BioMed Research International / 2021 / Article / Tab 2

Research Article

Qualitative and Quantitative MRI Analysis in IDH1 Genotype Prediction of Lower-Grade Gliomas: A Machine Learning Approach

Table 2

List of selected VASARI and radiomics features.

Feature selection
Top 5 VASARI featuresAUC valueTop 10 radiomics featuresAUC value

Enhancement quality0.752GLRLM short run low gray-level emphasis0.756
Deep white matter invasion0.738GLRLM low gray-level run emphasis0.682
Tumor location0.684GLRLM run-length variance0.678
Proportion of necrosis0.682Histogram minimum0.677
T1/FLAIR ratio0.632Eccentricity0.662
GLSZM large zone high gray-level emphasis0.641
GLSZM low gray-level zone emphasis0.628
Histogram energy0.616
Histogram standard deviation0.612
GLSZM zone-size nonuniformity0.607

VASARI: Visually Accessible Rembrandt Images; AUC: area under the receiver operating characteristic curve; GLRLM: gray-level run-length matrix; GLSZM: gray-level size zone matrix.

Article of the Year Award: Outstanding research contributions of 2020, as selected by our Chief Editors. Read the winning articles.