Research map / Vision-language and multimodal / Cross-modal learning
RL-U2Net: A Dual-Branch UNet with Reinforcement Learning-Assisted Multimodal Feature Fusion for Accurate 3D Whole-Heart Segmentation
Jierui Qu, Jianchun Zhao
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 cross-modal attention (CMA) to the dual-branch model (ablation) | RL-U2Net · MM-WHS 2017 MRI | Dice: 0.612 -> 0.870 | Improved |
| add cross-modal attention (CMA) (ablation) | RL-U2Net · MM-WHS 2017 CT | Dice: 0.884 -> 0.931 | Improved |
| add RL-XAlign module (ablation) | RL-U2Net · MM-WHS 2017 CT | Dice: 0.909 -> 0.931 | Improved |
| add RL-XAlign module (ablation) | RL-U2Net · MM-WHS 2017 MRI | Dice: 0.837 -> 0.870 | Improved |
| add auxiliary alignment loss (ablation) | RL-U2Net · MM-WHS 2017 CT | Dice: 0.912 -> 0.931 | Improved |
| add auxiliary alignment loss (ablation) | RL-U2Net · MM-WHS 2017 MRI | Dice: 0.834 -> 0.870 | Improved |
| add adaptive gradient weight distributor (AGWD) (ablation) | RL-U2Net · MM-WHS 2017 CT | Dice: 0.885 -> 0.931 | Improved |
| add AGWD (ablation) | RL-U2Net · MM-WHS 2017 MRI | Dice: 0.768 -> 0.870 | Improved |
| use RL-U2Net instead of HRMedSeg | MM-WHS 2017 CT · MM-WHS 2017 CT | average Dice: 0.921 -> 0.931 | Improved |
| use RL-U2Net instead of nnformer | MM-WHS 2017 CT · MM-WHS 2017 CT | HD95 (mm): 12.174 -> 11.471 | Improved |
Closest papers by meaning
- UniMRSeg: Unified Modality-Relax Segmentation via Hierarchical Self-Supervised Compensation (NeurIPS 2025 · similarity 0.85)
- Upping the Game: How 2D U-Net Skip Connections Flip 3D Segmentation (NeurIPS 2024 · similarity 0.85)
- DyCON: Dynamic Uncertainty-aware Consistency and Contrastive Learning for Semi-supervised Medical Image Segmentation (CVPR 2025 · similarity 0.84)
- UniPro: Unified Multi-Mode Medical Image Segmentation from 2D Images to 3D Volumes via Propagation (NeurIPS 2026 · similarity 0.84)
- MAPSeg: Unified Unsupervised Domain Adaptation for Heterogeneous Medical Image Segmentation Based on 3D Masked Autoencoding and Pseudo-Labeling (CVPR 2024 · similarity 0.84)
- FuseUNet: A Multi-Scale Feature Fusion Method for U-like Networks (ICML 2025 · similarity 0.84)
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.
