A Cohort Longitudinal Study Identifies Morphology and Hemodynamics Predictors of Abdominal Aortic Aneurysm Growth
- PDF / 2,666,979 Bytes
- 18 Pages / 593.972 x 792 pts Page_size
- 47 Downloads / 167 Views
Annals of Biomedical Engineering ( 2019) https://doi.org/10.1007/s10439-019-02375-1
Original Article
A Cohort Longitudinal Study Identifies Morphology and Hemodynamics Predictors of Abdominal Aortic Aneurysm Growth FLORIAN JOLY,1,3 GILLES SOULEZ,2 SIMON LESSARD,2 CLAUDE KAUFFMANN,2 and IRENE VIGNON-CLEMENTEL 1,3 1
Inria, Centre de recherche de Paris, 75012 Paris, France; 2Department of Medical Imaging, University of Montreal Hospital Research Center, Montreal H2X0C1, Canada; and 3Sorbonne Universite´, Laboratoire Jacques-Louis Lions, 75005 Paris, France (Received 25 June 2019; accepted 24 September 2019) Associate Editor Umberto Morbiducci oversaw the review of this article.
Abstract—Abdominal aortic aneurysms (AAA) are localized, commonly occurring aortic dilations. Following rupture only immediate treatment can prevent morbidity and mortality. AAA maximal diameter and growth are the current metrics to evaluate the associated risk and plan intervention. Although these criteria alone lack patient specificity, predicting their evolution would improve clinical decision. If the disease is known to be associated with altered morphology and blood flow, intraluminal thrombus deposit and clinical symptoms, the growth mechanisms are yet to be fully understood. In this retrospective longitudinal study of 138 scans, morphological analysis and blood flow simulations for 32 patients with clinically diagnosed AAAs and several follow-up CT-scans, are performed and compared to 9 control subjects. Several metrics stratify patients between healthy, low and high risk groups. Local correlations between hemodynamic metrics and AAA growth are also explored but due to their high inter-patient variability, do not explain AAA heterogeneous growth. Finally, high-risk predictors trained with successively clinical, morphological, hemodynamic and all data, and their link to the AAA evolution are built from supervise learning. Predictive performance is high for morphological, hemodynamic and all data, in contrast to clinical data. The morphology-based predictor exhibits an interesting effort-predictability tradeoff to be validated for clinical translation. Keywords—Abdominal aortic aneurysm, Growth, Computational fluid dynamics (CFD), Haemodynamics, Intra-luminal thrombus (ILT), Longitudinal study, Risk prediction, Supervised learning, Wall shear stress.
Address correspondence to Irene Vignon-Clementel, Inria, Centre de recherche de Paris, 75012 Paris, France. Electronic mail: [email protected]
INTRODUCTION Abdominal aortic aneurysms (AAA) are local dilations of the abdominal aorta which can rupture when blood pressure overcomes artery wall resistance. Following rupture only urgent treatment can prevent morbidity and mortality. It is the 14th leading cause of death in the USA50 with a prevalence of 8.9% for men and 2.2% for women. AAA are generally asymptomatic and generally detected through unrelated examinations. Risk is assessed using its maximal diameter (Dmax ),42 taken at the outer wall of the aneurysm on a plane perpendi
Data Loading...
