Application of feed forward and recurrent neural networks in simulation of left ventricular mechanics

Abstract An understanding of left ventricle (LV) mechanics is fundamental for designing better preventive, diagnostic, and treatment strategies for improved heart function. Because of the costs of clinical and experimental studies to treat and understand heart function, respectively, in-silico model...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Yaghoub Dabiri, Alex Van der Velden, Kevin L. Sack, Jenny S. Choy, Julius M. Guccione, Ghassan S. Kassab
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2020
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/d1e753bc8d8d4b1686bf77a7c7d2985d
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:d1e753bc8d8d4b1686bf77a7c7d2985d
record_format	dspace
spelling	oai:doaj.org-article:d1e753bc8d8d4b1686bf77a7c7d2985d2021-12-02T11:57:57ZApplication of feed forward and recurrent neural networks in simulation of left ventricular mechanics10.1038/s41598-020-79191-42045-2322https://doaj.org/article/d1e753bc8d8d4b1686bf77a7c7d2985d2020-12-01T00:00:00Zhttps://doi.org/10.1038/s41598-020-79191-4https://doaj.org/toc/2045-2322Abstract An understanding of left ventricle (LV) mechanics is fundamental for designing better preventive, diagnostic, and treatment strategies for improved heart function. Because of the costs of clinical and experimental studies to treat and understand heart function, respectively, in-silico models play an important role. Finite element (FE) models, which have been used to create in-silico LV models for different cardiac health and disease conditions, as well as cardiac device design, are time-consuming and require powerful computational resources, which limits their use when real-time results are needed. As an alternative, we sought to use deep learning (DL) for LV in-silico modeling. We used 80 four-chamber heart FE models for feed forward, as well as recurrent neural network (RNN) with long short-term memory (LSTM) models for LV pressure and volume. We used 120 LV-only FE models for training LV stress predictions. The active material properties of the myocardium and time were features for the LV pressure and volume training, and passive material properties and element centroid coordinates were features of the LV stress prediction models. For six test FE models, the DL error for LV volume was 1.599 ± 1.227 ml, and the error for pressure was 1.257 ± 0.488 mmHg; for 20 LV FE test examples, the mean absolute errors were, respectively, 0.179 ± 0.050 for myofiber, 0.049 ± 0.017 for cross-fiber, and 0.039 ± 0.011 kPa for shear stress. After training, the DL runtime was in the order of seconds whereas equivalent FE runtime was in the order of several hours (pressure and volume) or 20 min (stress). We conclude that using DL, LV in-silico simulations can be provided for applications requiring real-time results.Yaghoub DabiriAlex Van der VeldenKevin L. SackJenny S. ChoyJulius M. GuccioneGhassan S. KassabNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 10, Iss 1, Pp 1-11 (2020)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Yaghoub Dabiri Alex Van der Velden Kevin L. Sack Jenny S. Choy Julius M. Guccione Ghassan S. Kassab Application of feed forward and recurrent neural networks in simulation of left ventricular mechanics
description	Abstract An understanding of left ventricle (LV) mechanics is fundamental for designing better preventive, diagnostic, and treatment strategies for improved heart function. Because of the costs of clinical and experimental studies to treat and understand heart function, respectively, in-silico models play an important role. Finite element (FE) models, which have been used to create in-silico LV models for different cardiac health and disease conditions, as well as cardiac device design, are time-consuming and require powerful computational resources, which limits their use when real-time results are needed. As an alternative, we sought to use deep learning (DL) for LV in-silico modeling. We used 80 four-chamber heart FE models for feed forward, as well as recurrent neural network (RNN) with long short-term memory (LSTM) models for LV pressure and volume. We used 120 LV-only FE models for training LV stress predictions. The active material properties of the myocardium and time were features for the LV pressure and volume training, and passive material properties and element centroid coordinates were features of the LV stress prediction models. For six test FE models, the DL error for LV volume was 1.599 ± 1.227 ml, and the error for pressure was 1.257 ± 0.488 mmHg; for 20 LV FE test examples, the mean absolute errors were, respectively, 0.179 ± 0.050 for myofiber, 0.049 ± 0.017 for cross-fiber, and 0.039 ± 0.011 kPa for shear stress. After training, the DL runtime was in the order of seconds whereas equivalent FE runtime was in the order of several hours (pressure and volume) or 20 min (stress). We conclude that using DL, LV in-silico simulations can be provided for applications requiring real-time results.
format	article
author	Yaghoub Dabiri Alex Van der Velden Kevin L. Sack Jenny S. Choy Julius M. Guccione Ghassan S. Kassab
author_facet	Yaghoub Dabiri Alex Van der Velden Kevin L. Sack Jenny S. Choy Julius M. Guccione Ghassan S. Kassab
author_sort	Yaghoub Dabiri
title	Application of feed forward and recurrent neural networks in simulation of left ventricular mechanics
title_short	Application of feed forward and recurrent neural networks in simulation of left ventricular mechanics
title_full	Application of feed forward and recurrent neural networks in simulation of left ventricular mechanics
title_fullStr	Application of feed forward and recurrent neural networks in simulation of left ventricular mechanics
title_full_unstemmed	Application of feed forward and recurrent neural networks in simulation of left ventricular mechanics
title_sort	application of feed forward and recurrent neural networks in simulation of left ventricular mechanics
publisher	Nature Portfolio
publishDate	2020
url	https://doaj.org/article/d1e753bc8d8d4b1686bf77a7c7d2985d
work_keys_str_mv	AT yaghoubdabiri applicationoffeedforwardandrecurrentneuralnetworksinsimulationofleftventricularmechanics AT alexvandervelden applicationoffeedforwardandrecurrentneuralnetworksinsimulationofleftventricularmechanics AT kevinlsack applicationoffeedforwardandrecurrentneuralnetworksinsimulationofleftventricularmechanics AT jennyschoy applicationoffeedforwardandrecurrentneuralnetworksinsimulationofleftventricularmechanics AT juliusmguccione applicationoffeedforwardandrecurrentneuralnetworksinsimulationofleftventricularmechanics AT ghassanskassab applicationoffeedforwardandrecurrentneuralnetworksinsimulationofleftventricularmechanics
_version_	1718394777287786496

Application of feed forward and recurrent neural networks in simulation of left ventricular mechanics

Ejemplares similares