In this paper a new unified data analysis pipeline for neuroimaging-based diagnostic classification problems is proposed. Different feature extraction techniques, machine learning algorithms and processing toolboxes for brain imaging are considered.

The approach is illustrated by discovering new biomarkers for diagnostics of epilepsy and depression presence in simple and complex cases based on clinical and MRI data for patients and healthy volunteers.

It is also demonstrated that the proposed pipeline in many classification tasks provides better performance than conventional one.