Real-time AI-assisted Endocyroscopy for the Diagnosis of Colorectal Lesions

Plain-language summary

Colorectal cancer (CRC) is the third most common malignancy and the second leading cause of cancer-related death worldwide. Colonoscopy is considered the preferred method of screening for colorectal cancer, and early and resection detection of colorectal neoplastic lesions can significantly reduce colorectal cancer morbidity and mortality. In order to improve the diagnostic accuracy of endoscopy for colorectal lesions, many endoscopic techniques, such as image-enhanced endoscopy, including narrow band imaging (narrow-band imaging, NBI), magnifying endoscopy, pigment endoscopy, confocal laser endoscopy, and endocytoscopy(EC), are applied clinically. However, with the increasing number of endoscopic resection, the costs associated with the pathological diagnosis of endoscopic resection and resection specimens increase year by year. In clinical practice, some non-neoplastic colorectal lesions may not require resection, so it is important to identify the nature of the lesion during colonoscopy. Leveraging deep neural networks, AI systems support both computer-aided detection (CADe) and computer-aided classification (CADx). CADe specifically focuses on identifying polyps in colonoscopy, with the goal of reducing adenoma miss rates. Hovever, CADx can predict the pathology of the lesion based on the surface condition of the lesion. Endocytoscopy is a kind of ultra-high magnification endoscopy. But it is not something that can be easily mastered by endoscopic doctors. The investigators have previously developed an artificial intelligence system that can assist in endocytoscopy. The investigators plan to conduct a prospective, multicenter clinical trial to verify the accuracy of this CADx in predicting the histological characteristics of colorectal lesions during real-time endocytoscopy.

Who can participate

What they're measuring

Trial details