DSpace Angular :: Browsing by Author "Sahli Costabal, Francisco"

Browsing by Author "Sahli Costabal, Francisco"

Now showing 1 - 20 of 22

Benchmarking physics-informed frameworks for data-driven hyperelasticity
(2023) Taç, Vahidullah; Linka, Kevin; Sahli Costabal, Francisco; Kuhl, Ellen; Tepole, Adrian Buganza
Data-driven methods have changed the way we understand and model materials. However, while providing unmatched flexibility, these methods have limitations such as reduced capacity to extrapolate, overfitting, and violation of physics constraints. Recently, frameworks that automatically satisfy these requirements have been proposed. Here we review, extend, and compare three promising data-driven methods: Constitutive Artificial Neural Networks (CANN), Input Convex Neural Networks (ICNN), and Neural Ordinary Differential Equations (NODE). Our formulation expands the strain energy potentials in terms of sums of convex non-decreasing functions of invariants and linear combinations of these. The expansion of the energy is shared across all three methods and guarantees the automatic satisfaction of objectivity, material symmetries, and polyconvexity, essential within the context of hyperelasticity. To benchmark the methods, we train them against rubber and skin stress–strain data. All three approaches capture the data almost perfectly, without overfitting, and have some capacity to extrapolate. This is in contrast to unconstrained neural networks which fail to make physically meaningful predictions outside the training range. Interestingly, the methods find different energy functions even though the prediction on the stress data is nearly identical. The most notable differences are observed in the second derivatives, which could impact performance of numerical solvers. On the rich data used in these benchmarks, the models show the anticipated trade-off between number of parameters and accuracy. Overall, CANN, ICNN and NODE retain the flexibility and accuracy of other data-driven methods without compromising on the physics. These methods are ideal options to model arbitrary hyperelastic material behavior.
Brain structural Changes Over Time in the Presence of a Brain Tumour and their Connection with Language Lateralization Changes and Language-Based Behavioural Outcomes
(2024) Solomons, Daniel; Sahli Costabal, Francisco; Rodríguez Fernández, María; Mendez Orellana, Carolina; Pontificia Universidad Católica de Chile. Instituto de Ingeniería Biológica y Médica
La fMRI se usa comúnmente para evaluar la lateralización del lenguaje, pero su eficacia puede verse afectada por deterioros cognitivos, neuroplasticidad y movimiento. En cambio, el análisis del volumen de materia gris (GMV) con VBM ofrece un enfoque complementario y más estable. Esta tesis explora cómo el GMV en regiones relacionadas con el lenguaje se correlaciona con la lateralización derivada de la fMRI, analizando datos de participantes sanos y pacientes con tumores cerebrales. Los hallazgos sugieren un papel matizado del hemisferio derecho en el lenguaje.
Data-driven anisotropic finite viscoelasticity using neural ordinary differential equations
(2023) Taç, Vahidullah; Rausch, Manuel K.; Sahli Costabal, Francisco; Tepole, Adrian Buganza
We develop a fully data-driven model of anisotropic finite viscoelasticity using neural ordinary differential equations as building blocks. We replace the Helmholtz free energy function and the dissipation potential with data-driven functions that a priori satisfy physics-based constraints such as objectivity and the second law of thermodynamics. Our approach enables modeling viscoelastic behavior of materials under arbitrary loads in three-dimensions even with large deformations and large deviations from the thermodynamic equilibrium. The data-driven nature of the governing potentials endows the model with much needed flexibility in modeling the viscoelastic behavior of a wide class of materials. We train the model using stress–strain data from biological and synthetic materials including human brain tissue, blood clots, natural rubber and human myocardium and show that the data-driven method outperforms traditional, closed-form models of viscoelasticity.
Data-driven tissue mechanics with polyconvex neural ordinary differential equations
(2022) Taç, Vahidullah; Sahli Costabal, Francisco; Tepole, Adrian Buganza
Data-driven methods are becoming an essential part of computational mechanics due to their advantages over traditional material modeling. Deep neural networks are able to learn complex material response without the constraints of closed-form models. However, data-driven approaches do not a priori satisfy physics-based mathematical requirements such as polyconvexity, a condition needed for the existence of minimizers for boundary value problems in elasticity. In this study, we use a recent class of neural networks, neural ordinary differential equations (N-ODEs), to develop data-driven material models that automatically satisfy polyconvexity of the strain energy. We take advantage of the properties of ordinary differential equations to create monotonic functions that approximate the derivatives of the strain energy with respect to deformation invariants. The monotonicity of the derivatives guarantees the convexity of the energy. The N-ODE material model is able to capture synthetic data generated from closed-form material models, and it outperforms conventional models when tested against experimental data on skin, a highly nonlinear and anisotropic material. We also showcase the use of the N-ODE material model in finite element simulations of reconstructive surgery. The framework is general and can be used to model a large class of materials, especially biological soft tissues. We therefore expect our methodology to further enable data-driven methods in computational mechanics.
Fast Characterization of Inducible Regions of Atrial Fibrillation Models With Multi-Fidelity Gaussian Process Classification
(2022) Gander, Lia; Pezzuto, Simone; Gharaviri, Ali; Krause, Rolf; Perdikaris, Paris; Sahli Costabal, Francisco
Computational models of atrial fibrillation have successfully been used to predict optimal ablation sites. A critical step to assess the effect of an ablation pattern is to pace the model from different, potentially random, locations to determine whether arrhythmias can be induced in the atria. In this work, we propose to use multi-fidelity Gaussian process classification on Riemannian manifolds to efficiently determine the regions in the atria where arrhythmias are inducible. We build a probabilistic classifier that operates directly on the atrial surface. We take advantage of lower resolution models to explore the atrial surface and combine seamlessly with high-resolution models to identify regions of inducibility. We test our methodology in 9 different cases, with different levels of fibrosis and ablation treatments, totalling 1,800 high resolution and 900 low resolution simulations of atrial fibrillation. When trained with 40 samples, our multi-fidelity classifier that combines low and high resolution models, shows a balanced accuracy that is, on average, 5.7% higher than a nearest neighbor classifier. We hope that this new technique will allow faster and more precise clinical applications of computational models for atrial fibrillation. All data and code accompanying this manuscript will be made publicly available at: https://github.com/fsahli/AtrialMFclass.
Generative hyperelasticity with physics-informed probabilistic diffusion fields
(2024) Tac, Vahidullah; Rausch, Manuel K.; Bilionis, Ilias; Sahli Costabal, Francisco; Tepole, Adrian Buganza
Many natural materials exhibit highly complex, nonlinear, anisotropic, and heterogeneous mechanical properties. Recently, it has been demonstrated that data-driven strain energy functions possess the flexibility to capture the behavior of these complex materials with high accuracy while satisfying physics-based constraints. However, most of these approaches disregard the uncertainty in the estimates and the spatial heterogeneity of these materials. In this work, we leverage recent advances in generative models to address these issues. We use as building block neural ordinary equations (NODE) that-by construction-create polyconvex strain energy functions, a key property of realistic hyperelastic material models. We combine this approach with probabilistic diffusion models to generate new samples of strain energy functions. This technique allows us to sample a vector of Gaussian white noise and translate it to NODE parameters thereby representing plausible strain energy functions. We extend our approach to spatially correlated diffusion resulting in heterogeneous material properties for arbitrary geometries. We extensively test our method with synthetic and experimental data on biological tissues and run finite element simulations with various degrees of spatial heterogeneity. We believe this approach is a major step forward including uncertainty in predictive, data-driven models of hyperelasticity.
How drugs modulate the performance of the human heart
(2022) Peirlinck, M.; Yao, J.; Sahli Costabal, Francisco; Kuhl, E.
Many drugs interact with ion channels in the cells of our heart and trigger heart rhythm disorders with potentially fatal consequences. Computational modeling can provide mechanistic insight into the onset and propagation of drug-induced arrhythmias, but the effect of drugs on the mechanical performance of the heart remains poorly understood. Here we establish a multiphysics framework that integrates the biochemical, electrical, and mechanical effects of drugs, from cellular excitation to cardiac contraction. For the example of the drug dofetilide, we show that drug concentrations of 5x and 8x increase the heart rate to 122 and 114 beats per minute, increase myofiber stretches by 5%, and decrease overall tissue relaxation by 6%. This results in inter-ventricular and atrial-ventricular dyssynchronies and changes in cardiac output by % and +7%. Our results emphasize the need for multiphysics modeling to better understand the mechanical implications of drug-induced arrhythmias. Knowing how different drug concentrations affect the performance of the heart has important clinical implications in drug safety evaluation and personalized medicine.
Machine learning modeling of lung mechanics: Assessing the variability and propagation of uncertainty in respiratory-system compliance and airway resistance
(2024) Barahona Yáñez, José Miguel; Sahli Costabal, Francisco; Hurtado Sepúlveda, Daniel
Background and Objective: Traditional assessment of patient response in mechanical ventilation relies on respiratory-system compliance and airway resistance. Clinical evidence has shown high variability in these parameters, highlighting the difficulty of predicting them before the start of ventilation therapy. This motivates the creation of computational models that can connect structural and tissue features with lung mechanics. In this work, we leverage machine learning (ML) techniques to construct predictive lung function models informed by non-linear finite element simulations, and use them to investigate the propagation of uncertainty in the lung mechanical response. Methods: We revisit a continuum poromechanical formulation of the lungs suitable for determining patient response. Based on this framework, we create high-fidelity finite element models of human lungs from medical images. We also develop a low-fidelity model based on an idealized sphere geometry. We then use these models to train and validate three ML architectures: single-fidelity and multi-fidelity Gaussian process regression, and artificial neural networks. We use the best predictive ML model to further study the sensitivity of lung response to variations in tissue structural parameters and boundary conditions via sensitivity analysis and forward uncertainty quantification. Codes are available for download at https://github.com/comp-medicine-uc/ML-lung-mechanics-UQ. Results: The low-fidelity model delivers a lung response very close to that predicted by high-fidelity simulations and at a fraction of the computational time. Regarding the trained ML models, the multi-fidelity GP model consistently delivers better accuracy than the single-fidelity GP and neural network models in estimating respiratory-system compliance and resistance. In terms of computational efficiency, our ML model delivers a massive speed-up of with respect to high-fidelity simulations. Regarding lung function, we observed an almost matched and non-linear behavior between specific structural parameters and chest wall stiffness with compliance. Also, we observed a strong modulation of airways resistance with tissue permeability. Conclusions: Our findings unveil the relevance of specific lung tissue parameters and boundary conditions in the respiratory-system response. Furthermore, we highlight the advantages of adopting a multi-fidelity ML approach that combines data from different levels to yield accurate and efficient estimates of clinical mechanical markers. We envision that the methods presented here can open the way to the development of predictive ML models of the lung response that can inform clinical decisions.
Multi-fidelity classification using Gaussian processes : Accelerating the prediction of large-scale computational models
(2019) Sahli Costabal, Francisco; Perdikaris, P.; Kuhl, E.; Hurtado Sepúlveda, Daniel
On the Accuracy of Eikonal Approximations in Cardiac Electrophysiology in the Presence of Fibrosis
(Springer, 2023) Gander, Lia; Krause, Rolf; Weiser, Martin; Sahli Costabal, Francisco; Pezzuto, Simone
Fibrotic tissue is one of the main risk factors for cardiac arrhythmias. It is therefore a key component in computational studies. In this work, we compare the monodomain equation to two eikonal models for cardiac electrophysiology in the presence of fibrosis. We show that discontinuities in the conductivity field, due to the presence of fibrosis, introduce a delay in the activation times. The monodomain equation and eikonal-diffusion model correctly capture these delays, contrarily to the classical eikonal equation. Importantly, a coarse space discretization of the monodomain equation amplifies these delays, even after accounting for numerical error in conduction velocity. The numerical discretization may also introduce artificial conduction blocks and hence increase propagation complexity. Therefore, some care is required when comparing eikonal models to the discretized monodomain equation.
Outbreak dynamics of COVID-19 in China and the United States
(2020) Peirlinck, M.; Linka, K.; Sahli Costabal, Francisco; Kuhl, E.
Outbreak dynamics of COVID-19 in Europe and the effect of travel restrictions
(2020) Linka, K.; Peirlinck, M.; Sahli Costabal, Francisco; Kuhl, E.
Physics-informed neural networks approach to predict heart displacement field and in-vivo myofiber strain
(2024) Solís Paredes, Rodrigo Ignacio; Sahli Costabal, Francisco; Pontificia Universidad Católica de Chile. Escuela de Ingeniería
La deformación en la dirección de las fibras del corazón, llamada myofiber strain ha surgido como una métrica del desempeño mecánico del tejido del corazón que considera su microestructura, a diferencia de las métricas tradicionales: deformación longitudinal, circunferencial y radial, que son calculadas de una forma meramente geométrica. Predicciones certeras del myofiber strain entrega resultados prometedores para predecir fallas cardíacas. Combinándolo con un campo de desplazamiento continuo del corazón, se abren oportunidades para una mejor predicción de la función cardíaca y posibles diagnósticos. Esta tesis analiza el desempeño y la implementación de una red neuronal informada por modelos físicos considerando una descripción de la topología de los datos dada por las funciones propias del operador de Laplace y una descripción de la energía hiperelástica del tejido cardíaco del ventrículo izquierdo mediante un modelo de active strain para predecir un campo de desplazamiento continuo y myofiber strain. Esto usualmente se ha logrado usando el método de elementos finitos, pero en este trabajo se va a demostrar que las redes neuronales tienen mejores resultados. Este trabajo usa un campo de desplazamiento obtenido con imágenes DENSE y las direcciones de las fibras del corazón obtenidas con cDTI, las cuales son imágenes de resonancia magnética. Los resultados experimentales prueban que la red neural informada por un modelo físico entrega mejores resultados que los obtenido con elementos finitos. Adicionalmente es capaz de predecir valores para la deformación en la dirección de las fibras del corazón dentro de los valores presentes en la literatura. Las imágenes de DENSE tienen un tiempo largo de adquisición, haciéndolo un procedimiento clínicamente poco aplicable, sin embargo, la red neuronal propuesta entrega excelentes resultados considerando una cantidad reducida de datos de DENSE, permitiendo bajar el tiempo de adquisición para estas imágenes y entregando resultados prometedores para su aplicabilidad clínica.
Physics-Informed Neural Networks for Cardiac Activation Mapping
(2020) Sahli Costabal, Francisco; Yang, Y. B.; Perdikaris, P.; Hurtado Sepúlveda, Daniel; Kuhl, E.
Physics-informed neural networks to learn cardiac fiber orientation from multiple electroanatomical maps
(2022) Ruiz Herrera, Carlos; Grandits, Thomas; Plank, Gernot; Perdikaris, Paris; Sahli Costabal, Francisco; Pezzuto, Simone
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 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.
Sex Differences in Drug-Induced Arrhythmogenesis
(2021) Peirlinck, Mathias; Sahli Costabal, Francisco; Kuhl, Ellen
The electrical activity in the heart varies significantly between men and women and results in a sex-specific response to drugs. Recent evidence suggests that women are more than twice as likely as men to develop drug-induced arrhythmia with potentially fatal consequences. Yet, the sex-specific differences in drug-induced arrhythmogenesis remain poorly understood. Here we integrate multiscale modeling and machine learning to gain mechanistic insight into the sex-specific origin of drug-induced cardiac arrhythmia at differing drug concentrations. To quantify critical drug concentrations in male and female hearts, we identify the most important ion channels that trigger male and female arrhythmogenesis, and create and train a sex-specific multi-fidelity arrhythmogenic risk classifier. Our study reveals that sex differences in ion channel activity, tissue conductivity, and heart dimensions trigger longer QT-intervals in women than in men. We quantify the critical drug concentration for dofetilide, a high risk drug, to be seven times lower for women than for men. Our results emphasize the importance of including sex as an independent biological variable in risk assessment during drug development. Acknowledging and understanding sex differences in drug safety evaluation is critical when developing novel therapeutic treatments on a personalized basis. The general trends of this study have significant implications on the development of safe and efficacious new drugs and the prescription of existing drugs in combination with other drugs.
Structural parameters determining the strength of the porcine vertebral body affected by tumors
(2011) Sahli Costabal, Francisco; Ramos Grez, Jorge; Pontificia Universidad Católica de Chile. Escuela de Ingeniería
Los factores de riesgo de fractura para pacientes afectados por metástasis en la columna vertebral no están claros. Los parámetros estructurales que explican el debilitamiento de la vértebra no han sido determinados. En este trabajo, desarrollamos un modelo de elementos finitos para predecir la resistencia de la vértebra afectada por tumores, y usamos este modelo para encontrar los parámetros estructurales que determinan la resistencia. Trece vértebras porcinas fueron aisladas y escaneadas. A ocho muestras se le crearon defectos artificiales. Luego todas las muestras fueron escaneadas nuevamente y comprimidas hasta la falla. Se crearon modelos de elementos finitos desde las imágenes del escaneo. Se usó un modelo de material elasto plástico y propiedades mecánicas relacionadas con el nivel de gris de la imagen. Se encontró una alta correlación entre las cargas de fluencia del modelo y las experimentales (r=0.964, p<0.001).
Structural parameters determining the strength of the porcine vertebral body affected by tumours
(2015) Sahli Costabal, Francisco; Cuellar, Jorge; Pérez, Alfonso; Fields, Aaron J.; Campos Daziano, Mauricio Andrés; Ramos Grez, Jorge
The Fibrotic Kernel Signature: Simulation-Free Prediction of Atrial Fibrillation
(2023) Sahli Costabal, Francisco; Banduc, Tomás; Gander, Lia; Pezzuto, Simone
We propose a fast classifier that is able to predict atrial fibrillation inducibility in patient-specific cardiac models. Our classifier is general and it does not require re-training for new anatomies, fibrosis patterns, and ablation lines. This is achieved by training the classifier on a variant of the Heat Kernel Signature (HKS). Here, we introduce the “fibrotic kernel signature” (FKS), which extends the HKS by incorporating fibrosis information. The FKS is fast to compute, when compared to standard cardiac models like the monodomain equation. We tested the classifier on 9 combinations of ablation lines and fibrosis patterns. We achieved maximum balanced accuracies with the classifiers ranging from 75.8% to 95.8%, when tested on single points. The classifier is also able to predict very well the overall inducibility of the model. We think that our classifier can speed up the calculation of inducibility maps in a way that is crucial to create better personalized ablation treatments within the time constraints of the clinical setting.
Visualizing the invisible: The effect of asymptomatic transmission on the outbreak dynamics of COVID-19
(2020) Peirlinck, Mathias; Linka, Kevin; Sahli Costabal, Francisco; Bhattacharya, Jay; Bendavid, Eran; Ioannidis, John P.A.; Kuhl, Ellen
Understanding the outbreak dynamics of the COVID-19 pandemic has important implications for successful containment and mitigation strategies. Recent studies suggest that the population prevalence of SARS-CoV-2 antibodies, a proxy for the number of asymptomatic cases, could be an order of magnitude larger than expected from the number of reported symptomatic cases. Knowing the precise prevalence and contagiousness of asymptomatic transmission is critical to estimate the overall dimension and pandemic potential of COVID-19. However, at this stage, the effect of the asymptomatic population, its size, and its outbreak dynamics remain largely unknown. Here we use reported symptomatic case data in conjunction with antibody seroprevalence studies, a mathematical epidemiology model, and a Bayesian framework to infer the epidemiological characteristics of COVID-19. Our model computes, in real time, the time-varying contact rate of the outbreak, and projects the temporal evolution and credible intervals of the effective reproduction number and the symptomatic, asymptomatic, and recovered populations. Our study quantifies the sensitivity of the outbreak dynamics of COVID-19 to three parameters: the effective reproduction number, the ratio between the symptomatic and asymptomatic populations, and the infectious periods of both groups. For nine distinct locations, our model estimates the fraction of the population that has been infected and recovered by Jun 15, 2020 to 24.15% (95% CI: 20.48%-28.14%) for Heinsberg (NRW, Germany), 2.40% (95% CI: 2.09%-2.76%) for Ada County (ID, USA), 46.19% (95% CI: 45.81%-46.60%) for New York City (NY, USA), 11.26% (95% CI: 7.21%-16.03%) for Santa Clara County (CA, USA), 3.09% (95% CI: 2.27%-4.03%) for Denmark, 12.35% (95% CI: 10.03%-15.18%) for Geneva Canton (Switzerland), 5.24% (95% CI: 4.84%-5.70%) for the Netherlands, 1.53% (95% CI: 0.76%-2.62%) for Rio Grande do Sul (Brazil), and 5.32% (95% CI: 4.77%-5.93%) for Belgium. Our method traces the initial outbreak date in Santa Clara County back to January 20, 2020 (95% CI: December 29, 2019–February 13, 2020). Our results could significantly change our understanding and management of the COVID-19 pandemic: A large asymptomatic population will make isolation, containment, and tracing of individual cases challenging. Instead, managing community transmission through increasing population awareness, promoting physical distancing, and encouraging behavioral changes could become more relevant.

Browsing by Author "Sahli Costabal, Francisco"

Results Per Page

Sort Options