The Chinese University of Hong Kong's Faculty of Medicine (CU Medicine) has completed two groundbreaking studies demonstrating that artificial intelligence (AI) technology significantly enhances gastrointestinal cancer diagnosis and treatment while providing valuable training support for junior endoscopists.
Researchers found that AI-assisted colonoscopy increased adenoma detection rates by approximately 40% among less experienced endoscopists, according to findings published in the prestigious journals Nature Communications and Clinical Gastroenterology and Hepatology.
AI Dramatically Improves Adenoma Detection in Junior Endoscopists
Most colorectal cancers develop from adenomas, making their detection during colonoscopy critical for cancer prevention. However, detection accuracy varies considerably based on adenoma characteristics and physician experience.
To address this challenge, CU Medicine conducted a study between April 2021 and July 2022 involving 22 junior endoscopists-in-training with less than three years of experience and fewer than 500 procedures performed. The study included 766 patients, with 386 receiving AI-assisted colonoscopy and the remainder undergoing conventional procedures without AI assistance.
The results were striking: junior endoscopists achieved approximately 40% higher adenoma detection rates when using AI-assisted technology. The improvement was even more pronounced among beginners.
"Our research is significant to the future development of AI in clinical medicine and endoscopic training," said Dr. Louis Lau Ho-shing, Assistant Professor in the Department of Medicine and Therapeutics at CU Medicine. "Junior endoscopists are generally less skilful and require a higher level of assistance during their initial learning phases. Our research shows that AI provides them with imagery guidance to practice skills in a more standardized manner."
While previous international studies had demonstrated AI's benefits in colonoscopy, most involved experienced practitioners, leaving a significant knowledge gap regarding its impact on those still in training.
AI-Endo: A New Platform for Early-Stage GI Cancer Treatment
Building on their success with diagnostic applications, the CU Medicine team has also developed an AI surgical assistance platform called AI-Endo to support endoscopic submucosal dissection (ESD), a complex procedure for removing early-stage gastrointestinal cancers.
ESD, first introduced to Hong Kong by CU Medicine in 2004, requires specialized technical skills and extensive experience. The increasing detection of early-stage GI cancers through screening programs and AI diagnostic systems has created urgent demand for more trained endoscopists capable of performing this minimally invasive procedure.
Professor Dou Qi, Assistant Professor in CUHK's Department of Computer Science and Engineering, explained the platform's development: "To train AI-Endo, we compiled 47 complete ESD video clips spanning 12 years, consisting of over 2 million frames. This allowed it to learn the entire surgical workflow and dissect each real-time action."
The system guides physicians through the ESD procedure in real-time and provides data for post-operative analysis. Study results demonstrated that AI-Endo enabled endoscopists still in training to successfully complete ESD procedures in animal models.
National Implications for Minimally Invasive Surgery
Professor Philip Chiu Wai-yan, Professor and Head of Upper Gastrointestinal and Metabolic Surgery at CU Medicine and Director of Chow Yuk Ho Technology Centre for Innovative Medicine, highlighted the broader significance of these advances.
"The National Health Commission of the PRC has called for the promotion of minimally invasive surgery including endoscopic interventions across the nation as part of the National 14th Five-Year Plan, and encouraged innovation and knowledge transfer," said Professor Chiu. "As CU Medicine is a pioneer in the research and application of endoscopic technology, both in Hong Kong and globally, I believe its experience and expertise in healthcare and innovation can further the achievements of the nation and benefit more patients."
These developments represent significant progress in democratizing advanced endoscopic skills, potentially improving colorectal cancer detection and treatment outcomes while accelerating the training of the next generation of endoscopists.
