Predicting the imagined contents using brain activation
This work addresses the challenge of decoding cognitive states from brain imaging data, though it is incremental as it builds on known neural correlates of imagery and perception.
The researchers tackled the problem of predicting imagined content from brain activation patterns, achieving 75% accuracy in classifying whether participants imagined monetary rewards or scrambled pictures using a support vector machine trained on midbrain fMRI data.
Mental imagery refers to percept-like experiences in the absence of sensory input. Brain imaging studies suggest common, modality-specific, neural correlates imagery and perception. We associated abstract visual stimuli with either visually presented or imagined monetary rewards and scrambled pictures. Brain images for a group of 12 participants were collected using functional magnetic resonance imaging. Statistical analysis showed that human midbrain regions were activated irrespective of the monetary rewards being imagined or visually present. A support vector machine trained on the midbrain activation patterns to the visually presented rewards predicted with 75% accuracy whether the participants imagined the monetary reward or the scrambled picture during imagination trials. Training samples were drawn from visually presented trials and classification accuracy was assessed for imagination trials. These results suggest the use of machine learning technique for classification of underlying cognitive states from brain imaging data.