Research Article
An Automatic Gastrointestinal Polyp Detection System in Video Endoscopy Using Fusion of Color Wavelet and Convolutional Neural Network Features
Table 1
Comparison among different polyp detection.
| Paper | Used methodology | Used dataset | Result | Accuracy | Sensitivity | Specificity |
| Kodogiannis et al. [3] | Texture + ANFIS | 140 images | | 97% | | Park et al. [13] | CNN + CRF | 35 videos | | 86% | 85% | Ribeiro et al. [9] | CNN | 100 images | 90.96% | 95.16% | 74.19% | Zhu et al. [7] | CNN + SVM | 180 images | 80% | 79% | 79.54% | Alexandre et al. [4] | RGB + XY + SVM | 4620 images | 94.87% | | | Zou et al. [6] | DCNN | 25 videos | 95% | | | Li et al. [5] | Color + shape + MLP | 450 images | 94.20% | 95.07% | 93.33% | Karkanis et al. [1] | CWC + LDA | 60 videos | | 97% | 90% | Iakovidis et al. [2] | KL + wavelet + SVM | 86 videos | 94% | | | Proposed system | Color wavelet + CNN + SVM | 100 videos | 98.65% | 98.79% | 98.52% |
|
|