Research map / Architectures and efficiency / CNN design
Learning-Based Image Registration With Meta-Regularization
Ebrahim Al Safadi, Xubo Song
Check 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 learned meta-regularization (ablation) | U-Net registration network · Liver MRI, Train Large/Test Large | Dice (%): 80.08±7.08 -> 84.80±6.09 | Improved |
| add learned meta-regularization (ablation) | U-Net registration network · Liver MRI, Train Large/Test Large | |Jφ| ≥0 (%): 98.29±0.71 -> 99.97±0.06 | Improved |
| add learned meta-regularization (ablation) | U-Net registration network · Echocardiography | Dice (%): 84.00±5.90 -> 86.52±5.26 | Improved |
| add learned meta-regularization (ablation) | U-Net registration network · Echocardiography | |Jφ| ≥0 (%): 97.04±1.68 -> 98.73±1.15 | Improved |
| add learned meta-regularization (ablation) | U-Net registration network · Chest X-ray | Dice (%): 81.56±5.55 -> 85.20±4.85 | Improved |
| add learned meta-regularization (ablation) | U-Net registration network · Chest X-ray | |Jφ| ≥0 (%): 98.49±1.61 -> 97.46±2.06 | Hurt |
| add learned meta-regularization (ablation) | U-Net registration network · Liver MRI, Train Moderate/Test Moderate | Dice (%): 94.36±1.40 -> 94.12±1.41 | No clear effect |
| add learned meta-regularization | registration methods · Liver MRI, Train Large/Test Large | Dice (%): 80.50±6.64 -> 84.80±6.09 | Improved |
| add learned meta-regularization | registration methods · Liver MRI, Train Large/Test Moderate | Dice (%): 88.66±3.79 -> 92.60±1.79 | Improved |
| add learned meta-regularization | registration methods · Echocardiography | Dice (%): 84.12±5.70 -> 86.52±5.26 | Improved |
| add learned meta-regularization | registration methods · Chest X-ray | Dice (%): 83.86±5.85 -> 85.20±4.85 | Improved |
| add learned meta-regularization | registration methods · Chest X-ray | |Jφ| ≥0 (%): 97.74±1.89 -> 97.46±2.06 | Hurt |
Closest papers by meaning
- Metric Learning for Image Registration (CVPR 2019 · similarity 0.90)
- Learning Deformable Image Registration From Optimization: Perspective, Modules, Bilevel Training and Beyond (TPAMI 2021 · similarity 0.87)
- CARL: A Framework for Equivariant Image Registration (CVPR 2025 · similarity 0.87)
- Deep Learning in Medical Image Registration: Magic or Mirage? (NeurIPS 2024 · similarity 0.87)
- A Plug-and-Play Image Registration Network (ICLR 2024 · similarity 0.85)
- SACB-Net: Spatial-awareness Convolutions for Medical Image Registration (CVPR 2025 · 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.
