Research map / Detection and segmentation / CNN features
Breaking Task Boundaries: A Unified Model for 3D Medical Image Fusion and Segmentation Guided by Manifold Perspective
Zeyu Wang, Jiayu Wang, Haiyu Song
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 jointly trained fusion task (vs segmentation only) (ablation) | M2-CoFS · BraTS19 segmentation | Dice: 0.792 -> 0.858 | Improved |
| add cross-task weight adaptation (Stage II) (ablation) | M2-CoFS · BraTS19 segmentation | Dice: 0.812 -> 0.858 | Improved |
| add weight generation network stage (Stage III) (ablation) | M2-CoFS · MRBrainS segmentation | Dice: 0.714 -> 0.860 | Improved |
| add Stage III on BraTS19 (ablation) | M2-CoFS · BraTS19 segmentation | Dice: 0.729 -> 0.858 | Improved |
| add synaptic intelligence regularizer (ablation) | M2-CoFS Stage II · BraTS19 segmentation | Dice: 0.847 -> 0.858 | Improved |
| add manifold distance loss (ablation) | M2-CoFS Stage III · BraTS19 segmentation | Dice: 0.834 -> 0.858 | Improved |
| add synaptic intelligence regularizer (ablation) | M2-CoFS Stage II · MRBrainS segmentation | Dice: 0.857 -> 0.860 | Improved |
| plug the proposed training strategy into TransBTS | TransBTS · BraTS19 segmentation | Dice: 0.808 -> 0.855 | Improved |
| plug the proposed training strategy into UNETR | UNETR · BraTS19 segmentation | Dice: 0.792 -> 0.833 | Improved |
| M2-CoFS vs RMR-Fusion on CSF segmentation | MRBrainS segmentation · MRBrainS segmentation (CSF) | Dice: 0.8323 -> 0.8312 | Hurt |
Closest papers by meaning
- E2ENet: Dynamic Sparse Feature Fusion for Accurate and Efficient 3D Medical Image Segmentation (NeurIPS 2024 · similarity 0.87)
- A Robust Mutual-Reinforcing Framework for 3D Multi-Modal Medical Image Fusion Based on Visual-Semantic Consistency (AAAI 2024 · similarity 0.86)
- Combinatorial CNN-Transformer Learning with Manifold Constraints for Semi-supervised Medical Image Segmentation (AAAI 2024 · similarity 0.86)
- Knowledge Transfer Scaling Laws for 3D Medical Imaging (NeurIPS 2026 · similarity 0.86)
- Training Like a Medical Resident: Context-Prior Learning Toward Universal Medical Image Segmentation (CVPR 2024 · similarity 0.86)
- Upping the Game: How 2D U-Net Skip Connections Flip 3D Segmentation (NeurIPS 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.
