用卷积评分门控提升内窥镜息肉分割精度
CSG-Mamba: A Convolutional Scoring Gating Vision State Space Network for Endoscopic Polyp Segmentation
- 在编码器-解码器瓶颈处加入卷积评分门控模块，增强局部几何连续性
- 在Kvasir-SEG上达0.9220 Dice，CVC-ColonDB上0.7418 Dice，优于基线模型
- 适合需要高精度边界分割的医疗图像分析场景
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、反光亮点及设备相关外观变化。视觉状态空间模型（SSMs）以线性复杂度实现高效长程建模，但现有基于Vision Mamba的分割模型通常将二维特征转为一维扫描序列，可能削弱局部几何连续性并过度平滑不规则轮廓。本文提出CSG-Mamba，一种用于内窥镜息肉分割的卷积评分门控视觉状态空间网络。基于VM-UNet式非对称U形编码器-解码器结构，在语义丰富的瓶颈层插入卷积评分门控（CSG）模块，通过逐点与大核深度卷积生成局部空间评分图，并以乘性门控重校准状态空间特征。三次随机种子实验表明，CSG-Mamba在Kvasir-SEG上达到0.9220 Dice和15.87 HD95，CVC-ColonDB上达0.7418 Dice和0.6570 mIoU，多数重叠与召回指标优于基线，同时保持良好的边界精度。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。