Distortion correction of diffusion weighted MRI without reverse phase-encoding scans or field-maps.

Diffusion magnetic resonance images may suffer from geometric distortions due to susceptibility induced off resonance fields, which cause geometric mismatch with anatomical images and ultimately affect subsequent quantification of microstructural or connectivity indices. State-of-the art diffusion d...

Full description

Saved in:
Bibliographic Details
Main Authors: Kurt G Schilling, Justin Blaber, Colin Hansen, Leon Cai, Baxter Rogers, Adam W Anderson, Seth Smith, Praitayini Kanakaraj, Tonia Rex, Susan M Resnick, Andrea T Shafer, Laurie E Cutting, Neil Woodward, David Zald, Bennett A Landman
Format: Article
Language:English
Published: Public Library of Science (PLoS) 2020-01-01
Series:PLoS ONE
Online Access:https://doi.org/10.1371/journal.pone.0236418
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849228055949606912
author Kurt G Schilling
Justin Blaber
Colin Hansen
Leon Cai
Baxter Rogers
Adam W Anderson
Seth Smith
Praitayini Kanakaraj
Tonia Rex
Susan M Resnick
Andrea T Shafer
Laurie E Cutting
Neil Woodward
David Zald
Bennett A Landman
author_facet Kurt G Schilling
Justin Blaber
Colin Hansen
Leon Cai
Baxter Rogers
Adam W Anderson
Seth Smith
Praitayini Kanakaraj
Tonia Rex
Susan M Resnick
Andrea T Shafer
Laurie E Cutting
Neil Woodward
David Zald
Bennett A Landman
author_sort Kurt G Schilling
collection DOAJ
description Diffusion magnetic resonance images may suffer from geometric distortions due to susceptibility induced off resonance fields, which cause geometric mismatch with anatomical images and ultimately affect subsequent quantification of microstructural or connectivity indices. State-of-the art diffusion distortion correction methods typically require data acquired with reverse phase encoding directions, resulting in varying magnitudes and orientations of distortion, which allow estimation of an undistorted volume. Alternatively, additional field maps acquisitions can be used along with sequence information to determine warping fields. However, not all imaging protocols include these additional scans and cannot take advantage of state-of-the art distortion correction. To avoid additional acquisitions, structural MRI (undistorted scans) can be used as registration targets for intensity driven correction. In this study, we aim to (1) enable susceptibility distortion correction with historical and/or limited diffusion datasets that do not include specific sequences for distortion correction and (2) avoid the computationally intensive registration procedure typically required for distortion correction using structural scans. To achieve these aims, we use deep learning (3D U-nets) to synthesize an undistorted b0 image that matches geometry of structural T1w images and intensity contrasts from diffusion images. Importantly, the training dataset is heterogenous, consisting of varying acquisitions of both structural and diffusion. We apply our approach to a withheld test set and show that distortions are successfully corrected after processing. We quantitatively evaluate the proposed distortion correction and intensity-based registration against state-of-the-art distortion correction (FSL topup). The results illustrate that the proposed pipeline results in b0 images that are geometrically similar to non-distorted structural images, and more closely match state-of-the-art correction with additional acquisitions. In addition, we show generalizability of the proposed approach to datasets that were not in the original training / validation / testing datasets. These datasets included varying populations, contrasts, resolutions, and magnitudes and orientations of distortion and show efficacious distortion correction. The method is available as a Singularity container, source code, and an executable trained model to facilitate evaluation.
format Article
id doaj-art-0370be24fa574235bc4b9ce9bc22df1c
institution Kabale University
issn 1932-6203
language English
publishDate 2020-01-01
publisher Public Library of Science (PLoS)
record_format Article
series PLoS ONE
spelling doaj-art-0370be24fa574235bc4b9ce9bc22df1c2025-08-23T05:32:40ZengPublic Library of Science (PLoS)PLoS ONE1932-62032020-01-01157e023641810.1371/journal.pone.0236418Distortion correction of diffusion weighted MRI without reverse phase-encoding scans or field-maps.Kurt G SchillingJustin BlaberColin HansenLeon CaiBaxter RogersAdam W AndersonSeth SmithPraitayini KanakarajTonia RexSusan M ResnickAndrea T ShaferLaurie E CuttingNeil WoodwardDavid ZaldBennett A LandmanDiffusion magnetic resonance images may suffer from geometric distortions due to susceptibility induced off resonance fields, which cause geometric mismatch with anatomical images and ultimately affect subsequent quantification of microstructural or connectivity indices. State-of-the art diffusion distortion correction methods typically require data acquired with reverse phase encoding directions, resulting in varying magnitudes and orientations of distortion, which allow estimation of an undistorted volume. Alternatively, additional field maps acquisitions can be used along with sequence information to determine warping fields. However, not all imaging protocols include these additional scans and cannot take advantage of state-of-the art distortion correction. To avoid additional acquisitions, structural MRI (undistorted scans) can be used as registration targets for intensity driven correction. In this study, we aim to (1) enable susceptibility distortion correction with historical and/or limited diffusion datasets that do not include specific sequences for distortion correction and (2) avoid the computationally intensive registration procedure typically required for distortion correction using structural scans. To achieve these aims, we use deep learning (3D U-nets) to synthesize an undistorted b0 image that matches geometry of structural T1w images and intensity contrasts from diffusion images. Importantly, the training dataset is heterogenous, consisting of varying acquisitions of both structural and diffusion. We apply our approach to a withheld test set and show that distortions are successfully corrected after processing. We quantitatively evaluate the proposed distortion correction and intensity-based registration against state-of-the-art distortion correction (FSL topup). The results illustrate that the proposed pipeline results in b0 images that are geometrically similar to non-distorted structural images, and more closely match state-of-the-art correction with additional acquisitions. In addition, we show generalizability of the proposed approach to datasets that were not in the original training / validation / testing datasets. These datasets included varying populations, contrasts, resolutions, and magnitudes and orientations of distortion and show efficacious distortion correction. The method is available as a Singularity container, source code, and an executable trained model to facilitate evaluation.https://doi.org/10.1371/journal.pone.0236418
spellingShingle Kurt G Schilling
Justin Blaber
Colin Hansen
Leon Cai
Baxter Rogers
Adam W Anderson
Seth Smith
Praitayini Kanakaraj
Tonia Rex
Susan M Resnick
Andrea T Shafer
Laurie E Cutting
Neil Woodward
David Zald
Bennett A Landman
Distortion correction of diffusion weighted MRI without reverse phase-encoding scans or field-maps.
PLoS ONE
title Distortion correction of diffusion weighted MRI without reverse phase-encoding scans or field-maps.
title_full Distortion correction of diffusion weighted MRI without reverse phase-encoding scans or field-maps.
title_fullStr Distortion correction of diffusion weighted MRI without reverse phase-encoding scans or field-maps.
title_full_unstemmed Distortion correction of diffusion weighted MRI without reverse phase-encoding scans or field-maps.
title_short Distortion correction of diffusion weighted MRI without reverse phase-encoding scans or field-maps.
title_sort distortion correction of diffusion weighted mri without reverse phase encoding scans or field maps
url https://doi.org/10.1371/journal.pone.0236418
work_keys_str_mv AT kurtgschilling distortioncorrectionofdiffusionweightedmriwithoutreversephaseencodingscansorfieldmaps
AT justinblaber distortioncorrectionofdiffusionweightedmriwithoutreversephaseencodingscansorfieldmaps
AT colinhansen distortioncorrectionofdiffusionweightedmriwithoutreversephaseencodingscansorfieldmaps
AT leoncai distortioncorrectionofdiffusionweightedmriwithoutreversephaseencodingscansorfieldmaps
AT baxterrogers distortioncorrectionofdiffusionweightedmriwithoutreversephaseencodingscansorfieldmaps
AT adamwanderson distortioncorrectionofdiffusionweightedmriwithoutreversephaseencodingscansorfieldmaps
AT sethsmith distortioncorrectionofdiffusionweightedmriwithoutreversephaseencodingscansorfieldmaps
AT praitayinikanakaraj distortioncorrectionofdiffusionweightedmriwithoutreversephaseencodingscansorfieldmaps
AT toniarex distortioncorrectionofdiffusionweightedmriwithoutreversephaseencodingscansorfieldmaps
AT susanmresnick distortioncorrectionofdiffusionweightedmriwithoutreversephaseencodingscansorfieldmaps
AT andreatshafer distortioncorrectionofdiffusionweightedmriwithoutreversephaseencodingscansorfieldmaps
AT laurieecutting distortioncorrectionofdiffusionweightedmriwithoutreversephaseencodingscansorfieldmaps
AT neilwoodward distortioncorrectionofdiffusionweightedmriwithoutreversephaseencodingscansorfieldmaps
AT davidzald distortioncorrectionofdiffusionweightedmriwithoutreversephaseencodingscansorfieldmaps
AT bennettalandman distortioncorrectionofdiffusionweightedmriwithoutreversephaseencodingscansorfieldmaps