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 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.

[1]  Stefan Skare,et al.  How to correct susceptibility distortions in spin-echo echo-planar images: application to diffusion tensor imaging , 2003, NeuroImage.

[2]  Jessica A. Turner,et al.  MultiCenter Reliability of Diffusion Tensor Imaging , 2012, Brain Connect..

[3]  Satrajit S. Ghosh,et al.  BIDS apps: Improving ease of use, accessibility, and reproducibility of neuroimaging data analysis methods , 2016, bioRxiv.

[4]  Carlo Pierpaoli,et al.  Evaluating corrections for Eddy‐currents and other EPI distortions in diffusion MRI: methodology and a dataset for benchmarking , 2018, Magnetic resonance in medicine.

[5]  Carlo Pierpaoli,et al.  Comparison of EPI Distortion Correction Methods in Diffusion Tensor MRI Using a Novel Framework , 2008, MICCAI.

[6]  Sean P. Fitzgibbon,et al.  Automated quality control for within and between studies diffusion MRI data using a non-parametric framework for movement and distortion correction , 2019, NeuroImage.

[7]  Max C. Keuken,et al.  The Age-ility Project (Phase 1): Structural and functional imaging and electrophysiological data repository , 2016, NeuroImage.

[8]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[9]  Stamatios N. Sotiropoulos,et al.  An integrated approach to correction for off-resonance effects and subject movement in diffusion MR imaging , 2016, NeuroImage.

[10]  Yuankai Huo,et al.  Synthesized b0 for diffusion distortion correction (Synb0-DisCo). , 2019, Magnetic resonance imaging.

[11]  Andreia V Faria,et al.  Using Deep Siamese Neural Networks for Detection of Brain Asymmetries Associated with Alzheimer's Disease and Mild Cognitive Impairment. , 2019, Magnetic resonance imaging.

[12]  Julien Cohen-Adad,et al.  Geometric Evaluation of Distortion Correction Methods in Diffusion MRI of the Spinal Cord , 2019, 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019).

[13]  A. Leemans,et al.  2505 MASSIVE : Multiple Acquisitions for Standardization of Structural Imaging Validation and Evaluation , 2013 .

[14]  Carlo Pierpaoli,et al.  TORTOISE v 3 : Improvements and New Features of the NIH Diffusion MRI Processing Pipeline , 2018 .

[15]  Bruce R. Rosen,et al.  MGH–USC Human Connectome Project datasets with ultra-high b-value diffusion MRI , 2016, NeuroImage.

[16]  Justin P. Haldar,et al.  Correcting susceptibility-induced distortion in diffusion-weighted MRI using constrained nonrigid registration , 2012, Proceedings of The 2012 Asia Pacific Signal and Information Processing Association Annual Summit and Conference.

[17]  Camilo Bermudez,et al.  Inter-Scanner Harmonization of High Angular Resolution DW-MRI using Null Space Deep Learning , 2018, Lecture notes-monograph series.

[18]  Martijn Froeling,et al.  “MASSIVE” brain dataset: Multiple acquisitions for standardization of structural imaging validation and evaluation , 2017, Magnetic resonance in medicine.

[19]  M. Mallar Chakravarty,et al.  BIDS Apps: Improving ease of use, accessibility, and reproducibility of neuroimaging data analysis methods , 2016 .

[20]  Hui Zhang,et al.  Quantitative assessment of the susceptibility artefact and its interaction with motion in diffusion MRI , 2017, PloS one.

[21]  David Atkinson,et al.  Model‐based reconstruction framework for correction of signal pile‐up and geometric distortions in prostate diffusion MRI , 2019, Magnetic resonance in medicine.

[22]  Thomas Brox,et al.  3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation , 2016, MICCAI.

[23]  Min Chen,et al.  Multi-parametric neuroimaging reproducibility: A 3-T resource study , 2011, NeuroImage.

[24]  Olivier Coulon,et al.  Diffusion MRI: Assessment of the Impact of Acquisition and Preprocessing Methods Using the BrainVISA-Diffuse Toolbox , 2019, Front. Neurosci..

[25]  Luca Antiga,et al.  Automatic differentiation in PyTorch , 2017 .

[26]  A. Soricelli,et al.  Histogram analysis of DTI-derived indices reveals pontocerebellar degeneration and its progression in SCA2 , 2018, PloS one.

[27]  Richard M. Leahy,et al.  BrainSuite: An Automated Cortical Surface Identification Tool , 2000, MICCAI.

[28]  Thomas E. Nichols,et al.  Extending the Human Connectome Project across ages: Imaging protocols for the Lifespan Development and Aging projects , 2018, NeuroImage.

[29]  Steen Moeller,et al.  Advances in diffusion MRI acquisition and processing in the Human Connectome Project , 2013, NeuroImage.

[30]  Mark W. Woolrich,et al.  Advances in functional and structural MR image analysis and implementation as FSL , 2004, NeuroImage.

[31]  Carlo Pierpaoli,et al.  DR-BUDDI (Diffeomorphic Registration for Blip-Up blip-Down Diffusion Imaging) method for correcting echo planar imaging distortions , 2015, NeuroImage.

[32]  Daniel P. Kennedy,et al.  The Autism Brain Imaging Data Exchange: Towards Large-Scale Evaluation of the Intrinsic Brain Architecture in Autism , 2013, Molecular Psychiatry.