Physics-informed neural networks to learn cardiac fiber orientation from multiple electroanatomical maps

• URL: http://arxiv.org/abs/2201.12362v2
• Date: Tue, 1 Feb 2022 14:34:00 GMT
• Title: Physics-informed neural networks to learn cardiac fiber orientation from multiple electroanatomical maps
• Authors: Carlos Ruiz Herrera, Thomas Grandits, Gernot Plank, Paris Perdikaris, Francisco Sahli Costabal and Simone Pezzuto
• Abstract summary: We propose FiberNet, a method to estimate in-vivo the cardiac fiber architecture of the human atria from catheter recordings. We show that 3 maps are sufficient to accurately capture the fibers, also in thepresence of noise. We envision that FiberNet will help the creation of patient-specific models for personalized medicine.
• Score: 1.53934570513443
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: We propose FiberNet, a method to estimate in-vivo the cardiac fiber architecture of the human atria from multiple catheter recordings of the electrical activation. Cardiac fibers play a central rolein the electro-mechanical function of the heart, yet they aredifficult to determine in-vivo, and hence rarely truly patient-specificin existing cardiac models.FiberNet learns the fibers arrangement by solvingan inverse problem with physics-informed neural networks. The inverse problem amounts to identifyingthe conduction velocity tensor of a cardiac propagation modelfrom a set of sparse activation maps. The use of multiple mapsenables the simultaneous identification of all the componentsof the conduction velocity tensor, including the local fiber angle.We extensively test FiberNet on synthetic 2-D and 3-D examples, diffusion tensor fibers, and a patient-specific case. We show that 3 maps are sufficient to accurately capture the fibers, also in thepresence of noise. With fewer maps, the role of regularization becomesprominent. Moreover, we show that the fitted model can robustlyreproduce unseen activation maps. We envision that FiberNet will help the creation of patient-specific models for personalized medicine.The full code is available at http://github.com/fsahli/FiberNet.

Related papers

• Ensemble learning of the atrial fiber orientation with physics-informed neural networks [0.0]
  We propose Fibernet, a method for the automatic identification of the anisotropic conduction -- and thus fibers -- in the atria from local electrical recordings. We use an ensemble of neural networks to produce multiple samples, all fitting the observed data, and compute posterior statistics. Our approach can estimate the fiber orientation and conduction velocities in under 7 minutes with quantified uncertainty.
  arXiv  Detail & Related papers  (2024-10-30T18:45:19Z)
• Generation of patient specific cardiac chamber models using generative neural networks under a Bayesian framework for electroanatomical mapping [1.9336815376402723]
  A probabilistic machine learning model trained on a library of CT/MRI scans of the heart can be used during electroanatomical mapping. We introduce a Bayesian approach to surface reconstruction of cardiac chamber models from a sparse 3D point cloud data. We show how they provide insight into what the neural network learns from the segmented CT/MRI images used to train the network.
  arXiv  Detail & Related papers  (2023-11-27T03:47:33Z)
• Deep Learning-based Prediction of Electrical Arrhythmia Circuits from Cardiac Motion: An In-Silico Study [4.751438180388347]
  In cardiac electrophysiology, a primary diagnostic goal is to identify electrical triggers or drivers of heart rhythm disorders. It is currently impossible to map the three-dimensional morphology of the electrical waves throughout the entire heart muscle. Here, we demonstrate in computer simulations that it is possible to predict three-dimensional electrical wave dynamics from ventricular deformation mechanics.
  arXiv  Detail & Related papers  (2023-05-13T02:16:40Z)
• WarpPINN: Cine-MR image registration with physics-informed neural networks [2.338246743809955]
  Heart failure is typically diagnosed with a global function assessment, such as ejection fraction. We introduce WarpPINN, a physics-informed neural network to perform image registration to obtain local metrics of the heart deformation.
  arXiv  Detail & Related papers  (2022-11-22T19:48:02Z)
• Three-dimensional micro-structurally informed in silico myocardium -- towards virtual imaging trials in cardiac diffusion weighted MRI [58.484353709077034]
  We propose a novel method to generate a realistic numerical phantom of myocardial microstructure. In-silico tissue models enable evaluating quantitative models of magnetic resonance imaging.
  arXiv  Detail & Related papers  (2022-08-22T22:01:44Z)
• Three-dimensional microstructure generation using generative adversarial neural networks in the context of continuum micromechanics [77.34726150561087]
  This work proposes a generative adversarial network tailored towards three-dimensional microstructure generation. The lightweight algorithm is able to learn the underlying properties of the material from a single microCT-scan without the need of explicit descriptors.
  arXiv  Detail & Related papers  (2022-05-31T13:26:51Z)
• 3D Reconstruction of Curvilinear Structures with Stereo Matching DeepConvolutional Neural Networks [52.710012864395246]
  We propose a fully automated pipeline for both detection and matching of curvilinear structures in stereo pairs. We mainly focus on 3D reconstruction of dislocations from stereo pairs of TEM images.
  arXiv  Detail & Related papers  (2021-10-14T23:05:47Z)
• Learning atrial fiber orientations and conductivity tensors from intracardiac maps using physics-informed neural networks [7.70592139052601]
  We employ a recently developed approach, called physics informed neural networks, to learn the fiber orientations from electroanatomical maps. In particular, we train the neural network to weakly satisfy the anisotropic eikonal equation and to predict the measured activation times. The methodology is tested both in a synthetic example and for patient data.
  arXiv  Detail & Related papers  (2021-02-22T09:55:17Z)
• A reusable pipeline for large-scale fiber segmentation on unidirectional fiber beds using fully convolutional neural networks [68.8204255655161]
  We present an open computational pipeline to detect fibers in ex-situ X-ray computed tomography fiber beds. To separate the fibers in these samples, we tested four different architectures of fully convolutional neural networks. When comparing our neural network approach to a semi-supervised one, we obtained Dice and Matthews coefficients greater than $92.28 pm 9.65%$, reaching up to $98.42 pm 0.03 %$.
  arXiv  Detail & Related papers  (2021-01-13T00:58:29Z)
• Noise-Resilient Automatic Interpretation of Holter ECG Recordings [67.59562181136491]
  We present a three-stage process for analysing Holter recordings with robustness to noisy signal. First stage is a segmentation neural network (NN) with gradientdecoder architecture which detects positions of heartbeats. Second stage is a classification NN which will classify heartbeats as wide or narrow. Third stage is a boosting decision trees (GBDT) on top of NN features that incorporates patient-wise features.
  arXiv  Detail & Related papers  (2020-11-17T16:15:49Z)
• CS2-Net: Deep Learning Segmentation of Curvilinear Structures in Medical Imaging [90.78899127463445]
  We propose a generic and unified convolution neural network for the segmentation of curvilinear structures. We introduce a new curvilinear structure segmentation network (CS2-Net), which includes a self-attention mechanism in the encoder and decoder.
  arXiv  Detail & Related papers  (2020-10-15T03:06:37Z)

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.