Exploratory Analysis of Qualitative MR Imaging Features for the Differentiation of Glioblastoma and Brain Metastases

Abstract

ObjectivesTo identify qualitative VASARI (Visually AcceSIble Rembrandt Images) Magnetic Resonance (MR) Imaging features for differentiation of glioblastoma (GBM) and brain metastasis (BM) of different primary tumors.Materials and MethodsT1-weighted pre- and post-contrast, T2-weighted, and T2-weighted, fluid attenuated inversion recovery (FLAIR) MR images of a total of 239 lesions from 109 patients with either GBM or BM (breast cancer, non-small cell (NSCLC) adenocarcinoma, NSCLC squamous cell carcinoma, small-cell lung cancer (SCLC)) were included. A set of adapted, qualitative VASARI MR features describing tumor appearance and location was scored (binary; 1 = presence of feature, 0 = absence of feature). Exploratory data analysis was performed on binary scores using a combination of descriptive statistics (proportions with 95% binomial confidence intervals), unsupervised methods and supervised methods including multivariate feature ranking using either repeated fitting or recursive feature elimination with Support Vector Machines (SVMs).ResultsGBMs were found to involve all lobes of the cerebrum with a fronto-occipital gradient, often affected the corpus callosum (32.4%, 95% CI 19.1–49.2), and showed a strong preference for the right hemisphere (79.4%, 95% CI 63.2–89.7). BMs occurred most frequently in the frontal lobe (35.1%, 95% CI 28.9–41.9) and cerebellum (28.3%, 95% CI 22.6–34.8). The appearance of GBMs was characterized by preference for well-defined non-enhancing tumor margin (100%, 89.8–100), ependymal extension (52.9%, 36.7–68.5) and substantially less enhancing foci than BMs (44.1%, 28.9–60.6 vs. 75.1%, 68.8–80.5). Unsupervised and supervised analyses showed that GBMs are distinctively different from BMs and that this difference is driven by definition of non-enhancing tumor margin, ependymal extension and features describing laterality. Differentiation of histological subtypes of BMs was driven by the presence of well-defined enhancing and non-enhancing tumor margins and localization in the vision center. SVM models with optimal hyperparameters led to weighted F1-score of 0.865 for differentiation of GBMs from BMs and weighted F1-score of 0.326 for differentiation of BM subtypes.ConclusionVASARI MR imaging features related to definition of non-enhancing margin, ependymal extension, and tumor localization may serve as potential imaging biomarkers to differentiate GBMs from BMs.

Differentiating Glioblastomas from Solitary Brain Metastases: An Update on the Current Literature of Advanced Imaging Modalities

“…Decrease in FLAIR signal in glioblastoma compared with metastasis [10] 44% 91% Dynamic susceptibility contrast perfusion using rCBV [19] 90% 91% Both DWI and DTI [20] 79.8% 80.9% Diffusion tensor imaging using a VEC threshold of 0.48 [21] 100% 83.3% DTI parameters with DSC [22] 60-91% 55-100% 98% MRS with LM13 class lipids and cutoff of 81 mM [23] 81% 78% 85% PET imaging with α [11C] methyl-l-tryptophan with kinetic tracer analysis [24] 93% Machine learning algorithm with MRS and DSC data [25] 98% Two-dimensional morphological feature extraction for DTI [26] 97.9%…”

“…Tsolaki et al propose a machine learning algorithm that combines MRS data with DSC in the peritumoral area, leading to an accuracy of up to 98% [25]. Yang et al developed a computerized system using a semiautomatic segmentation method for DTI imaging and two-dimensional morphological feature extraction and selection and a pattern recognition module for tumor classification.…”

A Multiparametric MR-Based RadioFusionOmics Model with Robust Capabilities of Differentiating Glioblastoma Multiforme from Solitary Brain Metastasis

“…Radiomics convert digital medical images into mineable high-dimensional data and have been widely recognized as a practical alternative for noninvasive diagnosis/prognosis in oncology [ 13 , 30 ]. Previous studies demonstrated the feasibility of applying radiomics models to differentiate GBM from SBM based on either conventional MR images or advanced MR technologies [ 4 , 17 , 20 , 22 , 31 ]. Notably, one crucial and defining step for radiomics modeling is the delineation of the lesion VOI.…”

“…However, in cases of solitary brain metastasis (SBM), differentiating the GBM from SBM solely based on conventional characteristics on magnetic resonance imaging (MRI) remains challenging. GBM and SBM often share similar radiological manifestations, such as an intratumoral necrotic center and heterogeneous enhancement of the component surrounded by peritumoral edema regions [ 4 , 5 ].…”

“…These investigations have shed light on mining more concealed image textures barely captured by the naked eyes in distinguishing GBM from SBM. Nevertheless, these techniques are limited by the fact that the tumor VOI under investigation is tentatively chosen from either the peritumoral edema region [ 12 , 15 , 21 ] or the enhanced tumor area [ 4 , 11 ]. In addition, there is no definitive data on the tumor VOI (necrotic centers, enhancing margins, or peritumoral edema) that better characterizes GBM and SBM.…”