Table 1 Predictive performance of the DCNNs using whole tongue image data.

From: DCNN models with post-hoc interpretability for the automated detection of glossitis and OSCC on the tongue

Model

VGG16

ResNet50

VGG19

ResNet152

Ensemble_2

(VGG16 + VGG19)

Ensemble_4

(VGG16 + ResNet50 + VGG19 + ResNet152)

AUROC

(95% CI)

0.8428

(95% CI 0.7757–0.9100)

0.7771

(95% CI 0.6932–0.8559)

0.8639

(95% CI 0.7988–0.9170)

0.8179

(95% CI 0.7382–0.8856)

0.8731

(95% CI 0.8072–0.9298)

0.8629 (95% CI 0.7899–0.9229)

  1. VGG16: Visual Geometry Group 16-layer network, ResNet50: Residual Network with 50 layers, VGG19: Visual Geometry Group 19-layer network, ResNet152: Residual Network with 152 layers, Ensemble_2: Ensemble model combining VGG16 and VGG19, Ensemble_4: Ensemble model combining VGG16, ResNet50, VGG19, and ResNet152, AUROC: Area Under the Receiver Operating Characteristic curve, 95% CI: 95% Confidence Interval.
Back to article page