Non-Invasive Reconstruction of Cardiac Activation Dynamics Using Physics-Informed Neural Networks

• URL: http://arxiv.org/abs/2603.03832v1
• Date: Wed, 04 Mar 2026 08:33:16 GMT
• Title: Non-Invasive Reconstruction of Cardiac Activation Dynamics Using Physics-Informed Neural Networks
• Authors: Nathan Dermul, Hans Dierckx,
• Abstract summary: We present a physics-informed neural network framework for recovering cardiac activation patterns.<n>Our approach integrates nonlinear anisotropic modeling, heterogeneous fiber orientation, weak formulations of the governing mechanics, and finite-element loss functions to embed physical constraints directly into training.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Cardiac arrhythmogenesis is governed by complex electromechanical interactions that are not directly observable in vivo, motivating the development of non-invasive computational approaches for reconstructing three-dimensional activation dynamics. We present a physics-informed neural network framework for recovering cardiac activation patterns, active tension propagation, deformation fields, and hydrostatic pressure from measurable deformation data in simplified left ventricular geometries. Our approach integrates nonlinear anisotropic constitutive modeling, heterogeneous fiber orientation, weak formulations of the governing mechanics, and finite-element-based loss functions to embed physical constraints directly into training. We demonstrate that the proposed framework accurately reconstructs spatiotemporal activation dynamics under varying levels of measurement noise and reduced spatial resolution, while preserving global propagation patterns and activation timing. By coupling mechanistic modeling with data-driven inference, this method establishes a pathway toward patient-specific, non-invasive reconstruction of cardiac activation, with potential applications in digital phenotyping and computational support for arrhythmia assessment.

Related papers

• Learned Finite Element-based Regularization of the Inverse Problem in Electrocardiographic Imaging [33.8053325455413]
  We introduce a space-time regularization framework that couples temporal regularization with a learned Fields-of-Experts (FoE)<n>We derive a finite discrere element on cardiac surface meshes, prove Mosco-convergence, and develop a scalable optimization algorithm capable of handling the FoE term.
  arXiv  Detail & Related papers  (2026-02-07T09:44:55Z)
• Latent Interpolation Learning Using Diffusion Models for Cardiac Volume Reconstruction [26.7771170972558]
  existing methods face challenges, including reliance on predefined schemes, computational inefficiency, and dependence on additional semantic inputs.<n>We present a data-driven cardiac Latent Interpoltent Diffusion (CaLID) framework that can capture complex, non-temporal relationships between sparse slices.<n>Second, we design a computationally efficient method that operates in the latent space and speeds up 3D-heart upsampling by a factor of 24, reducing computational time.<n>Third, we extend our method to 2D+T data, enabling the effective modeling of temporal coherence.
  arXiv  Detail & Related papers  (2025-08-19T13:36:16Z)
• Nonperiodic dynamic CT reconstruction using backward-warping INR with regularization of diffeomorphism (BIRD) [9.894794660436693]
  This paper presents a novel INR-based framework, BIRD, for nonperiodic dynamic CT reconstruction.<n>It addresses these challenges through four key contributions: backward-warping deformation, motion-compensated analytical reconstruction, and dimensional-reduction design for efficient 4D coordinate encoding.<n>The framework enables more accurate dynamic CT reconstruction with potential clinical applications, such as one-beat cardiac reconstruction, cinematic image sequences for functional imaging, and motion artifact reduction in conventional CT scans.
  arXiv  Detail & Related papers  (2025-05-06T12:01:40Z)
• Physics-informed neural network estimation of active material properties in time-dependent cardiac biomechanical models [2.8763745263714005]
  This work investigates the application of physics-informed neural networks (PINNs) for inferring active contractility parameters in time-dependent cardiac biomechanical models.<n>We are able to reconstruct in various settings active stress fields in the presence of noise and with a high spatial resolution.<n>This approach opens a new pathway to significantly improve the diagnosis, treatment planning, and management of heart conditions associated with cardiac fibrosis.
  arXiv  Detail & Related papers  (2025-05-06T10:01:16Z)
• Generative System Dynamics in Recurrent Neural Networks [56.958984970518564]
  We investigate the continuous time dynamics of Recurrent Neural Networks (RNNs)<n>We show that skew-symmetric weight matrices are fundamental to enable stable limit cycles in both linear and nonlinear configurations.<n> Numerical simulations showcase how nonlinear activation functions not only maintain limit cycles, but also enhance the numerical stability of the system integration process.
  arXiv  Detail & Related papers  (2025-04-16T10:39:43Z)
• Leveraging Cardiovascular Simulations for In-Vivo Prediction of Cardiac Biomarkers [43.17768785084301]
  We train an amortized neural posterior estimator on a newly built large dataset of cardiac simulations.<n>We incorporate elements modeling effects to better align simulated data with real-world measurements.<n>The proposed framework can further integrate in-vivo data sources to refine its predictive capabilities on real-world data.
  arXiv  Detail & Related papers  (2024-12-23T13:05:17Z)
• Connectivity structure and dynamics of nonlinear recurrent neural networks [41.038855001225826]
  We develop a theory to analyze how connectivity structure shape high-dimensional collective activity in neural networks.<n>We show that connectivity structure can be invisible in single-neuron activities while dramatically shaping collective activity.
  arXiv  Detail & Related papers  (2024-09-03T15:08:37Z)
• Interpretable Spatio-Temporal Embedding for Brain Structural-Effective Network with Ordinary Differential Equation [56.34634121544929]
  In this study, we first construct the brain-effective network via the dynamic causal model. We then introduce an interpretable graph learning framework termed Spatio-Temporal Embedding ODE (STE-ODE) This framework incorporates specifically designed directed node embedding layers, aiming at capturing the dynamic interplay between structural and effective networks.
  arXiv  Detail & Related papers  (2024-05-21T20:37:07Z)
• Data-driven generation of plausible tissue geometries for realistic photoacoustic image synthesis [53.65837038435433]
  Photoacoustic tomography (PAT) has the potential to recover morphological and functional tissue properties. We propose a novel approach to PAT data simulation, which we refer to as "learning to simulate" We leverage the concept of Generative Adversarial Networks (GANs) trained on semantically annotated medical imaging data to generate plausible tissue geometries.
  arXiv  Detail & Related papers  (2021-03-29T11:30:18Z)
• Gradient Starvation: A Learning Proclivity in Neural Networks [97.02382916372594]
  Gradient Starvation arises when cross-entropy loss is minimized by capturing only a subset of features relevant for the task. This work provides a theoretical explanation for the emergence of such feature imbalance in neural networks.
  arXiv  Detail & Related papers  (2020-11-18T18:52:08Z)
• Limited-angle tomographic reconstruction of dense layered objects by dynamical machine learning [68.9515120904028]
  Limited-angle tomography of strongly scattering quasi-transparent objects is a challenging, highly ill-posed problem. Regularizing priors are necessary to reduce artifacts by improving the condition of such problems. We devised a recurrent neural network (RNN) architecture with a novel split-convolutional gated recurrent unit (SC-GRU) as the building block.
  arXiv  Detail & Related papers  (2020-07-21T11:48:22Z)
• Deep learning-based reduced order models in cardiac electrophysiology [0.0]
  We propose a new, nonlinear approach which exploits deep learning (DL) algorithms to obtain accurate and efficient reduced order models (ROMs) Our DL approach combines deep feedforward neural networks (NNs) and convolutional autoencoders (AEs) We show that the proposed DL-ROM framework can efficiently provide solutions to parametrized electrophysiology problems, thus enabling multi-scenario analysis in pathological cases.
  arXiv  Detail & Related papers  (2020-06-02T23:05:03Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.