[4A1] [General Session] 2. Machine Learning

[4A1-05] Proposals of Real-time Neurofeedback System Using fMRI and Neuroimage Classification using 3D Convolutional Neural Networks

〇Tomofumi Nakano¹, Shohei Kato^1,2, Epifanio Bagarinao³, Akihiro Yoshida⁴, Mika Ueno⁵, Toshiharu Nakai^4,5 (1. Dept. of Computer Science and Engineering, Graduate School of Engineering, Nagoya Institute of Technology, 2. Frontier Research Institutes for Information Science, Nagoya Institute of Technology, 3. Brain and Mind Research Center, Nagoya University, 4. Department of Radiological Sciences, Nagoya University Graduate School of Medicine, 5. NeuroImaging and Informatics Group, National Center for Geriatrics and Gerontology)

Keywords:3D-CNN, motor imagery, fMRI

Motor imagery (MI), a covert cognitive process where an individual mentally simulate an action but without actually moving any body part, could provide an effective neuro-rehabilitation tool for motor function improvement or recovery.
MI can become more efficient by providing feedback to the patient indicating whether he/she employs MI correctly or not. However, in order to provide the patient with the MI-feedback, it is necessary to identify which area of the human brain is involved in the specific MI. In this study, we will apply deep learning to brain images acquired using functional MRI and attempt to solve this problem.