Research map / Detection and segmentation / CNN features
VesMamba: 3D Pulmonary Vessel Segmentation from CT images via Mamba with Structural Perception and Scale-aware Filtering
Zhipeng Liu, Guilian Chen, Zheng Jiang, Huisi Wu, Jing Qin
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 SSP module to baseline (ablation) | UMamba baseline · Parse22 | Dice: 85.94 -> 86.42 | Improved |
| add BSF module to baseline (ablation) | UMamba baseline · Parse22 | Dice: 85.94 -> 86.35 | Improved |
| add both SSP and BSF (ablation) | UMamba baseline · Lung79 | Dice: 84.49 -> 85.06 | Improved |
| add MCDecoder on top of SSP and BSF (ablation) | VesMamba · Parse22 | Dice: 86.55 -> 86.65 | Improved |
| use DSAC instead of plain convolution in SSP (ablation) | SSP · Parse22 | clDice: 86.89 -> 87.15 | Improved |
| use MSAG instead of self-attention at SSP bottleneck (ablation) | SSP · Parse22 | Dice: 86.38 -> 86.42 | Improved |
| use concatenation instead of addition in BSF (ablation) | BSF · Parse22 | Dice: 84.32 -> 85.75 | Improved |
| use ShiftConv instead of plain convolution in BSF (ablation) | BSF · Parse22 | Dice: 85.75 -> 86.35 | Improved |
| add gating mechanism that filters encoder features in BSF (ablation) | BSF · Parse22 | Dice: 85.84 -> 86.35 | Improved |
| add decoder feature constraint in MCDecoder (ablation) | MCDecoder · Lung79 | Dice: 84.67 -> 84.76 | Improved |
| use VesMamba instead of UMamba baseline | UMamba · Parse22 | Dice: 85.94 -> 86.65 | Improved |
| VesMamba versus LKM-UNet on cost | VesMamba · Parse22 | computational effort | Improved |
Closest papers by meaning
- vesselFM: A Foundation Model for Universal 3D Blood Vessel Segmentation (CVPR 2025 · similarity 0.87)
- S³-Mamba: Small-Size-Sensitive Mamba for Lesion Segmentation (AAAI 2025 · similarity 0.85)
- Cross-Modal Interactive Perception Network with Mamba for Lung Tumor Segmentation in PET-CT Images (CVPR 2025 · similarity 0.85)
- DeNVeR: Deformable Neural Vessel Representations for Unsupervised Video Vessel Segmentation (CVPR 2025 · similarity 0.85)
- Learning Dynamic Collaborative Network for Semi-supervised 3D Vessel Segmentation (CVPR 2025 · similarity 0.84)
- VISTA3D: A Unified Segmentation Foundation Model For 3D Medical Imaging (CVPR 2025 · 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.
