引导采样而非卷积核网格：面向体积分割的几何引导采样算子
Steer the Sampling, Not the Kernel Grid: Geometry-Guided Sampling Operator for Volumetric Segmentation
- Monash University（莫纳什大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
该研究针对3D体积分割中精细结构易被卷积模糊的问题，提出几何引导采样算子，替换U-Net等骨干网络的下采样算子，在多医学影像数据集上提升分割性能并减少参数量。
AI中文摘要：
准确的3D分割是临床规划与随访中病灶定量评估及解剖结构映射的核心。细长、精细的解剖或病理结构（如血管）是极具挑战性的场景：一个体素级的边界误差即可断开分支，改变具有临床意义的拓扑结构。在编码器-解码器网络（如U-Net）中，重复的下采样和固定网格卷积会模糊或混叠精细结构，削弱方向线索，导致早期错误跨尺度传播。我们提出一种几何引导的局部算子，其作用是引导特征的采样位置，而非变形卷积核，该算子以统一形式同时支持特征细化（步长为1）和分辨率降低（步长大于1）。在每个体素处，该算子预测局部方向和有界步长，沿这些方向对称采样，并将成对样本转换为紧凑的几何与边界线索，同时进行轻量混合；跨尺度一致性在跳跃连接处对齐编码器与解码器特征，以减少几何不匹配。将该算子替换3D U-Net中所有步长为1和步长为2的算子，可在BraTS、MSD肝血管数据集和TDSC-ABUS数据集上取得一致提升，边界指标显著更优（例如BraTS的Dice从86.1升至88.9，HD95从7.1降至6.2；TDSC-ABUS的HD95从39.1降至27.8），同时参数规模从2.3M降至0.8M。我们进一步证明，该算子可集成到其他骨干网络（如nnU-Net、Swin-UNETR和MedNeXt）中，无需改变其宏观架构即可提供一致的性能提升。
英文摘要：
Accurate 3D segmentation is central to quantitative lesion assessment and anatomy mapping for clinical planning and follow-up. Thin, elongated, and fine anatomical/pathological structures (e.g., vessels) are a particularly challenging case: a one-voxel boundary error can disconnect a branch and change clinically relevant topology. In encoder-decoder networks (e.g., U-Net), repeated downsampling and fixed-grid convolution blur or alias fine structures and weaken orientation cues, so early mistakes propagate across scales. We propose a geometry-guided local operator that steers where features are sampled, rather than deforming convolutional kernels, under a single formulation for both feature refinement (stride 1) and resolution reduction (stride > 1). At each voxel, it predicts a local orientation and bounded step sizes, samples symmetrically along these directions, and transforms paired samples into compact geometric and boundary cues with lightweight mixing; a cross-scale consensus aligns encoder and decoder features at skip connections to reduce geometric mismatch. Replacing all stride 1 and stride 2 operators in a 3D U-Net yields consistent improvements on BraTS, MSD Hepatic Vessel, and TDSC-ABUS, with notably better boundary metrics (e.g., BraTS Dice 86.1 to 88.9, HD95 7.1 to 6.2; TDSC-ABUS HD95 39.1 to 27.8) while reducing parameters from 2.3M to 0.8M. We further demonstrate that the operator can be integrated into other backbones (e.g., nnU-Net, Swin-UNETR, and MedNeXt) without changing their macro-architectures while providing consistent performance gains.
