Table 3.

Deep Learning-Based Computer Vision Technologies for Analyzing Capsule Endoscopy Images

Study	No. of images for training	No. of images for testing	Outcome
Zou et al. [37]	60,000	15,000	Classify CE images according to the organ of origin, accuracy: 95%
Jia et al. [38]	8,200 (2,050 positives)	1,800 (800 positives)	Bleeding detection for annotated CE images, F1 score: 0.9955a)

CE, capsule endoscopy.

^a)The harmonic average of the precision and recall, $\mathrm{F}1=\frac{2\times Precision\times Recall}{Precision+Recall}$.