VerSe (Large Scale Vertebrae Segmentation Challenge)

脊柱或椎体分割是所有关于脊柱形态和病理学自动量化的应用中的关键步骤。随着深度学习的出现，对于计算机断层扫描 (CT) 扫描这样的任务，大而多样的数据是主要的抢手资源。但是，目前无法获得大规模的公共数据集。 VerSe 是一个大规模、多探测器、多站点、CT 脊柱数据集，由 355 名患者的 374 次扫描组成。该挑战与 MICCAI 2019 和 2020 一起进行了两次迭代。评估的任务包括：椎体标记和分割。

Spinal or vertebral segmentation is a critical step in all applications targeting the automatic quantification of spinal morphology and pathology. With the advent of deep learning, large and diverse datasets have become a highly sought-after resource for tasks involving computed tomography (CT) scans. However, large-scale public datasets are currently unavailable. VerSe is a large-scale, multi-detector, multi-site CT spinal dataset comprising 374 scans from 355 patients. This challenge was conducted in two iterations alongside the MICCAI 2019 and MICCAI 2020 conferences. The evaluated tasks include vertebral labeling and segmentation.