Table 5.
Comparison of previous methods with the proposed IR-v2 Type 5 considering colon cancer histopathological WSI.
| Reference | Method | Results |
|---|---|---|
| [32] | ML-based feature extraction | Accuracy: 98.07% |
| [36] | Quasi supervised learning | Accuracy: 95% |
| [37] | Multi-class texture analysis | Accuracy: 84% |
| [39] | DCNN | Accuracy: 100% F1-score: 100% MCC: 100% |
| [40] | VGG-variant | Accuracy: 93.48% Sensitivity: 95.1% Specificity: 92.76% |
| [41] | AlexNet | Accuracy: 97.5% |
| [42] | VGG16 + LSTM | AUC: 0.69 |
| [43] | CNN + RNN | AUC: 0.99 |
| [44] | Inception-v3 | AUC: 0.988 |
| Proposed model | IR-v2 Type 5 | AUC: 0.99 |