Abstract
Synthetic data generation plays a crucial role in medical research by mitigating privacy concerns and enabling large-scale patient data analysis. This study presents a beta-Variational Autoencoder Graph Convolutional Neural Network framework for generating synthetic Abdominal Aorta Aneurysms (AAA). Using a small real-world dataset, the approach extracts key anatomical features and captures complex statistical relationships within a compact disentangled latent space. To address data limitations, low-impact data augmentation based on Procrustes analysis was employed, preserving anatomical integrity. The generation strategies, both deterministic and stochastic, manage to enhance data diversity while ensuring realism. Compared to PCA-based approaches, the model performs more robustly on unseen data by capturing complex, nonlinear anatomical variations.
Please cite this paper as:
@article{fabbri2026graph,
title={Graph-Convolutional-Beta-{VAE} for Synthetic Abdominal Aortic Aneurysm Generation},
author={Fabbri, Francesco and Scarpolini, Martino Andrea and Iollo, Angelo and Viola, Francesco and Tudisco, Francesco},
journal={Medical \& Biological Engineering \& Computing},
volume={64},
number={3},
pages={827--845},
year={2026},
doi={10.1007/s11517-025-03491-y}
}