ZODIAC：基于八叉树的零样本解剖结构补全扩散模型

中文摘要 AI 辅助

从术中超声图像中恢复完整的3D脊柱解剖结构是一个不适定的逆问题，因为必须从不完整且含噪声的观测结果中推断出完整结构。声学遮挡和有限的视场造成了大量未观测区域，而依赖视角的伪影导致专家对可见解剖结构的标注存在差异。当前的监督式超声形状补全方法依赖于合成生成的不完整-完整配对数据，以在预定义的模拟遮挡分布下学习条件映射。然而，真实术中遮挡并不一定遵循该分布，这会限制其对患者数据的泛化能力。因此，从含噪声的部分观测中进行准确且鲁棒的补全仍是一个未解决的问题。我们提出了一种零样本形状补全框架，该框架无需依赖模拟训练数据，即可从部分超声观测中重建整个腰椎脊柱。为了适应不可见且不规则的缺失结构模式，我们引入了混合补全机制，该机制在推理时将学习到的解剖先验与输入的部分几何结构相融合。该方法在以自适应八叉树结构表示的完整解剖形状上学习生成式扩散先验，从而能够在单次前向传播中高效地对完整脊柱进行建模。在体模和志愿者数据上的验证表明，将补全与预定义的损坏分布解耦可提高真实遮挡下的泛化能力，在HD95补全误差指标上，其性能优于全监督变体22%。代码和数据可在该https URL获取。

英文摘要

Recovering the full 3D spine anatomy from intraoperative ultrasound is an ill-posed inverse problem, as the complete structure must be inferred from incomplete and noisy observations. Acoustic occlusions and limited field of view create large unobserved regions, while view-dependent artifacts lead to variability in expert annotations of the visible anatomy. Current supervised ultrasound shape completion methods rely on synthetically generated incomplete-complete paired data to learn conditional mappings under a predefined distribution of simulated occlusions. However, real intraoperative occlusions do not necessarily follow this distribution, which can limit generalization to patient data. As a result, accurate and robust completion from noisy partial observations remains an unsolved problem. We propose a zero-shot shape completion framework that reconstructs the entire lumbar spine from partial ultrasound observations without relying on simulated training data. To accommodate unseen and irregular patterns of missing structures, we introduce blended completion, a mechanism that integrates the learned anatomical prior with incoming partial geometry at inference time. The method learns a generative diffusion prior over full anatomical shapes represented in an adaptive octree structure, enabling efficient modeling of the complete spine in a single forward pass. Validation on phantom and volunteer data shows that decoupling completion from a predefined corruption distribution improves generalisation under real occlusions, outperforming a fully supervised variant by 22% on HD95 completion error. Code and data are available at https://github.com/miruna20/ZODIAC.

发表机构

• Munich Center for Machine Learning (MCML)（慕尼黑机器学习中心）
• Konrad Zuse School of Excellence in Reliable AI (relAI)（康拉德·楚泽可靠AI卓越学院（relAI））

机构由 AI 辅助整理，请以论文原文为准。