Skip to main content
. 2022 Dec 15;14(2):e00558. doi: 10.14309/ctg.0000000000000558

Figure 3.

Figure 3.

Diagnostic performance of multitask deep learning network (MTN) and high-resolution anoscopy (HRA) impression using histopathology as the gold standard. (a) Per site anal intraepithelial neoplasia grade 2 or more severe (AIN 2+) probability stratified by histopathologic diagnosis. Histopathologic diagnosis of AIN 2+ was considered positive. Error bars indicate the mean and 95% confidence intervals (CIs), while the solid line across all classes denotes a retrospective cutoff to discriminate AIN 2+ lesions. (b) Receiver operating characteristic curve for MTN; operating points for MTN and HRA impression are indicated with symbols. (c) Sensitivity and specificity of MTN and HRA impression at corresponding operating points. Error bars indicate 95% CI.