Research map / Learning theory and algorithms / Combinatorial and search optimization
Automatic Vertebra Localization and Identification in CT by Spine Rectification and Anatomically-Constrained Optimization
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add spine rectification and 1-D signal aggregation without anatomical constraints (ablation) | base vertebra detector · SpineWeb test set (All) | identification rate: 81.9 to 81.4 | No clear effect |
| add the hard constraint enforcing consecutive vertebra order (ablation) | base+rect · SpineWeb test set (All) | identification rate: 81.4% to 91.2% | Helped |
| add joint optimization regulating distances between predicted vertebrae while preserving order (ablation) | base+rect+order · SpineWeb test set (All) | identification rate: 91.2% to 97.4% | Helped |
| add vertebra weights λ (ablation) | base+rect+order · SpineWeb test set (All) | identification rate: 89.0% to 91.2% | Helped |
| add vertebra weights λ (ablation) | base+rect+optim · SpineWeb test set (All) | identification rate: 94.4% to 97.4% | Helped |
| add vertebra weights λ (ablation) | base+rect+optim · SpineWeb test set (All) | mean localization error (mm): 2.55 to 2.55 | No clear effect |
| use global joint search instead of directional Markov tracing | vertebra localization and identification · SpineWeb test set (Cervical) | identification rate: 90.8 -> 96.8 | Helped |
Closest papers by meaning
- SpineBench: A Clinically Salient, Level-Aware Benchmark Powered by the SpineMed-450k Corpus (ICLR 2026 · similarity 0.81)
- B-spine: Learning B-spline Curve Representation for Robust and Interpretable Spinal Curvature Estimation (AAAI 2024 · similarity 0.81)
- PolyPose: Deformable 2D/3D Registration via Polyrigid Transformations (NeurIPS 2025 · similarity 0.80)
- Coupled Laplacian Eigenmaps for Locally-Aware 3D Rigid Point Cloud Matching (CVPR 2024 · similarity 0.79)
- Intraoperative 2D/3D Image Registration via Differentiable X-ray Rendering (CVPR 2024 · similarity 0.78)
- Neural Localizer Fields for Continuous 3D Human Pose and Shape Estimation (NeurIPS 2024 · similarity 0.78)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.