Real-Time Pulsatile Flow Prediction for Realistic, Diverse Intracranial Aneurysm Morphologies using a Graph Transformer and Steady-Flow Data Augmentation

2026-01-27

AI Summary

This study addresses the high computational cost and specialized expertise required by traditional computational fluid dynamics (CFD) methods in hemodynamic analysis of intracranial aneurysms, which hinder their clinical applicability for real-time assessment. To overcome these limitations, the authors propose an end-to-end graph Transformer model that directly predicts time-varying wall shear stress (WSS) throughout the cardiac cycle from the aneurysm surface mesh. Innovatively, the model leverages low-cost steady-state CFD simulations to augment training data, substantially improving generalization under small-sample conditions. Experimental results demonstrate that the proposed method achieves a structural similarity index (SSIM) of 0.981 and a maximum relative L2 error of 2.8% in spatiotemporal WSS prediction, outperforming existing approaches and enabling, for the first time, efficient and highly accurate real-time prediction of pulsatile flow fields.

Technology Category

• Machine Learning: Time-Series/Data Streams
• Cognitive Modeling & Cognitive Systems: Computational Creativity
• Computer Vision: 3D Computer Vision

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Extensive studies suggested that fluid mechanical markers of intracranial aneurysms (IAs) derived from Computational Fluid Dynamics (CFD) can indicate disease progression risks, but to date this has not been translated clinically. This is because CFD requires specialized expertise and is time-consuming and low throughput, making it difficult to support clinical trials. A deep learning model that maps IA morphology to biomechanical markers can address this, enabling physicians to obtain these markers in real time without performing CFD. Here, we show that a Graph Transformer model that incorporates temporal information, which is supervised by large CFD data, can accurately predict Wall Shear Stress (WSS) across the cardiac cycle from IA surface meshes. The model effectively captures the temporal variations of the WSS pattern, achieving a Structural Similarity Index (SSIM) of up to 0.981 and a maximum-based relative L2 error of 2.8%. Ablation studies and SOTA comparison confirmed its optimality. Further, as pulsatile CFD data is computationally expensive to generate and sample sizes are limited, we engaged a strategy of injecting a large amount of steady-state CFD data, which are extremely low-cost to generate, as augmentation. This approach enhances network performance substantially when pulsatile CFD data sample size is small. Our study provides a proof of concept that temporal sequences cardiovascular fluid mechanical parameters can be computed in real time using a deep learning model from the geometric mesh, and this is achievable even with small pulsatile CFD sample size. Our approach is likely applicable to other cardiovascular scenarios.

Problem

• intracranial aneurysm
• wall shear stress
• computational fluid dynamics
• real-time prediction
• pulsatile flow

Innovation

• Graph Transformer
• Pulsatile Flow Prediction
• Wall Shear Stress
• Steady-Flow Data Augmentation
• Intracranial Aneurysm