Cargando…

Manifold-aware synthesis of high-resolution diffusion from structural imaging

The physical and clinical constraints surrounding diffusion-weighted imaging (DWI) often limit the spatial resolution of the produced images to voxels up to eight times larger than those of T1w images. The detailed information contained in accessible high-resolution T1w images could help in the synt...

Descripción completa

Detalles Bibliográficos
Autores principales: Anctil-Robitaille, Benoit, Théberge, Antoine, Jodoin, Pierre-Marc, Descoteaux, Maxime, Desrosiers, Christian, Lombaert, Hervé
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10406190/
https://www.ncbi.nlm.nih.gov/pubmed/37555146
http://dx.doi.org/10.3389/fnimg.2022.930496
_version_ 1785085696270139392
author Anctil-Robitaille, Benoit
Théberge, Antoine
Jodoin, Pierre-Marc
Descoteaux, Maxime
Desrosiers, Christian
Lombaert, Hervé
author_facet Anctil-Robitaille, Benoit
Théberge, Antoine
Jodoin, Pierre-Marc
Descoteaux, Maxime
Desrosiers, Christian
Lombaert, Hervé
author_sort Anctil-Robitaille, Benoit
collection PubMed
description The physical and clinical constraints surrounding diffusion-weighted imaging (DWI) often limit the spatial resolution of the produced images to voxels up to eight times larger than those of T1w images. The detailed information contained in accessible high-resolution T1w images could help in the synthesis of diffusion images with a greater level of detail. However, the non-Euclidean nature of diffusion imaging hinders current deep generative models from synthesizing physically plausible images. In this work, we propose the first Riemannian network architecture for the direct generation of diffusion tensors (DT) and diffusion orientation distribution functions (dODFs) from high-resolution T1w images. Our integration of the log-Euclidean Metric into a learning objective guarantees, unlike standard Euclidean networks, the mathematically-valid synthesis of diffusion. Furthermore, our approach improves the fractional anisotropy mean squared error (FA MSE) between the synthesized diffusion and the ground-truth by more than 23% and the cosine similarity between principal directions by almost 5% when compared to our baselines. We validate our generated diffusion by comparing the resulting tractograms to our expected real data. We observe similar fiber bundles with streamlines having <3% difference in length, <1% difference in volume, and a visually close shape. While our method is able to generate diffusion images from structural inputs in a high-resolution space within 15 s, we acknowledge and discuss the limits of diffusion inference solely relying on T1w images. Our results nonetheless suggest a relationship between the high-level geometry of the brain and its overall white matter architecture that remains to be explored.
format Online
Article
Text
id pubmed-10406190
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-104061902023-08-08 Manifold-aware synthesis of high-resolution diffusion from structural imaging Anctil-Robitaille, Benoit Théberge, Antoine Jodoin, Pierre-Marc Descoteaux, Maxime Desrosiers, Christian Lombaert, Hervé Front Neuroimaging Neuroimaging The physical and clinical constraints surrounding diffusion-weighted imaging (DWI) often limit the spatial resolution of the produced images to voxels up to eight times larger than those of T1w images. The detailed information contained in accessible high-resolution T1w images could help in the synthesis of diffusion images with a greater level of detail. However, the non-Euclidean nature of diffusion imaging hinders current deep generative models from synthesizing physically plausible images. In this work, we propose the first Riemannian network architecture for the direct generation of diffusion tensors (DT) and diffusion orientation distribution functions (dODFs) from high-resolution T1w images. Our integration of the log-Euclidean Metric into a learning objective guarantees, unlike standard Euclidean networks, the mathematically-valid synthesis of diffusion. Furthermore, our approach improves the fractional anisotropy mean squared error (FA MSE) between the synthesized diffusion and the ground-truth by more than 23% and the cosine similarity between principal directions by almost 5% when compared to our baselines. We validate our generated diffusion by comparing the resulting tractograms to our expected real data. We observe similar fiber bundles with streamlines having <3% difference in length, <1% difference in volume, and a visually close shape. While our method is able to generate diffusion images from structural inputs in a high-resolution space within 15 s, we acknowledge and discuss the limits of diffusion inference solely relying on T1w images. Our results nonetheless suggest a relationship between the high-level geometry of the brain and its overall white matter architecture that remains to be explored. Frontiers Media S.A. 2022-09-08 /pmc/articles/PMC10406190/ /pubmed/37555146 http://dx.doi.org/10.3389/fnimg.2022.930496 Text en Copyright © 2022 Anctil-Robitaille, Théberge, Jodoin, Descoteaux, Desrosiers and Lombaert. https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
spellingShingle Neuroimaging
Anctil-Robitaille, Benoit
Théberge, Antoine
Jodoin, Pierre-Marc
Descoteaux, Maxime
Desrosiers, Christian
Lombaert, Hervé
Manifold-aware synthesis of high-resolution diffusion from structural imaging
title Manifold-aware synthesis of high-resolution diffusion from structural imaging
title_full Manifold-aware synthesis of high-resolution diffusion from structural imaging
title_fullStr Manifold-aware synthesis of high-resolution diffusion from structural imaging
title_full_unstemmed Manifold-aware synthesis of high-resolution diffusion from structural imaging
title_short Manifold-aware synthesis of high-resolution diffusion from structural imaging
title_sort manifold-aware synthesis of high-resolution diffusion from structural imaging
topic Neuroimaging
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10406190/
https://www.ncbi.nlm.nih.gov/pubmed/37555146
http://dx.doi.org/10.3389/fnimg.2022.930496
work_keys_str_mv AT anctilrobitaillebenoit manifoldawaresynthesisofhighresolutiondiffusionfromstructuralimaging
AT thebergeantoine manifoldawaresynthesisofhighresolutiondiffusionfromstructuralimaging
AT jodoinpierremarc manifoldawaresynthesisofhighresolutiondiffusionfromstructuralimaging
AT descoteauxmaxime manifoldawaresynthesisofhighresolutiondiffusionfromstructuralimaging
AT desrosierschristian manifoldawaresynthesisofhighresolutiondiffusionfromstructuralimaging
AT lombaertherve manifoldawaresynthesisofhighresolutiondiffusionfromstructuralimaging