← 研踪 PaperTrailarXiv:2611.10032 · v1
GMD-Mamba: Lightweight 3D Medical Image Segmentation Using a Grouped Multi-Directional Mamba
首次提交 2026-11-05 21:07
版本更新 2026-11-05 21:07
雷达观测 2026-11-10 10:12
摘要
Mamba has the capability to capture global context in linear time for 3D medical image segmentation. However, existing methods employ Mamba with full-width directional scans at every resolution, keeping the model large (64-138M parameters and high FLOPs). We propose Grouped Multi-Directional (GMD) Mamba, a lightweight network based on the GMD scan that divides input channels $C$ into groups $G$ and flattens each group in different directions in one pass. This gives multi-directional context at $O(C^2/G)$ instead of $O(K \cdot C^2)$, where $K$ is the number of scan directions. Additionally, we employ Mamba only at the deepest encoder stages, resulting in 19.2M parameters. On BraTS2023, it achieves the best average Dice of 92.0% and the lowest HD95 of 2.7 at $\sim$1/7 the parameters of SegMamba-V2. For model validation, we also ran experiments on the MSD Spleen dataset, achieving competitive performance. The implementation details and code are publicly available at https://github.com/2802990u/GMD-Mamba.
作者备注：It is a four pages paper with 2 figures and submitted to ISBI2027
观测到的版本
相邻记录可能跳过中间版本；首次发现 v2 及以上也会标为版本更新。
v1 · 2026-11-05 21:07 · 最新观测版本
GMD-Mamba: Lightweight 3D Medical Image Segmentation Using a Grouped Multi-Directional Mamba
Mamba has the capability to capture global context in linear time for 3D medical image segmentation. However, existing methods employ Mamba with full-width directional scans at every resolution, keeping the model large (64-138M parameters and high FLOPs). We propose Grouped Multi-Directional (GMD) Mamba, a lightweight network based on the GMD scan that divides input channels $C$ into groups $G$ and flattens each group in different directions in one pass. This gives multi-directional context at $O(C^2/G)$ instead of $O(K \cdot C^2)$, where $K$ is the number of scan directions. Additionally, we employ Mamba only at the deepest encoder stages, resulting in 19.2M parameters. On BraTS2023, it achieves the best average Dice of 92.0% and the lowest HD95 of 2.7 at $\sim$1/7 the parameters of SegMamba-V2. For model validation, we also ran experiments on the MSD Spleen dataset, achieving competitive performance. The implementation details and code are publicly available at https://github.com/2802990u/GMD-Mamba.
查看此版本解读 →查看此版本原文 ↗