HemoSet
收藏资源简介:
HemoSet是由加州大学圣地亚哥分校创建的第一个血液分割数据集,专注于自动化止血管理。该数据集包含102,616个标记帧,用于训练和改进血液分割模型,以支持自动化血液吸引工具的开发。数据集通过在活体动物机器人手术中识别血管并诱导出血来收集,模拟了手术中常见的血液池形成条件。HemoSet的应用领域包括手术中血液损失的估计、辅助助手操作吸引工具以及自动识别关键出血区域,旨在提高手术的效率和安全性。
HemoSet is the first blood segmentation dataset developed by the University of California, San Diego, focusing on automated hemostasis management. This dataset contains 102,616 annotated frames, which are used to train and optimize blood segmentation models to support the development of automated blood suction tools. The dataset is collected by identifying blood vessels and inducing bleeding during robot-assisted surgery on live animals, simulating the common conditions of blood pool formation encountered in surgical procedures. The application scenarios of HemoSet include intraoperative blood loss estimation, assisting operators in manipulating suction tools, and automatically identifying critical bleeding areas, aiming to improve surgical efficiency and safety.

- 1HemoSet: The First Blood Segmentation Dataset for Automation of Hemostasis Management加州大学圣地亚哥分校 · 2024年



