Research map / Image generation / Fast diffusion sampling
Ambiguous Medical Image Segmentation Using Diffusion Models
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 |
|---|---|---|---|
| Use CIMD instead of the strongest baseline for GED | Ambiguous segmentation models · LIDC-IDRI | GED: 0.270 -> 0.321 | Hurt |
| Use CIMD instead of the strongest baseline for CI | Ambiguous segmentation models · LIDC-IDRI | CI: 0.736 -> 0.759 | Helped |
| Use CIMD instead of the strongest baseline for D_max | Ambiguous segmentation models · LIDC-IDRI | D_max: 0.905 -> 0.915 | Helped |
| Use CIMD instead of the strongest baseline for GED | Ambiguous segmentation models · Bone-US | GED: 0.289 -> 0.295 | Hurt |
| Use CIMD instead of the strongest baseline for CI | Ambiguous segmentation models · Bone-US | CI: 0.7544 -> 0.7578 | Helped |
| Use CIMD instead of the strongest baseline for D_max | Ambiguous segmentation models · Bone-US | D_max: 0.863 -> 0.889 | Helped |
| Use CIMD instead of the strongest baseline for GED | Ambiguous segmentation models · MS-MRI | GED: 0.678 -> 0.733 | Hurt |
| Use CIMD instead of the strongest baseline for CI | Ambiguous segmentation models · MS-MRI | CI: 0.522 -> 0.560 | Helped |
| Use CIMD instead of the strongest baseline for D_max | Ambiguous segmentation models · MS-MRI | D_max: 0.513 -> 0.562 | Helped |
| Add CIMD ambiguity modeling to diffusion segmentation (ablation) | DDPM segmentation · LIDC-IDRI | CI: 0.616 -> 0.759; 0.683 -> 0.759 | Helped |
| Add CIMD ambiguity modeling to diffusion segmentation (ablation) | DDPM segmentation · Bone-US | CI: 0.673 -> 0.757; 0.675 -> 0.757 | Helped |
| Add CIMD ambiguity modeling to diffusion segmentation (ablation) | DDPM segmentation · MS-MRI | CI: 0.507 -> 0.560; 0.509 -> 0.560 | Helped |
Closest papers by meaning
- Noise-Consistent Siamese-Diffusion for Medical Image Synthesis and Segmentation (CVPR 2025 · similarity 0.89)
- S2S2: Semantic Stacking for Robust Semantic Segmentation in Medical Imaging (AAAI 2025 · similarity 0.87)
- MedSegDiff-V2: Diffusion-Based Medical Image Segmentation with Transformer (AAAI 2024 · similarity 0.87)
- L-Diffusion: Laplace Diffusion for Efficient Pathology Image Segmentation (ICML 2025 · similarity 0.86)
- Distribution-aware Fairness Learning in Medical Image Segmentation From A Control-Theoretic Perspective (ICML 2025 · similarity 0.85)
- Factorized Diffusion Architectures for Unsupervised Image Generation and Segmentation (NeurIPS 2024 · similarity 0.85)
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.