用可编程椭球体生成心血管结构，实现几何属性精准控制。
CardioComposer: Leveraging Differentiable Geometry for Compositional Control of Anatomical Diffusion Models
- 用椭球体作为可解释的几何基元，构建多类解剖标签图
- 通过体素级几何矩设计可微测量函数，实现属性解耦控制
- 支持心脏、血管等非凸结构，适合医学影像生成与器械评估
3D心血管解剖生成模型可用于临床研究和医疗设备评估，但面临几何可控性与真实感之间的权衡。本文提出CardioComposer：一种在推理时使用的可编程框架，从可解释的椭球体基元生成多类别解剖标签图。这些基元表示离散子结构的尺寸、形状和位置等几何属性。我们特别设计基于体素级几何矩的可微测量函数，使扩散模型采样过程中可进行基于损失的梯度引导。实验表明，这些损失能以解耦方式约束单个几何属性，并实现对多个子结构的组合式控制。最后，验证该方法适用于包含非凸子结构的多种解剖系统，涵盖心脏、血管和骨骼器官。代码已开源：https://github.com/kkadry/CardioComposer。
原文摘要 · Abstract (English)
Generative models of 3D cardiovascular anatomy can synthesize informative structures for clinical research and medical device evaluation, but face a trade-off between geometric controllability and realism. We propose CardioComposer: a programmable, inference-time framework for generating multi-class anatomical label maps from interpretable ellipsoidal primitives. These primitives represent geometric attributes such as the size, shape, and position of discrete substructures. We specifically develop differentiable measurement functions based on voxel-wise geometric moments, enabling loss-based gradient guidance during diffusion model sampling. We demonstrate that these losses can constrain individual geometric attributes in a disentangled manner and provide compositional control over multiple substructures. Finally, we show that our method is compatible with a broad range of anatomical systems containing non-convex substructures, spanning cardiac, vascular, and skeletal organs. We release our code at https://github.com/kkadry/CardioComposer.
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。