header

Predicting and Understanding Age-Dependent Arterial Elasticity from Key Microstructural Features by Bidirectional Deep Learning

34 Pages Posted: 22 Jan 2022 Publication Status: Published

See all articles by Kevin Linka

Kevin Linka

Hamburg University of Technology

Cristina Cavinato

Yale University

Jay D. Humphrey

Yale University

Christian J. Cyron

Hamburg University of Technology

Abstract

Microstructural features and mechanical properties are closely related in all soft biological tissues. Both yet exhibit considerable inter-individual differences and are affected by factors such as aging and disease and its progression. Histological analysis, modern in situ imaging, and biomechanical testing have deepened our understanding of these complex interrelations, yet two key problems remain: (1) Given the specific microstructure, how can one predict the macroscopic mechanical properties without mechanical testing? (2) How can one quantify individual contributions of the different microstructural features to the macroscopic mechanical properties in an automated, systematic and largely unbiased way? Here we propose a bidirectional deep learning architecture to address these two problems. Our architecture uses data from standard histological analyses, two-photon microscopy and biaxial biomechanical testing. Its capabilities are demonstrated by predicting with high accuracy (R2=0.92) the evolving mechanical properties of the murine aorta during maturation and aging. Moreover, our architecture reveals that the extracellular matrix (ECM) composition and organization are the most prominent factors governing the macroscopic mechanical properties of the tissues studied herein.

Keywords: hybrid modeling, artery tissues, explainable AI, tissue maturation

Suggested Citation

Linka, Kevin and Cavinato, Cristina and Humphrey, Jay D. and Cyron, Christian J., Predicting and Understanding Age-Dependent Arterial Elasticity from Key Microstructural Features by Bidirectional Deep Learning. Available at SSRN: https://ssrn.com/abstract=4015205 or http://dx.doi.org/10.2139/ssrn.4015205

Kevin Linka (Contact Author)

Hamburg University of Technology ( email )

Hamburg
Germany

Cristina Cavinato

Yale University ( email )

493 College St
New Haven, CT CT 06520
United States

Jay D. Humphrey

Yale University ( email )

493 College St
New Haven, CT CT 06520
United States

Christian J. Cyron

Hamburg University of Technology ( email )

Hamburg
Germany

Do you have negative results from your research you’d like to share?

Paper statistics

Downloads
52
Abstract Views
188
PlumX Metrics