EUVIMEDEUVIMED entdecken
Crossref

Dynamic Mode Decomposition-based surrogate modeling of wall shear stress in an aneurysm artery

Joy Djuansjah, Ihab Omar, As'ad Alizadeh, Abdellatif M. Sadeq, Shaymaa Abed Hussein, Narinderjit Singh Sawaran Singh, Husam Rajab, Khalil Hajlaoui

Physics of Fluids · 01.08.2025 · 37 (8)

DOI: 10.1063/5.0284372 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Physics of Fluids, online erschienen am 15.08.2025. Verfasst von Joy Djuansjah und 7 weiteren Autor:innen. Die Arbeit wurde bisher 17-mal zitiert (Crossref) und nennt 47 Literaturangaben. Gefördert von: Deanship of Scientific Research, Imam Mohammed Ibn Saud Islamic University.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This study proposes a novel data-driven framework for rapid and accurate prediction of unsteady hemodynamics in a patient-specific cardiovascular model, based on a Deep Learning-based Reduced-Order Model (DL-ROM). High-fidelity simulations of pulsatile blood flow were used to generate a wall shear stress (WSS) dataset. To reduce dimensionality while preserving essential dynamics, Dynamic Mode Decomposition (DMD) was employed, capturing dominant spatiotemporal modes linked to flow instabilities and coherent structures. The extracted DMD time coefficients were then used to train an attention-augmented Convolutional Neural Network with a Long Short-Term Memory layer, enabling the prediction of temporal WSS evolution. The DL-ROM accurately reconstructs high-resolution flow fields at unseen time points, achieving pointwise relative errors below 3% across most of the aneurysm surface. Compared to traditional full-order models, the proposed approach offers over two orders of magnitude reduction in computational cost, supporting near real-time inference. Analysis of DMD mode components further revealed region-specific flow dynamics, with high-frequency oscillations concentrated near the aneurysm dome. This work introduces an efficient and interpretable surrogate model for transient hemodynamic analysis, with promising implications for clinical applications such as rupture risk stratification, fast patient screening, and future integration across multiple aneurysm geometries.

Förderung

  • Deanship of Scientific Research, Imam Mohammed Ibn Saud Islamic University

Zitieren

APA

Djuansjah, J., Omar, I., Alizadeh, A., Sadeq, A. M., Hussein, S. A., Singh, N. S. S., Rajab, H., & Hajlaoui, K. (2025). Dynamic Mode Decomposition-based surrogate modeling of wall shear stress in an aneurysm artery. Physics of Fluids, 37(8). https://doi.org/10.1063/5.0284372

Vancouver

Djuansjah J, Omar I, Alizadeh A, Sadeq AM, Hussein SA, Singh NSS, et al. Dynamic Mode Decomposition-based surrogate modeling of wall shear stress in an aneurysm artery. Physics of Fluids. 2025;37(8). doi:10.1063/5.0284372

BibTeX
@article{Djuansjah2025,
  author = {Djuansjah, Joy and Omar, Ihab and Alizadeh, As'ad and Sadeq, Abdellatif M. and Hussein, Shaymaa Abed and Singh, Narinderjit Singh Sawaran and Rajab, Husam and Hajlaoui, Khalil},
  title = {Dynamic Mode Decomposition-based surrogate modeling of wall shear stress in an aneurysm artery},
  journal = {Physics of Fluids},
  year = {2025},
  volume = {37},
  number = {8},
  doi = {10.1063/5.0284372}
}
Kostenlos starten →