Research Article
[Retracted] Automatic COVID-19 Lung Infection Segmentation through Modified Unet Model
Table 3
State-of-the-art comparison in terms of IoU, dice, recall, F1 score, precision, and accuracy.
| Source | Models | Acc | IoU | Dice | Recall | F1-score | Precision |
| [26] | 3D Unet | — | — | 61.0 | 62.8 | | 74.1 | [27] | Encoder-decoder method | — | — | 78.6 | 71.1 | 78.4 | 85.6 | [28] | AU-Net + FTL | — | — | 69.1 | 81.1 | — | — | [29] | Multiple deep CNN | 95.23 | — | 88.0 | 90.2 | — | — | [30] | Imagenet, VGG16 FCN8 | — | 60.0 | 75.0 | 92.0 | — | 63.0 | [31] | DDANet | — | — | 77.89 | 88.40 | — | — | [32] | ADID-Unet | 97.01 | — | 80.31 | 79.73 | 82.00 | 84.0 | [33] | Semi-Inf-Net | — | — | 73.01 | 72.00 | — | — | [12] | Unet | 91.78 | 82.83 | 90.43 | 91.33 | 91.82 | 92.31 | | Ours | 93.29 | 86.96 | 92.46 | 93.01 | 93.34 | 93.67 |
|
|