Learning Neural Representations of Human Cognition across Many fMRI Studies
This work addresses the problem of unifying cognitive neuroscience data for researchers, offering a scalable solution to analyze brain function across diverse studies, though it is incremental in applying existing machine-learning techniques to this domain.
The paper tackled the challenge of aggregating heterogeneous fMRI data across studies to relate cognitive processes to brain networks, achieving the best prediction performance on several large reference datasets and providing a substantial performance boost for small datasets.
Cognitive neuroscience is enjoying rapid increase in extensive public brain-imaging datasets. It opens the door to large-scale statistical models. Finding a unified perspective for all available data calls for scalable and automated solutions to an old challenge: how to aggregate heterogeneous information on brain function into a universal cognitive system that relates mental operations/cognitive processes/psychological tasks to brain networks? We cast this challenge in a machine-learning approach to predict conditions from statistical brain maps across different studies. For this, we leverage multi-task learning and multi-scale dimension reduction to learn low-dimensional representations of brain images that carry cognitive information and can be robustly associated with psychological stimuli. Our multi-dataset classification model achieves the best prediction performance on several large reference datasets, compared to models without cognitive-aware low-dimension representations, it brings a substantial performance boost to the analysis of small datasets, and can be introspected to identify universal template cognitive concepts.