Prediction of Abdominal Aortic Aneurysms Using Sparse Gaussian Process Regression

Author(s):  
A. Ijaz ◽  
J. Choi ◽  
W. Lee ◽  
S. Baek

Abdominal Aortic Aneurysms (AAA) is a form of vascular disease causing focal enlargement of abdominal aorta. It affects a large part of population and has up to 90% mortality rate. Since risks from open surgery or endovascular repair outweighs the risk of AAA rupture, surgical treatments are not recommended with AAA less than 5.5cm in diameter. Recent clinical recommendations suggest that people with small aneurysms should be examined 3∼36 months depending on size to get information about morphological changes. While advances in biomechanics provide state-of-the-art spatial estimates of stress distributions of AAA, there are still limitations in modeling its time evolution. Thus, there is no biomechanical framework to utilize such information from a series of medical images that would aid physicians in detecting small aneurysms with high risk of rupture. For the present study, we use series of CT images of small AAAs taken at different times to model and predict the spatio-temporal evolution of AAA. This is achieved using sparse local Gaussian process regression.

VASA ◽  
2005 ◽  
Vol 34 (4) ◽  
pp. 217-223 ◽  
Author(s):  
Diehm ◽  
Schmidli ◽  
Dai-Do ◽  
Baumgartner

Abdominal aortic aneurysm (AAA) is a potentially fatal condition with risk of rupture increasing as maximum AAA diameter increases. It is agreed upon that open surgical or endovascular treatment is indicated if maximum AAA diameter exceeds 5 to 5.5cm. Continuing aneurysmal degeneration of aortoiliac arteries accounts for significant morbidity, especially in patients undergoing endovascular AAA repair. Purpose of this review is to give an overview of the current evidence of medical treatment of AAA and describe prospects of potential pharmacological approaches towards prevention of aneurysmal degeneration of small AAAs and to highlight possible adjunctive medical treatment approaches after open surgical or endovascular AAA therapy.


Author(s):  
Jeffrey N. Kinkaid ◽  
Steven P. Marra ◽  
Francis E. Kennedy ◽  
Mark F. Fillinger

Abdominal Aortic Aneurysms (AAAs) are localized enlargements of the aorta. If untreated, AAAs will grow irreversibly until rupture occurs. Ruptured AAAs are usually fatal and are a leading cause of death in the United States, killing 15,000 per year (National Center for Health Statistics, 2001). Surgery to repair AAAs also carries mortality risks, so surgeons desire a reliable tool to evaluate the risk of rupture versus the risk of surgery.


2015 ◽  
Vol 35 (suppl_1) ◽  
Author(s):  
Joy Roy ◽  
Angela Silveira ◽  
Moritz Liljeqvist Lindquist ◽  
Maggie Folkesson ◽  
Siw Frebelius ◽  
...  

Introduction: Abdominal Aortic Aneurysms (AAA) often contain an intraluminal thrombus (ILT). AAA diameter and ILT volume are associated with growth of the aneurysm. Neutrophils, present in the ILT, contain elastase (NE). NE activity leads to production of fibrin degradation products (FDPs) with a specific epitope [[Unable to Display Character: &#8211;]] XDP. The present study evaluates NE-derived FDPs in aneurysm patients scheduled for elective aortic repair. The purpose of the study is to introduce an additional bio-marker for presence of AAA and possibly risk of rupture by measuring levels of NE derived FDPs in plasma of patients with AAA. Materials and Methods: 42 male patients, undergoing aortic repair for AAA were included. As controls, we collected blood samples from 42 men who attended an AAA screening program but had no AAAs on ultrasound. Computed Tomography (CT) images were available for 34 AAA patients and analyzed using A4 Clinics software (VASCOPS, Austria). Patient demographics, maximum diameter, aortic volume and ILT volume were recorded. Peak wall stress (PWS), peak wall rupture index (PWRI) and mean ILT stress were estimated by Finite Element Analysis using the A4 Clinics software. Plasma levels of elastase digests of cross-linked fibrin (E-XDP) were determined with a sandwich ELISA. Results: E-XDP levels were higher in AAA patients than in age-matched controls (8.5 vs 1.2 U/ml, p<0.0001). E-XDP levels correlated with ILT volume (r = 0.64, p<0.0001), aortic volume (r = 0.64, p<0.0001) and maximum diameter (r = 0.59, p=0.0003). AAA patients with other concomitant peripheral aneurysms had higher E-XDP levels than those with only an AAA (13.6 vs 6.8 U/ml, p=0.028). PWS, PWRI and bleeding signs in the thrombus did not significantly affect E-XDP levels. Interestingly, the mean ILT stress correlated significantly to E-XDP levels (r= 0.45, p=0.008). Conclusions: The study shows that it is feasible to measure E-XDP levels in plasma of patients with AAA and that E-XDP correlates with ILT volume and mean ILT stress. These results support the notion that the resident neutrophils in the ILT can actively lyse fibrin in the ILT, which may decrease ILT strength. E-XDP holds potential as a biomarker of the ILT in AAA patients and needs to be further investigated in AAA rupture risk assessment.


2004 ◽  
Vol 126 (4) ◽  
pp. 438-446 ◽  
Author(s):  
Robert A. Peattie ◽  
Tiffany J. Riehle ◽  
Edward I. Bluth

As one important step in the investigation of the mechanical factors that lead to rupture of abdominal aortic aneurysms, flow fields and flow-induced wall stress distributions have been investigated in model aneurysms under pulsatile flow conditions simulating the in vivo aorta at rest. Vortex pattern emergence and evolution were evaluated, and conditions for flow stability were delineated. Systolic flow was found to be forward-directed throughout the bulge in all the models, regardless of size. Vortices appeared in the bulge initially during deceleration from systole, then expanded during the retrograde flow phase. The complexity of the vortex field depended strongly on bulge diameter. In every model, the maximum shear stress occurred at peak systole at the distal bulge end, with the greatest shear stress developing in a model corresponding to a 4.3 cm AAA in vivo. Although the smallest models exhibited stable flow throughout the cycle, flow in the larger models became increasingly unstable as bulge size increased, with strong amplification of instability in the distal half of the bulge. These data suggest that larger aneurysms in vivo may be subject to more frequent and intense turbulence than smaller aneurysms. Concomitantly, increased turbulence may contribute significantly to wall stress magnitude and thereby to risk of rupture.


2015 ◽  
Vol 2015 ◽  
pp. 1-12 ◽  
Author(s):  
Tejas Canchi ◽  
S. D. Kumar ◽  
E. Y. K. Ng ◽  
Sriram Narayanan

Computational methods have played an important role in health care in recent years, as determining parameters that affect a certain medical condition is not possible in experimental conditions in many cases. Computational fluid dynamics (CFD) methods have been used to accurately determine the nature of blood flow in the cardiovascular and nervous systems and air flow in the respiratory system, thereby giving the surgeon a diagnostic tool to plan treatment accordingly. Machine learning or data mining (MLD) methods are currently used to develop models that learn from retrospective data to make a prediction regarding factors affecting the progression of a disease. These models have also been successful in incorporating factors such as patient history and occupation. MLD models can be used as a predictive tool to determine rupture potential in patients with abdominal aortic aneurysms (AAA) along with CFD-based prediction of parameters like wall shear stress and pressure distributions. A combination of these computer methods can be pivotal in bridging the gap between translational and outcomes research in medicine. This paper reviews the use of computational methods in the diagnosis and treatment of AAA.


1998 ◽  
Vol 85 (12) ◽  
pp. 1674-1680 ◽  
Author(s):  
Vardulaki ◽  
Prevost ◽  
Walker ◽  
Day ◽  
Wilmink ◽  
...  

Sign in / Sign up

Export Citation Format

Share Document