Assessment of Open Surgery Suturing Skill: Image-based Metrics Using Computer Vision.

Area of Science:

• Surgical Skill Assessment
• Medical Simulation
• Computer Vision in Surgery

Background:

• Suturing is a fundamental surgical skill.
• Objective assessment of suturing proficiency is challenging.
• Existing methods often lack quantitative, process-based metrics.

Purpose of the Study:

• To develop and validate a computer vision algorithm for extracting image-based metrics of suturing skill.
• To assess the performance differences between surgical residents and attending surgeons using these novel metrics.
• To explore the potential of these metrics for surgical training and education.

Main Methods:

• Utilized a suturing simulator adapted from the Fundamentals of Vascular Surgery (FVS) radial task.
• Employed a camera positioned beneath the suturing membrane to capture needle and thread dynamics.
• Developed a computer vision algorithm to analyze video data and extract objective, image-based performance metrics.

Main Results:

• The algorithm successfully extracted 9 image-based metrics, including 4 novel ones: Needle Tip Path Length, Needle Swept Area, Needle Tip Area, and Needle Sway Length.
• Statistically significant differences in performance were observed between attending surgeons and residents across 6 of the 9 metrics.
• The results indicate a clear distinction in suturing technique based on experience level.

Conclusions:

• The developed image-based metrics provide objective, quantitative assessments of suturing skill.
• Graphical representation of these metrics can facilitate surgical training and skill development.
• This computer vision approach holds significant potential for enhancing the assessment and training of open surgical suturing proficiency.