Objective:To develop an diagnostic equipment with artificial intelligence (AI) real-time assistance under endoscopy (endoscopic AI equipment) for the detection of gastrointestinal protruding lesions, and to evaluate its performance and safety.Methods:From January to December 2017, at Endoscopy Center of West China Hospital, Sichuan University, the endoscopic images of individuals who underwent routine gastroscopy and colonoscopy were collected. The model was established based on convolutional neural network and the endoscopic AI equipment was developed. From June to December 2019, a prospective, single center, blinded and parallel controlled study was conducted to compare the differences in evaluation of protruding lesions of the same patient under gastroscopy or colonoscopy between endoscopist and the endoscopic AI equipment and to evaluated the impact of lesion size (lesions <5 mm and ≥5 mm) on the detection of endoscopic AI equipment. The main outcome measure was the detection time difference in reporting the protruding lesion between endoscopic AI equipment and endoscopist; and the secondary indicator was the accuracy of endoscopic AI equipment in detecting the protruding lesion. Wilcoxon rank sum test and chi-square test were used for statistical analysis.Results:A total of 71 582 white light endoscopy images were used for endoscopic AI equipment training, which included 41 376 images of protruding lesions. The endoscopic AI equipment was successfully developed and obtained the registration certificate of medical devices of the People′s Republic of China (Sichuan Instrument Standard, 20202060049). The accuracy, sensitivity, and specificity of endoscopic AI equipment in detecting protruding lesions were 96.4%, 95.1% and 92.8%, respectively. The detection time of each protruding lesions under gastroscopy of endoscopic AI equipment was 1.524 seconds faster than that of endoscopist; but the detection time of each protruding lesions under colonoscopy was 0.070 seconds slower than that of endoscopist, and the differences were statistically significant ( Z=-5.505 and -4.394, both P<0.01). The detection time of each protruding lesions under gastroscopy or colonoscopy of endoscopic AI equipment was not inferior to that of endoscopist. The detection rate of protruding lesions under colonoscopy by endoscopic AI equipment was 89.9% (249/277) and the sensitivity was 89.9%; the detection rate of protruding lesions under colonoscopy was 87.0% (450/517) and the sensitivity was 86.9%. There were no statistically significant differences in the detection time difference, sensitivity and missed diagnostic rate between the lesions <5 mm and ≥5 mm detected by endoscopic AI equipment under gastroscopy (all P>0.05). The sensitivity of endoscopic AI equipment in detecting the lesions ≥5 mm under colonoscopy was higher than that of lesions <5 mm (96.8% vs. 84.9%), and the missed diagnostic rate was lower than that of lesions <5 mm (3.2%, 3/94 vs. 15.1%, 61/405), and the differences were statistically significant ( χ2=9.615 and 9.612, both P=0.002). No adverse events on patients and medical staffs occurred, and there were no cases of equipment electricity leakage, and abnormal work reported during the use of endoscopic AI equipment. Conclusions:The endoscopic AI equipment can report the protruding lesions simultaneously with endoscopists, and the accuracy is close to 90%, which is expected to be a practical assistant for endoscopists to avoid missed detection of protruding lesions.