Establishment and validation of a computer-assisted colonic polyp localization system based on deep learning

Table 2 Potential causes of false negatives and false positives

Causes of false negatives	No. of images, n (%)	Causes of false positives1	No. of images, n (%)
Test dataset
Fecal fluid/bubble	17 (24)	Folds	18 (19)
Reflections of light	15 (21)	Reflections of light	17 (18)
Difficult angle	13 (19)	Fecal fluid/bubble	16 (17)
Shadow	8 (11)	Colonic valve	11 (12)
Fuzzy image	6 (9)	Ileocecal valve	7 (7)
Color of background	2 (3)	Fuzzy image	5 (5)
Far distance	2 (3)	Others2	11 (12)
Unclassified	7 (10)	Unclassified	10 (11)
Validation in clinical colonoscopy
Shadow	1 (33.3)	Folds3	276 (59.0)
Difficult angle	1 (33.3)	Reflections of light	89 (19.0)
Depressed lesion	1 (33.3)	Fecal fluid/bubble	43 (9.2)
		Normal structures4	46 (9.8)
		Other lesions5	14 (3.0)

¹Twelve lesions were considered to be missed by senior colonoscopists on colonoscopy.

²Others included color change (3), anus (3), lesions under the mucous (2), melanosis coli (1), and bloodstain (1).

³Sixteen folds were caused by suction.

⁴Normal structures included vessels (20), ileocecal valve (12), anus (8), and lymphoid follicle (6).

⁵Other lesions included ulcers (7), cysts under the mucous (4), and diverticulum (3).