Linked-color imaging with or without artificial intelligence for adenoma detection: a randomized trial

Area of Science:

• Gastroenterology
• Medical Imaging
• Endoscopy

Background:

• Adenoma detection rate (ADR) is a key metric for colonoscopy quality and colorectal cancer (CRC) prevention.
• Linked-color imaging (LCI) and LCI with artificial intelligence (LCA) both enhance adenoma detection, but comparative efficacy is unclear.

Purpose of the Study:

• To compare the adenoma detection rate (ADR) between linked-color imaging with artificial intelligence (LCA) and linked-color imaging (LCI) alone.
• To evaluate the impact of endoscopist experience and polyp size on ADR in both imaging modalities.

Main Methods:

• A randomized controlled trial comparing LCA and LCI in patients undergoing colonoscopy.
• Data collected included ADR, adenoma per colonoscopy (APC), and polyp characteristics.

Main Results:

• LCA demonstrated a significantly higher ADR (58.8%) compared to LCI (43.5%).
• LCA also showed a higher mean APC and detected more non-polypoid and small adenomas (≤9mm).
• No significant difference in ADR was observed between expert and trainee endoscopists within each group.

Conclusions:

• Linked-color imaging with artificial intelligence (LCA) is superior to LCI alone for improving adenoma detection during colonoscopy.
• LCA enhances the detection of various adenoma types, including small and non-polypoid lesions.