CTSpine1K: A Large-Scale Dataset for Spinal Vertebrae Segmentation in Computed Tomography

TL;DR

The paper introduces CTSpine1K, a large-scale annotated CT dataset with over 1,000 volumes and 11,100 vertebrae labels, enabling improved deep learning-based spinal vertebrae segmentation and related tasks.

Contribution

It provides the first large-scale, publicly available spine CT dataset for vertebra segmentation, addressing data scarcity in current research.

Findings

Established a new benchmark for vertebra segmentation.

Demonstrated the dataset's utility in various spine image analysis tasks.

Facilitated future research in spine-related medical imaging.

Abstract

Spine-related diseases have high morbidity and cause a huge burden of social cost. Spine imaging is an essential tool for noninvasively visualizing and assessing spinal pathology. Segmenting vertebrae in computed tomography (CT) images is the basis of quantitative medical image analysis for clinical diagnosis and surgery planning of spine diseases. Current publicly available annotated datasets on spinal vertebrae are small in size. Due to the lack of a large-scale annotated spine image dataset, the mainstream deep learning-based segmentation methods, which are data-driven, are heavily restricted. In this paper, we introduce a large-scale spine CT dataset, called CTSpine1K, curated from multiple sources for vertebra segmentation, which contains 1,005 CT volumes with over 11,100 labeled vertebrae belonging to different spinal conditions. Based on this dataset, we conduct several spinal vertebrae segmentation experiments to set the first benchmark. We believe that this large-scale dataset will facilitate further research in many spine-related image analysis tasks, including but not limited to vertebrae segmentation, labeling, 3D spine reconstruction from biplanar radiographs, image super-resolution, and enhancement.