AFEF 2026 vs CoLo

L’application AFEF vous permet d’avoir accès au direct du congrès, au programme, aux résumés, au plan de l’exposition, à la liste des partenaires, mais également de participer au congrès en posant des questions aux intervenants, en votant, etc

Over the past several years, it has been clearly demonstrated that patient management in colonoscopy can be optimized — both economically and environmentally — by refraining from systematically submitting all resected colonic polyps for histopathological examination, provided that these polyps meet specific visual and dimensional criteria. Despite this proven benefit and the publication of international recommendations by the American Society for Gastrointestinal Endoscopy (ASGE, 2014) and the European Society of Gastrointestinal Endoscopy (ESGE, 2022), the practical implementation of selective histopathological analysis (Resect-and-Discard and Diagnose-and-Leave strategies) remains limited. This gap between recommendations and clinical practice is primarily due to the challenges associated with the training, certification, and objective evaluation of endoscopists’ ability to characterize polyps accurately. Furthermore, even with the integration of artificial intelligence (AI), current systems still fall short of the reliability thresholds required by professional societies. Colo-ID has been developed to address these unmet needs. The application provides a comprehensive training and assessment platform designed for endoscopists. It includes a learning module and an interactive training environment that allow users to review a large number of annotated endoscopic images and to evaluate their diagnostic accuracy, characterization skills, and therapeutic decision-making performance. Additionally, Colo-ID quantifies and displays the potential economic savings and carbon footprint reduction associated with the application of the Resect-and-Discard and Diagnose-and-Leave approaches. Finally, the platform also supports the creation and continuous enrichment of a structured database linking endoscopic image features with corresponding histopathological findings. This resource will contribute to the development and training of AI-based decision-support algorithms, with the long-term goal of improving the accuracy, safety, and sustainability of colorectal cancer prevention strategies.