Glioma grading using a machine-learning framework based on optimized features obtained from T₁ perfusion MRI and volumes of tumor components

Background: Glioma grading between intermediate grades (Grade II vs. III and Grade III vs. IV) as well as multiclass grades (Grade II vs. III vs. IV) is challenging and needs to be addressed.

Purpose: To develop an artificial intelligence-based methodology for glioma grading using T₁ perfusion parameters and volume of tumor components, and validate the efficacy of the methodology by grading on a cohort of glioma patients.

Study type: Retrospective.

Population: The development set consisted of 53 glioma patients and validation consisted of 13 glioma patients.

Field strength/sequence: Conventional MRI images (2D T₁ -W, dual PD-T₂ -W, and 3D FLAIR) and 3D T₁ perfusion MRI data obtained at 3 T.

Assessment: Enhancing and nonenhancing components of glioma were segmented out and combined to form the region of interest (ROI) for glioma grading. Prominent vessels were removed from the selected ROI. Different T₁ perfusion parameters from the ROI were combined with volume of tumor components to form the feature set for glioma grading. Optimization was carried out for selection of the statistic of the T₁ perfusion parameters and the features to be used for glioma grading using sequential feature selection and random forest-based feature selection method. An optimized support vector machine (SVM) classifier was used for glioma grading.

Statistical tests: Mean ± SD, analysis of variance (ANOVA) followed by the Tukey-Kramer test, ROC analysis.

Results: Classification error for Grade II vs. III was 3.7%, for Grade III vs. IV was 5.26%, and for Grade II vs. III vs. IV was 9.43% using the proposed methodology. The mean of the values above the 90^th percentile value of T₁ perfusion parameters provided a maximum area under the curve (AUC) for intermediate grade differentiation. Random forest obtained optimal feature set provided better grading results than other methods using the SVM classifier.

Data conclusion: It was feasible to achieve low classification error for intermediate as well as multiclass glioma grading using an SVM classifier based on optimized features obtained from T₁ perfusion MRI and volumes of tumor components.

Level of evidence: 4 Technical Efficacy: Stage 3 J. Magn. Reson. Imaging 2019;50:1295-1306.