RibSeg v2
收藏资源简介:
RibSeg v2是由复旦大学开发的大规模基准数据集,用于肋骨标注和解剖中心线提取。该数据集包含660个CT扫描(总计15,466个单独肋骨),并由专家手动检查标注肋骨标注和解剖中心线提取。RibSeg v2数据集利用公开的CT扫描数据,旨在解决临床应用中肋骨分割和标注的挑战,特别是在肋骨骨折检测和骨异常量化等领域。数据集的创建过程包括手动标注和一系列形态学操作,确保高质量的标注。该数据集的应用领域包括手术规划、术后评估和病理注册等。
RibSeg v2 is a large-scale benchmark dataset developed by Fudan University for rib annotation and anatomical centerline extraction. It contains 660 CT scans with a total of 15,466 individual ribs, and its rib annotation and anatomical centerline extraction labels were manually reviewed and validated by domain experts. Leveraging publicly accessible CT scan data, RibSeg v2 is designed to tackle the challenges of rib segmentation and annotation in clinical practice, especially in fields such as rib fracture detection and bone abnormality quantification. The dataset construction process includes manual annotation and a series of morphological operations to ensure high-quality annotations. Its application areas cover surgical planning, postoperative evaluation, pathological registration and other related scenarios.

- 1RibSeg v2: A Large-scale Benchmark for Rib Labeling and Anatomical Centerline Extraction复旦大学 · 2023年



