Abstract 16111: Clinical Application of Deep Learning for Stress Analysis of Ascending Thoracic Aortic Aneurysms

Circulation ◽  
2020 ◽  
Vol 142 (Suppl_3) ◽  
Author(s):  
Imon Rahaman ◽  
Zhongjie Wang ◽  
Yue XUAN ◽  
Liang Ge ◽  
Elaine E Tseng
Keyword(s):  
Deep Learning ◽  
Stress Analysis ◽  
Wall Stress ◽  
Longitudinal Direction ◽  
Absolute Error ◽  
Aortic Aneurysms ◽  
Patient Specific ◽  
Accurate Estimation ◽  
Stress Distributions ◽  
Thoracic Aortic Aneurysms

Introduction: Current guidelines for elective surgery of ascending thoracic aortic aneurysms (aTAAs) use aneurysm size as primary determinant for risk stratification of adverse events. Biomechanically, dissection may occur when wall stress exceeds wall strength. A widespread method for stress analysis is structural finite-element analysis (FEA). Patient-specific aortic geometries are easily obtainable and stress distributions can potentially predict risk of dissection. However, FEA is a time-consuming and difficult procedure. To bypass this issue, a recent study has developed the first deep learning (DL) approach for a fast and accurate estimation of aortic wall stress distributions. Hypothesis: In this study, we assessed the hypothesis that this deep learning approach can be applied to a large clinical dataset. Model performance was measured by comparing FEA and DL stress predictions in parallel. Methods: Patients with aTAA (n = 169) were studied. Patient-specific aneurysm geometries were obtained from ECG-gated computed tomography. Shapes were represented by hexahedral meshes with 9648 nodes and 6336 solid elements. FEA peak wall stresses and stress distributions were determined using LS-DYNA software with user-defined fiber-embedded material models under systolic pressure. The DL model was implemented in Julia and consisted of unsupervised and supervised learning algorithms. Training was performed on a training set of 152 shapes and testing set of 17 shapes with 10-fold cross-validation. Mean absolute error (MAE) and absolute error of peak stress values (APE) were used to compare DL model predictions with FEA values considered to be ground truth. Results: Average stress values predicted by our DL model were 175.64 ± 4.17 kPa and 95.69 ± 2.15 kPa in the circumferential and longitudinal direction, respectively. We computed a MAE of 5.06 ± 1.08 kPa and APE of 2.58 ± 1.39 kPa in the circumferential direction and MAE of 4.51 ± 0.98 kPa and APE of 2.32 ± 1.84 kPa in the longitudinal direction. Conclusions: DL model trained exclusively on clinical data was able to accurately predict stress distributions on complex aortic geometries. Fast and accurate stress predictions will facilitate real-time clinical applications for the risk assessment of aTAAs.

Local Mechanical Properties of Abdominal Aortic Aneurysms

2008 ◽  
Author(s):  
Evelyne van Dam ◽  
Marcel Rutten ◽  
Frans van de Vosse
Keyword(s):  
Mechanical Properties ◽  
Stress Analysis ◽  
Vessel Wall ◽  
Computational Models ◽  
Wall Stress ◽  
Abdominal Aortic Aneurysms ◽  
Aortic Aneurysms ◽  
Patient Specific ◽  
Rupture Risk ◽  
Abdominal Aortic

Rupture risk of abdominal aortic aneurysms (AAA) based on wall stress analysis may be superior to the currently used diameter-based rupture risk prediction [4; 5; 6; 7]. In patient specific computational models for wall stress analysis, the geometry of the aneurysm is obtained from CT or MR images. The wall thickness and mechanical properties are mostly assumed to be homogeneous. The pathological AAA vessel wall may contain collageneous areas, but also calcifications, cholesterol crystals and large amounts of fat cells. No research has yet focused yet on the differences in mechanical properties of the components present within the degrading AAA vessel wall.

Abstract 16806: Changes in Wall Stress in Ascending Thoracic Aortic Aneurysms From Systole to Diastole

Circulation ◽  
2020 ◽  
Vol 142 (Suppl_3) ◽  
Author(s):  
Andrew Liu ◽  
Zhongjie Wang ◽  
Yue XUAN ◽  
Michael D Hope ◽  
Liang Ge ◽  
...  
Keyword(s):  
Computer Aided Design ◽  
Cardiac Cycle ◽  
Aortic Rupture ◽  
Wall Stress ◽  
Ascending Aorta ◽  
Aortic Aneurysms ◽  
Patient Specific ◽  
Imaging Data ◽  
Element Analysis ◽  
Thoracic Aortic Aneurysms

Introduction: Aortic rupture or dissection of ascending thoracic aortic aneurysms (aTAA) is a life-threatening pathology that can occur when wall stress exceeds wall strength. Surgical guidelines for repair is when aneurysm max diameter ≥5.5 cm. However, rupture has been documented at various sizes, including 60% <4.5cm. Wall stress may be a better predictor of dissection than diameter, using finite element analysis (FEA) of patient-specific aTAA models to assess patient-specific risk of dissection. The purpose of this study was to determine changes in aneurysm FEA peak wall stresses in patients during the cardiac cycle from systole to diastole. Methods: Preoperative aTAA patients (n = 20) underwent ECG-gated computed tomography (CT) scans at systolic and diastolic phases. Patient-specific 3D aneurysm geometries were reconstructed from the imaging data at both phases and after accounting for pre-stress, underwent FEA using LS-DYNA solver. Wall stress distribution and magnitude were determined using user-defined fiber-embedded material model at systole (120mmHg) and diastole (80mmHg). Aortic volume changes during the cardiac cycle were determined using computer-aided design tools. Results: From the diastolic model, the 99 th percentile circumferential stresses were 348.8 ±105.6 kPa and 186.6 ±31.4 kPa for the sinus and ascending aorta respectively, while for the systolic model, they were 500.7 ±183.7 kPa (p=0.00072) and 296.5 ±64.4 kPa (p < .00001), respectively. The 99th percentile longitudinal stresses from the diastolic model were 223.2 ±75.4 kPa and 126.1 ±20.4 kPa for the sinus and ascending aorta, respectively, while for the systolic model, they were 336.3 ±78.4 kPa (p < .00001), and 235.2 ±48.0 kPa (p < .00001), respectively. Mean volume change of the ascending aorta in percentage between systolic and diastolic phases was 6.34%. Conclusions: Peak circumferential and longitudinal stresses changed significantly from systole to diastole. For patients with significant hypertension, these differences in wall stress may be magnified such that sudden or significant hypertension may result in wall stress values that exceed tissue strength leading to dissection.

Abstract 16886: Wall Stress Profiles in Tricuspid Aortic Valve Associated Ascending Thoracic Aortic Aneurysms: The Effect of Surgical Threshold Diameter ≥5.5cm

Circulation ◽  
2020 ◽  
Vol 142 (Suppl_3) ◽  
Author(s):  
Axel Gomez ◽  
Zhongjie Wang ◽  
Yue XUAN ◽  
Liang Ge ◽  
Elaine E Tseng
Keyword(s):  
Aortic Valve ◽  
Systolic Pressure ◽  
Peak Stress ◽  
Wall Stress ◽  
Aortic Aneurysms ◽  
Patient Specific ◽  
Thoracic Aortic Aneurysms ◽  
Tricuspid Aortic Valve ◽  
Elective Repair ◽  
Longitudinal Wall

Introduction: Ascending thoracic aortic aneurysms (aTAAs) carry a risk of dissection. Elective repair guidelines are designed around size thresholds, but the one-dimensional parameter is insufficient to predict acute events in small aneurysms. Biomechanically, aortic events can occur when wall stress exceeds wall strength. Patient-specific aTAA wall stresses may be a better predictor of complications. Our aim was to compare wall stresses in aTAAs associated with a tricuspid aortic valve (TAV) based on diameter. Methods: Patients with TAV-aTAA and diameter >4.0cm (n=448) were divided into groups by 0.5 cm diameter increments. Pre-stress three-dimensional aneurysm geometries were reconstructed from ECG-gated computer tomography images. A fiber-embedded hyperelastic material model was applied to obtain longitudinal and circumferential wall stress distributions under systolic pressure. Medians with interquartile ranges are reported. The Kruskal-Wallis test is used for comparisons between size groups. Results: Peak longitudinal wall stresses for TAV-aTAA were 308[282-338] kPa for size 4.0-4.4cm vs 341[309-362] kPa for 4.5-4.9cm vs 339[289-370] kPa for 5.0-5.4cm vs 319[297-355] kPa for 5.5-5.9cm vs 373[364-449] for 6.0cm (p=0.003). Peak circumferential wall stresses were 487[448-579] kPa for size 4.0-4.4cm vs 516[473-619] kPa for 4.5-4.9cm vs 506[422-580] kPa for 5.0-5.4cm vs 540[468-591] kPa for 5.5-5.9cm vs 565[506-634] for >6.0cm (p=0.19) (figure). 95th-percentile longitudinal peak stress for TAV-aTAA <5.5cm vs ≥5.5cm is 408 vs 465 kPa. Conclusions: Longitudinal wall stresses are higher as diameter increases. The 95% percentile longitudinal peak stress for diameter ≥5.5cm is ~450 kPa, which correlates with established ~5% dissection risk for size ≥5.5cm. Wall stress thresholds may be a better predictor of patient-specific risk of dissection than diameter and require testing in clinical trials.

scholarly journals Patient Specific Wall Stress Analysis and Mechanical Characterization of Abdominal Aortic Aneurysms Using 4D Ultrasound

2016 ◽  
Vol 52 (5) ◽  
pp. 635-642 ◽  
Author(s):  
E.M.J. van Disseldorp ◽  
N.J. Petterson ◽  
M.C.M. Rutten ◽  
F.N. van de Vosse ◽  
M.R.H.M. van Sambeek ◽  
...  
Keyword(s):  
Stress Analysis ◽  
Mechanical Characterization ◽  
Wall Stress ◽  
Abdominal Aortic Aneurysms ◽  
Aortic Aneurysms ◽  
Patient Specific ◽  
4D Ultrasound ◽  
Abdominal Aortic

Use of the Photoelastic Method to Determine the Wall Stress in Realistic Abdominal Aortic Aneurysm Models

2011 ◽  
Author(s):  
Barry J. Doyle ◽  
Anthony Callanan ◽  
John Killion ◽  
Timothy M. McGloughlin
Keyword(s):  
Wall Stress ◽  
Aortic Aneurysms ◽  
Maximum Diameter ◽  
Patient Specific ◽  
Western World ◽  
Photoelastic Method ◽  
Element Analysis ◽  
Abdominal Aortic ◽  
The Us ◽  
Numerical Tools

Abdominal aortic aneurysms (AAAs) remain a significant cause of death in the Western world with over 15,000 deaths per year in the US linked to AAA rupture. Recent research [1] has questioned the use of maximum diameter as a definitive risk parameter as it is now believed that alternative factors may be important in rupture-prediction. Wall stress was shown to be a better predictor than diameter of rupture [1], with biomechanics-based rupture indices [2,3] and asymmetry also reported to have potential clinical applicability [4]. However, the majority of numerical methods used to form these alternative rupture parameters are without rigorous experimental validation, and therefore may not be as accurate as believed. Validated experiments are required in order to convince the clinical community of the worth of numerical tools such as finite element analysis (FEA) in AAA risk-prediction. Strain gauges have been used in the past to determine the strain on an AAA [5], however, the photoelastic method has also proved to be a useful tool in AAA biomechanics [6]. This paper examines the approach using three medium-sized patient-specific AAA cases at realistic pressure loadings.

scholarly journals Patient-Specific AAA Wall Stress Analysis: 99-Percentile Versus Peak Stress

2008 ◽  
Vol 36 (6) ◽  
pp. 668-676 ◽  
Author(s):  
L. Speelman ◽  
E.M.H. Bosboom ◽  
G.W.H. Schurink ◽  
F.A.M.V.I. Hellenthal ◽  
J. Buth ◽  
...  
Keyword(s):  
Stress Analysis ◽  
Peak Stress ◽  
Wall Stress ◽  
Patient Specific ◽  
Versus Peak

scholarly journals Engineering Analysis of Aortic Wall Stress in the Surgery of V-shape Resection of the Noncoronary Sinus

2020 ◽  
Author(s):  
Hai Dong ◽  
Minliang Liu ◽  
Tongran Qin ◽  
Liang Liang ◽  
Bulat Ziganshin ◽  
...  
Keyword(s):  
Aortic Aneurysm ◽  
Stress Field ◽  
Aortic Arch ◽  
Aortic Root ◽  
Wall Stress ◽  
Aortic Aneurysms ◽  
Patient Specific ◽  
Rupture Risk ◽  
Ascending Aortic Aneurysm ◽  
Post Surgery

AbstractAscending aortic aneurysms often include the sinotubular junction (STJ) and extend into the root portion of the aorta. The novel surgery of the V-shape resection of the noncoronary sinus of the aortic root has been shown to be a simpler procedure, comparing with traditional surgeries such as full aortic root replacement, for patients with moderate ascending aortic aneurysm and aortic root ectasia. This novel surgery could reduce the diameter and cross-sectional area of the aortic root. However, the detailed effect on the stress field and the rupture risk of the aortic root and aneurysm has not been fully investigated. In this study, we performed patient-specific finite element (FE) analysis based on the 3D geometries of the aortic root and ascending aortic aneurysm, reconstructed directly from the clinical computed tomographic (CT) images. By comparing the pre- and post-surgery results, we investigated the influence of the V-shape surgery on the stress field and rupture risk of the aortic root, ascending aortic aneurysm and aortic arch. It was found that the surgery could significantly reduce the wall stress of the aortic root, ascending aortic aneurysm, as well the aortic arch, and hence lower the rupture risk.

A Comparative Study of Biomechanical and Geometrical Attributes of Abdominal Aortic Aneurysms in the Asian and Caucasian Populations

2020 ◽  
Vol 142 (6) ◽  
Author(s):  
Tejas Canchi ◽  
Sourav S. Patnaik ◽  
Hong N. Nguyen ◽  
E. Y. K. Ng ◽  
Sriram Narayanan ◽  
...  
Keyword(s):  
Wall Thickness ◽  
Gaussian Curvature ◽  
Wall Stress ◽  
Aneurysm Rupture ◽  
Aortic Aneurysms ◽  
Patient Specific ◽  
Backward Elimination ◽  
Abdominal Aortic ◽  
Highly Correlated ◽  
Peak Wall Stress

Abstract In this work, we provide a quantitative assessment of the biomechanical and geometric features that characterize abdominal aortic aneurysm (AAA) models generated from 19 Asian and 19 Caucasian diameter-matched AAA patients. 3D patient-specific finite element models were generated and used to compute peak wall stress (PWS), 99th percentile wall stress (99th WS), and spatially averaged wall stress (AWS) for each AAA. In addition, 51 global geometric indices were calculated, which quantify the wall thickness, shape, and curvature of each AAA. The indices were correlated with 99th WS (the only biomechanical metric that exhibited significant association with geometric indices) using Spearman's correlation and subsequently with multivariate linear regression using backward elimination. For the Asian AAA group, 99th WS was highly correlated (R2 = 0.77) with three geometric indices, namely tortuosity, intraluminal thrombus volume, and area-averaged Gaussian curvature. Similarly, 99th WS in the Caucasian AAA group was highly correlated (R2 = 0.87) with six geometric indices, namely maximum AAA diameter, distal neck diameter, diameter–height ratio, minimum wall thickness variance, mode of the wall thickness variance, and area-averaged Gaussian curvature. Significant differences were found between the two groups for ten geometric indices; however, no differences were found for any of their respective biomechanical attributes. Assuming maximum AAA diameter as the most predictive metric for wall stress was found to be imprecise: 24% and 28% accuracy for the Asian and Caucasian groups, respectively. This investigation reveals that geometric indices other than maximum AAA diameter can serve as predictors of wall stress, and potentially for assessment of aneurysm rupture risk, in the Asian and Caucasian AAA populations.

Sign in / Sign up

Export Citation Format

Share Document