Prediction of IDH1 Mutation Status in Glioblastoma Using Machine Learning Technique Based on Quantitative Radiomic Data

• Published in: World neurosurgery 2019-05, Vol.125, p.e688-e696
• Main Authors: Lee, Min Ho, Kim, Junhyung, Kim, Sung-Tae, Shin, Hye-Mi, You, Hye-Jin, Choi, Jung Won, Seol, Ho Jun, Nam, Do-Hyun, Lee, Jung-Il, Kong, Doo-Sik
• Format: Article
• Language: English
• Subjects: Adult; Aged; Aged, 80 and over; Algorithms; Brain Neoplasms - genetics; Brain Neoplasms - pathology; Female; Glioblastoma; Glioblastoma - genetics; Glioblastoma - pathology; Glioma - genetics; Glioma - pathology; Humans; Isocitrate dehydrogenase; Isocitrate Dehydrogenase - genetics; Machine Learning; Magnetic resonance imaging; Magnetic Resonance Imaging - methods; Male; Middle Aged; Mutation; Retrospective Studies
• ISSN: 1878-8750; 1878-8769
• DOI: 10.1016/j.wneu.2019.01.157

Isocitrate dehydrogenase 1 (IDH1) mutation status is an independent favorable prognostic factor for glioblastoma (GBM) and is usually determined by sequencing or immunohistochemistry. An accurate prediction of IDH1 mutation status via noninvasive methods helps establish the appropriate treatment strategy. We aimed to predict IDH1 mutation status using quantitative radiomic data in patients with GBM. Between May 2010 and June 2015, we retrospectively identified 88 patients with newly diagnosed GBM. After semiautomatic segmentation of the lesions, we extracted 31 features from preoperative multiparametric magnetic resonance images. We also determined IDH1 mutation status using targeted sequencing and immunohistochemistry. A training cohort (n = 88) was used to train machine learning−based classifiers, with internal validation. The machine-learning technique was then validated in an external dataset of 35 patients with GBM. We detected the IDH1 mutation in 12 out of 88 GBMs. Multiparametric radiomic profiles revealed that the IDH1 mutation was associated with a smaller enhancing area volume and a larger necrotic area volume. Using the machine learning−based classification algorithms, we identified 70.3%−87.3% of prediction rate of IDH1 mutation status and found 66.3%−83.4% accuracy in the external validation set. We demonstrate that machine learning algorithms can predict IDH1 mutation status in GBM using preoperative multiparametric magnetic resonance images.