Supervised Hyperalignment for multi-subject fMRI data alignment
This work addresses the need for improved alignment in fMRI-based cognitive state analysis, offering a domain-specific incremental advance over unsupervised methods.
The paper tackles the problem of suboptimal functional alignment in multi-subject fMRI data for supervised multivariate pattern analysis by proposing a Supervised Hyperalignment method, which achieves up to 19% better performance in multi-class problems compared to state-of-the-art hyperalignment algorithms.
Hyperalignment has been widely employed in Multivariate Pattern (MVP) analysis to discover the cognitive states in the human brains based on multi-subject functional Magnetic Resonance Imaging (fMRI) datasets. Most of the existing HA methods utilized unsupervised approaches, where they only maximized the correlation between the voxels with the same position in the time series. However, these unsupervised solutions may not be optimum for handling the functional alignment in the supervised MVP problems. This paper proposes a Supervised Hyperalignment (SHA) method to ensure better functional alignment for MVP analysis, where the proposed method provides a supervised shared space that can maximize the correlation among the stimuli belonging to the same category and minimize the correlation between distinct categories of stimuli. Further, SHA employs a generalized optimization solution, which generates the shared space and calculates the mapped features in a single iteration, hence with optimum time and space complexities for large datasets. Experiments on multi-subject datasets demonstrate that SHA method achieves up to 19% better performance for multi-class problems over the state-of-the-art HA algorithms.