Research Article
Exploring Deep Learning and Transfer Learning for Colonic Polyp Classification
Table 6
Results from i-Scan1 database with images resized to 224 × 224 and cropped in 25 patches of size 224 × 224.
| | CNN-F | CNN-M | CNN-S | CNN-F MCN | CNN-M MCN | CNN-S MCN | Google LeNet | VGG VD16 | VGG VD19 | AlexNet | AlexNet MCN | |
| Resizing image | 89.33 | 90.67 | 90.00 | 82.00 | 90.67 | 91.42 | 90.67 | 85.33 | 82.67 | 87.33 | 84.67 | 87.70 | Cropping 25 images | 84.00 | 82.67 | 84.67 | 78.67 | 84.67 | 88.67 | 91.29 | 89.67 | 78.67 | 85.33 | 85.33 | 84.87 |
|
|