Research map / Detection and segmentation / Weakly supervised detection and segmentation
An Annotation Sparsification Strategy for 3D Medical Image Segmentation via Representative Selection and Self-Training
Hao Zheng, Yizhe Zhang, Lin Yang, Chaoli Wang, Danny Z. Chen
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 self-training with pseudo-labels (meta-model) (ablation) | Sparse DVN* w/ RA (s5) · HVSMR 2016 overall score | overall score: -0.095 -> 0.166 | Improved |
| add self-training with pseudo-labels (meta-model) (ablation) | Sparse DVN* w/ RA (s5) · HVSMR 2016 myocardium Dice | Dice: 0.792 -> 0.830 | Improved |
| add self-training with pseudo-labels (meta-model) (ablation) | Sparse DVN* w/ RA (s5) · HVSMR 2016 myocardium Hausdorff | Hausdorff (mm): 6.906 -> 3.614 | Improved |
| add self-training with pseudo-labels (meta-model) (ablation) | Sparse DVN* w/ RA (s5) · HVSMR 2016 blood pool Dice | Dice: 0.932 -> 0.937 | Improved |
| select slices by representative selection instead of equal interval (ablation) | Sparse DVN* with self-training · HVSMR 2016 across budgets | overall score | Improved |
| RA+ST with 80 percent fewer annotation vs full-annotated DVN* | DVN* · HVSMR 2016 | overall score: 0.13 -> 0.166 | Improved |
| add RA+ST to sparse DVN* at s16 (ablation) | DVN* s16 · Mouse piriform cortex | V Rand F score: 0.9940 -> 0.9961 | Improved |
| add RA+ST to sparse DVN* at s64 (ablation) | DVN* s64 · Mouse piriform cortex | V Rand F score: 0.9951 -> 0.9957 | Improved |
| add RA+ST to sparse DVN* at s4 (ablation) | DVN* s4 · Mouse piriform cortex | V Rand F score: 0.9970 -> 0.9971 | No clear effect |
| reduce annotation (equal interval) from full to sparser budgets | DVN* · HVSMR 2016 | Dice/score | Hurt |
Closest papers by meaning
- Integrating Deep Metric Learning with Coreset for Active Learning in 3D Segmentation (NeurIPS 2024 · similarity 0.89)
- Revisiting MAE Pre-training for 3D Medical Image Segmentation (CVPR 2025 · similarity 0.88)
- Annotation Ambiguity Aware Semi-Supervised Medical Image Segmentation (CVPR 2025 · similarity 0.88)
- SGTC: Semantic-Guided Triplet Co-training for Sparsely Annotated Semi-Supervised Medical Image Segmentation (AAAI 2025 · similarity 0.87)
- Versatile Medical Image Segmentation Learned from Multi-Source Datasets via Model Self-Disambiguation (CVPR 2024 · similarity 0.87)
- Enhancing vision-language models for medical imaging: bridging the 3D gap with innovative slice selection (NeurIPS 2024 · similarity 0.86)
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.
