A radiomics nomogram may improve the prediction of IDH genotype for astrocytoma before surgery
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.
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.
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).
The radiomics nomogram might be a useful supporting tool for the preoperative prediction of IDH genotype for astrocytoma, which could aid pretreatment decision-making.
• 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.
KeywordsAstrocytoma Radiomics Nomogram Isocitrate dehydrogenase Survival
Apparent diffusion coefficient
Area under the curve
Contrast-enhanced T1-weighted images
Isocitrate dehydrogenase mutant type
Isocitrate dehydrogenase wild type
Least absolute shrinkage and selection operator
Recursive feature elimination
Receiver operating characteristic
Regions of interest
Linear support vector machine
T2 fluid-attenuated inversion recovery images
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
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.
Written informed consent was not required for this study because this is a retrospective study and patient data are anonymized.
Institutional Review Board approval was obtained.
• diagnostic or prognostic study
• performed at one institution
- 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
- 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
- 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
- 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.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
- 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
- 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
- 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
- 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.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.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