Research map / Point clouds / Registration and matching
Lung250M-4B: A Combined 3D Dataset for CT- and Point Cloud-Based Intra-Patient Lung Registration
Fenja Falta, Christoph Großbröhmer, Alessa Hering, Alexander Bigalke, Mattias P Heinrich
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 keypoint supervision (VoxelMorph+ to VoxelMorph++) with instance optimisation | VoxelMorph · COPD test | mean TRE (mm): 4.31 -> 2.26 | Improved |
| Add keypoint supervision without instance optimisation | VoxelMorph · COPD test | mean TRE (mm): 6.53 -> 4.47 | Improved |
| Add instance optimisation to VoxelMorph++ | VoxelMorph++ · COPD test | mean TRE (mm): 4.47 -> 2.26 | Improved |
| Add instance optimisation to VoxelMorph+ | VoxelMorph+ · COPD test | mean TRE (mm): 6.53 -> 4.31 | Improved |
| Add vein/artery labels to CPD | CPD · COPD test | mean TRE (mm): 3.13 -> 2.59 | Improved |
| Train PointPWC-Net on synthetic deformations instead of real pairs with automatic correspondences | PointPWC-Net · COPD test | mean TRE (mm): 2.85 -> 2.73 | Improved |
| Train on only TCIA-NSCLC instead of the full dataset (ablation) | VoxelMorph++ · COPD test | mean TRE (mm): 2.26 -> 5.07 | Hurt |
| Train on only TCIA-NLST instead of the full dataset (ablation) | VoxelMorph++ · COPD test | mean TRE (mm): 2.26 -> 3.30 | Hurt |
| Train on only Empire10 instead of the full dataset (ablation) | VoxelMorph++ · COPD test | mean TRE (mm): 2.26 -> 3.35 | Hurt |
| Train on only TCIA-Ventilation instead of the full dataset (ablation) | VoxelMorph++ · COPD test | mean TRE (mm): 2.26 -> 3.19 | Hurt |
| Train on only L2R-LungCT instead of the full dataset (ablation) | VoxelMorph++ · COPD test | mean TRE (mm): 2.26 -> 2.90 | Hurt |
| Train with 2-fold cross-validation on COPDgene instead of the proposed split (ablation) | VoxelMorph++ · COPD test | mean TRE (mm): 2.26 -> 2.10 | No clear effect |
Closest papers by meaning
- Intraoperative 2D/3D Image Registration via Differentiable X-ray Rendering (CVPR 2024 · similarity 0.85)
- Cross-Modal Interactive Perception Network with Mamba for Lung Tumor Segmentation in PET-CT Images (CVPR 2025 · similarity 0.85)
- Point2SSM: Learning Morphological Variations of Anatomies from Point Clouds (ICLR 2024 · similarity 0.83)
- 3DMedAgent: Unified Perception-to-Understanding for 3D Medical Analysis (ICML 2026 · similarity 0.83)
- Better Tokens for Better 3D: Advancing Vision-Language Modeling in 3D Medical Imaging (NeurIPS 2025 · similarity 0.83)
- CARL: A Framework for Equivariant Image Registration (CVPR 2025 · similarity 0.83)
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.
