用因果模型生成真实可信的骨骼影像，支持随访预测分析。
From Baseline to Follow-Up: Counterfactual Spine DXA Image Synthesis in UK Biobank Using a Causal Hierarchical Variational Autoencoder
- 基于因果分层变分自编码器，结合元数据控制影像生成。
- 年龄干预后关键椎体形态变量与实际随访值高度一致。
- 适合医学影像合成、长期健康风险研究者使用。
双能X射线吸收测定法（DXA）广泛用于大规模骨骼评估，但学习可控制且可解释的特定解剖变异仍具挑战。本文提出一种元数据条件化的因果分层变分自编码器（CHVAE），用于从英国生物银行（UK Biobank, UKB）中基于首次影像访问的3,743张原始前后位（AP）脊柱DXA扫描，生成具有因果一致性的影像。模型以参与者基础属性和腰椎形态为条件。通过基线到随访设置下的抽象-干预-预测（Abduction-Action-Prediction, AAP）评估因果一致性：从基线图像中抽象潜在变量，将年龄干预至重复扫描值，并比较生成的反事实随访形态与实际测量值。结果表明，在年龄干预下，关键椎体形态变量表现出强绝对水平的一致性，支持了与干预对齐的解剖合理影像合成。
原文摘要 · Abstract (English)
Dual-energy X-ray absorptiometry (DXA) is widely used for large-scale skeletal assessment, yet learning controllable and interpretable factor-specific anatomical variation remains challenging. We propose a metadata-conditioned causal hierarchical variational autoencoder (CHVAE) for causally consistent generation of anteroposterior (AP) spine DXA images from the UK Biobank (UKB). The model is trained on 3,743 raw AP spine scans from the first imaging visit and conditioned on basic participant attributes and lumbar morphometry. Causal consistency is evaluated in a baseline-to-follow-up setting using abduction--action--prediction (AAP): latent variables are abducted from baseline images, age is intervened to the repeat-imaging value, and the resulting counterfactual follow-up morphometry is compared with observed repeat-imaging measurements. Results show strong absolute-level agreement for key vertebral morphometry variables under age intervention, supporting intervention-aligned synthesis of anatomically plausible DXA images.
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。