Physics-informed neural networks for parameter estimation in blood flow models

Simple item page
dc.article.number108706
dc.catalogadordfo
dc.contributor.authorGaray Labra, Jeremías Esteban
dc.contributor.authorDunstan Escudero, Jocelyn Mariel
dc.contributor.authorUribe Arancibia, Sergio Andrés
dc.contributor.authorSahli Costábal, Francisco
dc.date.accessioned2025-03-18T12:32:52Z
dc.date.available2025-03-18T12:32:52Z
dc.date.issued2024
dc.description.abstractBackground: Physics-informed neural networks (PINNs) have emerged as a powerful tool for solving inverse problems, especially in cases where no complete information about the system is known and scatter measurements are available. This is especially useful in hemodynamics since the boundary information is often difficult to model, and high-quality blood flow measurements are generally hard to obtain. Methods: In this work, we use the PINNs methodology for estimating reduced-order model parameters and the full velocity field from scatter 2D noisy measurements in the aorta. Two different flow regimes, stationary and transient were studied. Results: We show robust and relatively accurate parameter estimations when using the method with simulated data, while the velocity reconstruction accuracy shows dependence on the measurement quality and the flow pattern complexity. Comparison with a Kalman filter approach shows similar results when the number of parameters to be estimated is low to medium. For a higher number of parameters, only PINNs were capable of achieving good results. Conclusion: The method opens a door to deep-learning-driven methods in the simulations of complex coupled physical systems.
dc.description.funderACIP
dc.description.funderANID
dc.description.funderFondecyt
dc.description.funderBasal Funds for Center of Excellence
dc.description.funderIMFD
dc.description.funderAC3E
dc.fuente.origenSCOPUS
dc.identifier.doi10.1016/j.compbiomed.2024.108706
dc.identifier.issn0010-4825
dc.identifier.scopusidSCOPUS_ID:85196029431
dc.identifier.urihttps://repositorio.uc.cl/handle/11534/102706
dc.information.autorucEscuela de Ingeniería; Garay Labra Jeremías Esteban; S/I; 1367093
dc.information.autorucEscuela de Ingeniería; Dunstan Escudero Jocelyn Mariel; S/I; 1285723
dc.information.autorucEscuela de Medicina; Uribe Arancibia Sergio Andres; S/I; 16572
dc.information.autorucEscuela de Ingeniería; Sahli Costabal Francisco; 0000-0002-2612-463X; 154857
dc.language.isoen
dc.nota.accesoContenido parcial
dc.revistaComputers in Biology and Medicine
dc.rightsacceso restringido
dc.subjectBlood flow
dc.subjectHemodynamics
dc.subjectPatient-specific model
dc.subjectPhysics-informed neural networks
dc.subjectReduced-order modeling
dc.subject.ddc620
dc.subject.deweyIngenieríaes_ES
dc.subject.ods03 Good health and well-being
dc.subject.odspa03 Salud y bienestar
dc.titlePhysics-informed neural networks for parameter estimation in blood flow models
dc.typeartículo
dc.volumen178
sipa.codpersvinculados1367093
sipa.codpersvinculados1285723
sipa.codpersvinculados16572
sipa.codpersvinculados154857
sipa.trazabilidadSCOPUS;2024-06-23
Files
Collections
Artículos de revistas