A single-center prospective study evaluating the usefulness of artificial intelligence for the diagnosis of esophageal squamous cell carcinoma in a real-time setting

Table 1 Characteristics of the patients and lesions

Characteristics			Value
Patient data (n = 380)
	Sex, male/female		306/74
	Median age, y (range)		72 (49–88)
	Number of lesions, ESCC/noncancerous		44/193
Lesion data (n = 237)
	ESCC (n = 44)
		Location: Ce/Ut/Mt/Lt/Ae	1/7/21/14/1
		Median diameter, mm (range)	8 (3–50)
		Macroscopic type: 0-I/0-IIa/0-IIb/0-IIc	0/1/33/10
		Invasion depth^†: EP/LPM/MM-SM2	17/17/0
	noncancerous (n = 193)
		SIN/atypical epithelium/esophagitis/no malignancy/others^‡	36/45/26/75/11

Ae, abdominal esophagus; Ce, cervical esophagus; ESCC, esophageal squamous cell carcinoma; EP, epithelium; LPM, lamina propria; Lt, lower thoracic esophagus; MM, muscularis mucosa; Mt, middle thoracic esophagus; SM, submucosa; SIN, squamous intraepithelial neoplasia; Ut, upper thoracic esophagus.
^†Ten ESCCs diagnosed by biopsy were excluded from analysis of invasion depth.
^‡e.g., glycogenic acanthosis and ectopic gastric mucosa

ISSN: 1471-230X