Table 12 Paired t-test results comparing hybrid ResUNet to the baseline model
From: Skin lesion segmentation using deep learning algorithm with ant colony optimization
Metric | Model | Mean value (%) | 95% CI | p-value |
|---|---|---|---|---|
Accuracy | Hybrid ResUNet (Proposed) | 95.8 | 94.5—97.1 |  < 0.01 |
Baseline Model | 92.1 | 90.8—93.4 |  | |
Dice coefficient | Hybrid ResUNet (Proposed) | 93.1 | 91.9—94.3 |  < 0.01 |
Baseline Model | 88.4 | 87.1—89.7 |  | |
Jaccard index | Hybrid ResUNet (Proposed) | 87.5 | 85.9—89.1 |  < 0.01 |
Baseline Model | 81.0 | 79.5—82.5 |  |