Abstract
In Echo-Planar Imaging (EPI)-based Magnetic Resonance Imaging (MRI), inter-subject registration typically uses the subject's T1-weighted (T1w) anatomical image to learn deformations of the subject's brain onto a template. The estimated deformation fields are then applied to the subject's EPI scans (functional or diffusion-weighted images) to warp the latter to a template space. Historically, such indirect T1w-based registration was motivated by the lack of clear anatomical details in low-resolution EPI images: a direct registration of the EPI scans to template space would be futile. A central prerequisite in such indirect methods is that the anatomical (aka the T1w) image of each subject is well aligned with their EPI images via rigid coregistration. We provide experimental evidence that things have changed: nowadays, there is a decent amount of anatomical contrast in high-resolution EPI data. That notwithstanding, EPI distortions due to B0 inhomogeneities cannot be fully corrected. Residual uncorrected distortions induce non-rigid deformations between the EPI scans and the same subject's anatomical scan. In this manuscript, we contribute a computationally cheap pipeline that leverages the high spatial resolution of modern EPI scans for direct inter-subject matching. Our pipeline is direct and does not rely on the T1w scan to estimate the inter-subject deformation. Results on a large dataset show that this new pipeline outperforms the classical indirect T1w-based registration scheme, across a variety of post-registration quality-assessment metrics including: Normalized Mutual Information, relative variance (variance-to-mean ratio), and to a lesser extent, improved peaks of group-level General Linear Model (GLM) activation maps.
Highlights
Registering brain images from different subjects in a common space, is an essential step in any multi-subject analysis pipeline (Friston et al, 1995)
Echo-Planar Imaging (EPI) and T1w images are rigidly aligned in a primary step called coregistration; one applies the T1w → template transformation—estimated in a separate step—to the EPI images to warp them from subject to template space
Using a variety of different task contrasts, we show that registration with our pipeline increases the pairwise Normalized Mutual Information (NMI) of subjects, over the classical pipeline; crucially, this leads to a decrease in residual post-registration inter-subject misalignement
Summary
Registering brain images from different subjects in a common space (for example, the MNI space Collins et al, 1994; Mazziotta et al, 1995), is an essential step in any multi-subject analysis pipeline (Friston et al, 1995). The use of a standard space opens the possibility to share results in a consistent fashion, the comparison of experiments and meta-analysis (Wager et al, 2007; Gorgolewski et al, 2015) This is especially true in functional Magnetic Resonance Imaging (fMRI) studies in which the activations might span just a few voxels in diameter. One typically assumes that distortion correction is good enough so that the EPI can be realigned to the T1w image with a rigid transformation Such an indirect T1w-based method for preprocessing functional images has been prompted by the fact that learning a deformation from the subject’s T1w image to a template is easier, due to the relatively high anatomical contrast in T1w images, than learning a deformation from the subject’s EPI image to the template
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
