针对脑病灶分割难题，提出中心优先的高效模型
CenterMamba-SAM: Center-Prioritized Scanning and Temporal Prototypes for Brain Lesion Segmentation
- 采用中心优先扫描策略，增强对微小病灶的敏感性
- 跨切片原型记忆机制提升切片间一致性，无需人工标注
- 轻量适配器设计支持高效微调，适合临床部署
脑病灶分割因病灶小、对比度低、各向异性采样及切片间不连续而极具挑战。本文提出CenterMamba-SAM，一种端到端框架，冻结预训练主干网络，仅训练轻量级适配器实现高效微调。核心为CenterMamba编码器，采用新颖的3×3角-轴-中心短序列扫描策略，实现中心优先、轴向强化与对角补偿的信息聚合，提升对弱边界和微小病灶的感知能力，同时保持稀疏但高效的特征表示。记忆驱动的结构化提示生成器在相邻切片间维护原型库，自动合成可靠提示，无需用户交互，提升切片间连贯性。内存增强的多尺度解码器在多层级集成记忆注意力模块，结合深度监督与渐进式优化，在保留全局一致性的同时恢复精细细节。在多个公开基准上的实验表明，CenterMamba-SAM在脑病灶分割任务中达到当前最优性能。
原文摘要 · Abstract (English)
Brain lesion segmentation remains challenging due to small, low-contrast lesions, anisotropic sampling, and cross-slice discontinuities. We propose CenterMamba-SAM, an end-to-end framework that freezes a pretrained backbone and trains only lightweight adapters for efficient fine-tuning. At its core is the CenterMamba encoder, which employs a novel 3x3 corner-axis-center short-sequence scanning strategy to enable center-prioritized, axis-reinforced, and diagonally compensated information aggregation. This design enhances sensitivity to weak boundaries and tiny foci while maintaining sparse yet effective feature representation. A memory-driven structural prompt generator maintains a prototype bank across neighboring slices, enabling automatic synthesis of reliable prompts without user interaction, thereby improving inter-slice coherence. The memory-augmented multi-scale decoder integrates memory attention modules at multiple levels, combining deep supervision with progressive refinement to restore fine details while preserving global consistency. Extensive experiments on public benchmarks demonstrate that CenterMamba-SAM achieves state-of-the-art performance in brain lesion segmentation.
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。