Skip to main content

Table 2 Diagnostic performance of comparison of radiomics and human assessment

From: Better efficacy in differentiating WHO grade II from III oligodendrogliomas with machine-learning than radiologist’s reading from conventional T1 contrast-enhanced and fluid attenuated inversion recovery images

 SensitivitySpecificityAUCACC
Radiomics (T1 CE)0.6720.7890.798 (95% CI: 0.699, 0.896)0.735
Radiomics (FLAIR)0.7000.6830.774 (95% CI: 0.671, 0.877)0.689
Radiomics (T1 CE + FLAIR)0.7780.7830.861 (95% CI: 0.783, 0.940)0.781
Reader10.8240.6320.700 (95% CI: 0.519, 0.880)0.722
Reader20.7060.6840.687 (95% CI: 0.507, 0.867)0.694
Reader30.6470.6320.714 (95% CI 0.545–0.883)0.667