D²Mamba：用可变形 Mamba 扫描分割视网膜微小病灶
Seeing the Small: Deformable Duality Mamba for Retinal Lesion Segmentation
眼科 AI 落地最怕漏掉微动脉瘤，这篇给了个能多提 10 个点 Dice 的开源方案。做医学影像分割的可以直接下代码复现，做 Mamba 架构改进的也能借鉴它的可变形扫描思路。
一篇新论文提出 D²Mamba，用于糖尿病视网膜病变（DR）病灶分割，核心思路是用全局上下文和形状自适应扫描来建模病灶区域的空间组织。微动脉瘤（MA）这类病灶只有几个像素大小、形状不规则，传统分割方法容易漏掉。
方法上，D²Mamba 把非因果状态空间对偶性与可变形 Mamba 扫描耦合，让扫描路径能贴合病灶的实际形状。在 DDR 数据集上做五折交叉验证，与代表性分割基线在相同训练协议下对比，并对每个组件做了消融实验。
结果显示 D²Mamba 取得 33.87% mIoU，比最强基线高 2.99 个百分点；增益最大的是最小的微动脉瘤，Dice 提升 10.06 个百分点。代码和预训练权重已在 GitHub 开源，可直接复现。
Seeing the Small: Deformable Duality Mamba for Retinal Lesion Segmentation
Diabetic retinopathy (DR) lesions vary widely in shape, and microaneurysms (MAs) span only a few pixels. We hypothesize that modeling the spatial organization of lesion regions, with global context and shape-adaptive scanning, improves the segmentation of such small and irregular lesions. To test this, we propose D$^2$Mamba, which couples non-causal state space duality with deformable Mamba scanning. We evaluate it with five-fold cross-validation on the DDR dataset, comparing against representative segmentation baselines under an identical training protocol, and conduct ablations on each component. D$^2$Mamba achieved the best overall performance, with 33.87% mIoU, 2.99 percentage points above the strongest baseline. The largest gain appeared on MAs, the smallest and most easily missed lesions, where Dice improved by 10.06 percentage points. These results confirm our hypothesis that spatially adaptive state space modeling benefits tiny-lesion segmentation. Code and pretrained weights are available at https://github.com/PUREPANEL1/D2Mamba.
本条情报归属 AITOP「论文」核心追踪栏目。在跨区域产业观察坐标中，该动态直接关联「AI 开发者工具链、Coding Agent 与工程化实践」研究主线，反映出当前技术演进与商业落地的最新风向。涉及核心实体与技术议题包括：D2Mamba、Mamba、医学影像分割、糖尿病视网膜病变，读者可通过下方标签进入对应专题页查阅历史脉络与关联对比。
信源核验说明：本文原始线索采编自「arXiv cs.LG」（@Chang Yu, Siqing Li, Yuanchen Liu, Zhenyu Bu, Luming Yang, Alper Yilmaz），经 AITOP 多维评分管线结构化提炼。