Abstract
Surgical skills are associated with clinical outcomes. To improve surgical skills and thereby reduce adverse outcomes, continuous surgical training and feedback is required. Currently, assessment of surgical skills is a manual and time-consuming process which is prone to subjective interpretation. This study aims to automate surgical skill assessment in laparoscopic cholecystectomy videos using machine learning algorithms. To address this, a three-stage machine learning method is proposed: first, a Convolutional Neural Network was trained to identify and localize surgical instruments. Second, motion features were extracted from the detected instrument localizations throughout time. Third, a linear regression model was trained based on the extracted motion features to predict surgical skills. This three-stage modeling approach achieved an accuracy of 87 ± 0.2% in distinguishing good versus poor surgical skill. While the technique cannot reliably quantify the degree of surgical skill yet it represents an important advance towards automation of surgical skill assessment.
Highlights
Surgical skills are associated with clinical outcomes
Another one exclusively relied on surgical videos and utilized a 3D convolutional neural network (CNN) to capture both spatial and temporal information for surgical skill prediction[21]
To apply automated surgical skill assessment to surgical practice it is necessary that machine learning models are based on data commonly recorded in surgery such as laparoscopic videos
Summary
Surgical skills are associated with clinical outcomes. To improve surgical skills and thereby reduce adverse outcomes, continuous surgical training and feedback is required. This study aims to automate surgical skill assessment in laparoscopic cholecystectomy videos using machine learning algorithms. A linear regression model was trained based on the extracted motion features to predict surgical skills. Methodologies have ranged from hidden markov chains[20] and traditional machine learning c lassifiers[14], over time series feature e xtraction[17,18] to CNNs15,16,21,22 These works provide an important contribution to the field their applicability in real-world clinical setting are limited as robotic surgeries are still rare and kinematics data frequently not available. To apply automated surgical skill assessment to surgical practice it is necessary that machine learning models are based on data commonly recorded in surgery such as laparoscopic videos. While being based on a small dataset these findings were promising and inspired us to suggest an extended modeling approach for surgical skill assessment
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
