Localized FNO for Spatiotemporal Hemodynamic Upsampling in Aneurysm MRI

TL;DR

This paper introduces LoFNO, a novel neural network architecture that significantly improves the resolution and accuracy of hemodynamic MRI data, enabling better diagnosis of aneurysms by predicting flow and wall shear stress more precisely.

Contribution

The paper presents LoFNO, a new 3D neural operator architecture that incorporates geometric priors and super-resolution techniques for enhanced spatiotemporal upsampling of MRI flow data.

Findings

LoFNO outperforms interpolation and other deep learning methods in velocity prediction.

LoFNO accurately predicts wall shear stress from clinical MRI data.

The method improves diagnostic capabilities for cerebrovascular conditions.

Abstract

Hemodynamic analysis is essential for predicting aneurysm rupture and guiding treatment. While magnetic resonance flow imaging enables time-resolved volumetric blood velocity measurements, its low spatiotemporal resolution and signal-to-noise ratio limit its diagnostic utility. To address this, we propose the Localized Fourier Neural Operator (LoFNO), a novel 3D architecture that enhances both spatial and temporal resolution with the ability to predict wall shear stress (WSS) directly from clinical imaging data. LoFNO integrates Laplacian eigenvectors as geometric priors for improved structural awareness on irregular, unseen geometries and employs an Enhanced Deep Super-Resolution Network (EDSR) layer for robust upsampling. By combining geometric priors with neural operator frameworks, LoFNO de-noises and spatiotemporally upsamples flow data, achieving superior velocity and WSS predictions compared to interpolation and alternative deep learning methods, enabling more precise cerebrovascular diagnostics.