Machine learning approaches to surrogate multifidelity Growth and Remodeling models for efficient abdominal aortic aneurysmal applications. (June 2021)

• Record Type: Journal Article
• Authors: Jiang, Zhenxiang; Choi, Jongeun; Baek, Seungik
• Is Part Of: Computers in biology and medicine. Volume 133(2021)
• Publication Date: 2021-06
• Subjects: Physics-based machine learning -- Constrained mixture model -- Kriging and cokriging -- Exploration and exploitation -- Parameter estimation; Medicine -- Data processing -- Periodicals; Biology -- Data processing -- Periodicals; 610.285
• DOI: 10.1016/j.compbiomed.2021.104394
• Languages: English
• ISSNs: 0010-4825

Abstract

Abstract: Computational Growth and Remodeling (G&R) models have been widely used to capture the pathological development of arterial diseases and have shown promise for aiding clinical diagnosis, prognosis prediction, and staging classification. However, due to the high complexity of the arterial adaptation mechanism, high-fidelity arterial G&R simulation usually takes hours or even days, which hinders its application in clinical practice. To remedy this problem, we develop a computationally efficient arterial G&R simulation framework that comprehensively combines the physics-based G&R simulations and data-driven machine learning approaches. The proposed framework greatly enhances the computational efficiency of arterial G&R simulations, thereby enabling more time-consuming arterial applications, including personalized parameter estimation and arterial disease progression prediction. In particular, we achieve significant computational cost reduction mainly through two methods: (1) constructing a Multifidelity Surrogate (MFS) to approximate multifidelity G&R simulations by using a cokriging approach and (2) developing a novel iterative optimization algorithm for personalized parameter estimation. The proposed framework is demonstrated by estimating G&R model parameters and predicting individual aneurysm growth using follow-up CT images of Abdominal Aortic Aneurysms (AAAs) from 21 patients. Results show that the personalized parameters are satisfactorily estimated and the growth of AAAs is predicted within the clinically relevant time frame, i.e., less than 2 h, without a loss of accuracy. Highlights: A physics-based machine learning is used to integrate G&R models and clinical data. Fast G&R simulations are enabled using cokriging based surrogate model. A personalized parameter estimation of G&R can be conducted within 2 h. Personalized AAA growth is predicted with an average error of 1.39 mm in diameter. Personalized values of intrinsic parameters in G&R are estimated from clinical data.