Table 1 Image classification comparison: classification results are reflected by accuracy, specificity and sensitivity
From: A deep learning model for diagnosing dystrophinopathies on thigh muscle MRI images
Model | Accuracy | Specificity | Sensitivity | AUC |
|---|---|---|---|---|
VGG-19 [24] | 0.87 (95%CI: 0.84, 0.89) | 0.98 (95%CI: 0.96, 0.99) | 0.66 (95%CI: 0.59, 0.72) | 0.91 |
ResNet50 [23] | 0.91 (95%CI: 0.88, 0.93) | 0.92 (95%CI: 0.89, 0.94) | 0.89 (95%CI: 0.85, 0.93) | 0.98 |
DenseNet201 [25] | 0.90 (95%CI: 0.87, 0.92) | 0.98 (95%CI: 0.96, 0.99) | 0.74 (95%CI: 0.68, 0.79) | 0.96 |
DenseNet121 [25] | 0.88 (95%CI: 0.85, 0.91) | 0.94 (95%CI: 0.91, 0.96) | 0.78 (95%CI: 0.72, 0.83) | 0.94 |
Inception-V3 [22] | 0.90 (95%CI: 0.87, 0.92) | 0.94 (95%CI: 0.91, 0.96) | 0.83 (95%CI: 0.77, 0.87) | 0.96 |