Research Article
Breast Cancer Pathological Image Classification Based on the Multiscale CNN Squeeze Model
Table 5
Comparison of categorization results of fusion methods under different number of feature scales.
| Number of scales | Fusion method | % | % |
| 2 | Add | 85.42 | 85.07 | 2 | Max | 83.55 | 82.13 | 2 | Cat1(sign) | 84.10 | 82.96 | 2 | Cat1 | 85.38 | 84.64 | 2 | Cat2(sign) | 83.93 | 82.76 | 2 | Cat2 | 84.61 | 82.88 | 3 | Add | 85.00 | 83.71 | 3 | Max | 83.45 | 82.22 | 3 | Cat1(sign) | 83.76 | 82.09 | 3 | Cat1 | 85.61 | 84.28 | 3 | Cat2(sign) | 83.57 | 82.39 | 3 | Cat2 | 84.50 | 83.25 |
|
|