Table 5.
Comparison of the performance of the MVT-OFML model and other mainstream methods on the BACH dataset.
| Backbone network or method | Year of publication | Accuracy | Precision | Recall rate | F1 score |
|---|---|---|---|---|---|
| Patch+Vote (24) | 2019 | 85 | 86.77 | 81.91 | 84.23 |
| Hybrid DNN (25) | 2020 | 95.29 | 94.46 | 94.43 | 94.31 |
| 3E-Net (26) | 2021 | 96.68 | 95.46 | 95.45 | 95.46 |
| TransMIL (27) | 2021 | 85.83 | 86.9 | 84.69 | 85.78 |
| MA-MIDN (28) | 2021 | 93.57 | 96.18 | 94.26 | 95.18 |
| MSMV-PFENet (29) | 2022 | 94.8 | 95.2 | 94.89 | 94.79 |
| MVT-OFML | 2023 | 98.94 | 98.56 | 98.48 | 98.67 |
| Improvement | 2.26↑ | 3.10↑ | 3.03↑ | 3.21↑ | |
The symbol “↑”defines the improved values.