In Vivo Determination of Elastic Properties of the Human Aorta Based on 4d Ultrasound Data

Wittek, Andreas; Bihari, Peter; Shelke, Amit; Nwe, Thet Htar; Nelson, Karen E.; Karatolios, Konstantinos; Vogt, Sebastian; Moosdorf, Rainer; Schmitz‐Rixen, T.; Blasé, Christopher

doi:10.1016/s0021-9290(12)70020-9

Cited by 25 publications

(45 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, since the input to the ML model is only a pair of in vivo shapes, the material parameters associated with the pair of shapes must be identified before using the FEA-based method, which may take an additional 1 to 2 weeks using the FE-updating-based methods. 35,36 We note that the time for FEA may increase significantly if FE model complexity increases. Since efficient GPU implementation of DNNs is publicly available (eg, TensorFlow 46 ) and GPU performance keeps increasing, DNNs can handle more complex geometries effectively by adding more layers and units.…”

Section: Discussionmentioning

confidence: 98%

“…Then a dataset from 3125 (125 shapes from SSM × 25 sets of material parameters) virtual patients was obtained, consisting of 3 shapes per virtual patient at the systolic phase, diastolic phase, and zero-pressure state. We note that on the basis of the previous studies, [35][36][37] the material parameters of the constitutive model (Equation A1) can be identified from the aorta shapes at 2 cardiac phases with known blood pressure levels (eg, systole and diastole), which implies the 2 geometries contain material property information.…”

Section: Finite Element Simulation and Virtual Patient Datamentioning

confidence: 93%

See 1 more Smart Citation

A machine learning approach as a surrogate of finite element analysis–based inverse method to estimate the zero‐pressure geometry of human thoracic aorta

Liang

Liu

Martin

et al. 2018

Numer Methods Biomed Eng

View full text Add to dashboard Cite

Advances in structural finite element analysis (FEA) and medical imaging have made it possible to investigate the in vivo biomechanics of human organs such as blood vessels, for which organ geometries at the zero-pressure level need to be recovered. Although FEA-based inverse methods are available for zero-pressure geometry estimation, these methods typically require iterative computation, which are time-consuming and may be not suitable for time-sensitive clinical applications. In this study, by using machine learning (ML) techniques, we developed an ML model to estimate the zero-pressure geometry of human thoracic aorta given 2 pressurized geometries of the same patient at 2 different blood pressure levels. For the ML model development, a FEA-based method was used to generate a dataset of aorta geometries of 3125 virtual patients. The ML model, which was trained and tested on the dataset, is capable of recovering zero-pressure geometries consistent with those generated by the FEA-based method. Thus, this study demonstrates the feasibility and great potential of using ML techniques as a fast surrogate of FEA-based inverse methods to recover zero-pressure geometries of human organs.

show abstract

Section: Discussionmentioning

confidence: 98%

Section: Finite Element Simulation and Virtual Patient Datamentioning

confidence: 93%

A machine learning approach as a surrogate of finite element analysis–based inverse method to estimate the zero‐pressure geometry of human thoracic aorta

Liang

Liu

Martin

et al. 2018

Numer Methods Biomed Eng

View full text Add to dashboard Cite

show abstract

“…39 However, the mean (homogenized) circumferential strain in this study (calculated by averaging the circumferential strain of all regions) is 0.14 ± 0.05, which is in close agreement to previously reported mean values of abdominal aortic circumferential strain via ultrasound of 0.132 ± 0.065 (Karatolios et al) and 0.123 ± 0.014 (Wittek et al). 31,40 Furthermore, Goergen et al report a consistent mean circumferential strain of the abdominal aorta even across multiple species from mice to humans of 0.12-0.16. 32 Second, our study used 2D DENSE and only calculated in-plane strain for a cross-section with 8 mm thickness.…”

Section: Discussionmentioning

confidence: 99%

Demonstration of circumferential heterogeneity in displacement and strain in the abdominal aortic wall by spiral cine DENSE MRI

Iffrig

Wilson

Zhong

et al. 2018

Magnetic Resonance Imaging

View full text Add to dashboard Cite

Background Knowledge of tissue properties of the abdominal aorta can improve understanding of vascular disease and guide interventional approaches. Existing MRI methods to quantify aortic wall displacement and strain are unable to discern circumferential heterogeneity. Purpose To assess regional variation in abdominal aortic wall displacement and strain as a function of circumferential position using spiral cine displacement encoding with stimulated echoes (DENSE). Study Type Prospective. Population Cardiovascular disease‐free men (n = 8) and women (n = 9) ages 30–42. Sequences Prospective electrocardiogram (ECG)‐gated and navigator echo‐gated spiral, cine 2D DENSE and retrospective ECG‐gated phase contrast MR (PCMR) sequences at 3T. Assessment In‐plane displacement values of the aortic wall acquired with DENSE were used to determine radial and circumferential aortic wall motion. A quadrilateral‐based 2D strain calculation method was implemented to determine strain from the displacement field. Peak displacement and its radial and circumferential contributions as well as peak circumferential strain were compared among eight circumferential wall segments. Distensibility was calculated using PCMR and compared with homogenized circumferential strain. Statistical Tests To account for repeated measurements in volunteers, linear mixed models for mean sector values were created for displacement magnitude, circumferential displacement, radial displacement, and circumferential strain. Comparisons were made between sectors. Calculated distensibility and homogenized circumferential strain were compared using Bland–Altman analysis. Statistical significance was defined as P < 0.05. Results Displacement was highest in the anterior wall (1.5 ± 0.7 mm) and was primarily in the radial as compared with circumferential direction (1.04 ± 0.05 mm vs. 0.81 ± 0.42 mm). Circumferential strain was highest in the lateral walls (left 0.16 ± 0.05 and right 0.21 ± 0.12) with homogenized circumferential strain of 0.14 ± 0.05. Data Conclusion DENSE imaging in the abdominal aortic wall demonstrated that the anterior aortic wall exhibits the greatest displacement, while the lateral wall experiences the largest circumferential strain. Level of Evidence: 3 Technical Efficacy: Stage 2 J. Magn. Reson. Imaging 2019;49:731–743.

show abstract

“…This optimization process yields the optimal constitutive parameters. Using finite element (FE) updating schemes, (Wittek et al, 2016;Wittek et al, 2013) developed two methods to determine GOH material parameters of the human abdominal aorta from in vivo 4D ultrasound data. However, numerous iterations were needed to reach the optimal solution, resulting in long computing time of 1~2 weeks.…”

Section: Introductionmentioning

confidence: 99%

Estimation of in vivo constitutive parameters of the aortic wall: a machine learning approach

Liu

Liang

Sun

2018

Preprint

View full text Add to dashboard Cite

The patient-specific biomechanical analysis of the aorta demands the in vivo mechanical properties of individual patients. Current inverse approaches have shown the feasibility of estimating the nonlinear, anisotropic material parameters from in vivo image data using certain optimization schemes. However, since such inverse methods are dependent on iterative nonlinear optimization, these methods are highly computation-intensive, which may take weeks to complete for only a single patient, inhibiting rapid feedback for clinical use. Recently, machine learning (ML) techniques have led to revolutionary breakthroughs in many applications. A potential paradigm-changing solution to the bottleneck associated with patient-specific computational modeling is to incorporate ML algorithms to expedite the procedure of in vivo material parameter identification. In this paper, we developed a ML-based approach to identify the material parameters from three-dimensional aorta geometries obtained at two different blood pressure levels, namely systolic and diastolic geometries. The nonlinear relationship between the two loaded shapes and the constitutive parameters are established by a ML-model, which was trained and tested using finite element (FE) simulation datasets. Cross-validation was used to adjust the ML-model structure on a training/validation dataset. The accuracy of the ML-model was examined using a testing dataset.

show abstract

In Vivo Determination of Elastic Properties of the Human Aorta Based on 4d Ultrasound Data

Cited by 25 publications

References 0 publications

A machine learning approach as a surrogate of finite element analysis–based inverse method to estimate the zero‐pressure geometry of human thoracic aorta

A machine learning approach as a surrogate of finite element analysis–based inverse method to estimate the zero‐pressure geometry of human thoracic aorta

Demonstration of circumferential heterogeneity in displacement and strain in the abdominal aortic wall by spiral cine DENSE MRI

Estimation of in vivo constitutive parameters of the aortic wall: a machine learning approach

Contact Info

Product

Resources

About