Skip to main content
. 2025 Jul 14;15:1626785. doi: 10.3389/fonc.2025.1626785

Table 4.

Comparison of classification performance between the MVT-OFML model and other mainstream methods on the BreakHis dataset.

Backbone network or method Year of publication Magnification/times Accuracy/% Accuracy/% Recall rate/% F1 score/%
Deep-Net (11) 2020 40 94.43 95.25 95.55 95.39
100 94.45 94.64 94.64 94.42
200 92.27 90.71 92.24 91.42
400 91.15 90.74 91.09 90.75
AnoGAN (21) 2021 40 99.15 99.64 99.46 99.78
100 97.09 98.07 98.49 98.22
200 87.58 88. 19 92.82 90.62
400 87.3 82.77 92.5 88.23
BHC-Net (22) 2022 40 94.71 95.25 95.55 95.39
100 94.6 94.51 94.64 94.42
200 92.35 90.71 92.24 91.42
400 91.5 90.74 91.09 90.75
BreaST-Net (23) 2022 40 96 95.8
100 92.6 92.4
200 93.5 93.6
400 91.5 98.88 93.2
MVT-OFML 2023 40 99.19 98.93 98.9 98.46
100 99.05 97.44 99.3 97.77
200 99.6 97.88 99.54 99.33
400 99.63 96.19 98.45
Improvement 40 3.19↑ 2.66↑
100 6.45↑ 5.37↑
200 6.10↑ 5.73↑
400 8.31↑ 5.25↑

The symbol “↑”defines the improved values.