Applying independent component analysis to detect silent speech in magnetic resonance imaging signals

Authors

  • Kazuhiro Abe,

    1. Department of Neurophysiology, Juntendo University School of Medicine, Tokyo, Japan
    2. Department of Neurosurgery, Juntendo University School of Medicine, Tokyo, Japan
    Search for more papers by this author
    • K.A. and T.T. contributed equally to this work.

  • Toshimitsu Takahashi,

    1. Department of Neurophysiology, Juntendo University School of Medicine, Tokyo, Japan
    2. Dynamic Brain Network Laboratory, Graduate School of Frontier Biosciences, Osaka University, Osaka, Japan
    3. Department of Brain Physiology, Graduate School of Medicine, Osaka University, Osaka, Japan
    4. CREST, Japan Science and Technology Agency, Saitama, Japan
    Search for more papers by this author
    • K.A. and T.T. contributed equally to this work.

  • Yoriko Takikawa,

    1. Department of Neurophysiology, Juntendo University School of Medicine, Tokyo, Japan
    2. CREST, Japan Science and Technology Agency, Saitama, Japan
    Search for more papers by this author
  • Hajime Arai,

    1. Department of Neurosurgery, Juntendo University School of Medicine, Tokyo, Japan
    Search for more papers by this author
  • Shigeru Kitazawa

    1. Department of Neurophysiology, Juntendo University School of Medicine, Tokyo, Japan
    2. Dynamic Brain Network Laboratory, Graduate School of Frontier Biosciences, Osaka University, Osaka, Japan
    3. Department of Brain Physiology, Graduate School of Medicine, Osaka University, Osaka, Japan
    4. CREST, Japan Science and Technology Agency, Saitama, Japan
    Search for more papers by this author

Shigeru Kitazawa, 3Dynamic Brain Network Laboratory, as above.
E-mail: kitazawa@fbs.osaka-u.ac.jp

Abstract

Independent component analysis (ICA) can be usefully applied to functional imaging studies to evaluate the spatial extent and temporal profile of task-related brain activity. It requires no a priori assumptions about the anatomical areas that are activated or the temporal profile of the activity. We applied spatial ICA to detect a voluntary but hidden response of silent speech. To validate the method against a standard model-based approach, we used the silent speech of a tongue twister as a ‘Yes’ response to single questions that were delivered at given times. In the first task, we attempted to estimate one number that was chosen by a participant from 10 possibilities. In the second task, we increased the possibilities to 1000. In both tasks, spatial ICA was as effective as the model-based method for determining the number in the subject’s mind (80–90% correct per digit), but spatial ICA outperformed the model-based method in terms of time, especially in the 1000-possibility task. In the model-based method, calculation time increased by 30-fold, to 15 h, because of the necessity of testing 1000 possibilities. In contrast, the calculation time for spatial ICA remained as short as 30 min. In addition, spatial ICA detected an unexpected response that occurred by mistake. This advantage was validated in a third task, with 13 500 possibilities, in which participants had the freedom to choose when to make one of four responses. We conclude that spatial ICA is effective for detecting the onset of silent speech, especially when it occurs unexpectedly.

Ancillary