Table 1.
State-of-the-Art Deep Learning Based Methods for Capsule Endoscopy
| Study | Class | No. of training/testing images | No. of patients or videos | Features | Accuracy | Sensitivity/Specificity |
|---|---|---|---|---|---|---|
| Zou et al. (2015) [27] | Localizationa) | 60K/15K | 25 patients | Alexnet | 95.5% | No info. |
| Seguí et al. (2016) [28] | Scene classificationb) | 100K/20K | 50 videos | CNN | 96.0% | No info. |
| Jia et al. (2016) [29] | Bleeding | 8.2K/1.8K | No info. | Alexnet | 99.9% | 99.2%/No info. |
| Li et al. (2017) [30] | Haemorrhage | 9,672/2,418 | No info. | LeNet | 100% | 98.7%/No info. |
| AlexNet | ||||||
| GoogLeNet | ||||||
| VGG-Net | ||||||
| Yuan et al. (2017) [32] | Polyp | 4,000 (No info.) | 35 patients | SSAE | 98.0% | No info. |
| Iakovidis et al. (2018) [34] | Various lesionsc) | 465/233 | 1,063 volunteers | CNN | 96.3% | 90.7%/88.2% |
| 852/344 | No info. | |||||
| He et al. (2018) [33] | Hookworm | 400K/40K | 11 patients | CNN | 88.5% | 84.6%/88.6% |
| Leenhardt et al. (2018) [31] | Angiectasia | 600/600 | 200 videos | CNN | No info. | 100%/96% |
CNN, convolutional neural networks; SSAE, stacked sparse autoencoder.
a)
Localization, Localization of stomach, small intestine, colon.
b)
Scene classification, Scene classification of Bubble, wrinkle, turbid, wall, clear.
c)
Various lesions, Gastritis, Cancer, bleeding, ulcer.