Localized FNO for Spatiotemporal Hemodynamic Upsampling in Aneurysm MRI

2025-07-18

AI Summary

Low spatiotemporal resolution and poor signal-to-noise ratio in clinical MRI impede accurate quantification of wall shear stress (WSS) for cerebral aneurysm hemodynamic analysis. Method: We propose LoFNO, the first end-to-end 3D deep learning architecture that integrates Fourier neural operators with Laplacian eigenvector–guided geometric encoding to explicitly model irregular vascular topology, coupled with an enhanced deep super-resolution network (EDSR) for direct reconstruction of high-fidelity 3D velocity fields and WSS distributions from low-resolution clinical MRI. Results: LoFNO significantly outperforms conventional interpolation and state-of-the-art deep learning methods in velocity and WSS prediction. It achieves, for the first time, CFD-free, MRI-driven, high-fidelity WSS super-resolution reconstruction—enabling robust imaging biomarkers for aneurysm rupture risk assessment and personalized therapeutic planning.

Technology Category

• Computer Vision: 3D Computer Vision
• Machine Learning: Neuro-Symbolic Learning
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

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.

Problem

• Enhances spatiotemporal resolution of aneurysm MRI hemodynamics
• Predicts wall shear stress from clinical imaging data
• Improves cerebrovascular diagnostics via denoising and upsampling

Innovation

• Localized Fourier Neural Operator enhances resolution
• Integrates Laplacian eigenvectors for structural awareness
• Combines geometric priors with neural operator frameworks