A Diffusion Model for Simulation Ready Coronary Anatomy with Morpho-skeletal Control

TL;DR

This paper introduces a novel diffusion model framework for generating and editing coronary artery anatomies with controllable features, facilitating virtual device deployment simulations and mechanistic insights.

Contribution

The study develops a diffusion-based approach for synthesizing coronary anatomies with morpho-skeletal control, extending guidance strategies for continuous attribute conditioning.

Findings

Enables controllable synthesis of coronary anatomies

Allows editing of anatomical features based on mid-level constraints

Supports virtual device deployment simulations

Abstract

Virtual interventions enable the physics-based simulation of device deployment within coronary arteries. This framework allows for counterfactual reasoning by deploying the same device in different arterial anatomies. However, current methods to create such counterfactual arteries face a trade-off between controllability and realism. In this study, we investigate how Latent Diffusion Models (LDMs) can custom synthesize coronary anatomy for virtual intervention studies based on mid-level anatomic constraints such as topological validity, local morphological shape, and global skeletal structure. We also extend diffusion model guidance strategies to the context of morpho-skeletal conditioning and propose a novel guidance method for continuous attributes that adaptively updates the negative guiding condition throughout sampling. Our framework enables the generation and editing of coronary anatomy in a controllable manner, allowing device designers to derive mechanistic insights regarding anatomic variation and simulated device deployment.