An AI Framework for Microanastomosis Motion Assessment
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911405512327168 |
|---|---|
| author | Meng, Yan Torres-Rodríguez, Eduardo J. Altshuler, Marcelle Gowda, Nishanth Naeem, Arhum Yilmaz, Recai Arnaout, Omar Donoho, Daniel A. |
| author_facet | Meng, Yan Torres-Rodríguez, Eduardo J. Altshuler, Marcelle Gowda, Nishanth Naeem, Arhum Yilmaz, Recai Arnaout, Omar Donoho, Daniel A. |
| contents | Proficiency in microanastomosis is a fundamental competency across multiple microsurgical disciplines. These procedures demand exceptional precision and refined technical skills, making effective, standardized assessment methods essential. Traditionally, the evaluation of microsurgical techniques has relied heavily on the subjective judgment of expert raters. They are inherently constrained by limitations such as inter-rater variability, lack of standardized evaluation criteria, susceptibility to cognitive bias, and the time-intensive nature of manual review. These shortcomings underscore the urgent need for an objective, reliable, and automated system capable of assessing microsurgical performance with consistency and scalability. To bridge this gap, we propose a novel AI framework for the automated assessment of microanastomosis instrument handling skills. The system integrates four core components: (1) an instrument detection module based on the You Only Look Once (YOLO) architecture; (2) an instrument tracking module developed from Deep Simple Online and Realtime Tracking (DeepSORT); (3) an instrument tip localization module employing shape descriptors; and (4) a supervised classification module trained on expert-labeled data to evaluate instrument handling proficiency. Experimental results demonstrate the effectiveness of the framework, achieving an instrument detection precision of 97%, with a mean Average Precision (mAP) of 96%, measured by Intersection over Union (IoU) thresholds ranging from 50% to 95% (mAP50-95). |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_21120 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | An AI Framework for Microanastomosis Motion Assessment Meng, Yan Torres-Rodríguez, Eduardo J. Altshuler, Marcelle Gowda, Nishanth Naeem, Arhum Yilmaz, Recai Arnaout, Omar Donoho, Daniel A. Computer Vision and Pattern Recognition Proficiency in microanastomosis is a fundamental competency across multiple microsurgical disciplines. These procedures demand exceptional precision and refined technical skills, making effective, standardized assessment methods essential. Traditionally, the evaluation of microsurgical techniques has relied heavily on the subjective judgment of expert raters. They are inherently constrained by limitations such as inter-rater variability, lack of standardized evaluation criteria, susceptibility to cognitive bias, and the time-intensive nature of manual review. These shortcomings underscore the urgent need for an objective, reliable, and automated system capable of assessing microsurgical performance with consistency and scalability. To bridge this gap, we propose a novel AI framework for the automated assessment of microanastomosis instrument handling skills. The system integrates four core components: (1) an instrument detection module based on the You Only Look Once (YOLO) architecture; (2) an instrument tracking module developed from Deep Simple Online and Realtime Tracking (DeepSORT); (3) an instrument tip localization module employing shape descriptors; and (4) a supervised classification module trained on expert-labeled data to evaluate instrument handling proficiency. Experimental results demonstrate the effectiveness of the framework, achieving an instrument detection precision of 97%, with a mean Average Precision (mAP) of 96%, measured by Intersection over Union (IoU) thresholds ranging from 50% to 95% (mAP50-95). |
| title | An AI Framework for Microanastomosis Motion Assessment |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2601.21120 |