Research map / Label-efficient and robust learning / Recognition and long-tail
MorphSeek: Fine-grained Latent Representation-Level Policy Optimization for Deformable Image Registration
Runxun Zhang, Yizhou Liu, Dongrui Li, Bo Xu, Jingwei Wei
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 MorphSeek latent GRPO to TransMorph | TransMorph · OASIS brain MRI | Mean Dice (%): 85.89 -> 88.89 | Improved |
| add MorphSeek to TransMorph | TransMorph · Abdomen MR-CT | Mean Dice (%): 82.37 -> 86.49 | Improved |
| add MorphSeek to NICE-Trans | NICE-Trans · LiTS liver CT | NJD (%): 0.17 -> 0.16 | No clear effect |
| add Gaussian head only (ablation) | TransMorph · OASIS brain MRI | Mean Dice (%): 76.84 -> 76.79 | No clear effect |
| add weakly supervised Dice loss (ablation) | TransMorph · OASIS brain MRI | Mean Dice (%): 76.79 -> 86.08 | Improved |
| add weakly supervised Dice loss (ablation) | TransMorph · OASIS brain MRI | NJD (%): 0.12 -> 0.29 | Hurt |
| add multi-step refinement (3 steps) without GRPO (ablation) | TransMorph · OASIS brain MRI | Mean Dice (%): 86.08 -> 86.37 | Improved |
| add multi-trajectory GRPO (6 trajs) (ablation) | TransMorph multi-step · OASIS brain MRI | Mean Dice (%): 86.37 -> 88.89 | Improved |
| add multi-trajectory GRPO (6 trajs) (ablation) | TransMorph multi-step · OASIS brain MRI | NJD (%): 0.35 -> 0.06 | Improved |
| increase trajectories from 2 to 6 (ablation) | MorphSeek TransMorph · OASIS brain MRI | Dice (%): 87.78 -> 88.89 (3 steps) | Improved |
| increase refinement steps beyond 3 (ablation) | MorphSeek TransMorph · OASIS brain MRI | Dice / NJD: 88.89 -> 88.51 (6 trajs, 3 -> 4 steps) | Hurt |
| add unsupervised warm-up before GRPO (ablation) | MorphSeek TransMorph · OASIS brain MRI | stable-training success rate (%): 33% -> 79% | Improved |
Closest papers by meaning
- Deep Learning in Medical Image Registration: Magic or Mirage? (NeurIPS 2024 · similarity 0.87)
- Correlation-aware Coarse-to-fine MLPs for Deformable Medical Image Registration (CVPR 2024 · similarity 0.86)
- A Plug-and-Play Image Registration Network (ICLR 2024 · similarity 0.86)
- CARL: A Framework for Equivariant Image Registration (CVPR 2025 · similarity 0.86)
- H-ViT: A Hierarchical Vision Transformer for Deformable Image Registration (CVPR 2024 · similarity 0.85)
- Intraoperative 2D/3D Image Registration via Differentiable X-ray Rendering (CVPR 2024 · similarity 0.85)
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.
