dStripe: slice artefact correction in diffusion MRI via constrained neural network

Maximilian Pietsch; Daan Christiaens; Joseph V Hajnal; Jacques-Donald Tournier

doi:10.1016/j.media.2021.102255

dStripe: slice artefact correction in diffusion MRI via constrained neural network

Maximilian Pietsch^*, Daan Christiaens, Joseph V Hajnal, Jacques-Donald Tournier

^*Corresponding author for this work

KU Leuven

Research output: Contribution to journal › Article › peer-review

2 Citations (Scopus)

Abstract

MRI scanner and sequence imperfections and advances in reconstruction and imaging techniques to increase motion robustness can lead to inter-slice intensity variations in Echo Planar Imaging. Leveraging deep convolutional neural networks as universal image filters, we present a data-driven method for the correction of acquisition artefacts that manifest as inter-slice inconsistencies, regardless of their origin. This technique can be applied to motion- and dropout-artefacted data by embedding it in a reconstruction pipeline. The network is trained in the absence of ground-truth data on, and finally applied to, the reconstructed multi-shell high angular resolution diffusion imaging signal to produce a corrective slice intensity modulation field. This correction can be performed in either motion-corrected or scattered source-space. We focus on gaining control over the learned filter and the image data consistency via built-in spatial frequency and intensity constraints. The end product is a corrected image reconstructed from the original raw data, modulated by a multiplicative field that can be inspected and verified to match the expected features of the artefact. In-plane, the correction approximately preserves the contrast of the diffusion signal and throughout the image series, it reduces inter-slice inconsistencies within and across subjects without biasing the data. We apply our pipeline to enhance the super-resolution reconstruction of neonatal multi-shell high angular resolution data as acquired in the developing Human Connectome Project.

Original language	English
Article number	102255
Journal	Medical Image Analysis
Volume	74
DOIs	https://doi.org/10.1016/j.media.2021.102255
Publication status	Published - 25 Sept 2021

Keywords

diffusion MRI
image artefact removal
venetian blind artefact

Access to Document

10.1016/j.media.2021.102255

Cite this

@article{452c51fa0e994b09b942a46cde64515e,

title = "dStripe: slice artefact correction in diffusion MRI via constrained neural network",

abstract = "MRI scanner and sequence imperfections and advances in reconstruction and imaging techniques to increase motion robustness can lead to inter-slice intensity variations in Echo Planar Imaging. Leveraging deep convolutional neural networks as universal image filters, we present a data-driven method for the correction of acquisition artefacts that manifest as inter-slice inconsistencies, regardless of their origin. This technique can be applied to motion- and dropout-artefacted data by embedding it in a reconstruction pipeline. The network is trained in the absence of ground-truth data on, and finally applied to, the reconstructed multi-shell high angular resolution diffusion imaging signal to produce a corrective slice intensity modulation field. This correction can be performed in either motion-corrected or scattered source-space. We focus on gaining control over the learned filter and the image data consistency via built-in spatial frequency and intensity constraints. The end product is a corrected image reconstructed from the original raw data, modulated by a multiplicative field that can be inspected and verified to match the expected features of the artefact. In-plane, the correction approximately preserves the contrast of the diffusion signal and throughout the image series, it reduces inter-slice inconsistencies within and across subjects without biasing the data. We apply our pipeline to enhance the super-resolution reconstruction of neonatal multi-shell high angular resolution data as acquired in the developing Human Connectome Project.",

keywords = "diffusion MRI, image artefact removal, venetian blind artefact",

author = "Maximilian Pietsch and Daan Christiaens and Hajnal, {Joseph V} and Jacques-Donald Tournier",

note = "Funding Information: This work received funding from the European Research Council under the European Union{\textquoteright}s Seventh Framework Programme ([FP7/20072013/ERC] grant agreement no. [319456] dHCP project), and was supported by the Wellcome/EPSRC Centre for Medical Engineering at Kings College London [WT 203148/Z/16/Z]; the Medical Research Council [MR/K006355/1] and by the National Institute for Health Research (NIHR) Biomedical Research Centre based at Guys and St Thomas NHS Foundation Trust and Kings College London. The views expressed are those of the author(s) and not necessarily those of the NHS, the NIHR or the Department of Health. We would like to thank Prof. Serena Counsell for access to the Philips Achieva 3T product sequence data. Funding Information: This work received funding from the European Research Council under the European Union's Seventh Framework Programme ([FP7/20072013/ERC] grant agreement no. [319456] dHCP project), and was supported by the Wellcome/EPSRC Centre for Medical Engineering at Kings College London [WT 203148/Z/16/Z]; the Medical Research Council [MR/K006355/1] and by the National Institute for Health Research (NIHR) Biomedical Research Centre based at Guys and St Thomas NHS Foundation Trust and Kings College London. The views expressed are those of the author(s) and not necessarily those of the NHS, the NIHR or the Department of Health. We would like to thank Prof. Serena Counsell for access to the Philips Achieva 3T product sequence data. Publisher Copyright: {\textcopyright} 2021",

year = "2021",

month = sep,

day = "25",

doi = "10.1016/j.media.2021.102255",

language = "English",

volume = "74",

journal = "Medical Image Analysis",

issn = "1361-8415",

publisher = "Elsevier",

}

TY - JOUR

T1 - dStripe: slice artefact correction in diffusion MRI via constrained neural network

AU - Pietsch, Maximilian

AU - Christiaens, Daan

AU - Hajnal, Joseph V

AU - Tournier, Jacques-Donald

N1 - Funding Information: This work received funding from the European Research Council under the European Union’s Seventh Framework Programme ([FP7/20072013/ERC] grant agreement no. [319456] dHCP project), and was supported by the Wellcome/EPSRC Centre for Medical Engineering at Kings College London [WT 203148/Z/16/Z]; the Medical Research Council [MR/K006355/1] and by the National Institute for Health Research (NIHR) Biomedical Research Centre based at Guys and St Thomas NHS Foundation Trust and Kings College London. The views expressed are those of the author(s) and not necessarily those of the NHS, the NIHR or the Department of Health. We would like to thank Prof. Serena Counsell for access to the Philips Achieva 3T product sequence data. Funding Information: This work received funding from the European Research Council under the European Union's Seventh Framework Programme ([FP7/20072013/ERC] grant agreement no. [319456] dHCP project), and was supported by the Wellcome/EPSRC Centre for Medical Engineering at Kings College London [WT 203148/Z/16/Z]; the Medical Research Council [MR/K006355/1] and by the National Institute for Health Research (NIHR) Biomedical Research Centre based at Guys and St Thomas NHS Foundation Trust and Kings College London. The views expressed are those of the author(s) and not necessarily those of the NHS, the NIHR or the Department of Health. We would like to thank Prof. Serena Counsell for access to the Philips Achieva 3T product sequence data. Publisher Copyright: © 2021

PY - 2021/9/25

Y1 - 2021/9/25

N2 - MRI scanner and sequence imperfections and advances in reconstruction and imaging techniques to increase motion robustness can lead to inter-slice intensity variations in Echo Planar Imaging. Leveraging deep convolutional neural networks as universal image filters, we present a data-driven method for the correction of acquisition artefacts that manifest as inter-slice inconsistencies, regardless of their origin. This technique can be applied to motion- and dropout-artefacted data by embedding it in a reconstruction pipeline. The network is trained in the absence of ground-truth data on, and finally applied to, the reconstructed multi-shell high angular resolution diffusion imaging signal to produce a corrective slice intensity modulation field. This correction can be performed in either motion-corrected or scattered source-space. We focus on gaining control over the learned filter and the image data consistency via built-in spatial frequency and intensity constraints. The end product is a corrected image reconstructed from the original raw data, modulated by a multiplicative field that can be inspected and verified to match the expected features of the artefact. In-plane, the correction approximately preserves the contrast of the diffusion signal and throughout the image series, it reduces inter-slice inconsistencies within and across subjects without biasing the data. We apply our pipeline to enhance the super-resolution reconstruction of neonatal multi-shell high angular resolution data as acquired in the developing Human Connectome Project.

AB - MRI scanner and sequence imperfections and advances in reconstruction and imaging techniques to increase motion robustness can lead to inter-slice intensity variations in Echo Planar Imaging. Leveraging deep convolutional neural networks as universal image filters, we present a data-driven method for the correction of acquisition artefacts that manifest as inter-slice inconsistencies, regardless of their origin. This technique can be applied to motion- and dropout-artefacted data by embedding it in a reconstruction pipeline. The network is trained in the absence of ground-truth data on, and finally applied to, the reconstructed multi-shell high angular resolution diffusion imaging signal to produce a corrective slice intensity modulation field. This correction can be performed in either motion-corrected or scattered source-space. We focus on gaining control over the learned filter and the image data consistency via built-in spatial frequency and intensity constraints. The end product is a corrected image reconstructed from the original raw data, modulated by a multiplicative field that can be inspected and verified to match the expected features of the artefact. In-plane, the correction approximately preserves the contrast of the diffusion signal and throughout the image series, it reduces inter-slice inconsistencies within and across subjects without biasing the data. We apply our pipeline to enhance the super-resolution reconstruction of neonatal multi-shell high angular resolution data as acquired in the developing Human Connectome Project.

KW - diffusion MRI

KW - image artefact removal

KW - venetian blind artefact

UR - http://www.scopus.com/inward/record.url?scp=85116561714&partnerID=8YFLogxK

U2 - 10.1016/j.media.2021.102255

DO - 10.1016/j.media.2021.102255

M3 - Article

SN - 1361-8415

VL - 74

JO - Medical Image Analysis

JF - Medical Image Analysis

M1 - 102255

ER -

dStripe: slice artefact correction in diffusion MRI via constrained neural network

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this