1
|
Narayanan A, Kong F, Shadden S. LinFlo-Net: A Two-Stage Deep Learning Method to Generate Simulation Ready Meshes of the Heart. J Biomech Eng 2024; 146:071005. [PMID: 38258957 DOI: 10.1115/1.4064527] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/16/2023] [Accepted: 01/19/2024] [Indexed: 01/24/2024]
Abstract
We present a deep learning model to automatically generate computer models of the human heart from patient imaging data with an emphasis on its capability to generate thin-walled cardiac structures. Our method works by deforming a template mesh to fit the cardiac structures to the given image. Compared with prior deep learning methods that adopted this approach, our framework is designed to minimize mesh self-penetration, which typically arises when deforming surface meshes separated by small distances. We achieve this by using a two-stage diffeomorphic deformation process along with a novel loss function derived from the kinematics of motion that penalizes surface contact and interpenetration. Our model demonstrates comparable accuracy with state-of-the-art methods while additionally producing meshes free of self-intersections. The resultant meshes are readily usable in physics based simulation, minimizing the need for postprocessing and cleanup.
Collapse
Affiliation(s)
- Arjun Narayanan
- Department of Mechanical Engineering, University of California, Berkeley, Berkeley, CA 94709
| | - Fanwei Kong
- Department of Pediatrics, Stanford University, Stanford, CA 94305
- Stanford University
| | - Shawn Shadden
- Department of Mechanical Engineering, University of California, Berkeley, Berkeley, CA 94709
| |
Collapse
|
2
|
Salvador M, Kong F, Peirlinck M, Parker DW, Chubb H, Dubin AM, Marsden AL. Digital twinning of cardiac electrophysiology for congenital heart disease. J R Soc Interface 2024; 21:20230729. [PMID: 38835246 DOI: 10.1098/rsif.2023.0729] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/08/2023] [Accepted: 03/15/2024] [Indexed: 06/06/2024] Open
Abstract
In recent years, blending mechanistic knowledge with machine learning has had a major impact in digital healthcare. In this work, we introduce a computational pipeline to build certified digital replicas of cardiac electrophysiology in paediatric patients with congenital heart disease. We construct the patient-specific geometry by means of semi-automatic segmentation and meshing tools. We generate a dataset of electrophysiology simulations covering cell-to-organ level model parameters and using rigorous mathematical models based on differential equations. We previously proposed Branched Latent Neural Maps (BLNMs) as an accurate and efficient means to recapitulate complex physical processes in a neural network. Here, we employ BLNMs to encode the parametrized temporal dynamics of in silico 12-lead electrocardiograms (ECGs). BLNMs act as a geometry-specific surrogate model of cardiac function for fast and robust parameter estimation to match clinical ECGs in paediatric patients. Identifiability and trustworthiness of calibrated model parameters are assessed by sensitivity analysis and uncertainty quantification.
Collapse
Affiliation(s)
- Matteo Salvador
- Institute for Computational and Mathematical Engineering, Stanford University , Stanford, CA, USA
- Cardiovascular Institute, Stanford University , Stanford, CA, USA
- Pediatric Cardiology, Stanford University , Stanford, CA, USA
| | - Fanwei Kong
- Institute for Computational and Mathematical Engineering, Stanford University , Stanford, CA, USA
- Cardiovascular Institute, Stanford University , Stanford, CA, USA
- Pediatric Cardiology, Stanford University , Stanford, CA, USA
| | - Mathias Peirlinck
- Department of Biomechanical Engineering, Delft University of Technology , Delft, The Netherlands
| | - David W Parker
- Stanford Research Computing Center, Stanford University , Stanford, CA, USA
| | - Henry Chubb
- Pediatric Cardiology, Stanford University , Stanford, CA, USA
| | - Anne M Dubin
- Pediatric Cardiology, Stanford University , Stanford, CA, USA
| | - Alison L Marsden
- Institute for Computational and Mathematical Engineering, Stanford University , Stanford, CA, USA
- Cardiovascular Institute, Stanford University , Stanford, CA, USA
- Pediatric Cardiology, Stanford University , Stanford, CA, USA
- Department of Bioengineering, Stanford University , Stanford, CA, USA
| |
Collapse
|
3
|
Pegolotti L, Pfaller MR, Rubio NL, Ding K, Brugarolas Brufau R, Darve E, Marsden AL. Learning reduced-order models for cardiovascular simulations with graph neural networks. Comput Biol Med 2024; 168:107676. [PMID: 38039892 PMCID: PMC10886437 DOI: 10.1016/j.compbiomed.2023.107676] [Citation(s) in RCA: 4] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/14/2023] [Revised: 10/23/2023] [Accepted: 11/06/2023] [Indexed: 12/03/2023]
Abstract
Reduced-order models based on physics are a popular choice in cardiovascular modeling due to their efficiency, but they may experience loss in accuracy when working with anatomies that contain numerous junctions or pathological conditions. We develop one-dimensional reduced-order models that simulate blood flow dynamics using a graph neural network trained on three-dimensional hemodynamic simulation data. Given the initial condition of the system, the network iteratively predicts the pressure and flow rate at the vessel centerline nodes. Our numerical results demonstrate the accuracy and generalizability of our method in physiological geometries comprising a variety of anatomies and boundary conditions. Our findings demonstrate that our approach can achieve errors below 3% for pressure and flow rate, provided there is adequate training data. As a result, our method exhibits superior performance compared to physics-based one-dimensional models while maintaining high efficiency at inference time.
Collapse
Affiliation(s)
- Luca Pegolotti
- Department of Pediatrics, Stanford University, United States of America; Institute for Computational and Mathematical Engineering, Stanford University, United States of America.
| | - Martin R Pfaller
- Department of Pediatrics, Stanford University, United States of America; Institute for Computational and Mathematical Engineering, Stanford University, United States of America
| | - Natalia L Rubio
- Department of Mechanical Engineering, Stanford University, United States of America
| | - Ke Ding
- Intel Corporation, United States of America
| | | | - Eric Darve
- Institute for Computational and Mathematical Engineering, Stanford University, United States of America; Department of Mechanical Engineering, Stanford University, United States of America
| | - Alison L Marsden
- Department of Pediatrics, Stanford University, United States of America; Institute for Computational and Mathematical Engineering, Stanford University, United States of America; Department of Mechanical Engineering, Stanford University, United States of America; Department of Bioengineering, Stanford University, United States of America
| |
Collapse
|
4
|
Salvador M, Kong F, Peirlinck M, Parker DW, Chubb H, Dubin AM, Marsden AL. Digital twinning of cardiac electrophysiology for congenital heart disease. BIORXIV : THE PREPRINT SERVER FOR BIOLOGY 2023:2023.11.27.568942. [PMID: 38076810 PMCID: PMC10705388 DOI: 10.1101/2023.11.27.568942] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Indexed: 12/21/2023]
Abstract
In recent years, blending mechanistic knowledge with machine learning has had a major impact in digital healthcare. In this work, we introduce a computational pipeline to build certified digital replicas of cardiac electrophysiology in pediatric patients with congenital heart disease. We construct the patient-specific geometry by means of semi-automatic segmentation and meshing tools. We generate a dataset of electrophysiology simulations covering cell-to-organ level model parameters and utilizing rigorous mathematical models based on differential equations. We previously proposed Branched Latent Neural Maps (BLNMs) as an accurate and efficient means to recapitulate complex physical processes in a neural network. Here, we employ BLNMs to encode the parametrized temporal dynamics of in silico 12-lead electrocardiograms (ECGs). BLNMs act as a geometry-specific surrogate model of cardiac function for fast and robust parameter estimation to match clinical ECGs in pediatric patients. Identifiability and trustworthiness of calibrated model parameters are assessed by sensitivity analysis and uncertainty quantification.
Collapse
Affiliation(s)
- Matteo Salvador
- Institute for Computational and Mathematical Engineering, Stanford University, California, USA
- Cardiovascular Institute, Stanford University, California, USA
- Pediatric Cardiology, Stanford University, California, USA
| | - Fanwei Kong
- Cardiovascular Institute, Stanford University, California, USA
- Pediatric Cardiology, Stanford University, California, USA
| | - Mathias Peirlinck
- Department of Biomechanical Engineering, Delft University of Technology, Delft, Netherlands
| | - David W Parker
- Stanford Research Computing Center, Stanford University, California, USA
| | - Henry Chubb
- Pediatric Cardiology, Stanford University, California, USA
| | - Anne M Dubin
- Pediatric Cardiology, Stanford University, California, USA
| | - Alison Lesley Marsden
- Department of Bioengineering, Stanford University, California, USA
- Institute for Computational and Mathematical Engineering, Stanford University, California, USA
- Cardiovascular Institute, Stanford University, California, USA
- Pediatric Cardiology, Stanford University, California, USA
| |
Collapse
|
5
|
Pham J, Wyetzner S, Pfaller MR, Parker DW, James DL, Marsden AL. svMorph: Interactive Geometry-Editing Tools for Virtual Patient-Specific Vascular Anatomies. J Biomech Eng 2023; 145:031001. [PMID: 36282508 PMCID: PMC9791670 DOI: 10.1115/1.4056055] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/06/2022] [Revised: 08/07/2022] [Indexed: 12/30/2022]
Abstract
We propose svMorph, a framework for interactive virtual sculpting of patient-specific vascular anatomic models. Our framework includes three tools for the creation of tortuosity, aneurysms, and stenoses in tubular vascular geometries. These shape edits are performed via geometric operations on the surface mesh and vessel centerline curves of the input model. The tortuosity tool also uses the physics-based Oriented Particles method, coupled with linear blend skinning, to achieve smooth, elastic-like deformations. Our tools can be applied separately or in combination to produce simulation-suitable morphed models. They are also compatible with popular vascular modeling software, such as simvascular. To illustrate our tools, we morph several image-based, patient-specific models to create a range of shape changes and simulate the resulting hemodynamics via three-dimensional, computational fluid dynamics. We also demonstrate the ability to quickly estimate the hemodynamic effects of the shape changes via the automated generation of associated zero-dimensional lumped-parameter models.
Collapse
Affiliation(s)
- Jonathan Pham
- Department of Mechanical Engineering, Stanford University, Stanford, CA 94305
| | - Sofia Wyetzner
- Department of Computer Science, Stanford University, Stanford, CA 94305
| | - Martin R Pfaller
- Department of Pediatrics, Stanford University, Stanford, CA 94305
| | - David W Parker
- Stanford Research Computing Center, Stanford University, Stanford, CA 94305
| | - Doug L James
- Department of Computer Science, Stanford University, Stanford, CA 94305
| | - Alison L Marsden
- Department of Bioengineering, Department of Pediatrics, Stanford University, Stanford, CA 94305
| |
Collapse
|
6
|
Kong F, Shadden SC. Learning Whole Heart Mesh Generation From Patient Images for Computational Simulations. IEEE TRANSACTIONS ON MEDICAL IMAGING 2023; 42:533-545. [PMID: 36327186 DOI: 10.1109/tmi.2022.3219284] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/16/2023]
Abstract
Patient-specific cardiac modeling combines geometries of the heart derived from medical images and biophysical simulations to predict various aspects of cardiac function. However, generating simulation-suitable models of the heart from patient image data often requires complicated procedures and significant human effort. We present a fast and automated deep-learning method to construct simulation-suitable models of the heart from medical images. The approach constructs meshes from 3D patient images by learning to deform a small set of deformation handles on a whole heart template. For both 3D CT and MR data, this method achieves promising accuracy for whole heart reconstruction, consistently outperforming prior methods in constructing simulation-suitable meshes of the heart. When evaluated on time-series CT data, this method produced more anatomically and temporally consistent geometries than prior methods, and was able to produce geometries that better satisfy modeling requirements for cardiac flow simulations. Our source code and pretrained networks are available at https://github.com/fkong7/HeartDeformNets.
Collapse
|
7
|
Laumer F, Amrani M, Manduchi L, Beuret A, Rubi L, Dubatovka A, Matter CM, Buhmann JM. Weakly supervised inference of personalized heart meshes based on echocardiography videos. Med Image Anal 2023; 83:102653. [PMID: 36327655 DOI: 10.1016/j.media.2022.102653] [Citation(s) in RCA: 4] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/28/2022] [Revised: 08/27/2022] [Accepted: 10/08/2022] [Indexed: 12/12/2022]
Abstract
Echocardiography provides recordings of the heart chamber size and function and is a central tool for non-invasive diagnosis of heart diseases. It produces high-dimensional video data with substantial stochasticity in the measurements, which frequently prove difficult to interpret. To address this challenge, we propose an automated framework to enable the inference of a high resolution personalized 4D (3D plus time) surface mesh of the cardiac structures from 2D echocardiography video data. Inferring such shape models arises as a key step towards accurate personalized simulation that enables an automated assessment of the cardiac chamber morphology and function. The proposed method is trained using only unpaired echocardiography and heart mesh videos to find a mapping between these distinct visual domains in a self-supervised manner. The resulting model produces personalized 4D heart meshes, which exhibit a high correspondence with the input echocardiography videos. Furthermore, the 4D heart meshes enable the automatic extraction of echocardiographic variables, such as ejection fraction, myocardial muscle mass, and volumetric changes of chamber volumes over time with high temporal resolution.
Collapse
Affiliation(s)
- Fabian Laumer
- Institute for Machine Learning at ETH Zürich, Zürich, Switzerland.
| | - Mounir Amrani
- Institute for Machine Learning at ETH Zürich, Zürich, Switzerland
| | - Laura Manduchi
- Institute for Machine Learning at ETH Zürich, Zürich, Switzerland
| | - Ami Beuret
- Institute for Machine Learning at ETH Zürich, Zürich, Switzerland
| | - Lena Rubi
- Institute for Machine Learning at ETH Zürich, Zürich, Switzerland
| | - Alina Dubatovka
- Institute for Machine Learning at ETH Zürich, Zürich, Switzerland
| | | | | |
Collapse
|
8
|
Li X, Liu X, Deng X, Fan Y. Interplay between Artificial Intelligence and Biomechanics Modeling in the Cardiovascular Disease Prediction. Biomedicines 2022; 10:2157. [PMID: 36140258 PMCID: PMC9495955 DOI: 10.3390/biomedicines10092157] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/13/2022] [Revised: 08/26/2022] [Accepted: 08/28/2022] [Indexed: 11/16/2022] Open
Abstract
Cardiovascular disease (CVD) is the most common cause of morbidity and mortality worldwide, and early accurate diagnosis is the key point for improving and optimizing the prognosis of CVD. Recent progress in artificial intelligence (AI), especially machine learning (ML) technology, makes it possible to predict CVD. In this review, we first briefly introduced the overview development of artificial intelligence. Then we summarized some ML applications in cardiovascular diseases, including ML-based models to directly predict CVD based on risk factors or medical imaging findings and the ML-based hemodynamics with vascular geometries, equations, and methods for indirect assessment of CVD. We also discussed case studies where ML could be used as the surrogate for computational fluid dynamics in data-driven models and physics-driven models. ML models could be a surrogate for computational fluid dynamics, accelerate the process of disease prediction, and reduce manual intervention. Lastly, we briefly summarized the research difficulties and prospected the future development of AI technology in cardiovascular diseases.
Collapse
Affiliation(s)
- Xiaoyin Li
- Beijing Advanced Innovation Centre for Biomedical Engineering, Key Laboratory for Biomechanics and Mechanobiology of Chinese Education Ministry, School of Biological Science and Medical Engineering, Beihang University, Beijing 100083, China
| | - Xiao Liu
- Beijing Advanced Innovation Centre for Biomedical Engineering, Key Laboratory for Biomechanics and Mechanobiology of Chinese Education Ministry, School of Biological Science and Medical Engineering, Beihang University, Beijing 100083, China
| | - Xiaoyan Deng
- Beijing Advanced Innovation Centre for Biomedical Engineering, Key Laboratory for Biomechanics and Mechanobiology of Chinese Education Ministry, School of Biological Science and Medical Engineering, Beihang University, Beijing 100083, China
| | - Yubo Fan
- Beijing Advanced Innovation Centre for Biomedical Engineering, Key Laboratory for Biomechanics and Mechanobiology of Chinese Education Ministry, School of Biological Science and Medical Engineering, Beihang University, Beijing 100083, China
- School of Engineering Medicine, Beihang University, Beijing 100083, China
| |
Collapse
|
9
|
Machine Learning for Cardiovascular Biomechanics Modeling: Challenges and Beyond. Ann Biomed Eng 2022; 50:615-627. [PMID: 35445297 DOI: 10.1007/s10439-022-02967-4] [Citation(s) in RCA: 19] [Impact Index Per Article: 9.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/08/2022] [Accepted: 04/07/2022] [Indexed: 12/13/2022]
Abstract
Recent progress in machine learning (ML), together with advanced computational power, have provided new research opportunities in cardiovascular modeling. While classifying patient outcomes and medical image segmentation with ML have already shown significant promising results, ML for the prediction of biomechanics such as blood flow or tissue dynamics is in its infancy. This perspective article discusses some of the challenges in using ML for replacing well-established physics-based models in cardiovascular biomechanics. Specifically, we discuss the large landscape of input features in 3D patient-specific modeling as well as the high-dimensional output space of field variables that vary in space and time. We argue that the end purpose of such ML models needs to be clearly defined and the tradeoff between the loss in accuracy and the gained speedup carefully interpreted in the context of translational modeling. We also discuss several exciting venues where ML could be strategically used to augment traditional physics-based modeling in cardiovascular biomechanics. In these applications, ML is not replacing physics-based modeling, but providing opportunities to solve ill-defined problems, improve measurement data quality, enable a solution to computationally expensive problems, and interpret complex spatiotemporal data by extracting hidden patterns. In summary, we suggest a strategic integration of ML in cardiovascular biomechanics modeling where the ML model is not the end goal but rather a tool to facilitate enhanced modeling.
Collapse
|
10
|
Bracamonte JH, Saunders SK, Wilson JS, Truong UT, Soares JS. Patient-Specific Inverse Modeling of In Vivo Cardiovascular Mechanics with Medical Image-Derived Kinematics as Input Data: Concepts, Methods, and Applications. APPLIED SCIENCES-BASEL 2022; 12:3954. [PMID: 36911244 PMCID: PMC10004130 DOI: 10.3390/app12083954] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/16/2022]
Abstract
Inverse modeling approaches in cardiovascular medicine are a collection of methodologies that can provide non-invasive patient-specific estimations of tissue properties, mechanical loads, and other mechanics-based risk factors using medical imaging as inputs. Its incorporation into clinical practice has the potential to improve diagnosis and treatment planning with low associated risks and costs. These methods have become available for medical applications mainly due to the continuing development of image-based kinematic techniques, the maturity of the associated theories describing cardiovascular function, and recent progress in computer science, modeling, and simulation engineering. Inverse method applications are multidisciplinary, requiring tailored solutions to the available clinical data, pathology of interest, and available computational resources. Herein, we review biomechanical modeling and simulation principles, methods of solving inverse problems, and techniques for image-based kinematic analysis. In the final section, the major advances in inverse modeling of human cardiovascular mechanics since its early development in the early 2000s are reviewed with emphasis on method-specific descriptions, results, and conclusions. We draw selected studies on healthy and diseased hearts, aortas, and pulmonary arteries achieved through the incorporation of tissue mechanics, hemodynamics, and fluid-structure interaction methods paired with patient-specific data acquired with medical imaging in inverse modeling approaches.
Collapse
Affiliation(s)
- Johane H. Bracamonte
- Department of Mechanical and Nuclear Engineering, Virginia Commonwealth University, Richmond, VA 23284, USA
| | - Sarah K. Saunders
- Department of Mechanical and Nuclear Engineering, Virginia Commonwealth University, Richmond, VA 23284, USA
| | - John S. Wilson
- Department of Biomedical Engineering and Pauley Heart Center, Virginia Commonwealth University, Richmond, VA 23219, USA
| | - Uyen T. Truong
- Department of Pediatrics, School of Medicine, Children’s Hospital of Richmond at Virginia Commonwealth University, Richmond, VA 23219, USA
| | - Joao S. Soares
- Department of Mechanical and Nuclear Engineering, Virginia Commonwealth University, Richmond, VA 23284, USA
- Correspondence:
| |
Collapse
|
11
|
A deep-learning approach for direct whole-heart mesh reconstruction. Med Image Anal 2021; 74:102222. [PMID: 34543913 DOI: 10.1016/j.media.2021.102222] [Citation(s) in RCA: 24] [Impact Index Per Article: 8.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/17/2021] [Revised: 07/14/2021] [Accepted: 08/31/2021] [Indexed: 01/16/2023]
Abstract
Automated construction of surface geometries of cardiac structures from volumetric medical images is important for a number of clinical applications. While deep-learning-based approaches have demonstrated promising reconstruction precision, these approaches have mostly focused on voxel-wise segmentation followed by surface reconstruction and post-processing techniques. However, such approaches suffer from a number of limitations including disconnected regions or incorrect surface topology due to erroneous segmentation and stair-case artifacts due to limited segmentation resolution. We propose a novel deep-learning-based approach that directly predicts whole heart surface meshes from volumetric CT and MR image data. Our approach leverages a graph convolutional neural network to predict deformation on mesh vertices from a pre-defined mesh template to reconstruct multiple anatomical structures in a 3D image volume. Our method demonstrated promising performance of generating whole heart reconstructions with as good or better accuracy than prior deep-learning-based methods on both CT and MR data. Furthermore, by deforming a template mesh, our method can generate whole heart geometries with better anatomical consistency and produce high-resolution geometries from lower resolution input image data. Our method was also able to produce temporally-consistent surface mesh predictions for heart motion from CT or MR cine sequences, and therefore can potentially be applied for efficiently constructing 4D whole heart dynamics. Our code and pre-trained networks are available at https://github.com/fkong7/MeshDeformNet.
Collapse
|