Table 7 Comparison of ensemble performance according to the number of snapshots used in Snap-MAE.

From: Integrating snapshot ensemble learning into masked autoencoders for efficient self-supervised pretraining in medical imaging

Number of snapshots

AUC

AUPRC

Sensitivity

Precision

F1-score

2 snapshots

0.751 (0.006)

0.526 (0.010)

0.739 (0.018)

0.555 (0.013)

0.614 (0.010)

4 snapshots

0.761 (0.003)

0.623 (0.005)

0.742 (0.008)

0.558 (0.013)

0.615 (0.005)

8 snapshots

0.757 (0.008)

0.525 (0.008)

0.757 (0.008)

0.552 (0.008)

0.623 (0.002)

Back to article page