基于深度主动学习的甲状腺癌病理图像分类方法
|
张萌, 韩冰, 王哲, 尤富生, 李浩然
|
Papillary thyroid carcinoma pathological image classification based on deep active learning
|
Meng Zhang, Bing Han, Zhe Wang, Fusheng You, Haoran Li
|
|
表2 不同方法分类结果
|
Table 2 Classification results of different methods
|
|
Used data | Uncertainty | QBC | GD | QUIRE | SPAL | Random | Ours |
---|
1% | 0.817 | 0.782 | 0.823 | 0.830 | 0.840 | 0.702 | 0.862 | 5% | 0.834 | 0.795 | 0.842 | 0.835 | 0.854 | 0.809 | 0.879 | 10% | 0.849 | 0.800 | 0.858 | 0.850 | 0.836 | 0.848 | 0.893 | 20% | 0.865 | 0.802 | 0.867 | 0.855 | 0.857 | 0.860 | 0.898 | 30% | 0.874 | 0.801 | 0.876 | 0.868 | 0.898 | 0.866 | 0.914 | 40% | 0.877 | 0.802 | 0.873 | 0.873 | 0.912 | 0.866 | 0.918 | 50% | 0.880 | 0.803 | 0.876 | 0.879 | 0.915 | 0.872 | 0.919 |
|
|
|