Research map / Detection and segmentation / Weakly supervised detection and segmentation
Deep Complementary Joint Model for Complex Scene Registration and Few-shot Segmentation on Medical Images
Yuting He, Tiantian Li, Guanyu Yang, Youyong Kong, Yang Chen, Huazhong Shu, Jean-Louis Coatrieux, Jean-Louis Dillenseger, Shuo Li
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 registration-generated data to segmentation (direct joint model) (ablation) | 3D U-Net · MM-WHS segmentation | Dice: 78.8 -> 80.5 | Improved |
| add DSS block (random perturbation of deformation field) (ablation) | joint model · MM-WHS segmentation | Dice: 80.5 -> 83.9 | Improved |
| add DSS block (ablation) | joint model · MM-WHS registration | Dice: 72.9 -> 72.9 | No clear effect |
| add ACM (alignment confidence maps) (ablation) | joint model · MM-WHS segmentation | Dice: 80.5 -> 84.1 | Improved |
| add ACM (ablation) | joint model · MM-WHS registration | Dice: 72.9 -> 72.5 | No clear effect |
| add DRC (deep-based region constraint) (ablation) | joint model · MM-WHS registration | Dice: 72.9 -> 75.9 | Improved |
| add DRC (ablation) | joint model · MM-WHS segmentation | Dice: 80.5 -> 82.5 | Improved |
| combine DSS, ACM and DRC (ablation) | joint model · MM-WHS registration | Dice: 72.9 -> 77.6 | Improved |
| combine DSS, ACM and DRC (ablation) | joint model · MM-WHS segmentation | Dice: 80.5 -> 85.7 | Improved |
| use registration-based augmentation instead of manual augmentation | 3D U-Net · MM-WHS segmentation | Dice: 80.0 -> 85.7 | Improved |
| reduce labeled images to 1 | DeepRS vs 3D U-Net · MM-WHS segmentation | Dice: 18.1% higher than 3D U-Net | Improved |
| use DeepRS instead of VoxelMorph-2 | registration · MM-WHS registration | Dice: 71.7 -> 77.6 | Improved |
Closest papers by meaning
- JSSR: A Joint Synthesis, Segmentation, and Registration System for 3D Multi-Modal Image Alignment of Large-scale Pathological CT Scans (ECCV 2020 · similarity 0.87)
- Adversarial Data Augmentation via Deformation Statistics (ECCV 2020 · similarity 0.87)
- Alternative Baselines for Low-Shot 3D Medical Image Segmentation—An Atlas Perspective (AAAI 2021 · similarity 0.86)
- Deep Learning in Medical Image Registration: Magic or Mirage? (NeurIPS 2024 · similarity 0.85)
- CARL: A Framework for Equivariant Image Registration (CVPR 2025 · similarity 0.85)
- GapMatch: Bridging Instance and Model Perturbations for Enhanced Semi-Supervised Medical Image Segmentation (AAAI 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.
