Research map / Detection and segmentation / CNN features
CROWn: A Unified Framework for Anti-Aliased Downsampling and Phase-Calibrated Fusion in 3D Medical Segmentation
Xingru Huang, Shuanghua Ye, Zhao Huang, Wenwen Tang, Huiyu Zhou, Zhiwen Zheng, Jin Liu, Xiaoshuai Zhang
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 uPCAD to encoder (ablation) | 3D U-Net · OIMHS | Dice: 93.18 -> 94.14 | Improved |
| add SE module instead of uPCAD (ablation) | 3D U-Net · OIMHS | Dice: 93.18 -> 93.89 | Improved |
| add OCF on skip pathway (ablation) | 3D U-Net · OIMHS | Dice: 93.18 -> 93.88 | Improved |
| expand uPCAD along W axis instead of D or H (ablation) | CROWn · OIMHS | Dice: 93.93 (D), 93.62 (H) -> 94.36 (W) | Improved |
| add anti-alias blur prefilter in OCF (ablation) | OCF · FLARE2022 | Dice: 89.15 -> 89.76 | Improved |
| add phase attention in OCF (ablation) | OCF · FLARE2022 | Dice: 89.26 -> 89.76 | Improved |
| use learned coset phases instead of fixed/shuffled (ablation) | OCF · FLARE2022 | Dice: 88.80 -> 89.76 | Improved |
| CROWn vs best baseline on MSD Lung Tumour | CROWn · MSD Lung Tumour | Dice: 73.29 -> 73.63 | Improved |
| CROWn vs strongest baseline on Dice across 15 datasets | CROWn · 15 CT/MRI/OCT benchmarks | Dice: e.g. 90.78 -> 91.05 on SegTHOR | Improved |
| CROWn boundary error HD95 vs baselines | CROWn · 15 benchmarks | HD95: HD95 e.g. 26.45 on SLIVER07 vs 25.15 SwinUNETR | Mixed |
Closest papers by meaning
- VISTA3D: A Unified Segmentation Foundation Model For 3D Medical Imaging (CVPR 2025 · similarity 0.86)
- EffiDec3D: An Optimized Decoder for High-Performance and Efficient 3D Medical Image Segmentation (CVPR 2025 · similarity 0.86)
- Upping the Game: How 2D U-Net Skip Connections Flip 3D Segmentation (NeurIPS 2024 · similarity 0.86)
- UniPro: Unified Multi-Mode Medical Image Segmentation from 2D Images to 3D Volumes via Propagation (NeurIPS 2026 · similarity 0.86)
- A Unified Degradation-Robust Approach to SSL and UDA for 3D Medical Images (AAAI 2025 · similarity 0.85)
- E2ENet: Dynamic Sparse Feature Fusion for Accurate and Efficient 3D Medical Image 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.
