A semi-automated method to obtain metrics of interest to evaluate an Ascending Aortic Aneurysm evolution

P0021 

Abstract Submission 

Jacques Tomasi (1), Pierre Flores (2), Leonardo Geronzi (3), Albadi Waleed (2), Pascal Haigron (4), Jean-Philippe Verhoye (5)

(1) Universtity Hospital of Rennes, Rennes, France, (2) University Hospital of Rennes, Rennes, France, (3) University of Roma, Roma, Italy, (4) University of Rennes, Rennes, France, (5) University hospital of Rennes, Rennes, France

Jacques Tomasi    -  Contact Me
Universtity Hospital of Rennes

Pierre Flores    -  Contact Me
University Hospital of Rennes

Leonardo Geronzi    -  Contact Me
University of Roma

Albadi Waleed    -  Contact Me
University Hospital of Rennes

Pascal Haigron    -  Contact Me
University of Rennes

Jean-Philippe Verhoye    -  Contact Me
University hospital of Rennes

Jacques Tomasi    -  Contact Me
Universtity Hospital of Rennes

Ascending aortic aneurysms concern 3 to 4% of the population aged from 65 years old and older. One of the major issues is to detect and evaluate aneurysms at high risk of growth or rupture. As many aortic dissections can appear below the admitted 50mm cut-off limit of diameter. New parameters should be found to improve characterization of individual risk. In the present study, we present a workflow to obtain new metrics of interest.
We studied a cohort of ninety-one patients with a follow-up of ascending aortic aneurysm using CT-scan. For each patient, we evaluated with semi-automated method diameter but also less often used measurements such as centerline, external and internal curvature, surface and volume. We also implemented original metrics helped by "morphing process" : strain over time and local growth area using a computer-helped method.
In this study, we propose a method to compute a set of local shape features that, in addition to the maximum diameter D, are intended to improve the classification performances for the ascending aortic aneurysm growth risk assessment. Apart from D, these are the ratio DCR between D and the length of the ascending aorta centerline, the ratio EILR between the length of the external and the internal lines and the tortuosity T. 50 patients with two 3D acquisitions at least 6 months apart were segmented and the growth rate (GR) with the shape features related to the first exam computed. The correlation between them has been investigated. After, the dataset was divided into two classes according to the growth rate value. We used six different classifiers with input data exclusively from the first exam to predict the class to which each patient belonged. A first classification was performed using only D and a second with all the shape features together. The performances have been evaluated by computing accuracy, sensitivity, specificity, area under the receiver operating characteristic curve (AUROC) and positive (negative) likelihood ratio LHR+ (LHR-). A positive correlation was observed between growth rate and DCR (r = 0.511, p = 1.3e-4) and between GR and EILR (r = 0.472, p = 2.7e-4). Overall, the classifiers based on the four metrics outperformed the same ones based only on D. Among the diameter-based classifiers, k-nearest neighbours (KNN) reported the best accuracy (86%), sensitivity (55.6%), AUROC (0.74), LHR+ (7.62) and LHR- (0.48). Concerning the classifiers based on the four shape features, we obtained the best accuracy (94%), sensitivity (66.7%), specificity (100%), AUROC (0.94), LHR+ (+∞) and LHR- (0.33) with support vector machine (SVM).
Our method provided for each patient diameter along centerline but also lenghts of external, internal curvatures, surface, and volume. Strain and local growth area were obtained for four patients. These different parameters seem to increase with aneurysmal dilatation.
The workflow presented enables to obtain metrics of interests which seem correlated to aneurysmal evolution. Further studies are needed to assess correlation of these metrics with risk of acute complications such as rupture or aortic dissection. Also these parameters does not take into account for now the arterial pressure that can have potential effect in aneurysm evolution.

Ascending Aorta