Decoding semantics from intermodulation responses in frequency-tagged stereotactic EEG.

ABSTRACT

BACKGROUND: Humans perform object recognition using holistic processing, which is different from computers. Intermodulation responses in the steady-state visual evoked potential (SSVEP) of scalp electroencephalography (EEG) have recently been used as an objective label for holistic processing. NEW METHOD: Using stereotactic EEG (sEEG) to record SSVEP directly from inside of the brain, we aimed to decode Chinese characters from non-characters with activation from multiple brain areas including occipital, parietal, temporal, and frontal cortices. RESULTS: Semantic categories could be decoded from responses at the intermodulation frequency with high accuracy (80%-90%), but not the base frequency. Moreover, semantic categories could be decoded with activation from multiple areas including temporal, parietal, and frontal areas. COMPARISON WITH EXISTING METHOD(S) Previous studies investigated holistic processing in faces and words with frequency-tagged scalp EEGs. The current study extended the results to stereotactic EEG signals directly recorded from the brain. CONCLUSIONS: The human brain applies holistic processing in recognizing objects like Chinese characters. Our findings could be extended to an add-on feature in the existing SSVEP BCI speller.