CSG-Mamba：用于内窥镜息肉分割的卷积评分门控视觉状态空间网络
CSG-Mamba: A Convolutional Scoring Gating Vision State Space Network for Endoscopic Polyp Segmentation
- School of Advanced Interdisciplinary Studies, Tiangong University（天津工业大学先进交叉学科研究院）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
针对现有视觉Mamba息肉分割模型易削弱局部几何连续性的问题，提出CSG-Mamba模型，在VM-UNet架构瓶颈处插入CSG模块，在两个息肉分割数据集上的多数指标优于基线。
AI中文摘要：
准确的息肉分割对计算机辅助结肠镜检查至关重要，但内窥镜图像常存在低对比度边界、黏膜纹理干扰、镜面高光及设备相关的外观偏移。视觉状态空间模型（SSMs）具备线性复杂度的高效长程建模能力，然而现有视觉Mamba分割模型通常将二维特征转换为一维扫描序列，这可能削弱局部几何连续性并过度平滑不规则轮廓。我们提出用于内窥镜息肉分割的卷积评分门控视觉状态空间网络CSG-Mamba，其构建于VM-UNet风格的非对称U型编解码器架构，在语义丰富的瓶颈处插入卷积评分门控（CSG）模块；CSG通过逐点卷积与大核深度卷积生成局部空间评分图，并以乘法门控重新校准状态空间特征。采用三个随机种子的实验显示，CSG-Mamba在Kvasir-SEG数据集上达到0.9220的Dice系数与15.87的HD95，在CVC-ColonDB数据集上达到0.7418的Dice系数与0.6570的mIoU，在多数重叠度与召回率指标上优于基线模型，同时保持具有竞争力的边界精度。
英文摘要：
Accurate polyp segmentation is critical for computer-aided colonoscopy, yet endoscopic images often contain low-contrast boundaries, mucosal texture interference, specular highlights, and device-dependent appearance shifts. Vision State Space Models (SSMs) provide efficient long-range modeling with linear complexity, but existing Vision Mamba segmentation models typically convert 2D features into 1D scanning sequences, which may weaken local geometric continuity and over-smooth irregular contours. We propose CSG-Mamba, a convolutional scoring gating Vision State Space network for endoscopic polyp segmentation. Built on a VM-UNet-style asymmetric U-shaped encoder-decoder, CSG-Mamba inserts a Convolutional Scoring Gating (CSG) module at the semantically rich bottleneck. CSG generates a local spatial score map through pointwise and large-kernel depthwise convolutions and recalibrates state-space features by multiplicative gating. Experiments with three random seeds show that CSG-Mamba achieves 0.9220 Dice and 15.87 HD95 on Kvasir-SEG, and 0.7418 Dice and 0.6570 mIoU on CVC-ColonDB, outperforming the baselines on most overlap and recall metrics while maintaining competitive boundary accuracy.
