Advertisement

A radiomics nomogram may improve the prediction of IDH genotype for astrocytoma before surgery

  • Yan Tan
  • Shuai-tong Zhang
  • Jing-wei Wei
  • Di Dong
  • Xiao-chun Wang
  • Guo-qiang Yang
  • Jie TianEmail author
  • Hui ZhangEmail author
Imaging Informatics and Artificial Intelligence
  • 93 Downloads

Abstract

Objectives

To develop and validate a radiomics nomogram to preoperative prediction of isocitrate dehydrogenase (IDH) genotype for astrocytomas, which might contribute to the pretreatment decision-making and prognosis evaluating.

Methods

One hundred five astrocytomas (Grades II–IV) with contrast-enhanced T1-weighted imaging (CE-T1WI), T2 fluid-attenuated inversion recovery (T2FLAIR), and apparent diffusion coefficient (ADC) map were enrolled in this study (training cohort: n = 74; validation cohort: n = 31). IDH1/2 genotypes were determined using Sanger sequencing. A total of 3882 radiomics features were extracted. Support vector machine algorithm was used to build the radiomics signature on the training cohort. Incorporating radiomics signature and clinico-radiological risk factors, the radiomics nomogram was developed. Receiver operating characteristic (ROC) curve and area under the curve (AUC) were used to assess these models. Kaplan–Meier survival analysis and log rank test were performed to assess the prognostic value of the radiomics nomogram.

Results

The radiomics signature was built by six selected radiomics features and yielded AUC values of 0.901 and 0.888 in the training and validation cohorts. The radiomics nomogram based on the radiomics signature and age performed better than the clinico-radiological model (training cohort, AUC = 0.913 and 0.817; validation cohort, AUC = 0.900 and 0.804). Additionally, the survival analysis showed that prognostic values of the radiomics nomogram and IDH genotype were similar (log rank test, p < 0.001; C-index = 0.762 and 0.687; z-score test, p = 0.062).

Conclusions

The radiomics nomogram might be a useful supporting tool for the preoperative prediction of IDH genotype for astrocytoma, which could aid pretreatment decision-making.

Key Points

• The radiomics signature based on multiparametric and multiregional MRI images could predict IDH genotype of Grades II–IV astrocytomas.

• The radiomics nomogram performed better than the clinico-radiological model, and it might be an easy-to-use supporting tool for IDH genotype prediction.

• The prognostic value of the radiomics nomogram was similar with that of the IDH genotype, which might contribute to prognosis evaluating.

Keywords

Astrocytoma Radiomics Nomogram Isocitrate dehydrogenase Survival 

Abbreviations

ADC

Apparent diffusion coefficient

AUC

Area under the curve

CE-T1WI

Contrast-enhanced T1-weighted images

IDH

Isocitrate dehydrogenase

IDH-M

Isocitrate dehydrogenase mutant type

IDH-W

Isocitrate dehydrogenase wild type

LASSO

Least absolute shrinkage and selection operator

LOOCV

Leave-one-out cross-validation

OS

Overall survival

RFE

Recursive feature elimination

ROC

Receiver operating characteristic

ROI

Regions of interest

SVM

Linear support vector machine

T2FLAIR

T2 fluid-attenuated inversion recovery images

Notes

Funding

This study has received funding by the National Natural Science Foundation (81471652 and 81771824 to Hui Zhang; 81227901, 81527805, 61231004, and 81671851 to Jie Tian; 81701681 to Yan Tan; 81771924, 81501616 to Di Dong; 11705112 to Guo-qiang Yang); National Key R&D Program of China (2017YFA0205200 and 2017YFC1309100 to Jie Tian, 2017YFC1308700 to Di Dong); the Precision Medicine Key Innovation Team Project (YT1601 to Hui Zhang); the Social Development Projects of Key R&D Program in Shanxi Province (201703D321016 to Hui Zhang); and the Natural Science Foundation of Shanxi Province (201601D021162 to Yan Tan).

Compliance with ethical standards

Guarantor

The scientific guarantor of this publication is Hui Zhang.

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 has significant statistical expertise.

Informed consent

Written informed consent was not required for this study because this is a retrospective study and patient data are anonymized.

Ethical approval

Institutional Review Board approval was obtained.

Methodology

• retrospective

• diagnostic or prognostic study

• performed at one institution

Supplementary material

330_2019_6056_MOESM1_ESM.docx (1.1 mb)
ESM 1 (DOCX 1175 kb)

References

  1. 1.
    Ichimura K, Narita Y, Hawkins CE (2015) Diffusely infiltrating astrocytomas: pathology, molecular mechanisms and markers. Acta Neuropathol 129(6):789–808CrossRefGoogle Scholar
  2. 2.
    Louis DN, Perry A, Reifenberger G et al (2016) The 2016 world health organization classification of tumours of the central nervous system: a summary. Acta Neuropathol 131(6):803–820CrossRefGoogle Scholar
  3. 3.
    Rogers TW, Tsui A, Gonzales M (2018) Re-classification of gliomas by the 2016 revision of the who classification of CNS tumours. Pathology 50(Sup1):S123CrossRefGoogle Scholar
  4. 4.
    Brat DJ, Verhaak RG, Aldape KD et al (2015) Comprehensive, integrative genomic analysis of diffuse lower-grade gliomas. N Engl J Med 372(26):2481–2498CrossRefGoogle Scholar
  5. 5.
    Beiko J, Suki D, Hess KR et al (2014) IDH1 mutant malignant astrocytomas are more amenable to surgical resection and have a survival benefit associated with maximal surgical resection. Neuro Oncol 16(1):81–91CrossRefGoogle Scholar
  6. 6.
    Kizilbash SH, Giannini C, Voss JS et al (2014) The impact of concurrent temozolomide with adjuvant radiation and IDH mutation status among patients with anaplastic astrocytoma. J Neurooncol 120(1):85–93CrossRefGoogle Scholar
  7. 7.
    Tran AN, Lai A, Li S et al (2016) Increased sensitivity to radiochemotherapy in IDH1 mutant glioblastoma as demonstrated by serial quantitative MR volumetry. Neuro Oncol 16(3):414–420CrossRefGoogle Scholar
  8. 8.
    Rohle D, Popovici-Muller J, Palaskas N et al (2013) An inhibitor of mutant IDH1 delays growth and promotes differentiation of glioma cells. Science 340(6132):626–630CrossRefGoogle Scholar
  9. 9.
    Waitkus MS, Dilpas BH, Yan H (2018) Biological role and therapeutic potential of IDH mutation in cancer. Cancer Cell.  https://doi.org/10.1061/j.ccell.2-18.04.011
  10. 10.
    Andronesi OC, Arrillaga-Romany IC, Ina Ly K et al (2018) Pharmacodynamics of mutant-IDH1 inhibitors in glioma patients probed by in vivo 3D MRS imaging of 2-hydroxyglutarate. Nat Commun 9:1474.  https://doi.org/10.1038/s41467-018-03905-6 CrossRefGoogle Scholar
  11. 11.
    Sullivan DC, Obuchowski NA, Kessler LG et al (2015) Metrology standards for quantitative imaging biomarkers. Radiology 277(3):813–825CrossRefGoogle Scholar
  12. 12.
    Liu Z, Zhang Y, Yan H et al (2012) Altered topological patterns of brain networks in mild cognitive impairment and Alzheimer's disease: a resting-state fMRI study. Psychiat Res-Neuroim 202(2):118–125Google Scholar
  13. 13.
    Qi S, Yu L, Li H et al (2014) Isocitrate dehydrogenase mutation is associated with tumour location and magnetic resonance imaging characteristics in astrocytic neoplasms. Oncol Lett 7(6):1895–1902CrossRefGoogle Scholar
  14. 14.
    Metellus P, Coulibaly B, Colin C et al (2010) Absence of IDH mutation identifies a novel radiologic and molecular subtype of WHO grade II gliomas with dismal prognosis. Acta Neuropathol 120(6):719–729CrossRefGoogle Scholar
  15. 15.
    Gillies RJ, Kinahan PE, Hricak H (2015) Radiomics: images are more than pictures, they are data. Radiology 278(2):563–577CrossRefGoogle Scholar
  16. 16.
    Lambin P, Leijenaar RTH, Deist TM et al (2017) Radiomics: the bridge between medical imaging and personalized medicine. Nat Rev Clin Oncol 14:947–762CrossRefGoogle Scholar
  17. 17.
    Yu J, Shi Z, Lian Y et al (2017) Noninvasive IDH1 mutation estimation based on a quantitative radiomics approach for grade II glioma. Eur Radiol 27(8):3509–3522CrossRefGoogle Scholar
  18. 18.
    Li Z, Wang Y, Yu J, Guo Y, Cao W (2017) Deep learning based radiomics (DLR) and its usage in noninvasive IDH1 prediction for low grade glioma. Sci Rep 7(1):5467CrossRefGoogle Scholar
  19. 19.
    Zhang X, Tian Q, Wang L et al (2018) Radiomics strategy for molecular subtype stratification of lower-grade glioma: detecting IDH and TP53 mutations based on multimodal MRI. J Magn Reson Imaging.  https://doi.org/10.1002/jmri.25960
  20. 20.
    Zhang B, Chang K, Ramkissoon S et al (2017) Multimodel MRI features predict isocitrate dehydrogenase genotype in high-grade gliomas. Neuro Oncol 19(1):109–117CrossRefGoogle Scholar
  21. 21.
    Hsieh KL, Chen CY, Lo CM (2017) Radiomic model for predicting mutations in the isocitrate dehydrogenase gene in glioblastomas. Oncotarget 8(28):45888–45897CrossRefGoogle Scholar
  22. 22.
    Baldock AL, Yagle K, Born DE et al (2014) Invasion and proliferation kinetics in enhancing gliomas predict IDH1 mutation status. Neuro Oncol 16(6):779–786CrossRefGoogle Scholar
  23. 23.
    Chen J, Tian J (2009) Real-time multi-modal rigid registration based on a novel symmetric-SIFT descriptor. Prog Nat Sci 19(5):643–651Google Scholar
  24. 24.
    Gebejes A, Huertas R (2013) Texture characterization based on grey-level co-occurrence matrix. International Conference on Information and Communication Technologies 1:375–378Google Scholar
  25. 25.
    Galloway MM (1975) Texture analysis using gray level run lengths. Computer Graphics and Image Processing 4:172–179CrossRefGoogle Scholar
  26. 26.
    Chu A, Sehgal CM, Greenleaf JF (1990) Use of gray value distribution of run lengths for texture analysis. Pattern Recognit Lett 11:415–419CrossRefGoogle Scholar
  27. 27.
    Dasarathy BV, Holder EB (1991) Image characterizations based on joint gray level—run length distributions. Pattern Recognit Lett 12:497–502CrossRefGoogle Scholar
  28. 28.
    Thibault G, Fertil B, Navarro C et al (2013) Shape and texture indexes application to cell nuclei classification. Intern J Pattern Recognit Artif Intell 27:1357002CrossRefGoogle Scholar
  29. 29.
    Thibault G, Fertil B, Navarro C et al (2009) Texture indexes and gray level size zone matrix: application to cell nuclei classification. Pattern Recognition Inf Process 140–145Google Scholar
  30. 30.
    Amadasun M, King R (1989) Textural features corresponding to textural properties. IEEE Trans Syst Man Cybern 19:1264–1274CrossRefGoogle Scholar
  31. 31.
    Zhang B, Tian J, Dong D et al (2017) Radiomics features of multiparametric MRI as novel prognostic factors in advanced nasopharyngeal carcinoma. Clin Cancer Res 23(15):4259–4269Google Scholar
  32. 32.
    Chalkidou A, O’Doherty MJ, Marsden PK et al (2015) False discovery rates in PET and CT studies with texture features: a systematic review. PLoS One 10(5):e0124165CrossRefGoogle Scholar
  33. 33.
    Rathore S, Akbari H, Doshi J et al (2018) Radiomic signature of infiltration in peritumoural edema predicts subsequent recurrence in glioblastoma: implications for personalized radiotherapy planning. J Med Imaging (Bellingham) 5(2):021219.  https://doi.org/10.1117/1.JMI.5.2.021219 Google Scholar
  34. 34.
    Prasanna P, Patel J, Partov S, Anant Madabhushi A, Tiwari R (2017) Radiomic features from the peritumoural brain parenchyma on treatment-naïve multi-parametric MR imaging predict long versus short-term survival in glioblastoma multiforme: preliminary findings. Eur Radiol 27:4188–4197CrossRefGoogle Scholar
  35. 35.
    Parsons DW, Jones S, Zhang X et al (2008) An integrated genomic analysis of human glioblastoma multiforme. Science 321(5897):1807–1812CrossRefGoogle Scholar
  36. 36.
    Dang L, Yen K, Attar EC (2016) IDH mutations in cancer and progress toward development of targeted therapeutics. Ann Oncol 27(4):599–608CrossRefGoogle Scholar
  37. 37.
    Colen R, Ashour O, Zinn PO (2013) Imaging genomic IDH-1 biomarker signature. Neuro Oncol 15(Suppl 3):iii191–iii205CrossRefGoogle Scholar
  38. 38.
    Santelli L, Ramondo G, Della Puppa A et al (2010) Diffusion-weighted imaging does not predict histological grading in meningiomas. Acta Neurochir (Wien) 152(8):1315–1319Google Scholar
  39. 39.
    Lam WW, Poon WS, Metreweli C (2002) Diffusion MR imaging in glioma: does it have any role in the pre-operation determination of grading of glioma. Clin Radiol 57(3):219–225Google Scholar
  40. 40.
    Xing Z, Yang X, She D, Lin Y, Zhang Y, Cao D (2017) Noninvasive assessment of IDH mutational status in World Health Organization Grade II and III Astrocytomas using DWI and DSC-PWI combined with conventional MR imaging. AJNR Am J Neuroradiol 38(6):1138–1144Google Scholar
  41. 41.
    Turcan S, Rohle D, Goenka A et al (2012) IDH mutation is sufficient to establish the glioma hypermethylator phenotype. Nature 483(7390):479–483CrossRefGoogle Scholar
  42. 42.
    Reuss DE, Mamatjan Y, Schrimpf D et al (2015) IDH mutant diffuse and anaplastic astrocytomas have similar age at presentation and little difference in survival: a grading problem for WHO. Acta Neuropathol 129(6):867–873CrossRefGoogle Scholar

Copyright information

© European Society of Radiology 2019

Authors and Affiliations

  • Yan Tan
    • 1
    • 2
  • Shuai-tong Zhang
    • 3
    • 4
  • Jing-wei Wei
    • 3
    • 4
  • Di Dong
    • 3
  • Xiao-chun Wang
    • 1
    • 2
  • Guo-qiang Yang
    • 1
    • 2
  • Jie Tian
    • 3
    Email author
  • Hui Zhang
    • 1
    • 2
    Email author
  1. 1.Department of RadiologyThe first hospital of Shanxi Medical UniversityTaiyuanChina
  2. 2.Department of Medical ImagingShanxi Medical UniversityTaiyuanChina
  3. 3.Key Laboratory of Molecular Imaging, Chinese Academy of SciencesInstitute of AutomationBeijingChina
  4. 4.University of Chinese Academy of SciencesBeijingChina

Personalised recommendations