发表机构
Kahlert School of Computing, University of Utah; Scientific Computing and Imaging Institute, University of Utah（犹他大学卡勒特计算学院; 犹他大学科学计算与成像研究所）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究针对单轴切片传播的3D器官分割误差问题，提出推理时使用轴向、冠状、矢状三个正交种子，融合其传播标签，在多器官CT数据集上较单轴基线显著提升了分割性能。
AI 中文摘要
体素级密集标注仍是3D医学图像分割的主要瓶颈。Sli2Vol等单切片传播方法通过使用无标签配准将一个标注的种子切片传播至整个体积，减轻了该负担。但仅轴向传播会随与种子的距离累积误差，尤其是在表面距离指标上，因为它忽略了冠状和矢状方向的证据，因此未充分利用CT/MRI体积中可用的3D信息。为更好地利用体积几何，我们研究了关键的训练和推理选择对切片传播模型的影响，包括单轴与多轴无标签配准、单种子与多种子传播，以及正交种子配置。我们未从单个轴向种子传播，而是使用三个正交种子——一个轴向、一个冠状和一个矢状，并通过简单的无标签规则融合它们的传播标签。我们的结果表明，训练范式的影响有限：在离轴种子上应用经轴向训练的网络可捕获几乎所有改进，而显式三轴训练几乎无增益。相反，性能由推理时的种子几何驱动，尤其是正交性而非标注切片的数量，因为预算匹配的三轴对照无益处，甚至可能降低性能。在多器官CT队列上，以轴向Sli2Vol为骨干的正交种子初始化相比单轴基线，Dice提升21.9%，归一化表面Dice提升25.5%，平均豪斯多夫距离降低53.5%。
英文摘要
Dense voxel-level annotation remains a major bottleneck in 3D medical image segmentation. Single-slice propagation methods such as Sli2Vol reduce this burden by propagating one annotated seed slice through a volume using label-free registration. However, axial-only propagation accumulates errors with distance from the seed, especially in surface-distance metrics, because it ignores coronal and sagittal evidence and therefore underuses the 3D information available in CT/MRI volumes. To better leverage volumetric geometry, we study how key training and inference choices affect slice-propagation models, including single-axis versus multi-axis label-free registration, single-seed versus multi-seed propagation, and orthogonal seed configurations. Instead of propagating from a single axial seed, we use three orthogonal seeds---one axial, one coronal, and one sagittal---and fuse their propagated labels with a simple label-free rule. Our results show that the training paradigm has limited impact: an axially trained network applied to off-axis seeds captures nearly all the improvement, while explicit three-axis training adds little. Instead, performance is driven by inference-time seed geometry, especially orthogonality rather than the number of annotated slices, as a budget-matched three-axial control provides no benefit and can even degrade performance. On a multi-organ CT cohort, orthogonal seeding with the axial Sli2Vol backbone improves Dice by 21.9%, Normalized Surface Dice by 25.5%, and reduces Average Hausdorff Distance by 53.5% over the single-axis baseline.
Comments8 Pages Accepted at MLMI Workshop MICCAI 2026
