Development of Computer Vision Algorithm towards Assessment of Suturing Skill

Irfan Kil • Anand Jagannathan • Ravikiran Singapogu • Richard E Groff

09:05 - 09:55 | Thursday 16 February 2017 | Ballroom D


In this paper, we present a computer vision algorithm to extract key information pertinent to assessing surgical suturing. This algorithm uses an instrumented platform designed to quantify suturing skill. As subjects performed suturing on the platform, the vision algorithm computes the time and the location of suture needle's entry and exit, stitch length, needle trace, and hesitation time, which were identified as potential metrics to assess suturing skill. Preliminary experimental data from a study with 14 subjects with minimal suturing experience are presented. The results demonstrate that the algorithm is feasible for use in quantifying suturing expertise.