A machine learning approach to investigate the relationship between shape features and numerically predicted risk of ascending aortic aneurysm

• Type of Material: Article
• Authors: Liang Liang, Georgia Institute of Technology; Minliang Liu, Georgia Institute of Technology; Caitlin Martin, Georgia Institute of Technology; John A. Elefteriades, Yale University; Wei Sun, Emory University
• Language: English
• Date: 2017-10
• Publisher: Springer (part of Springer Nature): Springer Open Choice Hybrid Journals
• Publication Version: Author Accepted Manuscript (After Peer Review)
• Copyright Statement: © 2017, Springer-Verlag Berlin Heidelberg
• Final Published Version (URL): http://dx.doi.org/10.1007/s10237-017-0903-9
• Title of Journal or Parent Work: Biomechanics and Modeling in Mechanobiology
• ISSN: 1617-7959
• Volume: 16
• Issue: 5
• Start Page: 1519
• End Page: 1533
• Grant/Funding Information: Research for this project was funded in part by NIH grant R01 HL104080.; Liang Liang is supported by an American Heart Association Post-doctoral fellowship 16POST30210003.
• Keywords: machine learning; computer aided diagnosis; ascending aortic aneurysm; finite element analysis
• Research Categories: Engineering, Biomedical

Abstract

Geometric features of the aorta are linked to patient risk of rupture in the clinical decision to electively repair an ascending aortic aneurysm (AsAA). Previous approaches have focused on relationship between intuitive geometric features (e.g. diameter and curvature) and wall stress. This work investigates the feasibility of a machine learning approach to establish the linkages between shape features and FEA predicted AsAA rupture risk, and it may serve as a faster surrogate for FEA associated with long simulation time and numerical convergence issues. This method consists of four main steps: (1) constructing a statistical shape model (SSM) from clinical 3D CT images of AsAA patients; (2) generating a dataset of representative aneurysm shapes and obtaining FEA predicted risk scores defined as systolic pressure divided by rupture pressure (rupture is determined by a threshold criterion); (3) establishing relationship between shape features and risk by using classifiers and regressors; and (4) evaluating such relationship in cross validation. The results show that SSM parameters can be used as strong shape features to make predictions of risk scores consistent with FEA, which lead to an average risk classification accuracy of 95.58% by using support vector machine and an average regression error of 0.0332 by using support vector regression, while intuitive geometric features have relatively weak performance. Compared to FEA, this machine learning approach is magnitudes faster. In our future studies, material properties and inhomogeneous thickness will be incorporated into the models and learning algorithms, which may lead to a practical system for clinical applications.