Research map / 3D vision / Face and shape
Deep Implicit Statistical Shape Models for 3D Medical Image Delineation
Ashwin Raju, Shun Miao, Dakai Jin, Le Lu, Junzhou Huang, Adam P. Harrison
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 DIAS anatomical shape modeling to nnU-Net | nnU-Net · Clinical liver | DSC (%): 92.4% to 95.9% | Improved |
| Add DIAS anatomical shape modeling to nnU-Net | nnU-Net · Clinical liver | HD (mm): 34.1mm to 21.8mm | Improved |
| Add DIAS shape prior and pose estimation | FCN baselines · MSD liver | HD (mm): 7.5-14.3 mm | Improved |
| Add DIAS shape prior and pose estimation | FCN baselines · Clinical liver | worst-case DSC (%): 88.1% to 93.4% | Improved |
| Add local surface refinement (ablation) | DIAS without refinement · MSD liver | HD (mm): 23.4 $\pm$ 12.2 -> 21.4 $\pm$ 11.8 | Improved |
| Add local surface refinement (ablation) | DIAS without refinement · Clinical liver | DSC (%): 95.7 $\pm$ 1.8 -> 95.9 $\pm$ 1.6 | Improved |
| Add scale estimation after translation (ablation) | DIAS translation stage · MSD liver | DSC (%): 79.2 $\pm$ 12.3 -> 83.4 $\pm$ 12.1 | Improved |
| Add rotation estimation after translation and scale (ablation) | DIAS translation and scale stages · MSD liver | DSC (%): 83.4 $\pm$ 12.1 -> 89.1 $\pm$ 10.5 | Improved |
| Add non-rigid PCA deformation after rigid pose estimation (ablation) | DIAS translation, scale, and rotation stages · MSD liver | DSC (%): 89.1 $\pm$ 10.5 -> 96.1 $\pm$ 0.9 | Improved |
| Use 72% rather than 90% explained variance in the PCA basis (ablation) | DIAS without refinement · MSD liver | DSC (%): 95.9 $\pm$ 1.2 -> 96.1 $\pm$ 0.9 | Improved |
Closest papers by meaning
- Point2SSM: Learning Morphological Variations of Anatomies from Point Clouds (ICLR 2024 · similarity 0.89)
- ImplicitAtlas: Learning Deformable Shape Templates in Medical Imaging (CVPR 2022 · similarity 0.88)
- SHAPE: Structure-aware Hierarchical Unsupervised Domain Adaptation with Plausibility Evaluation for Medical Image Segmentation (CVPR 2026 · similarity 0.87)
- Probabilistic Shape Models of Anatomy Directly from Images (AAAI 2023 · similarity 0.87)
- Mine yOur owN Anatomy: Revisiting Medical Image Segmentation With Extremely Limited Labels (TPAMI 2024 · similarity 0.86)
- Implicit Modeling of Non-rigid Objects with Cross-Category Signals (AAAI 2024 · similarity 0.84)
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.
