Welcome to the UPF Digital Repository

Deep learning framework for real-time estimation of in-silico thrombotic risk indices in the left atrial appendage

Show simple item record

dc.contributor.author Morales Ferez, Xabier
dc.contributor.author Mill, Jordi
dc.contributor.author Juhl, Kristine Aavild
dc.contributor.author Acebes Pinilla, César
dc.contributor.author Iriart, Xavier
dc.contributor.author Legghe, Benoit
dc.contributor.author Cochet, Hubert
dc.contributor.author De Backer, Ole
dc.contributor.author Paulsen, Rasmus R.
dc.contributor.author Camara, Oscar
dc.date.accessioned 2022-06-21T05:57:12Z
dc.date.available 2022-06-21T05:57:12Z
dc.date.issued 2021
dc.identifier.citation Xabier Morales Ferez X, Mill J, Juhl KA, Acebes C, Iriart X, Legghe B, Cochet H, De Backer O, Paulsen RR, Camara O. Deep learning framework for real-time estimation of in-silico thrombotic risk indices in the left atrial appendage. Front. Physiol. 2021;12:694945. DOI: 10.3389/fphys.2021.694945
dc.identifier.issn 1664-042X
dc.identifier.uri http://hdl.handle.net/10230/53539
dc.description.abstract Patient-specific computational fluid dynamics (CFD) simulations can provide invaluable insight into the interaction of left atrial appendage (LAA) morphology, hemodynamics, and the formation of thrombi in atrial fibrillation (AF) patients. Nonetheless, CFD solvers are notoriously time-consuming and computationally demanding, which has sparked an ever-growing body of literature aiming to develop surrogate models of fluid simulations based on neural networks. The present study aims at developing a deep learning (DL) framework capable of predicting the endothelial cell activation potential (ECAP), an in-silico index linked to the risk of thrombosis, typically derived from CFD simulations, solely from the patient-specific LAA morphology. To this end, a set of popular DL approaches were evaluated, including fully connected networks (FCN), convolutional neural networks (CNN), and geometric deep learning. While the latter directly operated over non-Euclidean domains, the FCN and CNN approaches required previous registration or 2D mapping of the input LAA mesh. First, the superior performance of the graph-based DL model was demonstrated in a dataset consisting of 256 synthetic and real LAA, where CFD simulations with simplified boundary conditions were run. Subsequently, the adaptability of the geometric DL model was further proven in a more realistic dataset of 114 cases, which included the complete patient-specific LA and CFD simulations with more complex boundary conditions. The resulting DL framework successfully predicted the overall distribution of the ECAP in both datasets, based solely on anatomical features, while reducing computational times by orders of magnitude compared to conventional CFD solvers.
dc.description.sponsorship This work was supported by the Agency for Management of University and Research Grants of the Generalitat de Catalunya under the Grants for the Contracting of New Research Staff Programme—FI (2020-FI-B-00690) and the Spanish Ministry of Economy and Competitiveness under the Programme for the Formation of Doctors (PRE2018-084062), the Maria de Maeztu Units of Excellence Programme (MDM-2015-0502) and the Retos Investigación project (RTI2018-101193-B-I00). Additionally, this work was supported by the H2020 EU SimCardioTest project (Digital transformation in Health and Care SC1-DTH-06-2020; grant agreement No. 101016496).
dc.format.mimetype application/pdf
dc.language.iso eng
dc.publisher Frontiers
dc.relation.ispartof Frontiers in physiology. 2021;12:694945.
dc.rights © 2021 Morales Ferez, Mill, Juhl, Acebes, Iriart, Legghe, Cochet, De Backer, Paulsen and Camara. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
dc.rights.uri https://creativecommons.org/licenses/by/4.0/
dc.title Deep learning framework for real-time estimation of in-silico thrombotic risk indices in the left atrial appendage
dc.type info:eu-repo/semantics/article
dc.identifier.doi http://doi.org/10.3389/fphys.2021.694945
dc.subject.keyword geometric deep learning
dc.subject.keyword left atrial appendage
dc.subject.keyword convolutional neural network
dc.subject.keyword thrombus-atrial fibrillation
dc.subject.keyword computational fluid dynamics
dc.subject.keyword principal component analysis
dc.relation.projectID info:eu-repo/grantAgreement/EC/H2020/101016496
dc.relation.projectID info:eu-repo/grantAgreement/ES/2PE/PRE2018-084062
dc.rights.accessRights info:eu-repo/semantics/openAccess
dc.type.version info:eu-repo/semantics/publishedVersion

Thumbnail

This item appears in the following Collection(s)

Show simple item record

Search DSpace


Advanced Search

Browse

My Account

Statistics

Compliant to Partaking