Table 7 The average DSC scores per fold (F) between the algorithm’s predicted segmentations and each expert’s segmentation labels, ordered from worst to best DSC
From: Automatic deep learning-based pleural effusion segmentation in lung ultrasound images
F | Algorithm / Expert 1 | F | Algorithm / Expert 2 |
|---|---|---|---|
9 | 0.662 +/- 0.15 | 8 | 0.656 +/- 0.14 |
10 | 0.689 +/- 0.13 | 10 | 0.669 +/- 0.14 |
4 | 0.690 +/- 0.12 | 5 | 0.692 +/- 0.11 |
6 | 0.692 +/- 0.16 | 2 | 0.693 +/- 0.13 |
7 | 0.698 +/- 0.11 | 3 | 0.695 +/- 0.10 |
3 | 0.707 +/- 0.10 | 7 | 0.710 +/- 0.12 |
2 | 0.721 +/- 0.11 | 4 | 0.712 +/- 0.15 |
1 | 0.724 +/- 0.12 | 6 | 0.747 +/- 0.10 |
8 | 0.725 +/- 0.07 | 1 | 0.757 +/- 0.10 |
5 | 0.727 +/- 0.12 | 9 | 0.768 +/- 0.09 |