Localized FNO for Spatiotemporal Hemodynamic Upsampling in Aneurysm MRI

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Flouris, Kyriakos, Halter, Moritz, Lee, Yolanne Y. R., Castonguay, Samuel, Jacobs, Luuk, Dirix, Pietro, Nestmann, Jonathan, Kozerke, Sebastian, Konukoglu, Ender
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866913948645720064
author Flouris, Kyriakos
Halter, Moritz
Lee, Yolanne Y. R.
Castonguay, Samuel
Jacobs, Luuk
Dirix, Pietro
Nestmann, Jonathan
Kozerke, Sebastian
Konukoglu, Ender
author_facet Flouris, Kyriakos
Halter, Moritz
Lee, Yolanne Y. R.
Castonguay, Samuel
Jacobs, Luuk
Dirix, Pietro
Nestmann, Jonathan
Kozerke, Sebastian
Konukoglu, Ender
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2507_13789
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Localized FNO for Spatiotemporal Hemodynamic Upsampling in Aneurysm MRI
Flouris, Kyriakos
Halter, Moritz
Lee, Yolanne Y. R.
Castonguay, Samuel
Jacobs, Luuk
Dirix, Pietro
Nestmann, Jonathan
Kozerke, Sebastian
Konukoglu, Ender
Computer Vision and Pattern Recognition
Artificial Intelligence
Computational Physics
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.
title Localized FNO for Spatiotemporal Hemodynamic Upsampling in Aneurysm MRI
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Computational Physics
url https://arxiv.org/abs/2507.13789