Developing and evaluating image-based metrics for open surgical suturing skill assessment
Global Surgical Education - Journal of the Association for Surgical Education · 13.10.2026 · 5 (1)
DOI: 10.1007/s44186-026-00596-2 ↗Kurz gefasst
Fachartikel in der Zeitschrift Global Surgical Education - Journal of the Association for Surgical Education, online erschienen am 13.10.2026. Verfasst von Jianxin Gao und 8 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electrical and Computer Engineering, Clemson University, Clemson, SC USA. Die Arbeit nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NHLBI NIH HHS, National Institutes of Health.
Abstract (Originalsprache)
Purpose
Open surgery training is vital in vascular surgery education. Traditionally, trainees’ open surgical suturing skills are evaluated by their educators, which is a subjective and time-consuming process. This paper evaluates image-based metrics for surgical suturing skill assessment by comparing performance among three groups: attending surgeons, resident surgeons, and novices.
Methods
A simulator, named SutureCoach, is developed to simulate a radial suturing task, performed either at “depth,” representing a cavity, or at “surface.” Among other sensors, the simulator includes cameras and computer vision software to track the motion of the needle and thread under the membrane being sutured. A set of image-based metrics are calculated for each suture based on video data. The set of metrics includes four previously proposed metrics as well as four new metrics inspired by a refined suturing phase segmentation scheme. To evaluate the performance of the image-based metrics, we conducted a study with 97 participants, divided almost evenly between attending surgeons, resident surgeons, and novices. Data was collected at several events over a 5-month period.
Results
The statistical analysis shows that all metrics have significantly different means when comparing performance between novices and surgeons at both conditions, surface and depth. Furthermore, seven out of eight metrics have significant mean differences when comparing resident surgeons’ and attending surgeons’ performance at the depth condition.
Conclusion
Image-based metrics are capable of suturing skill assessment, especially for distinguishing novices from surgeons. Depth constraints allow higher skill levels to be better differentiated.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Electrical and Computer Engineering, Clemson University, Clemson, SC USA.
- Department of Bioengineering, Clemson University, Clemson, SC USA.
- Division of Vascular Surgery, Baylor Scott & White Heart and Vascular Hospital, Dallas, TX USA.
- School of Mathematical and Statistical Sciences, Clemson University, Clemson, SC USA.
- School of Medicine, University of South Carolina, Greenville, SC USA.
ORCID-Profile: Richard E Groff
Förderung
- NHLBI NIH HHS
- National Institutes of Health
Zitieren
APA
Gao, J., Singh, S. P., Shayan, A. M., Eidt, J. F., Bible, J., Blas, J. V. V., Gandhi, S. S., Singapogu, R., & Groff, R. E. (2026). Developing and evaluating image-based metrics for open surgical suturing skill assessment. Global Surgical Education - Journal of the Association for Surgical Education, 5(1). https://doi.org/10.1007/s44186-026-00596-2
Vancouver
Gao J, Singh SP, Shayan AM, Eidt JF, Bible J, Blas JVV, et al. Developing and evaluating image-based metrics for open surgical suturing skill assessment. Global Surgical Education - Journal of the Association for Surgical Education. 2026;5(1). doi:10.1007/s44186-026-00596-2
BibTeX
@article{Gao2026,
author = {Gao, Jianxin and Singh, Simar P and Shayan, Amir Mehdi and Eidt, John F and Bible, Joe and Blas, Joseph Vincent Valentino and Gandhi, Sagar S and Singapogu, Ravikiran and Groff, Richard E},
title = {Developing and evaluating image-based metrics for open surgical suturing skill assessment},
journal = {Global Surgical Education - Journal of the Association for Surgical Education},
year = {2026},
volume = {5},
number = {1},
doi = {10.1007/s44186-026-00596-2}
}
EUVIMED