A Semisupervised Learning Scheme with Self-Paced Learning for Classifying Breast Cancer Histopathological Images

Table 4

Accuracy (%) performance for binary classification. Baseline indicates that the model was fine-tuned with labeled samples only. (top-N) indicates the portion of the most confident pseudolabels used. Best results are indicated in italics.

ST approach	40X	100X	200X	400X
Baseline
(Top-5%) pseudolabels		99.44 ± 0.41
(Top-10%) pseudolabels	99.52 ± 0.33		99.48 ± 0.30	99.47 ± 0.37
(Top-20%) pseudolabels
All pseudolabels