Surgical Performance Analysis and Classification Based on Video Annotation of Laparoscopic Tasks

Abstract

Background and Objectives: Current approaches in surgical skills assessment employ virtual reality simulators, motion sensors, and task-specific checklists. Although accurate, these methods may be complex in the interpretation of the generated measures of performance. The aim of this study is to propose an alternative methodology for skills assessment and classification, based on video annotation of laparoscopic tasks. Methods: Two groups of 32 trainees (students and residents) performed two laparoscopic tasks: peg transfer (PT) and knot tying (KT). Each task was annotated via a video analysis software based on a vocabulary of eight surgical gestures (surgemes) that denote the elementary gestures required to perform a task. The extracted metrics included duration/counts of each surgeme, penalty events, and counts of sequential surgemes (transitions). Our analysis focused on trainees’ skill level comparison and classification using a nearest neighbor approach. The classification was assessed via accuracy, sensitivity, and specificity. Results: For PT, almost all metrics showed significant performance difference between the two groups ( p < 0.001). Residents were able to complete the task with fewer, shorter surgemes and fewer penalty events. Moreover, residents performed significantly fewer transitions ( p < 0.05). For KT, residents performed two surgemes in significantly shorter time ( p < 0.05). The metrics derived from the video annotations were also able to recognize the trainees’ skill level with 0.71 – 0.86 accuracy, 0.80 – 1.00 sensitivity, and 0.60 – 0.80 specificity. Conclusion: The proposed technique provides a tool for skills assessment and experience classification of surgical trainees, as well as an intuitive way for describing what and how surgemes are performed.

Machine learning for technical skill assessment in surgery: a systematic review

“…Bad performance when imbalanced sampling datasets. • k-means clustering 14 , 17 , 77 , 80 , 86 , 87 , 89 , 94 – 96 , 104 Naïve Bayes Supervised classification algorithm based on Bayes Theorem. The simplified from of the Bayes Algorithm—Naïve Bayes is built with the assumption that features are conditionally independent.…”

Surgical Gesture Recognition in Laparoscopic Tasks Based on the Transformer Network and Self-Supervised Learning

“…Figure 1 shows sample video frames for each task. More details may be found in our prior work [ 18 ].…”

“…In this study, we defined a vocabulary of nine elements to describe the surgical gestures involved in the performance of the two tasks: five gestures for PT and another four gestures for KT ( Table 1 ). This gesture decomposition was proposed in [ 18 ] and a similar definition of activities was utilized in [ 19 ]. The videos were annotated using Anvil 6.0 [ 20 ].…”

Effect of background music on STress Responses Amongst Undergraduates and Surgeons performing Simulated Surgical tasks: A randomised cross-over interventional trial (The STRAUSS Study)

“…Unsurprisingly, the greater experience was associated with improved speed and quality of the task performance. 58 59 A time x group interaction in HR is suggestive of attenuated cardiovascular reactivity to the task in the VS group, for whom the surgical task would have been more familiar. This is in line with previous work that has shown senior surgeons to display a better stress management capacity and are less prone to cognitive distraction compared to junior surgeons.…”