Research Article
Classification on Digital Pathological Images of Breast Cancer Based on Deep Features of Different Levels
Table 17
Literature comparison results on image-level accuracy (/%).
| Magnifications | 40× | 100× | 200× | 400× |
| Literature [12] | — | — | — | — | Literature [22] | 85.60 ± 4.80 | 83.50 ± 3.90 | 82.70 ± 1.70 | 80.30 ± 2.90 | Literature [23] | 84.60 ± 2.90 | 84.80 ± 4.20 | 84.20 ± 1.70 | 81.60 ± 3.70 | Literature [24] | 87.80 ± 5.60 | 85.60 ± 4.30 | 80.80 ± 2.80 | 82.90 ± 4.10 | Literature [27] | — | — | — | — | Our method | 87.85 ± 2.69 | 86.68 ± 2.28 | 87.75 ± 2.37 | 85.30 ± 4.41 |
|
|