An Automated Machine Learning Framework for Surgical Suturing Action Detection under Class Imbalance
This work addresses the problem of real-time surgical action detection for machine guided training systems in laparoscopy surgical training and evaluation, which is significant for surgeons and medical training institutions.
The authors tackled the problem of detecting surgical suturing actions in real-time, achieving robust predictions across varying skill levels of surgeons with a rapid deployment approach. The approach demonstrated potential for quick, reliable, and effective real-time detection in surgical training environments.
In laparoscopy surgical training and evaluation, real-time detection of surgical actions with interpretable outputs is crucial for automated and real-time instructional feedback and skill development. Such capability would enable development of machine guided training systems. This paper presents a rapid deployment approach utilizing automated machine learning methods, based on surgical action data collected from both experienced and trainee surgeons. The proposed approach effectively tackles the challenge of highly imbalanced class distributions, ensuring robust predictions across varying skill levels of surgeons. Additionally, our method partially incorporates model transparency, addressing the reliability requirements in medical applications. Compared to deep learning approaches, traditional machine learning models not only facilitate efficient rapid deployment but also offer significant advantages in interpretability. Through experiments, this study demonstrates the potential of this approach to provide quick, reliable and effective real-time detection in surgical training environments