Prediction of Abdominal Aortic Aneurysm Growth Using Dynamical Gaussian Process Implicit Surface
- 2 July 2018
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Biomedical Engineering
- Vol. 66 (3) , 609-622
Abstract
An Abdominal Aortic Aneurysm (AAA) is a form of vascular disease causing focal enlargement of the abdominal aorta. It affects a large part of the population, and in case of rupture, has up to 90% mortality rate. Recent clinical recom- mendations suggest that people with small aneurysms should be examined 3-36 months depending on the size, to monitor morphological changes. While advances in biomechanics provide state-of-the-art spatial estimates of stress distributions of AAAs, there are still limitations in modeling its time evolution and uncertainty qualification. To date, there are a few biomechanical frameworks that utilize longitudinal medical images, which would aid physicians in detecting small aneurysms with high risk of rupture. In this study, we use longitudinal computer tomography (CT) scans of AAAs that are captured at different times to predict the spatio-temporal evolution of AAAs' shape in future time. We consider a surface of 3D AAA as a manifold embedded in a scalar field over the three dimensional space. The changes of the scalar field propagate into the changes in the surface. For this formulation, we develop our Dynamical Gaussian Process Implicit Surface (DGPIS) model based on observed surfaces of 3D AAAs as visible variables while the scalar fields are hidden fields. First of all, we utilize the concept of the implicit surface field as a parameterization-free framework to describe a 3D shape. We then use Gaussian process regression to construct the field as an observation model from CT training image data. Furthermore, we propose a dynamic model to represent the evolution of the field. Finally, we derive the predicted surface from the predicted field. Our model is deployed on a real medical data set, which indicates its effectiveness. In addition, we discuss our prediction results with respect to ones from conventional analysis techniques.Keywords
Funding Information
- National Heart, Lung, and Blood Institute of the National Institutes of Health (R01HL115185, R21HL113857)
- National Science Foundation (CMMI-1150376)
- Vietnam Education Fund
- National Research Foundation of Korea (2018R1A4A1025986)
- Korea government
This publication has 34 references indexed in Scilit:
- Importance of initial aortic properties on the evolving regional anisotropy, stiffness and wall thickness of human abdominal aortic aneurysmsJournal of The Royal Society Interface, 2012
- Making Predictions from Complex Longitudinal Data, with Application to Planning Monitoring Intervals in a National Screening ProgrammeJournal of the Royal Statistical Society Series A: Statistics in Society, 2011
- Diagnostic and therapeutic strategies for small abdominal aortic aneurysmsNature Reviews Cardiology, 2011
- Should the Size Threshold for Elective Abdominal Aortic Aneurysm Repair be Lowered in the Endovascular Era? YesAngiology, 2010
- Intraluminal thrombus and risk of rupture in patient specific abdominal aortic aneurysm – FSI modellingComputer Methods in Biomechanics and Biomedical Engineering, 2009
- Genotype–phenotype relationships in an investigation of the role of proteases in abdominal aortic aneurysm expansionBritish Journal of Surgery, 2005
- Treatment of Ruptured Abdominal Aortic Aneurysm, a Permanent Challenge or a Waste of Resources? Prediction of Outcome Using a Multi-organ-dysfunction ScoreEuropean Journal of Vascular and Endovascular Surgery, 2000
- Comparing images using the Hausdorff distanceIEEE Transactions on Pattern Analysis and Machine Intelligence, 1993
- On the Convergence Properties of the EM AlgorithmThe Annals of Statistics, 1983
- AN APPROACH TO TIME SERIES SMOOTHING AND FORECASTING USING THE EM ALGORITHMJournal of Time Series Analysis, 1982