Research map / Label-efficient and robust learning / Semi-supervised learning
Semi-supervised Medical Image Segmentation through Dual-task Consistency
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 dual-task consistency to joint segmentation and level-set supervision (ablation) | Dual-task VNet · Pancreas CT (12 labeled scans) | Dice (%): 73.08 -> 74.84 | Helped |
| Add dual-task consistency to joint segmentation and level-set supervision (ablation) | Dual-task VNet · Pancreas CT (62 labeled scans) | Dice (%): 82.46 -> 82.80 | Helped |
| Use joint segmentation and level-set supervision instead of segmentation alone (ablation) | VNet · Pancreas CT (12 labeled scans) | Dice (%): 70.63 -> 73.08 | Helped |
| Use joint segmentation and level-set supervision instead of segmentation alone (ablation) | VNet · Pancreas CT (62 labeled scans) | Dice (%): 81.78 -> 82.46 | Helped |
| Use the semi-supervised dual-task framework with unlabeled images | Dual-task VNet · Pancreas CT | Dice | Helped |
| Use dual-task consistency rather than existing semi-supervised methods | VNet · Pancreas CT (12 labeled, 50 unlabeled) | Dice (%): 77.66 -> 78.27 | Helped |
| Use dual-task consistency rather than existing semi-supervised methods | VNet · Left Atrium MRI (16 labeled, 64 unlabeled) | Dice (%): 89.27 -> 89.42 | Helped |
Closest papers by meaning
- Combinatorial CNN-Transformer Learning with Manifold Constraints for Semi-supervised Medical Image Segmentation (AAAI 2024 · similarity 0.90)
- Steady Progress Beats Stagnation: Mutual Aid of Foundation and Conventional Models in Mixed Domain Semi-Supervised Medical Image Segmentation (CVPR 2025 · similarity 0.88)
- DuSSS: Dual Semantic Similarity-Supervised Vision-Language Model for Semi-Supervised Medical Image Segmentation (AAAI 2025 · similarity 0.88)
- GapMatch: Bridging Instance and Model Perturbations for Enhanced Semi-Supervised Medical Image Segmentation (AAAI 2025 · similarity 0.88)
- Semi-supervised TEE Segmentation via Interacting with SAM Equipped with Noise-Resilient Prompting (AAAI 2024 · similarity 0.87)
- SGTC: Semantic-Guided Triplet Co-training for Sparsely Annotated Semi-Supervised Medical Image Segmentation (AAAI 2025 · similarity 0.87)
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.