Research map / Image generation / Image restoration
Dynamic Stream Network for Combinatorial Explosion Problem in Deformable Medical Image Registration
Shaochen Bi, Yuting He, Weiming Wang, Hao Chen
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 dynamic stream attention (DySA) to bidirectional XMorpher baseline (ablation) | DySNet-X · 2D Brain MRI (OASIS-1) | DSC (%): 76.5% -> around 82% | Improved |
| Add adaptive stream basin (AdSB) on top of DySA (ablation) | DySNet-X · 2D Brain MRI (OASIS-1) | DSC (%): around 82% -> 83.0% | Improved |
| Replace XMorpher CAT blocks with DySNet blocks | XMorpher · 3D Brain MRI | DSC (%): 71.2 -> 77.8 (+6.6) | Improved |
| Replace ModeT module with DySNet | ModeT · 3D Brain MRI | DSC (%): 77.4 -> 79.7 (+2.3) | Improved |
| Replace ModeT module with DySNet | ModeT · 2D Brain MRI (OASIS-1) | DSC (%): 81.9 -> 82.2 (+0.3) | No clear effect |
| Replace ModeT module with DySNet | ModeT · 3D Cardiac CT | DSC (%): 83.6 -> 84.1 (+0.5) | Improved |
| Replace XMorpher blocks with DySNet | XMorpher · 3D Cardiac CT | negative Jacobian volume (%): 0.03 -> 0.98 | Hurt |
| Increase kernel size from 1x1 to 7x7 (ablation) | DySNet · 2D Brain MRI (OASIS-1) | DSC (%): 82.9% to 83.02% | No clear effect |
| Increase kernel size (ablation) | DySNet · 2D Brain MRI (OASIS-1) | FLOPs | Hurt |
Closest papers by meaning
- A Plug-and-Play Image Registration Network (ICLR 2024 · similarity 0.83)
- Correlation-aware Coarse-to-fine MLPs for Deformable Medical Image Registration (CVPR 2024 · similarity 0.83)
- Deep Learning in Medical Image Registration: Magic or Mirage? (NeurIPS 2024 · similarity 0.83)
- SACB-Net: Spatial-awareness Convolutions for Medical Image Registration (CVPR 2025 · similarity 0.82)
- Hypernetworks for Dynamic Feature Selection (NeurIPS 2026 · similarity 0.82)
- H-ViT: A Hierarchical Vision Transformer for Deformable Image Registration (CVPR 2024 · similarity 0.82)
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.
