Research map / 3D vision / 3D generation
Elastic Boundary Projection for 3D Medical Image Segmentation
Tianwei Ni, Lingxi Xie, Huangjie Zheng, Elliot K. Fishman, Alan L. Yuille
Check 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 |
|---|---|---|---|
| Use EBP instead of RSTN | 3D organ segmentation · Multi-organ CT, left kidney | DSC (%): 94.50\pm2.66 -> 93.45\pm1.62 | Hurt |
| Use EBP instead of RSTN | 3D organ segmentation · Multi-organ CT, right kidney | DSC (%): 96.09\pm2.21 -> 95.26\pm1.59 | Hurt |
| Use EBP instead of RSTN | 3D organ segmentation · Multi-organ CT, spleen | DSC (%): 94.63\pm4.21 -> 94.50\pm2.64 | No clear effect |
| Use EBP instead of RSTN | 3D organ segmentation · MSD spleen | DSC (%): 89.70\pm12.60 -> 92.01\pm4.50 | Improved |
| Use EBP instead of VNet | 3D organ segmentation · Multi-organ CT, left kidney | DSC (%): 91.95\pm4.63 -> 93.45\pm1.62 | Improved |
| Use EBP instead of VNet | 3D organ segmentation · Multi-organ CT, right kidney | DSC (%): 92.97\pm3.67 -> 95.26\pm1.59 | Improved |
| Use EBP instead of VNet | 3D organ segmentation · Multi-organ CT, spleen | DSC (%): 92.68\pm3.25 -> 94.50\pm2.64 | Improved |
| Use EBP instead of VNet | 3D organ segmentation · MSD spleen | DSC (%): 92.94\pm3.58 -> 92.01\pm4.50 | No clear effect |
| Train with prediction-generated updates during curriculum learning (ablation) | EBP · Validation | accuracy | Improved |
| Add multiple shell and inner-volume context channels instead of using only one boundary slice (ablation) | EBP · 3D organ segmentation | accuracy | Improved |
| Add noisy radius samples as spatial-consistency data augmentation (ablation) | EBP · Testing stability | stability | Improved |
| Lower the inner-pivot threshold slightly (ablation) | EBP spleen segmentation · Multi-organ CT, one unusual spleen case | DSC (%): 86.44% | Improved |
Closest papers by meaning
- Upping the Game: How 2D U-Net Skip Connections Flip 3D Segmentation (NeurIPS 2024 · similarity 0.87)
- VISTA3D: A Unified Segmentation Foundation Model For 3D Medical Imaging (CVPR 2025 · similarity 0.86)
- UniPro: Unified Multi-Mode Medical Image Segmentation from 2D Images to 3D Volumes via Propagation (NeurIPS 2026 · similarity 0.86)
- E2ENet: Dynamic Sparse Feature Fusion for Accurate and Efficient 3D Medical Image Segmentation (NeurIPS 2024 · similarity 0.85)
- ToNNO: Tomographic Reconstruction of a Neural Network's Output for Weakly Supervised Segmentation of 3D Medical Images (CVPR 2024 · similarity 0.85)
- EffiDec3D: An Optimized Decoder for High-Performance and Efficient 3D Medical Image Segmentation (CVPR 2025 · 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.
