Table 2 Differences in the performance by the number of classifications
From: Liver fibrosis stage classification in stacked microvascular images based on deep learning
a) | ||||
Classification | Accuracy↑ | Precision↑ | Recall↑ | F1 score↑ |
2 class (F0–1, F2–4) | 0.838 | 0.812 | 0.839 | 0.821 |
3 class (F0–1Low, F0–1High, F2–4) | 0.663 | 0.590 | 0.592 | 0.585 |
5 class (F0–1Low, F0–1High, F2, F3, F4) | 0.538 | 0.368 | 0.395 | 0.372 |
b) | ||||
Classification | Accuracy↑ | Precision↑ | Recall↑ | F1 score↑ |
2 class (F0–1, F2–4) | 0.816 | 0.636 | 0.775 | 0.698 |
3 class (F0–1Low, F0–1High, F2–4) | 0.655 | 0.580 | 0.586 | 0.583 |
5 class (F0–1Low, F0–1High, F2, F3, F4) | 0.557 | 0.375 | 0.396 | 0.385 |