Geometry-aware PointNet for rapid prediction of cerebral aneurysm hemodynamics

Clinical Snapshot

Key Findings

• P Value: Not applicable for this validation study

• Effect Size: NMAE 4.05% for velocity fields, 2.59% for wall shear stress on idealized geometries

• Primary Outcome: Velocity field prediction accuracy on test set

• Nnt Or Sensitivity: Inference time: 1.6 seconds for velocity, 0.3 seconds for wall shear stress

• Confidence Interval: Not reported

Clinical Application

Low for immediate clinical use due to poor real-world generalization Would require TGA approval as medical device software; limited applicability until validated on Australian patient populations Currently limited to research settings with idealized aneurysm geometries

Abstract

BACKGROUND AND OBJECTIVE: Cerebral aneurysms affect 2-5% of the global population and pose a significant health risk upon rupture. While computational fluid dynamics provides detailed hemodynamic information for risk assessment, its high computational demands limit routine clinical use. This study aims to develop a deep learning model to rapidly predict three-dimensional velocity fields and wall shear stress at peak systole using aneurysm geometry. METHODS: We synthesized a dataset of 984 idealized middle cerebral artery bifurcation aneurysms. For each case, computational fluid dynamics simulations were conducted with pulsatile boundary conditions to generate ground-truth data, and peak-systolic snapshots were extracted. We developed a single-input point-cloud network augmented with a distance-to-wall feature to predict both velocity fields and wall shear stress. Model performance was evaluated using mean absolute error (MAE), normalized MAE (NMAE), and relative L2 error (rL2). RESULTS: On the test set, the model achieved velocity-field accuracy of NMAE 4.05% and rL2 19.2% over the full geometry domain, and WSS accuracy of NMAE 2.59% and rL2 23.9%. The mean inference time was approximately 1.6 seconds for velocity and 0.3 seconds for wall shear stress per case. Out-of-distribution evaluation on non-idealized geometries showed substantial zero-shot degradation (NMAE 19.1%, rL2 62.4%), while leave-one-out fine-tuning improved performance (NMAE 10.8%, rL2 37.0%). CONCLUSIONS: The proposed geometry-aware point-cloud surrogate provides fast peak-systolic hemodynamic prediction on idealized aneurysm geometries. However, out-of-distribution evaluation indicates that broader patient-specific training, physiological boundary conditions, and reliability assessment are required before routine clinical application.

References

1. 1.Sheng, Y., Liao, C., Li, W., Yang, E., Zhu, Y., Sun, H., & Leo, H. L. (2026). Geometry-aware PointNet for rapid prediction of cerebral aneurysm hemodynamics. Computer Methods and Programs in Biomedicine, 109308. https://doi.org/10.1016/j.cmpb.2026.109308