Radiomic MRI signature reveals three distinct subtypes of glioblastoma with different clinical and molecular characteristics, offering prognostic value beyond IDH1

Abstract

The remarkable heterogeneity of glioblastoma, across patients and over time, is one of the main challenges in precision diagnostics and treatment planning. Non-invasive in vivo characterization of this heterogeneity using imaging could assist in understanding disease subtypes, as well as in risk-stratification and treatment planning of glioblastoma. The current study leveraged advanced imaging analytics and radiomic approaches applied to multi-parametric MRI of de novo glioblastoma patients (n = 208 discovery, n = 53 replication), and discovered three distinct and reproducible imaging subtypes of glioblastoma, with differential clinical outcome and underlying molecular characteristics, including isocitrate dehydrogenase-1 (IDH1), O⁶-methylguanine-DNA methyltransferase, epidermal growth factor receptor variant III (EGFRvIII), and transcriptomic subtype composition. The subtypes provided risk-stratification substantially beyond that provided by WHO classifications. Within IDH1-wildtype tumors, our subtypes revealed different survival (p < 0.001), thereby highlighting the synergistic consideration of molecular and imaging measures for prognostication. Moreover, the imaging characteristics suggest that subtype-specific treatment of peritumoral infiltrated brain tissue might be more effective than current uniform standard-of-care. Finally, our analysis found subtype-specific radiogenomic signatures of EGFRvIII-mutated tumors. The identified subtypes and their clinical and molecular correlates provide an in vivo portrait of phenotypic heterogeneity in glioblastoma, which points to the need for precision diagnostics and personalized treatment.

Figure 1

Glioblastoma imaging subtypes identified by the clustering process. (A) The frequency of each subtype. (B) Kaplan–Meier survival curves of the subtypes. (C) Relationship between the molecular composition (Neural/Mesenchymal/Proneural/Classical) and imaging subtypes (rim-enhancing/irregular/solid). (D) Three representative subjects of each subtype (closest to the mean of the cluster). (E) Spatial distribution probability of the tumors of each subtype. The color look-up tables show the probability of tumor existence. HR = Hazard ratio.

Figure 2

Identification of intrinsic imaging subtypes of glioblastoma using unsupervised clustering. Upper half of the figure shows heat map of the discovery cohort with columns representing subtypes (subjects) and rows representing features. Underneath the heat map are the color-coded survival rates, epidermal growth factor recipient variant -III (EGFRvIII) mutation status and molecular subtype for these subjects. The lower half of the figure shows heat map of the replication cohort with columns representing subtypes (subject) and rows representing features. Underneath the heat map are the color-coded values of survival rates, IDH1 mutation status and MGMT methylation status. The survival rates after 98th percentile were replaced with that value to alleviate the effect of outliers (long survivors) in the color bar. Only the subjects having gross total resection were shown here.

Figure 3

Survival analysis of the replication cohort. The identifiers (m) and (um) on the vertical axis, respectively, show MGMT methylated and un-methylated subjects. The identifiers C and UC in the legend entries, respectively, show censored (which were all alive at the time of last recorded follow-up or record check) and uncensored subjects (death was confirmed). IDH1+ and IDH1−, respectively, show IDH1-mutated and IDH1-wildtype patients.

Figure 4

Image post-processing workflow. (A) Pre-processed images (examples: T1CE, FLAIR) and segmentations. (B) = Extracted radiomic features calculated in all images in the segmented regions (ED, TU, NC). (C) K-Means clustering. (D) Analysis of the identified imaging subtypes of glioblastoma in terms of overall survival rates, spatial distribution, molecular subtype composition, and EGFRvIII prediction.