Radiomics and MGMT promoter methylation for prognostication of newly diagnosed glioblastoma

• Published in: Scientific reports Vol. 9; no. 1; pp. 14435 - 9
• Main Authors: Sasaki, Takahiro, Kinoshita, Manabu, Fujita, Koji, Fukai, Junya, Hayashi, Nobuhide, Uematsu, Yuji, Okita, Yoshiko, Nonaka, Masahiro, Moriuchi, Shusuke, Uda, Takehiro, Tsuyuguchi, Naohiro, Arita, Hideyuki, Mori, Kanji, Ishibashi, Kenichi, Takano, Koji, Nishida, Namiko, Shofuda, Tomoko, Yoshioka, Ema, Kanematsu, Daisuke, Kodama, Yoshinori, Mano, Masayuki, Nakao, Naoyuki, Kanemura, Yonehiro
• Format: Journal Article
• Language: English
• Published: England Nature Publishing Group 08.10.2019; Nature Publishing Group UK
• Subjects: Brain cancer; Brain Neoplasms - diagnostic imaging; Brain Neoplasms - genetics; Brain Neoplasms - metabolism; Cohort Studies; DNA Methylation; DNA methyltransferase; DNA Modification Methylases - genetics; DNA Repair Enzymes - genetics; Glioblastoma; Glioblastoma - diagnostic imaging; Glioblastoma - genetics; Glioblastoma - metabolism; Humans; Image Processing, Computer-Assisted; Magnetic Resonance Imaging; Medical prognosis; Methylguanine; NMR; Nuclear magnetic resonance; O6-methylguanine-DNA methyltransferase; Prognosis; Promoter Regions, Genetic; Radiometry; Radiomics; Risk groups; Tumor Suppressor Proteins - genetics
• ISSN: 2045-2322; 2045-2322
• DOI: 10.1038/s41598-019-50849-y

We attempted to establish a magnetic resonance imaging (MRI)-based radiomic model for stratifying prognostic subgroups of newly diagnosed glioblastoma (GBM) patients and predicting O (6)-methylguanine-DNA methyltransferase promotor methylation (pMGMT-met) status of the tumor. Preoperative MRI scans from 201 newly diagnosed GBM patients were included in this study. A total of 489 texture features including the first-order feature, second-order features from 162 datasets, and location data from 182 datasets were collected. Supervised principal component analysis was used for prognostication and predictive modeling for pMGMT-met status was performed based on least absolute shrinkage and selection operator regression. 22 radiomic features that were correlated with prognosis were used to successfully stratify patients into high-risk and low-risk groups (p = 0.004, Log-rank test). The radiomic high- and low-risk stratification and pMGMT status were independent prognostic factors. As a matter of fact, predictive accuracy of the pMGMT methylation status was 67% when modeled by two significant radiomic features. A significant survival difference was observed among the combined high-risk group, combined intermediate-risk group (this group consists of radiomic low risk and pMGMT-unmet or radiomic high risk and pMGMT-met), and combined low-risk group (p = 0.0003, Log-rank test). Radiomics can be used to build a prognostic score for stratifying high- and low-risk GBM, which was an independent prognostic factor from pMGMT methylation status. On the other hand, predictive accuracy of the pMGMT methylation status by radiomic analysis was insufficient for practical use.