AD-GBC：用于基于UNet的医学图像分割的各向异性粒球跳跃连接细化器
AD-GBC: Anisotropic Granular-Ball Skip-Connection Refiner for UNet-Based Medical Image Segmentation
AD-GBC 将原型推广为可学习的各向异性几何区域，并以全可微分方式聚合与重分配特征，为 UNet 类分割网络提供了一种即插即用的几何感知细化模块；其 Wasserstein 多样性损失和尺度一致性损失可防止中心坍缩，这种区域级表示思路可迁移到其他密集预测任务。
原文依据 AD-GBC aggregates local features into region-level semantics and redistributes the refined representation back to pixels in a fully differentiable manner
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论原型或区域注意力模块近期改进了医学图像分割，但仍存在两个基本局限：1）它们将每个语义概念表示为点或各向同性区域，无法捕捉真实特征分布固有的各向异性几何结构；2）许多方法依赖不可微的聚类或单向核加权，限制了形成连贯区域级表示的能力。我们通过各向异性可微分粒球（AD-GBC）模块解决这些问题，该模块将原型推广为可学习的几何区域，由中心和各向异性向量尺度参数化。AD-GBC 以全可微分的方式将局部特征聚合为区域级语义，并将细化后的表示重新分配到像素，从而在现代 UNet 风格架构内实现几何感知的细化。两个几何正则化器——基于 Wasserstein 的多样性损失和尺度一致性损失——缓解中心坍缩并促进稳定、形态良好的区域几何。当集成到两个强骨干网络（Rolling-UNet 和 U-KAN）时，AD-GBC 在四个广泛使用的医学分割基准（BUSI、GlaS、CVC-ClinicDB、ISIC17）上取得一致改进，表明所提出的几何区域公式在不同成像条件下具有良好的泛化能力。代码见 https://github.com/SiaShen-dot/AD-GBC。
英文原文摘要 1438 字符
Prototype or region-attention modules have recently improved medical image segmentation but still suffer from two fundamental limitations: 1) they represent each semantic concept as a point or isotropic region, failing to capture the inherently anisotropic geometry of real feature distributions; and 2) many rely on non-differentiable clustering or one-way kernel weighting, which restricts their ability to form coherent region-level representations. We address these issues with the Anisotropic Differentiable Granular-Ball (AD-GBC) module, which generalizes prototypes into learnable geometric regions parameterized by a center and an anisotropic vector scale. AD-GBC aggregates local features into region-level semantics and redistributes the refined representation back to pixels in a fully differentiable manner, enabling geometry-aware refinement within modern UNet-style architectures. Two geometric regularizers, a Wasserstein-based diversity loss and a scale consistency loss, mitigate center collapse and encourage stable, well-formed region geometry.AD-GBC yields consistent improvements across four widely used medical segmentation benchmarks (BUSI, GlaS, CVC-ClinicDB, ISIC17) when integrated into two strong backbones (Rolling-UNet and U-KAN), demonstrating that the proposed geometric region formulation generalizes well across different imaging conditions. The code is available at https://github.com/SiaShen-dot/AD-GBC.