Table 1 The macro-average performance metrics along with 95% confidence intervals for DeepOpacityNet and other methods on the testing dataset.
From: A deep network DeepOpacityNet for detection of cataracts from color fundus photographs
Network | Accuracy | Precision | Recall | F1 score | κ | AUC | AP |
|---|---|---|---|---|---|---|---|
VGG16 | 0.63 (0.61, 0.64) | 0.63 (0.61, 0.64) | 0.63 (0.61, 0.64) | 0.63 (0.61, 0.64) | 0.25 (0.22, 0.29) | 0.67 (0.65, 0.69) | 0.66 (0.64, 0.68) |
ResNet50 | 0.59 (0.58, 0.61) | 0.59 (0.58, 0.61) | 0.59 (0.58, 0.61) | 0.59 (0.58, 0.61) | 0.18 (0.15, 0.22) | 0.63 (0.61, 0.65) | 0.62 (0.60, 0.64) |
ResNet152V2 | 0.63 (0.62, 0.65) | 0.64 (0.62, 0.65) | 0.63 (0.62, 0.65) | 0.63 (0.61, 0.65) | 0.26 (0.23, 0.30) | 0.69 (0.68, 0.71) | 0.69 (0.67, 0.71) |
InceptionResNetV2 | 0.65 (0.64, 0.67) | 0.65 (0.64, 0.67) | 0.65 (0.64, 0.67) | 0.65 (0.64, 0.67) | 0.31 (0.27, 0.34) | 0.71 (0.70, 0.73) | 0.71 (0.69, 0.72) |
InceptionV3 | 0.63 (0.61, 0.64) | 0.63 (0.61, 0.64) | 0.63 (0.61, 0.64) | 0.63 (0.61, 0.64) | 0.25 (0.22, 0.28) | 0.68 (0.67, 0.7) | 0.68 (0.66, 0.70) |
Dense201 | 0.64 (0.63, 0.66) | 0.64 (0.63, 0.66) | 0.64 (0.63, 0.66) | 0.64 (0.63, 0.66) | 0.28 (0.25, 0.32) | 0.69 (0.67, 0.71) | 0.69 (0.67, 0.70) |
Xception | 0.64 (0.63, 0.66) | 0.64 (0.63, 0.66) | 0.64 (0.63, 0.66) | 0.64 (0.63, 0.66) | 0.29 (0.26, 0.32) | 0.70 (0.68, 0.72) | 0.69 (0.67, 0.71) |
DeepOpacityNet | 0.66 (0.64, 0.68) | 0.66 (0.65, 0.68) | 0.66 (0.64, 0.68) | 0.66 (0.64, 0.68) | 0.32 (0.29, 0.35) | 0.72 (0.70, 0.74) | 0.71 (0.69, 0.72) |
