Research map / Detection and segmentation / CNN features
EccoMamba: Enhanced Cross-hierarchical Continuity Orthogonal Mamba for Medical Image Segmentation
Junlin Xu, Jincan Li, Feifei Cui, Zhuang Zhang, Jialiang Yang, Shuting Jin, Qiangguo Jin, Yajie Meng
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 HAE module to base model (ablation) | EccoMamba base · ISIC 2018 | DSC: 88.52 -> 90.42 | Improved |
| add SCO module to base model (ablation) | EccoMamba base · ISIC 2018 | DSC: 88.52 -> 90.22 | Improved |
| combine HAE and SCO (ablation) | EccoMamba base · ISIC 2018 | DSC: 90.42 -> 91.18 | Improved |
| add SCO on top of HAE (ablation) | Base+HAE · ISIC 2018 | Sens: 90.51 -> 90.84 | No clear effect |
| place HAE in encoder only instead of encoder and decoder (ablation) | EccoMamba · ISIC 2018 | DSC: 90.51 -> 91.18 | Improved |
| place HAE in encoder only instead of decoder only (ablation) | EccoMamba · ISIC 2018 | DSC: 89.48 -> 91.18 | Improved |
| place HAE in encoder only instead of encoder and decoder (ablation) | EccoMamba · ISIC 2017 | DSC: 88.55 -> 89.39 | Improved |
| place HAE in encoder only instead of decoder only (ablation) | EccoMamba · ISIC 2017 | DSC: 88.76 -> 89.39 | Improved |
| use EccoMamba instead of VM-UNet | VM-UNet · Synapse | DSC: 80.42 -> 81.51 | Improved |
| use EccoMamba instead of VM-UNet | VM-UNet · ACDC | DSC: 91.04 -> 91.83 | Improved |
| use EccoMamba instead of VM-UNet | VM-UNet · Synapse | HD95: 24.84 -> 22.02 | Improved |
| use EccoMamba instead of VM-UNet | VM-UNet · ISIC 2017 | DSC: 86.35 -> 89.39 | Improved |
Closest papers by meaning
- EMCAD: Efficient Multi-scale Convolutional Attention Decoding for Medical Image Segmentation (CVPR 2024 · similarity 0.86)
- Mamba Goes HoME: Hierarchical Soft Mixture-of-Experts for 3D Medical Image Segmentation (NeurIPS 2025 · similarity 0.86)
- S³-Mamba: Small-Size-Sensitive Mamba for Lesion Segmentation (AAAI 2025 · similarity 0.86)
- ConDSeg: A General Medical Image Segmentation Framework via Contrast-Driven Feature Enhancement (AAAI 2025 · similarity 0.85)
- Unleashing the Potential of SAM for Medical Adaptation via Hierarchical Decoding (CVPR 2024 · similarity 0.85)
- Rethinking U-Net: Task-Adaptive Mixture of Skip Connections for Enhanced Medical Image Segmentation (AAAI 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.
