轻量级等变网络实现多器官分割，对姿态变化鲁棒性强
Augmented Equivariant Mesh Networks for Anatomical Segmentation
- 基于等变图神经网络，融合解剖先验与局部几何特征
- 在牙科扫描上姿态倾斜40度时，性能仅降25-26个IoU点
- 无需特定任务结构，适用于不同粒度的标注数据
解剖网格分割需在不规则表面几何上建模，且对患者任意体位和网格分辨率变化保持鲁棒性。现有任务专用的网格与点云方法不具备等变性，在测试时扰动下性能急剧下降，例如在口腔扫描分割中，40°倾斜时交并比（IoU）下降25-26点。本文提出EAMS（等变解剖网格分割器），基于等变网格神经网络（EMNN），在四种临床差异显著的任务上评估，涵盖边、顶点、面级别的监督。结合内在网格描述符与解剖先验（如基于PCA的牙弓和肝脏表面坐标系），并通过增强消息传递引入轻量级全局上下文。在颅内动脉瘤和口腔分割任务中，EAMS在无扰动输入下性能可媲美专用基线，且在几何扰动下保持稳定；在肝脏表面分割中展现出规范姿态精度与旋转鲁棒性的良好权衡。结果表明，一个参数量小于200万的轻量级等变框架，可在无需任务定制架构的前提下，跨多种标注类型实现稳健的解剖网格分割。
原文摘要 · Abstract (English)
Anatomical mesh segmentation requires models that operate directly on irregular surface geometry while remaining robust to arbitrary patient pose and mesh resolution variation. Existing task-specific mesh and point-cloud methods are not equivariant, and can degrade sharply under test-time perturbation, for example dropping by 25-26 IoU points on intraoral scan segmentation at $40^\circ$ tilt. We present EAMS, an Equivariant Anatomical Mesh Segmentor built on Equivariant Mesh Neural Networks (EMNN), and evaluate it across four clinically distinct tasks spanning edge-, vertex-, and face-level supervision. We combine intrinsic mesh descriptors with anatomy-aware priors, including PCA-derived frames for dental arches and liver surfaces, and augment message passing to provide lightweight global context. Across intracranial aneurysm and intraoral segmentation, EAMS variants are competitive with specialized baselines on unperturbed inputs while remaining stable under geometric perturbations, and on liver surfaces they expose a favorable trade-off between canonical-pose accuracy and rotation robustness. These results show that a lightweight ($<2$M parameters) equivariant framework can deliver robust anatomical mesh segmentation across diverse supervision types without task-specific architectures.
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。