Reproduce “CTSpine1K: A Large-Scale Dataset for Spinal Vertebrae Segmentation in Computed Tomography” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Yang Deng, Ce Wang, Yuan Hui, Qian Li, Jun Li, Shiwei Luo, Mengke Sun, Quan Quan and 7 more
CTSpine1K is a vertebra segmentation dataset for CT. It combines scans from multiple sources, using model-generated masks refined through human review. It contains 1,005 volumes and 11,172 vertebrae. A 3D full-resolution nnU-Net benchmark achieved mean-of-vertebrae Dice scores of 0.869 on the public test set and 0.840 on the private test set. These scores describe benchmark performance, not clinical outcomes.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.