Shape-informed cardiac mechanics surrogates in data-scarce regimes via geometric encoding and generative augmentation
This work addresses the problem of accelerating high-fidelity cardiac simulations for clinical use, though it is incremental as it builds on existing surrogate and geometric encoding methods.
The paper tackled the challenge of generalizing surrogate models for cardiac mechanics across diverse anatomies in data-scarce settings by proposing a two-step framework that decouples geometric representation from physics learning, resulting in accurate predictions and generalization to unseen geometries with robustness to noisy or sparse inputs.
High-fidelity computational models of cardiac mechanics provide mechanistic insight into the heart function but are computationally prohibitive for routine clinical use. Surrogate models can accelerate simulations, but generalization across diverse anatomies is challenging, particularly in data-scarce settings. We propose a two-step framework that decouples geometric representation from learning the physics response, to enable shape-informed surrogate modeling under data-scarce conditions. First, a shape model learns a compact latent representation of left ventricular geometries. The learned latent space effectively encodes anatomies and enables synthetic geometries generation for data augmentation. Second, a neural field-based surrogate model, conditioned on this geometric encoding, is trained to predict ventricular displacement under external loading. The proposed architecture performs positional encoding by using universal ventricular coordinates, which improves generalization across diverse anatomies. Geometric variability is encoded using two alternative strategies, which are systematically compared: a PCA-based approach suitable for working with point cloud representations of geometries, and a DeepSDF-based implicit neural representation learned directly from point clouds. Overall, our results, obtained on idealized and patient-specific datasets, show that the proposed approaches allow for accurate predictions and generalization to unseen geometries, and robustness to noisy or sparsely sampled inputs.