Developing an Artificial Intelligence (AI)-based self-training platform for laparoscopic surgery

Various research throughout the years have been devoted to exploring different and more effective ways of training for laparoscopy, within the conventional frameworks of using box trainers and virtual reality simulators. However, the incremental ameliorations within these frameworks have not been sufficient to meet the medical need of training a greater number of laparoscopy surgeons in shorter times. The laparoscopic training method with Artificial Intelligence (AI) would address the core challenges that have not been met with the current training platforms: i) wide accessibility, ii) self-training with effective and immediate feedback, iii) scalability (low cost) to be widely applied in any country (low- and middle-income countries). This project will be involved in developing a fully autonomous laparoscopy self-training system that provides insightful, intuitive, and timely feedback for improvement. We will develop machine vision and machine learning techniques and integrate those with physical box trainers. The autonomous and Intelligent Laparoscopy (AILap) Trainer with Real-Time Feedback system will be tested on commonly performed laparoscopic procedures associated with proficiency-gain/learning curve and that involves laparoscopic suturing as an unreplaceable skill (e.g., laparoscopic fundoplication, laparoscopic gastric-bypass of bariatric surgery, and laparoscopic closure of common bile duct after common bile exploration).

Diversity statement

Our research community thrives on the diversity of students and staff which helps to make the University of Dundee a UK university of choice for postgraduate research. We welcome applications from all talented individuals and are committed to widening access to those who have the ability and potential to benefit from higher education.