Coronary artery properties in atherosclerosis: A deep learning predictive model

被引:5
作者
Caballero, Ricardo [1 ]
Martinez, Miguel Angel [1 ,2 ]
Pena, Estefania [1 ,2 ]
机构
[1] Univ Zaragoza, Aragon Inst Engn Res I3A, Zaragoza, Spain
[2] Biomed Res Networking Ctr Bioengn Biomat & Nanome, Madrid, Spain
关键词
cardiovascular diseases; atheroma plaque; in silico modeling; deep learning; artificial neural network; INTRAVASCULAR ULTRASOUND; MATERNAL HYPERCHOLESTEROLEMIA; ENDOVASCULAR ELASTOGRAPHY; CIRCUMFERENTIAL STRESS; VULNERABLE PLAQUES; CAP THICKNESS; ESTIMATOR; QUANTIFICATION; CLASSIFICATION; VALIDATION;
D O I
10.3389/fphys.2023.1162436
中图分类号
Q4 [生理学];
学科分类号
071003 ;
摘要
In this work an Artificial Neural Network (ANN) was developed to help in the diagnosis of plaque vulnerability by predicting the Young modulus of the core (E ( core )) and the plaque (E ( plaque )) of atherosclerotic coronary arteries. A representative in silico database was constructed to train the ANN using Finite Element simulations covering the ranges of mechanical properties present in the bibliography. A statistical analysis to pre-process the data and determine the most influential variables was performed to select the inputs of the ANN. The ANN was based on Multilayer Perceptron architecture and trained using the developed database, resulting in a Mean Squared Error (MSE) in the loss function under 10(-7), enabling accurate predictions on the test dataset for E ( core ) and E ( plaque ). Finally, the ANN was applied to estimate the mechanical properties of 10,000 realistic plaques, resulting in relative errors lower than 3%.
引用
收藏
页数:11
相关论文
共 69 条
[1]   Basic concepts of artificial neural network (ANN) modeling and its application in pharmaceutical research [J].
Agatonovic-Kustrin, S ;
Beresford, R .
JOURNAL OF PHARMACEUTICAL AND BIOMEDICAL ANALYSIS, 2000, 22 (05) :717-727
[2]   Intima heterogeneity in stress assessment of atherosclerotic plaques [J].
Akyildiz, Ali C. ;
Speelman, Lambert ;
van Velzen, Bas ;
Stevens, Raoul R. F. ;
van der Steen, Antonius F. W. ;
Huberts, Wouter ;
Gijsen, Frank J. H. .
INTERFACE FOCUS, 2018, 8 (01)
[3]   Effects of intima stiffness and plaque morphology on peak cap stress [J].
Akyildiz, Ali C. ;
Speelman, Lambert ;
van Brummelen, Harald ;
Gutierrez, Miguel A. ;
Virmani, Renu ;
van der Lugt, Aad ;
van der Steen, Anton F. W. ;
Wentzel, Jolanda J. ;
Gijsen, Frank J. H. .
BIOMEDICAL ENGINEERING ONLINE, 2011, 10
[4]  
[Anonymous], 2011, Cardiovascular disease
[5]   Finite element modeling and intravascular ultrasound elastography of vulnerable plaques: parameter variation [J].
Baldewsing, RA ;
de Korte, CL ;
Schaar, JA ;
Mastik, F ;
van der Steen, AFW .
ULTRASONICS, 2004, 42 (1-9) :723-729
[6]  
Banegas JR., 2005, Hipertension, V22, P353, DOI 10.1016/S0212-8241(05)71587-5
[7]   DISTRIBUTION OF CIRCUMFERENTIAL STRESS IN RUPTURED AND STABLE ATHEROSCLEROTIC LESIONS - A STRUCTURAL-ANALYSIS WITH HISTOPATHOLOGICAL CORRELATION [J].
CHENG, GC ;
LOREE, HM ;
KAMM, RD ;
FISHBEIN, MC ;
LEE, RT .
CIRCULATION, 1993, 87 (04) :1179-1187
[8]   Machine Learning Techniques as a Helpful Tool Toward Determination of Plaque Vulnerability [J].
Cilla, Myriam ;
Martinez, Javier ;
Pena, Estefania ;
Angel Martinez, Miguel .
IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, 2012, 59 (04) :1155-1161
[9]   Characterization of fracture behavior of human atherosclerotic fibrous caps using a miniature single edge notched tensile test [J].
Davis, Lindsey A. ;
Stewart, Samantha E. ;
Carsten, Christopher G., III ;
Snyder, Bruce A. ;
Sutton, Michael A. ;
Lessner, Susan M. .
ACTA BIOMATERIALIA, 2016, 43 :101-111
[10]   Automatic quantification and characterization of coronary atherosclerosis with computed tomography coronary angiography: cross-correlation with intravascular ultrasound virtual histology [J].
de Graaf, Michiel A. ;
Broersen, Alexander ;
Kitslaar, Pieter H. ;
Roos, Cornelis J. ;
Dijkstra, Jouke ;
Lelieveldt, Boudewijn P. F. ;
Jukema, J. Wouter ;
Schalij, Martin J. ;
Delgado, Victoria ;
Bax, Jeroen J. ;
Reiber, Johan H. C. ;
Scholte, Arthur J. .
INTERNATIONAL JOURNAL OF CARDIOVASCULAR IMAGING, 2013, 29 (05) :1177-1190