Abstract <p>Aortic aneurysms pose a significant risk of rupture. Previous research has shown that areas exposed to low wall shear stress (WSS) are more prone to rupture. Therefore, precise WSS determination on the aneurysm is crucial for rupture risk assessment. Computational fluid dynamics (CFD) is a powerful approach for WSS calculations, but they are computationally intensive, hindering time-sensitive clinical decision-making. In this study, we propose a deep learning (DL) surrogate, MultiViewUNet, to rapidly predict time-averaged WSS (TAWSS) distributions on abdominal aortic aneurysms (AAA). Our novel approach employs a domain transformation technique to translate complex aortic geometries into representations compatible with state-of-the-art neural networks. MultiViewUNet was trained on <InlineEquation ID="IEq1"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="11517_2025_3311_Article_IEq1.gif" Format="GIF" Height="14" Rendition="HTML" Resolution="72" Type="Linedraw" Width="21" /> </InlineMediaObject> <EquationSource Format="TEX">$\varvec{23}$</EquationSource> <EquationSource Format="MATHML"><math> <mrow> <mn mathvariant="bold">23</mn> </mrow> </math></EquationSource> </InlineEquation> real and <InlineEquation ID="IEq2"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="11517_2025_3311_Article_IEq2.gif" Format="GIF" Height="14" Rendition="HTML" Resolution="72" Type="Linedraw" Width="31" /> </InlineMediaObject> <EquationSource Format="TEX">$\varvec{230}$</EquationSource> <EquationSource Format="MATHML"><math> <mrow> <mn mathvariant="bold">230</mn> </mrow> </math></EquationSource> </InlineEquation> synthetic AAA geometries, demonstrating an average normalized mean absolute error (NMAE) of just <InlineEquation ID="IEq3"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="11517_2025_3311_Article_IEq3.gif" Format="GIF" Height="16" Rendition="HTML" Resolution="72" Type="Linedraw" Width="62" /> </InlineMediaObject> <EquationSource Format="TEX">$\varvec{0.362\%}$</EquationSource> <EquationSource Format="MATHML"><math> <mrow> <mn mathvariant="bold">0.362</mn> <mo mathvariant="bold">%</mo> </mrow> </math></EquationSource> </InlineEquation> in WSS prediction. This framework has the potential to streamline hemodynamic analysis in AAA and other clinical scenarios where fast and accurate stress quantification is essential.</p> Graphical abstract <p></p>

Rapid wall shear stress prediction for aortic aneurysms using deep learning: a fast alternative to CFD

期刊论文
出版模式：

开放获取
发表日期：

2025年2月17日

查看全文

Md. Ahasan Atick Faisal,
Onur Mutlu,
Sakib Mahmud,
Anas Tahir,
Muhammad E. H. Chowdhury,
Faycal Bensaali,
Abdulrahman Alnabti,
Mehmet Metin Yavuz,
Ayman El-Menyar,
Hassan Al-Thani,
Huseyin Cagatay Yalcin

摘要

Abstract

Aortic aneurysms pose a significant risk of rupture. Previous research has shown that areas exposed to low wall shear stress (WSS) are more prone to rupture. Therefore, precise WSS determination on the aneurysm is crucial for rupture risk assessment. Computational fluid dynamics (CFD) is a powerful approach for WSS calculations, but they are computationally intensive, hindering time-sensitive clinical decision-making. In this study, we propose a deep learning (DL) surrogate, MultiViewUNet, to rapidly predict time-averaged WSS (TAWSS) distributions on abdominal aortic aneurysms (AAA). Our novel approach employs a domain transformation technique to translate complex aortic geometries into representations compatible with state-of-the-art neural networks. MultiViewUNet was trained on $\varvec{23}$ $23$ real and $\varvec{230}$ $230$ synthetic AAA geometries, demonstrating an average normalized mean absolute error (NMAE) of just $\varvec{0.362\%}$ $0.362 %$ in WSS prediction. This framework has the potential to streamline hemodynamic analysis in AAA and other clinical scenarios where fast and accurate stress quantification is essential.

Graphical abstract