Research map / Detection and segmentation / Open-set and few-shot detection
LT-Net: Label Transfer by Learning Reversible Voxel-Wise Correspondence for One-Shot Medical Image Segmentation
Check 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 image adversarial loss (ablation) | VoxelMorph · CANDI test (28 structures) | mean Dice (%): 76.0 (9.7) -> 79.0 (3.1) | Helped |
| add image cycle-consistency loss after the GAN loss (ablation) | VoxelMorph + GAN loss · CANDI test (28 structures) | mean Dice (%): 79.0 (3.1) -> 79.2 (2.8) | No clear effect |
| add transformation consistency loss (ablation) | Baseline · CANDI test (28 structures) | mean Dice (%): 79.2 (2.8) -> 80.9 (2.7) | Helped |
| add anatomy cycle-consistency loss (ablation) | Baseline · CANDI test (28 structures) | mean Dice (%): 79.2 (2.8) -> 80.5 (2.5) | Helped |
| add anatomy cycle-consistency loss alongside transformation consistency (ablation) | Baseline + transformation consistency · CANDI test (28 structures) | mean Dice (%): 80.9 (2.7) -> 81.4 (2.6) | Helped |
| add transformation consistency and anatomy cycle-consistency losses together (ablation) | Baseline · CANDI test (28 structures) | mean Dice (%): 79.2 (2.8) -> 81.4 (2.6) | Helped |
| add anatomy difference consistency loss after transformation and anatomy cycle consistency (ablation) | Baseline + transformation consistency + anatomy cycle consistency · CANDI test (28 structures) | mean Dice (%): 81.4 (2.6) -> 82.3 (2.5) | Helped |
| use LT-Net instead of DataAug | one-shot segmentation · CANDI test (28 structures) | mean Dice (%): 80.4 (4.3) -> 82.3 (2.5) | Helped |
| use LT-Net instead of VoxelMorph | one-shot segmentation · CANDI test (28 structures) | mean Dice (%): 76.0 (9.7) -> 82.3 (2.5) | Helped |
| use LT-Net with one atlas instead of MABMIS with five atlases | CANDI test (28 structures) · CANDI test (28 structures) | mean Dice (%): 81.1 (3.6) -> 82.3 (2.5) | Helped |
Closest papers by meaning
- Alternative Baselines for Low-Shot 3D Medical Image Segmentation—An Atlas Perspective (AAAI 2021 · similarity 0.89)
- Robust One-Shot Segmentation of Brain Tissues via Image-Aligned Style Transformation (AAAI 2023 · similarity 0.88)
- Modeling the Probabilistic Distribution of Unlabeled Data for One-shot Medical Image Segmentation (AAAI 2021 · similarity 0.88)
- Combinatorial CNN-Transformer Learning with Manifold Constraints for Semi-supervised Medical Image Segmentation (AAAI 2024 · similarity 0.84)
- SGTC: Semantic-Guided Triplet Co-training for Sparsely Annotated Semi-Supervised Medical Image Segmentation (AAAI 2025 · similarity 0.83)
- Pancakes: Consistent Multi-Protocol Image Segmentation Across Biomedical Domains (NeurIPS 2025 · similarity 0.83)
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.