Table 6 The generated cross-validation folds or repeated 5-fold cross-validation per expert, includes the patients in the training set (comprising the original Training (T) and Validation (V) sets) and the test sets. The first 5 folds (1-5) use the contours from expert 1, and the next 5 folds (6-10) use the contours from expert 2
From: Automatic deep learning-based pleural effusion segmentation in lung ultrasound images
Fold | Set type | Test set | Expert |
|---|---|---|---|
T : Training | Patient # | Ground | |
V : Validation | Truths | ||
1 | T , V + 1 | (R1,2,3,4,5) | Expert 1 |
2 | T , V + 2 | (1,R2,3,4,5) | Expert 1 |
3 | T , V + 3 | (1,2,R3,4,5) | Expert 1 |
4 | T , V + 4 | (1,2,3,R4,5) | Expert 1 |
5 | T , V + 5 | (1,2,3,4,R5) | Expert 1 |
6 | T , V + 1 | (R6,2,3,4,5) | Expert 2 |
7 | T , V + 2 | (1,R7,3,4,5) | Expert 2 |
8 | T , V + 3 | (1,2,R8,4,5) | Expert 2 |
9 | T , V + 4 | (1,2,3,R9,5) | Expert 2 |
10 | T , V + 5 | (1,2,3,4,R10) | Expert 2 |