Background & aims: Both Computer-aided detection (CADe)- assisted and Endocuff-assisted colonoscopy have shown to increase adenoma detection. We investigated the performance of the combination of the two tools compared to CADe-assisted colonoscopy alone to detect colorectal neoplasias during colonoscopy in a multicenter randomized trial. Methods: Men and women undergoing colonoscopy for CRC screening, polyp surveillance, or clincial indications at 6 centers in Italy and Switzerland were enrolled. Patients were assigned (1:1) to colonoscopy with the combinations of CADe (GI-Genius, Medtronic) and a mucosal exposure device (Endocuff Vision -ECV-, Olympus) or to CADe-assisted colonoscopy alone (control group). All detected lesions were removed and sent to histopathology for diagnosis. The primary outcome was adenoma detection rate (ADR, the percentage of patients with at least 1 histologically proven adenoma or carcinoma). Secondary outcomes were adenomas detected per colonoscopy, advanced adenomas and serrated lesions detection rate, the rate of unnecessary polypectomies (polyp resection without histologically proven adenomas), and withdrawal time. Results: From July 1, 2021 to May 31, 2022, 1316 subjects were randomized and eligible for analysis; 660 to the ECV group, 656 to control group). The ADR was significantly higher in the ECV group (49.6%) than in the control group (44.0%) (relative risk [RR], 1.12; 95% confidence interval [CI], 1.00-1.26; p = 0.04). Adenomas detected per colonoscopy were significantly higher in the ECV group (mean, 0.94+0.54) than in the control group (0.74+0.21) (incidence rate ratio, 1.26; 95% CI: 1.04-1.54; p: 0.02). The two groups did not differ in term of detection of advanced adenomas and serrated lesions. There was no significant difference between groups in withdrawal time (9.01±2.48 seconds for the ECV group vs 8.96 ±2.24 for controls; P = 0.69) or proportion of subjects undergoing unnecessary polypectomies (RR: 0.89; 95% CI: 0.69-1.14. p: 0.38). Conclusions: The combination of CADe and EndocuffVision during colonoscopy increases ADR and adenomas detected per colonoscopy without increasing withdrawal time compared to CADe alone. Clinicaltrials: gov no: NCT04676308.
Combination of mucosa-exposure device and computer-aided detection for Adenoma Detection during Colonoscopy: a randomized trial
Facciorusso, Antonio;
2023-01-01
Abstract
Background & aims: Both Computer-aided detection (CADe)- assisted and Endocuff-assisted colonoscopy have shown to increase adenoma detection. We investigated the performance of the combination of the two tools compared to CADe-assisted colonoscopy alone to detect colorectal neoplasias during colonoscopy in a multicenter randomized trial. Methods: Men and women undergoing colonoscopy for CRC screening, polyp surveillance, or clincial indications at 6 centers in Italy and Switzerland were enrolled. Patients were assigned (1:1) to colonoscopy with the combinations of CADe (GI-Genius, Medtronic) and a mucosal exposure device (Endocuff Vision -ECV-, Olympus) or to CADe-assisted colonoscopy alone (control group). All detected lesions were removed and sent to histopathology for diagnosis. The primary outcome was adenoma detection rate (ADR, the percentage of patients with at least 1 histologically proven adenoma or carcinoma). Secondary outcomes were adenomas detected per colonoscopy, advanced adenomas and serrated lesions detection rate, the rate of unnecessary polypectomies (polyp resection without histologically proven adenomas), and withdrawal time. Results: From July 1, 2021 to May 31, 2022, 1316 subjects were randomized and eligible for analysis; 660 to the ECV group, 656 to control group). The ADR was significantly higher in the ECV group (49.6%) than in the control group (44.0%) (relative risk [RR], 1.12; 95% confidence interval [CI], 1.00-1.26; p = 0.04). Adenomas detected per colonoscopy were significantly higher in the ECV group (mean, 0.94+0.54) than in the control group (0.74+0.21) (incidence rate ratio, 1.26; 95% CI: 1.04-1.54; p: 0.02). The two groups did not differ in term of detection of advanced adenomas and serrated lesions. There was no significant difference between groups in withdrawal time (9.01±2.48 seconds for the ECV group vs 8.96 ±2.24 for controls; P = 0.69) or proportion of subjects undergoing unnecessary polypectomies (RR: 0.89; 95% CI: 0.69-1.14. p: 0.38). Conclusions: The combination of CADe and EndocuffVision during colonoscopy increases ADR and adenomas detected per colonoscopy without increasing withdrawal time compared to CADe alone. Clinicaltrials: gov no: NCT04676308.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
