A Conditional Flow Variational Autoencoder for Controllable Synthesis of Virtual Populations of Anatomy
This work addresses the need for generating plausible and controlled virtual populations of anatomy for in silico medical trials, representing an incremental improvement over existing methods.
The authors tackled the problem of generating virtual populations of anatomy for medical device trials by proposing a conditional flow variational autoencoder that enhances controllable synthesis, achieving superior performance over a standard cVAE in terms of generalisation, specificity, and preservation of clinically relevant biomarkers for cardiac left ventricles.
The generation of virtual populations (VPs) of anatomy is essential for conducting in silico trials of medical devices. Typically, the generated VP should capture sufficient variability while remaining plausible and should reflect the specific characteristics and demographics of the patients observed in real populations. In several applications, it is desirable to synthesise virtual populations in a \textit{controlled} manner, where relevant covariates are used to conditionally synthesise virtual populations that fit a specific target population/characteristics. We propose to equip a conditional variational autoencoder (cVAE) with normalising flows to boost the flexibility and complexity of the approximate posterior learnt, leading to enhanced flexibility for controllable synthesis of VPs of anatomical structures. We demonstrate the performance of our conditional flow VAE using a data set of cardiac left ventricles acquired from 2360 patients, with associated demographic information and clinical measurements (used as covariates/conditional information). The results obtained indicate the superiority of the proposed method for conditional synthesis of virtual populations of cardiac left ventricles relative to a cVAE. Conditional synthesis performance was evaluated in terms of generalisation and specificity errors and in terms of the ability to preserve clinically relevant biomarkers in synthesised VPs, that is, the left ventricular blood pool and myocardial volume, relative to the real observed population.