Abstract
The inability to individuate finger movements is a common impairment following stroke. Conventional physical therapy ignores underlying neural changes with recovery, leaving it unclear why sensorimotor function often remains impaired. Functional MRI neurofeedback can monitor neural activity and reinforce it towards a healthy template to restore function. However, identifying an individualized training template may not be possible depending on the severity of impairment. In this study, we investigated the use of functional alignment of brain data across healthy participants to create an idealized neural template to be used as a training target for new participants. We employed multi-voxel pattern analyses to assess the prediction accuracy and robustness to missing data of pre-trained functional templates corresponding to individual finger presses. We found a significant improvement in classification accuracy (p < 0.001) of individual finger presses when group data was aligned based on function (88%) rather than anatomy (46%). Importantly, we found no significant drop in performance when aligning a new participant to a pre-established template as compared to including this new participant in the creation of a new template. These results indicate that functionally aligned templates could provide an effective surrogate training target for patients following neurological injury.
Highlights
One other advantage of hyperalignment is its ability to generalize to new data[48]
The fMRI data was used to train three separate pattern classifiers to discriminate between the four fingers: a within-subject classifier trained in a participant’s native space, a between-subject classifier trained on anatomically aligned data in MNI152 (Montreal Neurological Institute) standard-space, and a between-subject classifier trained on hyperaligned data from other participants
To further validate the effectiveness of a surrogate training target, we evaluated the classification accuracy when a new individual was brought into alignment with a pre-established common model space
Summary
One other advantage of hyperalignment is its ability to generalize to new data[48]. Recently, TaschereauDumouchel et al.[43] used hyperalignment to infer the neural representation for feared animals (e.g., a snake) in a given participant with a snake phobia based only on data from other participants. We sought to investigate the use of hyperalignment to create a neural template of individual finger presses from healthy individuals Such a template could be used in an fMRI neurofeedback intervention for patients with fine motor deficiencies and who are unable to provide a personalized training target. We addressed several important methodological questions about the implementation of hyperalignment: the effect of subject order on hyperalignment, the effect of aligning a new individual to a pre-established common model (compared to creating a new common model informed by all participants), and how much data is required to accurately align a new participant to a common model space
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
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 callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
