H-LDM: Hierarchical Latent Diffusion Models for Controllable and Interpretable PCG Synthesis from Clinical Metadata
This addresses data scarcity in cardiovascular disease diagnosis for AI systems, with incremental advancements in controllable synthesis.
The paper tackled the problem of scarce labeled pathological data for phonocardiogram (PCG) analysis by introducing H-LDM, a Hierarchical Latent Diffusion Model that generates clinically accurate and controllable PCG signals from metadata, achieving a Fréchet Audio Distance of 9.7, 92% attribute disentanglement, and improving rare disease classification accuracy by 11.3%.
Phonocardiogram (PCG) analysis is vital for cardiovascular disease diagnosis, yet the scarcity of labeled pathological data hinders the capability of AI systems. To bridge this, we introduce H-LDM, a Hierarchical Latent Diffusion Model for generating clinically accurate and controllable PCG signals from structured metadata. Our approach features: (1) a multi-scale VAE that learns a physiologically-disentangled latent space, separating rhythm, heart sounds, and murmurs; (2) a hierarchical text-to-biosignal pipeline that leverages rich clinical metadata for fine-grained control over 17 distinct conditions; and (3) an interpretable diffusion process guided by a novel Medical Attention module. Experiments on the PhysioNet CirCor dataset demonstrate state-of-the-art performance, achieving a Fréchet Audio Distance of 9.7, a 92% attribute disentanglement score, and 87.1% clinical validity confirmed by cardiologists. Augmenting diagnostic models with our synthetic data improves the accuracy of rare disease classification by 11.3\%. H-LDM establishes a new direction for data augmentation in cardiac diagnostics, bridging data scarcity with interpretable clinical insights.