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

• Published in: Medical image analysis 2021-12, Vol.74, p.102255, Article 102255
• Main Authors: Pietsch, Maximilian, Christiaens, Daan, Hajnal, Joseph V, Tournier, J-Donald
• Format: Article
• Language: English
• Subjects: Angular resolution; Artificial neural networks; Brain - diagnostic imaging; Constraints; Data acquisition; Diffusion; Diffusion Magnetic Resonance Imaging; Diffusion MRI; Embedding; Frequency dependence; Humans; Image acquisition; Image artefact removal; Image contrast; Image filters; Image Processing, Computer-Assisted; Image reconstruction; Imaging techniques; Infant, Newborn; Magnetic resonance imaging; Neonates; Neural networks; Neural Networks, Computer; Venetian blind artefact
• ISSN: 1361-8415; 1361-8423; 1361-8423
• DOI: 10.1016/j.media.2021.102255

•dStripe allows removing inter-slice intensity artefacts in the presence of motion.•It is not tied to a particular q-space sampling scheme or motion correction method.•Can be trained in the absence of ground truth data.•Uses explicit constraints that locally preserve in-plane image contrast. [Display omitted] 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.