# From Baseline to Follow-Up: Counterfactual Spine DXA Image Synthesis in UK Biobank Using a Causal Hierarchical Variational Autoencoder

arXiv: https://arxiv.org/abs/2605.22649 · HTML: https://mlsanity.com/paper/2605.22649/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 24 references that are in the map.
- First posted on arXiv 21 May 2026.

## Builds on (most cited first, 8 of 8)

- [NVAE: A Deep Hierarchical Variational Autoencoder](https://mlsanity.com/paper/2007.03898/) (2020)
- [Ladder Variational Autoencoders](https://mlsanity.com/paper/1602.02282/) (2016)
- [Deep Structural Causal Models for Tractable Counterfactual Inference](https://mlsanity.com/paper/2006.06485/) (2020)
- [Causal Inference and Causal Explanation with Background Knowledge](https://mlsanity.com/paper/1302.4972/) (2013)
- [CausalGAN: Learning Causal Implicit Generative Models with Adversarial Training](https://mlsanity.com/paper/1709.02023/) (2017)
- [Diffusion Causal Models for Counterfactual Estimation](https://mlsanity.com/paper/2202.10166/) (2022)
- [Unified Brain MR-Ultrasound Synthesis using Multi-Modal Hierarchical Representations](https://mlsanity.com/paper/2309.08747/) (2023)
- [Conditional Diffusion Model for Longitudinal Medical Image Generation](https://mlsanity.com/paper/2411.05860/) (2024)

## Abstract (arXiv)

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.