Research map / Detection and segmentation / Open-set and few-shot detection
SPA: Efficient User-Preference Alignment against Uncertainty in Medical Image Segmentation
Jiayuan Zhu, Junde Wu, Cheng Ouyang, Konstantinos Kamnitsas, J. Alison Noble
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 Gaussian mean and variance updating to random sampling (ablation) | SPA · REFUGE2 (3-Iter) | Dice (%): 80.29 -> 84.12 | Improved |
| add Gaussian mean and variance updating to random sampling (ablation) | SPA · Kidney (3-Iter) | Dice (%): 90.05 -> 92.06 | Improved |
| add mixture weight adjustment to random sampling (ablation) | SPA · REFUGE2 (3-Iter) | Dice (%): 80.29 -> 82.87 | Improved |
| add mixture weight adjustment to random sampling (ablation) | SPA · Kidney (3-Iter) | Dice (%): 90.05 -> 92.29 | Improved |
| combine mean/variance and weight calibration (ablation) | SPA · REFUGE2 (3-Iter) | Dice (%): 84.12 -> 85.42 | Improved |
| combine mean/variance and weight calibration (ablation) | SPA · Kidney (3-Iter) | Dice (%): 92.29 -> 94.26 | Improved |
| increase sampled predictions from 24 to 48 (ablation) | SPA · REFUGE2 (6 iterations) | Dice (%): 83.05 -> 86.22 | Improved |
| use user-adapted GMM parameters across images | SPA · Kidney | Dice (%): 91.68 -> 92.43 | Improved |
| use SPA multi-choice interaction instead of MedSAM prompts | SPA · REFUGE2 user study | time per image (s): 6.62 -> 4.34 | Improved |
| use SPA instead of SAM-U V2 for iterations to Dice target | SPA · REFUGE2 | iterations to Dice 84%: 5.6 -> 5.02 | Improved |
Closest papers by meaning
- Enhancing SAM with Efficient Prompting and Preference Optimization for Semi-supervised Medical Image Segmentation (CVPR 2025 · similarity 0.88)
- Training Like a Medical Resident: Context-Prior Learning Toward Universal Medical Image Segmentation (CVPR 2024 · similarity 0.87)
- GapMatch: Bridging Instance and Model Perturbations for Enhanced Semi-Supervised Medical Image Segmentation (AAAI 2025 · similarity 0.87)
- DyCON: Dynamic Uncertainty-aware Consistency and Contrastive Learning for Semi-supervised Medical Image Segmentation (CVPR 2025 · similarity 0.86)
- S2S2: Semantic Stacking for Robust Semantic Segmentation in Medical Imaging (AAAI 2025 · similarity 0.86)
- Steady Progress Beats Stagnation: Mutual Aid of Foundation and Conventional Models in Mixed Domain Semi-Supervised Medical Image Segmentation (CVPR 2025 · 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.
