Deep Convolutional Neural Network for Ulcer Recognition in Wireless Capsule Endoscopy: Experimental Feasibility and Optimization

Table 1

Representative studies and datasets of WCE videos in the literature.

Experiment	Cases	Detail
Li and Meng [5]	10 patients’ videos	10 patients’ videos, 200 images
Li and Meng [16]	10 patients’ videos	10 patients’ videos (five for bleeding and the other five for ulcer)
Li et al. [17]	—	80 representative small intestine ulcer WCE images and 80 normal images
Karargyris and Bourbakis [9]	—	A WCE video containing 10 frames with polyps and 40 normal frames and extra 20 frames with ulcer
Li and Meng [8]	10 patients’ videos	10 patients’ videos, 600 representative polyp images and 600 normal images from data; 60 normal images and 60 polyp images from each patient’s video segments
Yu et al. [10]	60 patients’ videos	60 patients’ videos, 344 endoscopic images for training; another 120 ulcer images and 120 normal images for testing
Fu et al. [12]	20 patients’ videos	20 patients’ videos, 5000 WCE images consisting of 1000 bleeding frames and 4000 nonbleeding frames
Yeh et al. [11]	—	607 images containing 220, 159, and 228 images of bleeding, ulcers, and nonbleeding/ulcers, respectively
Yuan et al. [3]	10 patients’ videos	10 patients’ videos, 2400 WCE images that consist of 400 bleeding frames and 2000 normal frames
Yuan and Meng [7]	35 patients’ videos	35 patients’ videos, 3000 normal WCE images (1000 bubbles, 1000 TIs, and 1000 CIs) and 1000 polyp images
He et al. [6]	11 patients’ videos	11 patients’ videos, 440K WCE images
Aoki et al. [18]	180 patients’ videos	115 patients’ videos, 5360 images of small-bowel erosions and ulcerations for training; 65 patients’ videos, 10,440 independent images for validation
Ours	1,416 patients’ videos	1,416 patients’ videos with 24,839 representative ulcer frames