Deep Structural Causal Shape Models
Rajat Rasal 11 Daniel C. Castro 22 Nick Pawlowski 22 Ben Glocker 11
Abstract
Causal reasoning provides a language to ask important interventional and counterfactual questions beyond purely statistical association. In medical imaging, for example, we may want to study the causal effect of genetic, environmental, or lifestyle factors on the normal and pathological variation of anatomical phenotypes. However, while anatomical shape models of 3D surface meshes, extracted from automated image segmentation, can be reliably constructed, there is a lack of computational tooling to enable causal reasoning about morphological variations. To tackle this problem, we propose deep structural causal shape models (CSMs), which utilise high-quality mesh generation techniques, from geometric deep learning, within the expressive framework of deep structural causal models. CSMs enable subject-specific prognoses through counterfactual mesh generation (“How would this patient’s brain structure change if they were ten years older?”), which is in contrast to most current works on purely population-level statistical shape modelling. We demonstrate the capabilities of CSMs at all levels of Pearl’s causal hierarchy through a number of qualitative and quantitative experiments leveragi
中文速览
想象一下你能问电脑"如果这位病人年龄大十岁，他的大脑结构会有什么变化"——这正是因果推断（causal reasoning）想做到的事，但此前没有工具能把这种推断用在三维解剖形状上。这篇论文提出了深度因果形状模型（Causal Shape Model, CSM），将几何深度学习中高质量的三维网格生成技术嵌入深度结构因果模型框架，让模型既能理解年龄、性别、脑体积等因素之间的因果关系，又能对具体某位患者的三维脑表面网格做"反事实"预测。研究者在英国生物银行近万例脑干三维表面数据上验证了方法，在Pearl因果层次的三个层级（关联、干预、反事实）均给出了定量和定性结果，显示CSM能生成解剖上合理、个体特异性的三维形状。这项工作填补了因果推断与三维几何建模之间的空白，有望为个体化预后模拟和虚拟随机对照试验提供新工具。
原文 arXiv:2208.10950;中英对照 + 大白话阅读 https://aha.fim.ai/paper/2208.10950v1