• Biqi Zhang, Ken Chang, Shakti Ramkissoon, Shyam Tanguturi, Wenya Linda Bi, David A Reardon, Keith L Ligon, Brian M Alexander, Patrick Y Wen, and Raymond Y Huang.
• Department of Radiology, Brigham and Women's Hospital, Boston, Massachusetts (B.Z., K.C., R.Y.H.); Department of Pathology, Brigham and Women's Hospital, Boston, Massachusetts (S.R., K.L.L.); Department of Pathology, Harvard Medical School, Boston, Massachusetts (S.R., K.L.L.); Department of Pathology, Boston Children's Hospital, Boston, Massachusetts (S.R., K.L.L.); Department of Medical Oncology, Dana-Farber Cancer Institute, Boston, Massachusetts(S.R., D.A.R., K.L.L., P.Y.W.); Harvard Radiation Oncology Program, Boston, Massachusetts (S.T.); Department of Neurosurgery, Brigham and Women's Hospital, Boston, Massachusetts (W.L.B.); Center of Neuro-Oncology, Dana-Farber/Brigham and Women's Cancer Center, Boston, Massachusetts (D.A.R., P.Y.W.); Department of Radiation Oncology, Dana-Farber/Brigham and Women's Cancer Center, Boston, Massachusetts (B.M.A.).
• Neuro-oncology. 2017 Jan 1; 19 (1): 109-117.

BackgroundHigh-grade gliomas with mutations in the isocitrate dehydrogenase (IDH) gene family confer longer overall survival relative to their IDH-wild-type counterparts. Accurate determination of the IDH genotype preoperatively may have both prognostic and diagnostic value. The current study used a machine-learning algorithm to generate a model predictive of IDH genotype in high-grade gliomas based on clinical variables and multimodal features extracted from conventional MRI.MethodsPreoperative MRIs were obtained for 120 patients with primary grades III (n = 35) and IV (n = 85) glioma in this retrospective study. IDH genotype was confirmed for grade III (32/35, 91%) and IV (22/85, 26%) tumors by immunohistochemistry, spectrometry-based mutation genotyping (OncoMap), or multiplex exome sequencing (OncoPanel). IDH1 and IDH2 mutations were mutually exclusive, and all mutated tumors were collapsed into one IDH-mutated cohort. Cases were randomly assigned to either the training (n = 90) or validation cohort (n = 30). A total of 2970 imaging features were extracted from pre- and postcontrast T1-weighted, T2-weighted, and apparent diffusion coefficient map. Using a random forest algorithm, nonredundant features were integrated with clinical data to generate a model predictive of IDH genotype.ResultsOur model achieved accuracies of 86% (area under the curve [AUC] = 0.8830) in the training cohort and 89% (AUC = 0.9231) in the validation cohort. Features with the highest predictive value included patient age as well as parametric intensity, texture, and shape features.ConclusionUsing a machine-learning algorithm, we achieved accurate prediction of IDH genotype in high-grade gliomas with preoperative clinical and MRI features.© The Author(s) 2016. Published by Oxford University Press on behalf of the Society for Neuro-Oncology. All rights reserved. For permissions, please e-mail: journals.permissions@oup.com.

34 keywords...

hide…