TY - JOUR
T1 - Embedding high-dimensional Bayesian optimization via generative modeling
T2 - Parameter personalization of cardiac electrophysiological models
AU - Dhamala, Jwala
AU - Bajracharya, Pradeep
AU - Arevalo, Hermenegild J.
AU - Sapp, John L L.
AU - Horácek, B. Milan
AU - Wu, Katherine C.
AU - Trayanova, Natalia A.
AU - Wang, Linwei
N1 - Funding Information:
This work was supported by the National Science Foundation CAREER Award ACI-1350374 , the National Institutes of Health Award R01HL145590 and R01HL142496 , and the Leducq Foundation .
Publisher Copyright:
© 2020
PY - 2020/5
Y1 - 2020/5
N2 - The estimation of patient-specific tissue properties in the form of model parameters is important for personalized physiological models. Because tissue properties are spatially varying across the underlying geometrical model, it presents a significant challenge of high-dimensional (HD) optimization at the presence of limited measurement data. A common solution to reduce the dimension of the parameter space is to explicitly partition the geometrical mesh. In this paper, we present a novel concept that uses a generative variational auto-encoder (VAE) to embed HD Bayesian optimization into a low-dimensional (LD) latent space that represents the generative code of HD parameters. We further utilize VAE-encoded knowledge about the generative code to guide the exploration of the search space. The presented method is applied to estimating tissue excitability in a cardiac electrophysiological model in a range of synthetic and real-data experiments, through which we demonstrate its improved accuracy and substantially reduced computational cost in comparison to existing methods that rely on geometry-based reduction of the HD parameter space.
AB - The estimation of patient-specific tissue properties in the form of model parameters is important for personalized physiological models. Because tissue properties are spatially varying across the underlying geometrical model, it presents a significant challenge of high-dimensional (HD) optimization at the presence of limited measurement data. A common solution to reduce the dimension of the parameter space is to explicitly partition the geometrical mesh. In this paper, we present a novel concept that uses a generative variational auto-encoder (VAE) to embed HD Bayesian optimization into a low-dimensional (LD) latent space that represents the generative code of HD parameters. We further utilize VAE-encoded knowledge about the generative code to guide the exploration of the search space. The presented method is applied to estimating tissue excitability in a cardiac electrophysiological model in a range of synthetic and real-data experiments, through which we demonstrate its improved accuracy and substantially reduced computational cost in comparison to existing methods that rely on geometry-based reduction of the HD parameter space.
KW - High-dimensional Bayesian optimization
KW - personalized modeling
KW - variational autoencoder
UR - http://www.scopus.com/inward/record.url?scp=85081129194&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85081129194&partnerID=8YFLogxK
U2 - 10.1016/j.media.2020.101670
DO - 10.1016/j.media.2020.101670
M3 - Article
C2 - 32171168
AN - SCOPUS:85081129194
VL - 62
JO - Medical Image Analysis
JF - Medical Image Analysis
SN - 1361-8415
M1 - 101670
ER -