Classification on ADHD with Deep Learning

Effective discrimination of attention deficit hyperactivity disorder (ADHD) using imaging and functional biomarkers would have fundamental influence on public health. In usual, the discrimination is based on the standards of American Psychiatric Association. In this paper, we modified one of the deep learning method on structure and parameters according to the properties of ADHD data, to discriminate ADHD on the unique public dataset of ADHD-200. We predicted the subjects as control, combined, inattentive or hyperactive through their frequency features. The results achieved improvement greatly compared to the performance released by the competition. Besides, the imbalance in datasets of deep learning model influenced the results of classification. As far as we know, it is the first time that the deep learning method has been used for the discrimination of ADHD with fMRI data.