Research Article
Local Binary Convolutional Neural Networks' Long Short-Term Memory Model for Human Embryos' Anomaly Detection
Table 8
Embryo video anomaly detection results based on different pretrained model’s architectures.
| Model | Accuracy | Precision | Recall | F1-score |
| VGG16 + LSTM | 0.91 | 0.89 | 0.84 | 0.86 | LeNet 5 + LSTM | 0.76 | 0.75 | 0.75 | 0.76 | Resnet-50 + LSTM | 0.97 | 0.98 | 0.93 | 0.98 | Inception V3 + LSTM | 0.96 | 0.95 | 0.94 | 0.96 | MobileNet V2 + LSTM | 0.95 | 0.93 | 0.93 | 0.93 | Xception + LSTM | 0.96 | 0.97 | 0.92 | 0.97 | Baseline CNN + LSTM | 0.95 | 0.94 | 0.94 | 0.94 | LBCNN + LSTM | 0.97 | 0.98 | 0.93 | 0.98 |
|
|