Challenges in surgical video annotation

Computer Assisted Surgery

Danyal M. Fer¹  Thomas M. Ward²  Ozanan R. Meireles²  Daniel A. Hashimoto²  Yutong Ban³  Guy Rosman³ 

[1] Department of Surgery, University of California San Francisco East Bay, Hayward, CA, US;Surgical AI & Innovation Laboratory, Department of Surgery, Massachusetts General Hospital, Boston, MA, US;Surgical AI & Innovation Laboratory, Department of Surgery, Massachusetts General Hospital, Boston, MA, US;Distributed Robotics Laboratory, Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA, US;

关键词: Surgical video;    Annotation;    Image classification;    Object detection;    Semantic segmentation;    temporal annotation;    inter-rater reliability;   

DOI  :  10.1080/24699322.2021.1937320

来源: Taylor & Francis

【 摘 要 】

Annotation of surgical video is important for establishing ground truth in surgical data science endeavors that involve computer vision. With the growth of the field over the last decade, several challenges have been identified in annotating spatial, temporal, and clinical elements of surgical video as well as challenges in selecting annotators. In reviewing current challenges, we provide suggestions on opportunities for improvement and possible next steps to enable translation of surgical data science efforts in surgical video analysis to clinical research and practice.

【 授权许可】

CC BY