Physics-informed neural networks to learn cardiac fiber orientation from multiple electroanatomical maps
Pontificia Universidad Católica de Chile（智利天主教大学）；University of Graz（格拉茨大学）；Medical University of Graz（格拉茨医科大学）；University of Pennsylvania（宾夕法尼亚大学）；Università della Svizzera italiana（瑞士意大利语区大学）
Carlos Ruiz Herrera, Thomas Grandits, Gernot Plank, Paris Perdikaris, Francisco Sahli Costabal, Simone Pezzuto
We propose FiberNet, a method to estimate \emph{in-vivo} the cardiac fiber architecture of the human atria from multiple catheter recordings of the electrical activation. Cardiac fibers play a central role in the electro-mechanical function of the heart, yet they are difficult to determine in-vivo, and hence rarely truly patient-specific in existing cardiac models. FiberNet learns the fiber arrangement by solving an inverse problem with physics-informed neural networks. The inverse problem amounts to identifying the conduction velocity tensor of a cardiac propagation model from a set of sparse activation maps. The use of multiple maps enables the simultaneous identification of all the components of 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 the presence of noise. With fewer maps, the role of regularization becomes prominent. Moreover, we show that the fitted model can robustly reproduce 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.
TU Graz（格拉茨技术大学）；BioTechMed-Graz（格拉茨生物技术医学中心）；Università della Svizzera italiana（瑞士意大利语大学）；Pontificia Universidad Católica de Chile（智利天主教大学）；University of Pennsylvania（宾夕法尼亚大学）；Medical University of Graz（格拉茨医科大学）
Electroanatomical maps are a key tool in the diagnosis and treatment of atrial fibrillation. Current approaches focus on the activation times recorded. However, more information can be extracted from the available data. The fibers in cardiac tissue conduct the electrical wave faster, and their direction could be inferred from activation times. In this work, we employ a recently developed approach, called physics informed neural networks, to learn the fiber orientations from electroanatomical maps, taking into account the physics of the electrical wave propagation. In particular, we train the n…
Ensemble learning of the atrial fiber orientation with physics-informed neural networks
Pontificia Universidad Católica de Chile（智利天主教大学）；University of Trento（特伦托大学）；Università della Svizzera italiana（瑞士意大利语大学）；Institute for Biological and Medical Engineering（生物与医学工程研究所）；Millennium Institute for Intelligent Healthcare Engineering, iHEALTH（千禧智能医疗工程研究所iHEALTH）
WarpPINN-fibers: improved cardiac strain estimation from cine-MR with physics-informed neural networks
Millennium Institute for Intelligent Healthcare Engineering, iHEALTH；Department of Mechanical；Metallurgical Engineering, School of Engineering, Pontificia Universidad Cat\'olica de Chile, Santiago, Chile；Institute for Biological；Medical Engineering, Schools of Engineering, Medicine
Physics-Informed Neural Operators for Cardiac Electrophysiology
Department of Informatics, King’s College London, UK（信息学院，伦敦国王学院，英国）；Research Department of Digital Twins in Healthcare, King’s College London, UK（医疗数字孪生研究部，伦敦国王学院，英国）
Physics-informed neural network estimation of active material properties in time-dependent cardiac biomechanical models
Department of Mathematics and Scientific Computing, NAWI Graz, University of Graz, Austria（数学与科学计算系，格拉茨大学，奥地利）；BioTechMed-Graz, Austria（格拉茨生物技术医学研究所，奥地利）；MOX, Department of Mathematics, Politecnico di Milano, Milano, Italy（MOX，米兰理工学院数学系，意大利）；Gottfried Schatz Research Center: Division of Biophysics, Medical University of Graz, Austria（戈特弗里德·施茨研究中心：生物物理部，格拉茨医科大学，奥地利）
WarpPINN: Cine-MR image registration with physics-informed neural networks
University of Bath（巴斯大学）；Pontificia Universidad Católica de Valparaíso（瓦尔帕莱索天主大学）；Millennium Institute for Intelligent Healthcare Engineering（千年智能医疗工程研究所）；Pontificia Universidad Católica de Chile（智利天主大学）
Universidad de Valladolid（巴利亚多利德大学）；King’s College London（伦敦国王学院）；Instituto Superior Técnico, Universidade de Lisboa（里斯本大学高等技术学院）；Centre for Marine Sciences - CCMAR（海洋科学中心（CCMAR））
First-pass perfusion cardiac magnetic resonance (FPP-CMR) is becoming an essential non-invasive imaging method for detecting deficits of myocardial blood flow, allowing the assessment of coronary heart disease. Nevertheless, acquisitions suffer from relatively low spatial resolution and limited heart coverage. Compressed sensing (CS) methods have been proposed to accelerate FPP-CMR and achieve higher spatial resolution. However, the long reconstruction times have limited the widespread clinical use of CS in FPP-CMR. Deep learning techniques based on supervised learning have emerged as alternat…
We present a methodology combining neural networks with physical principle constraints in the form of partial differential equations (PDEs). The approach allows to train neural networks while respecting the PDEs as a strong constraint in the optimisation as apposed to making them part of the loss function. The resulting models are discretised in space by the finite element method (FEM). The method applies to both stationary and transient as well as linear/nonlinear PDEs. We describe implementation of the approach as an extension of the existing FEM framework FEniCS and its algorithmic differen…
Personalized Topology-Informed Localization of Standard 12-Lead ECG Electrode Placement from Incomplete Cardiac MRIs for Efficient Cardiac Digital Twins
School of Electronics & Computer Science, University of Southampton（南安普顿大学电子与计算机科学学院）；University of Oxford（牛津大学）；National University of Singapore（新加坡国立大学）；School of Biomedical Engineering and Imaging Sciences, Kings College London（伦敦国王学院生物医学工程与影像科学学院）
Yale University（耶鲁大学）；Yale School of Medicine（耶鲁医学院）
Learning spatial-temporal correspondences in cardiac motion from images is important for understanding the underlying dynamics of cardiac anatomical structures. Many methods explicitly impose smoothness constraints such as the $\mathcal{L}_2$ norm on the displacement vector field (DVF), while usually ignoring biomechanical feasibility in the transformation. Other geometric constraints either regularize specific regions of interest such as imposing incompressibility on the myocardium or introduce additional steps such as training a separate network-based regularizer on physically simulated data…
Biomedical Imaging Research Institute, Cedars-Sinai Medical Center, United States Berlin Ultrahigh Field Facility (B.U.F.F.), Max Delbrück Center for Molecular Medicine in the Helmholtz Association (MDC), Germany Department of Imaging Physics, Delft University of Technology, Netherlands TUM School of Computation, Information；Technology, Technische Universität München, Germany Department of Surgery, Taipei Veterans General Hospital, Taiwan
Multiparametric mapping MRI has become a viable tool for myocardial tissue characterization. However, misalignment between multiparametric maps makes pixel-wise analysis challenging. To address this challenge, we developed a generalizable physics-informed deep-learning model using test-time adaptation to enable group image registration across contrast weighted images acquired from multiple physical models (e.g., a T1 mapping model and T2 mapping model). The physics-informed adaptation utilized the synthetic images from specific physics model as registration reference, allows for transductive l…
Physics-Guided Neural Networks for Intraventricular Vector Flow Mapping
INSA-Lyon（里昂国立应用科学学院）；Universite Claude Bernard Lyon 1（里昂第一大学克劳德·贝尔纳分校）；CNRS（法国国家科学研究中心）；Inserm（法国国家健康与医学研究院）；CREATIS（CREATIS研究所）；IMAG（IMAG研究所）；University of Montpellier（蒙彼利埃大学）；Univ. Grenoble Alpes（格勒诺布尔大学）；Grenoble INP（格勒诺布尔理工学院）；Hôpital Croix-Rousse, Hospices Civils de Lyon（里昂市立医院集团克鲁瓦鲁斯医院）；Hôpital Lyon Sud, Hospices Civils de Lyon（里昂市南医院）
IMC-PINN-FE: A Physics-Informed Neural Network for Patient-Specific Left Ventricular Finite Element Modeling with Image Motion Consistency and Biomechanical Parameter Estimation
Department of Bioengineering, Imperial College London（帝国理工学院生物工程系）
Johns Hopkins University School of Medicine（约翰斯·霍普金斯大学医学院）；Johns Hopkins University（约翰斯·霍普金斯大学）；Johns Hopkins Hospital（约翰斯·霍普金斯医院）
Visualizing disease-induced scarring and fibrosis in the heart on cardiac magnetic resonance (CMR) imaging with contrast enhancement (LGE) is paramount in characterizing disease progression and quantifying pathophysiological substrates of arrhythmias. However, segmentation and scar/fibrosis identification from LGE-CMR is an intensive manual process prone to large inter-observer variability. Here, we present a novel fully-automated anatomically-informed deep learning solution for left ventricle (LV) and scar/fibrosis segmentation and clinical feature extraction from LGE-CMR. The technology invo…
TAI-GAN: A Temporally and Anatomically Informed Generative Adversarial Network for early-to-late frame conversion in dynamic cardiac PET inter-frame motion correction
Yale University（耶鲁大学）；IBM Research（IBM研究院）；Yale New Haven Hospital（耶鲁-纽黑文医院）；Yale School of Medicine（耶鲁医学院）
Liquid Fourier Latent Dynamics Networks for fast GPU-based numerical simulations in computational cardiology
Institute for Computational and Mathematical Engineering, Stanford University（斯坦福大学计算与数学工程研究所）；Cardiovascular Institute, Stanford University（斯坦福大学心血管研究所）；Pediatric Cardiology, Stanford University（斯坦福大学儿科心脏病研究所）；Department of Bioengineering, Stanford University（斯坦福大学生物工程系）
University of Edinburgh（爱丁堡大学）；Fudan University（复旦大学）；Imperial College London（帝国理工学院）；Technical University of Munich（慕尼黑工业大学）
Myocardial motion and deformation are rich descriptors that characterize cardiac function. Image registration, as the most commonly used technique for myocardial motion tracking, is an ill-posed inverse problem which often requires prior assumptions on the solution space. In contrast to most existing approaches which impose explicit generic regularization such as smoothness, in this work we propose a novel method that can implicitly learn an application-specific biomechanics-informed prior and embed it into a neural network-parameterized transformation model. Particularly, the proposed method …
Atrial fibrillation is a heart rhythm disorder that affects tens of millions people worldwide. The most effective treatment is catheter ablation. This involves irreversible heating of abnormal cardiac tissue facilitated by electroanatomical mapping. However, it is difficult to consistently identify the triggers and sources that may initiate or perpetuate atrial fibrillation due to its chaotic behavior. We developed a patient-specific computational heart model that can accurately reproduce the activation patterns to help in localizing these triggers and sources. Our model has high spatial resol…
Imperial College London（帝国理工学院）；University of Edinburgh（爱丁堡大学）
Image registration is an ill-posed inverse problem which often requires regularisation on the solution space. In contrast to most of the current approaches which impose explicit regularisation terms such as smoothness, in this paper we propose a novel method that can implicitly learn biomechanics-informed regularisation. Such an approach can incorporate application-specific prior knowledge into deep learning based registration. Particularly, the proposed biomechanics-informed regularisation leverages a variational autoencoder (VAE) to learn a manifold for biomechanically plausible deformations…
