Grading of Gliomas by Using Radiomic Features on Multiple Magnetic Resonance Imaging (MRI) Sequences

Abstract

BackgroundGliomas are the most common primary brain neoplasms. Misdiagnosis occurs in glioma grading due to an overlap in conventional MRI manifestations. The aim of the present study was to evaluate the power of radiomic features based on multiple MRI sequences – T2-Weighted-Imaging-FLAIR (FLAIR), T1-Weighted-Imaging-Contrast-Enhanced (T1-CE), and Apparent Diffusion Coefficient (ADC) map – in glioma grading, and to improve the power of glioma grading by combining features.Material/MethodsSixty-six patients with histopathologically proven gliomas underwent T2-FLAIR and T1WI-CE sequence scanning with some patients (n=63) also undergoing DWI scanning. A total of 114 radiomic features were derived with radiomic methods by using in-house software. All radiomic features were compared between high-grade gliomas (HGGs) and low-grade gliomas (LGGs). Features with significant statistical differences were selected for receiver operating characteristic (ROC) curve analysis. The relationships between significantly different radiomic features and glial fibrillary acidic protein (GFAP) expression were evaluated.ResultsA total of 8 radiomic features from 3 MRI sequences displayed significant differences between LGGs and HGGs. FLAIR GLCM Cluster Shade, T1-CE GLCM Entropy, and ADC GLCM Homogeneity were the best features to use in differentiating LGGs and HGGs in each MRI sequence. The combined feature was best able to differentiate LGGs and HGGs, which improved the accuracy of glioma grading compared to the above features in each MRI sequence. A significant correlation was found between GFAP and T1-CE GLCM Entropy, as well as between GFAP and ADC GLCM Homogeneity.ConclusionsThe combined radiomic feature had the highest efficacy in distinguishing LGGs from HGGs.

GFAP expression is influenced by astrocytoma grade and rs2070935 polymorphism

“…Using qRT-PCR and western blot assays, we found GFAP expression to correlate negatively with tumor grade, as mRNA and protein levels of the following gene are significantly lower in grade IV, compared to grade II or III astrocytoma. In previous studies similar results were obtained using immunohistochemistry 10 9 . However, our findings further expand on these studies, as our data indicates that GFAP mRNA expression in grade II and III astrocytoma is considerably higher than in the reference human brain control, which represents a healthy CNS.…”

“…GFAP translational activity was reported to experience changes in human astrocytoma 9 . Since GFAP expression is a biomarker for astrocyte maturity, a decrease in the total amount of the following filament might be a result of cellular dedifferentiation in brain tumor tissue 10 .…”

Radiomics Nomogram Building From Multiparametric MRI to Predict Grade in Patients With Glioma: A Cohort Study

“…Qin et al extracted 114 features from CET 1 WI, T 2 Flair, and ADC sequences. They compared all radiomic features between high‐grade gliomas (HGGs) and low‐grade gliomas (LGGs).…”

“…Their results showed that MRI texture assessments were useful for accurate tumor grading. Qin et al compared 114 features extracted from a T 2 ‐weighted imaging fluid attenuated inversion recovery (T 2 W‐FLAIR) sequence, CET 1 WI, and apparent diffusion coefficient (ADC) maps between low‐grade and high‐grade gliomas. They showed that eight features displayed significant differences between high‐grade and low‐grade glioma patients, and diagnostic efficiency could be improved when these eight features were combined together (0.943 of AUC of receiving operating characteristics, 89% of specificity)…”

Overview of established and emerging immunohistochemical biomarkers and their role in correlative studies in MRI

“…DWI is a technique of great interest in cancer due to the impaired diffusivity of water molecules in highly cellular tissues, which can be used to detect the proliferative rate and aggressive growth of GBM. DWI‐MRI ADC maps were also able to effectively evaluate tumor grade in patients with gliomas . Other brain MRI studies suggest that cerebral blood flow (CBV) may be able to accurately reflect VEGF expression and tumor grade in gliomas and meningiomas.…”