusion

Texture analysis of conventional MRI sequences enhanced by ML analysis can accurately predict the IDH1 status of HGG. Adding textural analysis of ADC maps to conventional MRI results in incremental diagnostic performance.

Keywords

Artificial intelligence IDH1 Gliomas Machine-learning Texture analysis 

Notes

Compliance with ethical standards

Conflict of interest

All authors declare that they have no conflict of interest.

Ethical Statement

The local ethics committee approved this retrospective study conducted between January 2011 and May 2019. The committee waived the need for informed consent for the de-identified use of medical and radiological data. All procedures performed in studies involving human participants were in accordance with the ethical standards of the institutional and/or national research committee and with the 1964 Helsinki Declaration and its later amendments or comparable ethical standards.

Supplementary material

11604_2019_902_MOESM1_ESM.docx (15 kb)
Supplementary material 1 (DOCX 15 kb)

References

  1. 1.
    Weller M, van den Bent M, Tonn JC, Stupp R, Preusser M, Cohen-Jonathan-Moyal E, et al. European Association for Neuro-Oncology (EANO) guideline on the diagnosis and treatment of adult astrocytic and oligodendroglial gliomas. Lancet Oncol. 2017;18:e315–29.  https://doi.org/10.1016/S1470-2045(17)30194-8.CrossRefPubMedGoogle Scholar
  2. 2.
    Louis DN, Perry A, Reifenberger G, von Deimling A, Figarella-Branger D, Cavenee WK, et al. The 2016 World Health Organization Classification of tumors of the central nervous system: a summary. Acta Neuropathol. 2016;131:803–20.  https://doi.org/10.1007/s00401-016-1545-1.CrossRefPubMedPubMedCentralGoogle Scholar
  3. 3.
    Weller M, Pfister SM, Wick W, Hegi ME, Reifenberger G, Stupp R. Molecular neuro-oncology in clinical practice: a new horizon. Lancet Oncol. 2013;14:e370–9.  https://doi.org/10.1016/S1470-2045(13)70168-2.CrossRefPubMedGoogle Scholar
  4. 4.
    Song Tao Q, Lei Y, Si G, Yan Qing D, Hui Xia H, Xue Lin Z, et al. IDH mutations predict longer survival and response to temozolomide in secondary glioblastoma. Cancer Sci. 2012;103:269–73.  https://doi.org/10.1111/j.1349-7006.2011.02134.x.CrossRefGoogle Scholar
  5. 5.
    Ellingson BM. Radiogenomics and imaging phenotypes in glioblastoma: novel observations and correlation with molecular characteristics. Curr Neurol Neurosci Rep. 2015;15:506.  https://doi.org/10.1007/s11910-014-0506-0.CrossRefPubMedGoogle Scholar
  6. 6.
    Qi SS, Yu L, Li H, Ou Y, Qiu X, Ding Y, et al. Isocitrate dehydrogenase mutation is associated with tumor location and magnetic resonance imaging characteristics in astrocytic neoplasms. Oncol Lett. 2014;7:1895–902.CrossRefGoogle Scholar
  7. 7.
    Metellus P, Coulibaly B, Colin C, de Paula AM, Vasiljevic A, Taieb D, et al. Absence of IDH mutation identifies a novel radiologic and molecular subtype of WHO grade II gliomas with dismal prognosis. Acta Neuropathol. 2010;120:719–29.  https://doi.org/10.1007/s00401-010-0777-8.CrossRefPubMedPubMedCentralGoogle Scholar
  8. 8.
    Kickingereder P, Sahm F, Radbruch A, Wick W, Heiland S, Deimling AV, et al. IDH mutation status is associated with a distinct hypoxia/angiogenesis transcriptome signature which is non invasively predictable with rCBV imaging in human glioma. Sci Rep. 2015;5:16238.  https://doi.org/10.1038/srep16238.CrossRefPubMedPubMedCentralGoogle Scholar
  9. 9.
    Biller A, Badde S, Nagel A, Neumann JO, Wick W, Hertenstein A, et al. Improved brain tumor classification by sodium MR imaging: prediction of IDH mutation status and tumor progression. AJNR Am J Neuroradiol. 2016;37:66–73.  https://doi.org/10.3174/ajnr.A4493.CrossRefPubMedGoogle Scholar
  10. 10.
    Pope WB, Prins RM, Albert Thomas M, Nagarajan R, Yen KE, Bittinger MA, et al. Non-invasive detection of 2-hydroxyglutarate and other metabolites in IDH1 mutant glioma patients using magnetic resonance spectroscopy. J Neurooncol. 2012;107:197–205.  https://doi.org/10.1007/s11060-011-0737-8.CrossRefPubMedGoogle Scholar
  11. 11.
    Gillies RJ, Kinahan PE, Hricak H. Radiomics: images are more than pictures, they are data. Radiology. 2015;278:563–77.  https://doi.org/10.1148/radiol.2015151169.CrossRefPubMedPubMedCentralGoogle Scholar
  12. 12.
    van Griethuysen JJM, Fedorov A, Parmar C, Hosny A, Aucoin N, Narayan V, et al. Computational radiomics system to decode the radiographic phenotype. Cancer Res. 2017;77:e104–7.  https://doi.org/10.1158/0008-5472.CAN-17-0339.CrossRefPubMedPubMedCentralGoogle Scholar
  13. 13.
    Park YW, Han K, Ahn SS, Bae S, Choi YS, Chang JH, et al. Prediction of IDH1-mutation and 1p/-19q-codeletion status using pre-operative MR imaging phenotypes in lower grade gliomas. AJNR Am J Neuroradiol. 2018;39:47.  https://doi.org/10.3174/ajnr.A5421.CrossRefGoogle Scholar
  14. 14.
    Li Z, Wang Y, Yu J, Guo Y, Cao W. Deep learning based radiomics (DLR) and its usage in non-invasive IDH1 prediction for low grade glioma. Sci. Rep. 2017;7:5467.  https://doi.org/10.1038/s41598-017-05848-2.CrossRefPubMedPubMedCentralGoogle Scholar
  15. 15.
    Yu J, Shi Z, Lian Y, Li Z, Liu T, Gao Y, et al. Non-invasive IDH1 mutation estimation based on a quantitative radiomics approach for grade II glioma. Eur Radiol. 2017;27:3509–22.  https://doi.org/10.1007/s00330-016-4653-3.CrossRefPubMedGoogle Scholar
  16. 16.
    Zhang B, Chang K, Ramkissoon SS, Tanguturi S, Bi WL, Reardon DA, et al. Multimodal MRI features predict isocitrate dehydrogenase genotype in high-grade gliomas. Neuro Oncol. 2017;19:109–17.  https://doi.org/10.1093/neuonc/now121.CrossRefPubMedGoogle Scholar
  17. 17.
    Sonoda Y, Shibahara I, Kawaguchi T, Saito R, Kanamori M, Watanabe M, et al. Association between molecuar alterations and tumor location and MRI characteristics in anaplastic gliomas. Brain Tumor Pathol. 2015;32:99–104.  https://doi.org/10.1007/s10014-014-0211-3.CrossRefPubMedGoogle Scholar
  18. 18.
    Yamashita K, Hiwatashi A, Togao O, Kikuchi K, Hatae R, Yoshimoto K, et al. MR imaging-based analysis of glioblastoma multiforme: estimation of IDH1 mutation status. AJNR Am J Neuroradiol. 2016;37:58–65.  https://doi.org/10.3174/ajnr.A4491.CrossRefPubMedGoogle Scholar
  19. 19.
    Reuss DE, Sahm F, Schrimpf D, Wiestler B, Capper D, Koelsche C, et al. ATRX and IDH1-R132H immunohistochemistry with subsequent copy number analysis and IDH sequencing as a basis for an “integrated” diagnostic approach for adult astrocytoma, oligodendroglioma and glioblastoma. Acta Neuropathol. 2015;129:133–46.  https://doi.org/10.1007/s00401-014-1370-3.CrossRefPubMedGoogle Scholar
  20. 20.
    Shafiq-Ul-Hassan M, Zhang GG, Latifi K, Ullah G, Hunt DC, Balagurunathan Y, et al. Intrinsic dependencies of CT radiomic features on voxel size and number of gray levels. Med Phys. 2017;44:1050–62.  https://doi.org/10.1002/mp.12123.CrossRefPubMedPubMedCentralGoogle Scholar
  21. 21.
    Szczypiński PM, Klepaczko A. MaZda-A Framework for biomedical image texture analysis and data exploration. Biomed Texture Anal. 2017;315–47.Google Scholar
  22. 22.
    Thibault G, Fertil B, Navarro C, Pereira S, Cau P, Levy N, et al. Texture indexes and gray level size zone matrix application to cell nuclei classification. Pattern Recogn Inform Process. 2009;140–5.Google Scholar
  23. 23.
    Mao J, Jain AK. Texture classification and segmentation using multiresolution simultaneous autoregressive models. Pattern Recogn. 1992;25:173–88.CrossRefGoogle Scholar
  24. 24.
    Frank E, Hall AM, Witten I. The WEKA Workbench. Online Appendix for “Data mining: practical machine learning tools and technique”, Morgan Kaufmann, 4th edn., 2016.Google Scholar
  25. 25.
    Breiman L. Random forests. Mach Learn. 2001;45:5–32.CrossRefGoogle Scholar
  26. 26.
    Arlot S, Celisse A. A survey of cross-validation procedures for model selection. Stat Surv. 2010;4:40–79.CrossRefGoogle Scholar
  27. 27.
    Kocak B. Durmaz ES, Ates E, Kilickesmez O. Radiomics with artificial intelligence: a practical guide for beginners. Diagn Interv Radiol.  https://doi.org/10.5152/dir.2019.19321.CrossRefGoogle Scholar
  28. 28.
    Bisdas S, Shen H, Thust S, Katsaros V, Stranjalis G, Boskos C, et al. Texture analysis-and support vector machine-assisted diffusional kurtosis imaging may allow in vivo gliomas grading and IDH-mutation status prediction: a preliminary study. Sci Rep. 2018;8:6108.  https://doi.org/10.1038/s41598-018-24438-4.CrossRefPubMedPubMedCentralGoogle Scholar
  29. 29.
    Han L, Wang S, Miao Y, Shen H, Guo Y, Xie L, et al. MRI texture analysis based on 3D tumor measurement reflects the IDH1 mutations in gliomas—a preliminary study. Eur J Radiol. 2019;112.169–179.  https://doi.org/10.1016/j.ejrad.2019.01.025.CrossRefGoogle Scholar
  30. 30.
    Su CQ, Lu SS, Zhou MD, Shen H, Shi HB, Hong XN. Combined texture analysis of diffusion-weighted imaging with conventional MRI for non-invasive assessment of IDH1 mutation in anaplastic gliomas. Clin Radiol. 2019;74:154–60.  https://doi.org/10.1016/j.crad.2018.10.002.CrossRefPubMedGoogle Scholar
  31. 31.
    Lewis MA, Ganeshan B, Barnes A, Bisdas S, Jaunmuktane Z, Brandner SS, et al. Filtration-histogram based magnetic resonance texture analysis (MRTA) for glioma IDH and 1p19q genotyping. Eur J Radiol. 2019;113:116–23.  https://doi.org/10.1016/j.ejrad.2019.02.014.CrossRefPubMedGoogle Scholar
  32. 32.
    Zhou H, Chang K, Bai HX, Xiao B, Su C, Bi WL, et al. Machine learning reveals multimodal MRI patterns predictive of isocitrate dehydrogenase and 1p/19q status in diffuse low-and high-grade gliomas. J Neurooncol. 2019;142:299–307.  https://doi.org/10.1007/s11060-019-03096-0.CrossRefPubMedPubMedCentralGoogle Scholar
  33. 33.
    Balagurunathan Y, Kumar V, Gu Y, Kim J, Wang H, Liu Y, et al. Test–retest reproducibility analysis of lung CT image features. J Digit Imaging. 2014;27:805–23.  https://doi.org/10.1007/s10278-014-9716-x.CrossRefPubMedPubMedCentralGoogle Scholar

Copyright information

© Japan Radiological Society 2019

Authors and Affiliations

  1. 1.Department of RadiologyIstanbul Mehmet Akif Ersoy Thoracic and Cardiovascular Surgery Training and Research HospitalHalkali/IstanbulTurkey
  2. 2.Department of Radiology, Istanbul University-Cerrahpasa, Cerrahpasa Faculty of MedicineKMPasaIstanbulTurkey
  3. 3.Department of Software Engineering and Applied SciencesBahcesehir UniversityIstanbulTurkey
  4. 4.Department of Neurosurgery, Istanbul University-Cerrahpasa, Cerrahpasa Faculty of MedicineKMPasaIstanbulTurkey

Personalised recommendations