ASGE Annual Postgraduate Course: Clinical Challenges and Real-Time Decision Making in GI Endoscopy (On-demand)

Video Transcription

Video Summary

In this video, Dr. Yuichi Mori, a Japanese gastroenterologist, discusses computer vision in endoscopy. He explains that computer vision is a computational task and that machine learning and AI play important roles in optimizing computer vision. Dr. Mori presents examples of computer vision in endoscopy, including edge detection, optical flow, image stitching, and image processing. He also discusses the roles of AI in endoscopy, such as computer-aided detection, computer-aided diagnosis, and computer-aided quality assurance. Dr. Mori emphasizes the importance of understanding AI and deep learning, as well as the difference between conventional machine learning methods and deep learning. He explains the significance of data and the need for a large volume of images for machine learning models. Dr. Mori also discusses potential pitfalls in machine learning, such as patient-level overlap, data leakage, and exclusion of real-world data. He emphasizes the importance of optimizing the dataset by considering quantity, variety, and reliable labeling. To further explore AI in endoscopy, Dr. Mori recommends a textbook published in GUT in 2020.

Asset Subtitle

Yuichi Mori, MD, PhD, FASGE

Keywords

computer vision

endoscopy

machine learning

AI

deep learning