2026-10-13T06:02:17Z https://www.scidb.cn/oai

10.57760/sciencedb.31422 2026-10-05T18:53:06Z

2026-10-05 A large 4K dataset of supermicrosurgical anastomosis at the 0.2 mm scale doi:10.57760/sciencedb.31422 en Supermicrosurgery, involving vessels smaller than 0.8 mm, is an important emerging field in reconstructive surgery. Its development is limited by the lack of suitable training resources and the current performance of microsurgical robotic systems. Existing robots provide limited intelligent assistance, and their anastomosis procedures are significantly slower than manual techniques. In this study, we present a dataset of complete end-to-end anastomoses on 0.2 mm vessel models. The dataset includes 452 procedures performed by 571 operators from 158 hospitals across 28 provinces in China, with a total of 40.8 hours of 4K video (3840 × 2160 pixels). All procedures were performed using standardized microsurgical instruments and imaging settings to ensure consistency and comparability. The participants represented a wide range of experience levels, with completion times between 125 and 600 seconds, providing a broad spectrum of technical performance for analysis. Each procedure is accompanied by quantitative metadata, including completion time and expert-assessed performance scores based on predefined criteria, enabling objective evaluation of proficiency and analysis of performance-related factors. In addition, the dataset contains 47,452 segmentation annotation surgical frames, supporting computer vision studies. This dataset addresses the current gap in supermicrosurgical training data and serves both to support the development of surgical robotics and to improve human training through objective performance assessment. Its scale and standardized design provide a reliable basis for building intelligent assistance systems and establishing benchmarks for skill evaluation in supermicrosurgery. supermicrosurgery; anastomosis; dataset Jing Liang Jingyuan Fan Aihemaitijiang Yusufu Jianxi Hou Dewei Zhao Qingtang Zhu PUBLIC https://creativecommons.org/licenses/by/4.0/ dataset Science Data Bank