AI-powered assessment of biomarkers for growth prediction of abdominal aortic aneurysms

Arianna Forneris; Richard Beddoes; Mitchel Benovoy; Peter Faris; Randy D Moore; Elena S Di Martino

doi:10.1016/j.jvssci.2023.100119

AI-powered assessment of biomarkers for growth prediction of abdominal aortic aneurysms

JVS Vasc Sci. 2023 Jul 10:4:100119. doi: 10.1016/j.jvssci.2023.100119. eCollection 2023.

Authors

Arianna Forneris^{1

2}, Richard Beddoes³, Mitchel Benovoy^{3

4}, Peter Faris⁵, Randy D Moore^{2

6}, Elena S Di Martino^{1

2}

Affiliations

¹ Department of Biomedical Engineering, Schulich School of Engineering, University of Calgary, Calgary, AB, Canada.
² R&D Department, ViTAA Medical Solutions, Montreal, QC, Canada.
³ Product Development Department, ViTAA Medical Solutions, Montreal, QC, Canada.
⁴ McGill University Health Center, Montreal, QC, Canada.
⁵ Department of Community Health Sciences, Faculty of Medicine, University of Calgary, Calgary, AB, Canada.
⁶ Division of Vascular Surgery, University of Calgary, Calgary, AB, Canada.

Abstract

Objective: The purpose of this study was to employ biomechanics-based biomarkers to locally characterize abdominal aortic aneurysm (AAA) tissue and investigate their relation to local aortic growth by means of an artificial intelligence model.

Methods: The study focused on a population of 36 patients with AAAs undergoing serial monitoring with electrocardiogram-gated multiphase computed tomography angiography acquisitions. The geometries of the aortic lumen and wall were reconstructed from the baseline scans and used for the baseline assessment of regional aortic weakness with three functional biomarkers, time-averaged wall-shear stress, in vivo principal strain, and intra-luminal thrombus thickness. The biomarkers were encoded as regional averages on axial and circumferential sections perpendicularly to the aortic centerline. Local diametric growth was obtained as difference in diameter between baseline and follow-up at the level of each axial section. An artificial intelligence model was developed to predict accelerated aneurysmal growth with the Extra Trees algorithm used as a binary classifier where the positive class represented regions that grew more than 2.5 mm/year. Additional clinical biomarkers, such as maximum aortic diameter at baseline, were also investigated as predictors of growth.

Results: The area under the curve for the constructed receiver operating characteristic curve for the Extra Trees classifier showed a very good performance in predicting relevant aortic growth (area under the curve = 0.92), with the three biomechanics-based functional biomarkers being objectively selected as the main predictors of growth.

Conclusions: The use of features based on the functional and local characterization of the aortic tissue resulted in a superior performance in terms of growth prediction when compared with models based on geometrical assessments. With rapid growth linked to increasing risk for patients with AAAs, the ability to access functional information related to tissue weakening and disease progression at baseline has the potential to support early clinical decisions and improve disease management.

Keywords: Abdominal aortic aneurysms; Artificial intelligence; Computational fluid dynamics; Growth; In vivo strain; Thrombus.