Fig. 3

Comparison of AUCs among three prediction models using different combinations of radiomic features (n = 1, 5, 10, 15 and 20) in the testing cohort. a-c model 1 using features derived from medial temporal lobe, gray matter, and white matter respectively. d-f model 2 using features derived from medial temporal lobe, gray matter, and white matter respectively. g-i model 3 using features derived from medial temporal lobe, gray matter, and white matter respectively