Flow-based conditional cardiac anatomy generation for virtual cohorts
2026-08-10 • Machine Learning
Machine LearningComputer Vision and Pattern Recognition
AI summaryⓘ
The authors developed CAN-FLOW, a new way to create realistic virtual heart shapes based on important patient details like sex, age, and body mass index. Unlike previous methods, their approach first learns how heart shapes can change naturally, then models how these changes depend on specific patient information. They tested CAN-FLOW on a large dataset and found it produced more accurate and varied heart shapes that match real clinical data better than older techniques. This helps build better virtual groups of heart models for medical research and simulations.
cardiac digital twinconditional generative modelsnormalizing flowsvariational autoencoderslatent representationsbiventricular anatomystochastic generationmetadata conditioningin silico clinical trialsUK Biobank
Authors
Konstantinos Kevopoulos, Beatrice Moscoloni, Benjamin Alheit, Cameron Beeche, Julio A. Chirinos, Alexander Heinlein, Mathias Peirlinck
Abstract
Cardiac digital twin research is moving from subject-specific anatomical replicas toward virtual cohorts that represent clinically relevant population subgroups. Yet access to representative imaging-derived anatomy datasets remains limited by cohort size, subgroup sparsity, and data-sharing constraints. Conditional generative models could help address this gap, but virtual cohorts are useful only if they preserve realistic, metadata-dependent anatomical variability. Existing cardiac anatomy generators largely rely on conditional variational autoencoders (cVAEs), which couple representation learning and metadata conditioning through a shared regularized latent prior. We introduce CAN-FLOW, a two-step Conditional ANatomy generation framework based on normalizing FLOWs that first learns geometry-only latent representations of diffeomorphic cardiac shape momenta and then models their sex-, age-, and body-mass-index-dependent distribution with a conditional normalizing flow. We trained CAN-FLOW on 2,208 healthy UK Biobank subjects and compared it with cVAEs across regularization strengths. CAN-FLOW generated plausible stochastic biventricular anatomies that better reproduced clinical phenotype distributions, metadata-dependent trends, subgroup variability, point-cloud coverage, and high-dimensional shape variability. Together, these results establish CAN-FLOW as a shareable framework for generating realistic, stochastically varying, metadata-conditioned biventricular anatomies for virtual cohort construction and in silico clinical trial workflows.