AI-powered breakthrough boosts early cancer detection rates
The team has pioneered an AI-powered surgical assistance platform, AI-Endo, to facilitate ESD.
CU Medicine is pioneering a transformative approach in the fight against gastrointestinal cancers. By applying AI to endoscopic procedures, CU Medicine is enhancing the accuracy of early cancer detection and improving the training of the next generation of endoscopists. Results have been published in international journals Nature Communications and Clinical Gastroenterology and Hepatology.
Endoscopic examinations are critical for identifying tumours known as adenomas, which are common precursors to colorectal cancer. However, the effectiveness of these procedures is largely dependent on the size, shape and location of the adenoma as well as the experience of the endoscopist. To address this, CU Medicine has validated a cutting-edge AI-assisted colonoscopy system that offers real-time analysis of endoscopic images, enabling immediate identification of potential adenomas and tumours.
Empowering the next generation of endoscopists
A CU Medicine study conducted between April 2021 and July 2022 has demonstrated the potentially transformative impact of AI assistance. The study involved 22 junior endoscopists-in-training who performed colonoscopies on 766 patients, around half of which used AI assistance and half of which used conventional methods.
The results were striking: with AI assistance, there was a relative increase of approximately 40% in the adenoma detection rate. This demonstrates the promise of AI in clinical practice and highlights how it can enhance the skills of less experienced medical professionals.
Dr. Louis Lau of the Department of Medicine and Therapeutics said, ‘Junior endoscopists are generally less skillful and require a higher level of assistance during their initial learning phases. Our research is significant for endoscopic training because it shows that the use of AI provides them with imagery guidance to practice the skills in a more standardised manner.’
Bringing AI to the operating room
Furthermore, CU Medicine has pioneered an AI-powered surgical assistance platform, AI-Endo, designed to facilitate endoscopic submucosal dissection (ESD), a complex procedure required for the resection of early-stage GI cancer. The AI-Endo system was trained using an extensive dataset of over two million video image frames taken from past ESD procedures.
Prof. Qi Dou of the Department of Computer Science and Engineering explained, ‘The AI interface is able to discern real-time procedures while the doctor performs ESD, guide the doctor during the process, and provide data for postoperative analysis and review.’
Given that more and more people are detected of having early-stage GI cancers through screening programmes, Al-Endo’s ability to provide a step-by-step guide during the ESD process is a major leap forward. It not only enhances the quality of the procedure but also significantly reduces the steep learning curve for trainee endoscopists.
Prof. Philip Chiu of the Department of Surgery said, ‘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. 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.’
Read more: