An empirical evaluation of functional alignment using inter-subject decoding

• Published in: bioRxiv
• Main Authors: Bazeille, Thomas, Dupre, Elizabeth, Hugo, Richard, Jean-Baptiste Poline, Thirion, Bertrand
• Format: Paper
• Language: English
• Published: Cold Spring Harbor Cold Spring Harbor Laboratory Press 02.07.2021; Cold Spring Harbor Laboratory
• Edition: 1.2
• Subjects: Brain architecture; Computational neuroscience; Functional morphology; Neural coding; Neuroscience; Structure-function relationships; fMRI; inter-subject variability; predictive modeling; functional alignment
• ISSN: 2692-8205; 2692-8205
• DOI: 10.1101/2020.12.07.415000

Inter-individual variability in the functional organization of the brain presents a major obstacle to identifying generalizable neural coding principles. Functional alignment---a class of methods that matches subjects' neural signals based on their functional similarity---is a promising strategy for addressing this variability. To date, however, a range of functional alignment methods have been proposed and their relative performance is still unclear. In this work, we benchmark five functional alignment methods for inter-subject decoding on four publicly available datasets. Specifically, we consider three existing methods: piecewise Procrustes, searchlight Procrustes, and piecewise Optimal Transport. We also introduce and benchmark two new extensions of functional alignment methods: piecewise Shared Response Modelling (SRM), and intra-subject alignment. We find that functional alignment generally improves inter-subject decoding accuracy though the best performing method depends on the research context. Specifically, SRM and Optimal Transport perform well at both the region-of-interest level of analysis as well as at the whole-brain scale when aggregated through a piecewise scheme. We also benchmark the computational efficiency of each of the surveyed methods, providing insight into their usability and scalability. Taking inter-subject decoding accuracy as a quantification of inter-subject similarity, our results support the use of functional alignment to improve inter-subject comparisons in the face of variable structure-function organization. We provide open implementations of all methods used. Competing Interest Statement The authors have declared no competing interest. Footnotes * As suggested by reviewer comments, we have (1) introduced a new piecewise Shared Response Model, (2) changed our region-of-interest experiments to learn unaggregated alignment transformations, (3) clarified the relationship between our included Procrustes methods and the commonly-used hyperalignment method, (4) re-generated derivatives for three of our four decoding data sets and updated the decoding task for Courtois-Neuromod to better reflect the range of cognitive tasks considered in the field. We have added Mr Hugo Richard as a co-author for his significant help in implementing these changes. Finally, we have re-generated all included figures and reviewed the text to correct grammatical errors and generally improve readability.