ESD-DZSeg
收藏资源简介:
ESD-DZSeg数据集是由中国香港中文大学电子工程系、中国深圳研究院、中国济南山东大学齐鲁医院消化内科联合创建,专门用于机器人辅助内镜下黏膜剥离术(ESD)中的解剖区域分割任务。该数据集包含1849张图像,来源于21个离体猪模型的机器人ESD手术视频,每张图像均由专家标注了解剖区域。数据集的创建旨在解决内镜手术环境中解剖区域分割的复杂性问题,通过引入视觉提示(如涂鸦和边界框)来提高分割的准确性和用户体验。ESD-DZSeg数据集的应用领域主要集中在机器人辅助内镜手术中的解剖区域建议和视觉提示解释,旨在为未来的研究提供基准。
The ESD-DZSeg dataset was co-developed by the Department of Electronic Engineering of The Chinese University of Hong Kong, Shenzhen Research Institute of The Chinese University of Hong Kong, and the Department of Gastroenterology of Qilu Hospital of Shandong University in Jinan, China. It is specifically designed for the anatomical region segmentation task in robot-assisted endoscopic submucosal dissection (ESD). This dataset contains 1849 images sourced from robot-assisted ESD surgical videos of 21 ex vivo porcine models, and each image has been expertly annotated with anatomical regions. The dataset was developed to address the complexity of anatomical region segmentation in endoscopic surgical environments, by introducing visual prompts such as scribbles and bounding boxes to improve segmentation accuracy and user experience. The application scenarios of the ESD-DZSeg dataset mainly focus on anatomical region proposal and visual prompt interpretation in robot-assisted endoscopic surgery, aiming to provide a benchmark for future research.

- 1PDZSeg: Adapting the Foundation Model for Dissection Zone Segmentation with Visual Prompts in Robot-assisted Endoscopic Submucosal Dissection中国香港中文大学电子工程系,中国深圳研究院,中国广州中山大学计算机科学与工程系,中国济南山东大学齐鲁医院消化内科 · 2024年



