Cargando…
Joint super-resolution and synthesis of 1 mm isotropic MP-RAGE volumes from clinical MRI exams with scans of different orientation, resolution and contrast
Most existing algorithms for automatic 3D morphometry of human brain MRI scans are designed for data with near-isotropic voxels at approximately 1 mm resolution, and frequently have contrast constraints as well-typically requiring T1-weighted images (e.g., MP-RAGE scans). This limitation prevents th...
Autores principales: | , , , , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Academic Press
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8354427/ https://www.ncbi.nlm.nih.gov/pubmed/34048902 http://dx.doi.org/10.1016/j.neuroimage.2021.118206 |
_version_ | 1783736589723107328 |
---|---|
author | Iglesias, Juan Eugenio Billot, Benjamin Balbastre, Yaël Tabari, Azadeh Conklin, John Gilberto González, R. Alexander, Daniel C. Golland, Polina Edlow, Brian L. Fischl, Bruce |
author_facet | Iglesias, Juan Eugenio Billot, Benjamin Balbastre, Yaël Tabari, Azadeh Conklin, John Gilberto González, R. Alexander, Daniel C. Golland, Polina Edlow, Brian L. Fischl, Bruce |
author_sort | Iglesias, Juan Eugenio |
collection | PubMed |
description | Most existing algorithms for automatic 3D morphometry of human brain MRI scans are designed for data with near-isotropic voxels at approximately 1 mm resolution, and frequently have contrast constraints as well-typically requiring T1-weighted images (e.g., MP-RAGE scans). This limitation prevents the analysis of millions of MRI scans acquired with large inter-slice spacing in clinical settings every year. In turn, the inability to quantitatively analyze these scans hinders the adoption of quantitative neuro imaging in healthcare, and also precludes research studies that could attain huge sample sizes and hence greatly improve our understanding of the human brain. Recent advances in convolutional neural networks (CNNs) are producing outstanding results in super-resolution and contrast synthesis of MRI. However, these approaches are very sensitive to the specific combination of contrast, resolution and orientation of the input images, and thus do not generalize to diverse clinical acquisition protocols – even within sites. In this article, we present SynthSR, a method to train a CNN that receives one or more scans with spaced slices, acquired with different contrast, resolution and orientation, and produces an isotropic scan of canonical contrast (typically a 1 mm MP-RAGE). The presented method does not require any preprocessing, beyond rigid coregistration of the input scans. Crucially, SynthSR trains on synthetic input images generated from 3D segmentations, and can thus be used to train CNNs for any combination of contrasts, resolutions and orientations without high-resolution real images of the input contrasts. We test the images generated with SynthSR in an array of common downstream analyses, and show that they can be reliably used for subcortical segmentation and volumetry, image registration (e.g., for tensor-based morphometry), and, if some image quality requirements are met, even cortical thickness morphometry. The source code is publicly available at https://github.com/BBillot/SynthSR. |
format | Online Article Text |
id | pubmed-8354427 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2021 |
publisher | Academic Press |
record_format | MEDLINE/PubMed |
spelling | pubmed-83544272021-08-15 Joint super-resolution and synthesis of 1 mm isotropic MP-RAGE volumes from clinical MRI exams with scans of different orientation, resolution and contrast Iglesias, Juan Eugenio Billot, Benjamin Balbastre, Yaël Tabari, Azadeh Conklin, John Gilberto González, R. Alexander, Daniel C. Golland, Polina Edlow, Brian L. Fischl, Bruce Neuroimage Article Most existing algorithms for automatic 3D morphometry of human brain MRI scans are designed for data with near-isotropic voxels at approximately 1 mm resolution, and frequently have contrast constraints as well-typically requiring T1-weighted images (e.g., MP-RAGE scans). This limitation prevents the analysis of millions of MRI scans acquired with large inter-slice spacing in clinical settings every year. In turn, the inability to quantitatively analyze these scans hinders the adoption of quantitative neuro imaging in healthcare, and also precludes research studies that could attain huge sample sizes and hence greatly improve our understanding of the human brain. Recent advances in convolutional neural networks (CNNs) are producing outstanding results in super-resolution and contrast synthesis of MRI. However, these approaches are very sensitive to the specific combination of contrast, resolution and orientation of the input images, and thus do not generalize to diverse clinical acquisition protocols – even within sites. In this article, we present SynthSR, a method to train a CNN that receives one or more scans with spaced slices, acquired with different contrast, resolution and orientation, and produces an isotropic scan of canonical contrast (typically a 1 mm MP-RAGE). The presented method does not require any preprocessing, beyond rigid coregistration of the input scans. Crucially, SynthSR trains on synthetic input images generated from 3D segmentations, and can thus be used to train CNNs for any combination of contrasts, resolutions and orientations without high-resolution real images of the input contrasts. We test the images generated with SynthSR in an array of common downstream analyses, and show that they can be reliably used for subcortical segmentation and volumetry, image registration (e.g., for tensor-based morphometry), and, if some image quality requirements are met, even cortical thickness morphometry. The source code is publicly available at https://github.com/BBillot/SynthSR. Academic Press 2021-08-15 /pmc/articles/PMC8354427/ /pubmed/34048902 http://dx.doi.org/10.1016/j.neuroimage.2021.118206 Text en © 2021 The Authors https://creativecommons.org/licenses/by/4.0/This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/). |
spellingShingle | Article Iglesias, Juan Eugenio Billot, Benjamin Balbastre, Yaël Tabari, Azadeh Conklin, John Gilberto González, R. Alexander, Daniel C. Golland, Polina Edlow, Brian L. Fischl, Bruce Joint super-resolution and synthesis of 1 mm isotropic MP-RAGE volumes from clinical MRI exams with scans of different orientation, resolution and contrast |
title | Joint super-resolution and synthesis of 1 mm isotropic MP-RAGE volumes from clinical MRI exams with scans of different orientation, resolution and contrast |
title_full | Joint super-resolution and synthesis of 1 mm isotropic MP-RAGE volumes from clinical MRI exams with scans of different orientation, resolution and contrast |
title_fullStr | Joint super-resolution and synthesis of 1 mm isotropic MP-RAGE volumes from clinical MRI exams with scans of different orientation, resolution and contrast |
title_full_unstemmed | Joint super-resolution and synthesis of 1 mm isotropic MP-RAGE volumes from clinical MRI exams with scans of different orientation, resolution and contrast |
title_short | Joint super-resolution and synthesis of 1 mm isotropic MP-RAGE volumes from clinical MRI exams with scans of different orientation, resolution and contrast |
title_sort | joint super-resolution and synthesis of 1 mm isotropic mp-rage volumes from clinical mri exams with scans of different orientation, resolution and contrast |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8354427/ https://www.ncbi.nlm.nih.gov/pubmed/34048902 http://dx.doi.org/10.1016/j.neuroimage.2021.118206 |
work_keys_str_mv | AT iglesiasjuaneugenio jointsuperresolutionandsynthesisof1mmisotropicmpragevolumesfromclinicalmriexamswithscansofdifferentorientationresolutionandcontrast AT billotbenjamin jointsuperresolutionandsynthesisof1mmisotropicmpragevolumesfromclinicalmriexamswithscansofdifferentorientationresolutionandcontrast AT balbastreyael jointsuperresolutionandsynthesisof1mmisotropicmpragevolumesfromclinicalmriexamswithscansofdifferentorientationresolutionandcontrast AT tabariazadeh jointsuperresolutionandsynthesisof1mmisotropicmpragevolumesfromclinicalmriexamswithscansofdifferentorientationresolutionandcontrast AT conklinjohn jointsuperresolutionandsynthesisof1mmisotropicmpragevolumesfromclinicalmriexamswithscansofdifferentorientationresolutionandcontrast AT gilbertogonzalezr jointsuperresolutionandsynthesisof1mmisotropicmpragevolumesfromclinicalmriexamswithscansofdifferentorientationresolutionandcontrast AT alexanderdanielc jointsuperresolutionandsynthesisof1mmisotropicmpragevolumesfromclinicalmriexamswithscansofdifferentorientationresolutionandcontrast AT gollandpolina jointsuperresolutionandsynthesisof1mmisotropicmpragevolumesfromclinicalmriexamswithscansofdifferentorientationresolutionandcontrast AT edlowbrianl jointsuperresolutionandsynthesisof1mmisotropicmpragevolumesfromclinicalmriexamswithscansofdifferentorientationresolutionandcontrast AT fischlbruce jointsuperresolutionandsynthesisof1mmisotropicmpragevolumesfromclinicalmriexamswithscansofdifferentorientationresolutionandcontrast AT jointsuperresolutionandsynthesisof1mmisotropicmpragevolumesfromclinicalmriexamswithscansofdifferentorientationresolutionandcontrast |