WORD

WORD数据集是由电子科技大学机电工程学院等机构合作创建的大型临床腹部器官分割数据集，包含150个腹部CT扫描图像，覆盖16个腹部器官，每个器官均有精细的像素级标注。该数据集旨在推动腹部器官分割算法的研究与临床应用开发，通过高分辨率的图像和详细的标注，为深度学习模型提供高质量的训练数据。此外，数据集还用于评估多种最先进的分割方法，并邀请经验丰富的肿瘤学家对模型预测进行修正，以衡量深度学习方法与专业人员之间的差距。WORD数据集的建立为腹部多器官分割任务提供了一个新的基准，并为未来的研究和临床应用开发提供了基线。

The WORD dataset is a large-scale clinical abdominal organ segmentation dataset co-developed by the School of Mechanical and Electrical Engineering of the University of Electronic Science and Technology of China and other institutions. It contains 150 abdominal CT scan images covering 16 abdominal organs, each with precise pixel-level annotations. This dataset aims to promote the research and clinical application development of abdominal organ segmentation algorithms, providing high-quality training data for deep learning models through high-resolution images and detailed annotations. In addition, the dataset is also used to evaluate multiple state-of-the-art segmentation methods, and invites experienced oncologists to revise model predictions to measure the gap between deep learning approaches and professional clinicians. The establishment of the WORD dataset provides a new benchmark for the abdominal multi-organ segmentation task and a reliable baseline for future research and clinical application development.

搜集汇总

背景与挑战

背景概述

WORD数据集是一个大型临床腹部器官分割数据集，包含150个腹部CT扫描图像，覆盖16个腹部器官并具有精细像素级标注。它旨在推动腹部器官分割算法的研究与临床应用开发，通过高质量图像和标注为深度学习模型提供训练数据，同时作为新基准用于评估先进方法并衡量与专业人员的差距。