Understanding of the human brain architecture and its neuronal functional connectivity is an important neuroscience goal, because it may help to understand how the brain processing a lot of complexity information stream. Resting state functional Magnetic Resonance Imaging (fMRI) is a popular neuroimaging tool what measures spontaneous, low frequency fluctuations in the BOLD signal (Blood Oxygenation Level Dependent) to investigate the functional architecture of the brain. During a resting state condition can reveal the co-activation of specific brain regions in distributed networks, called resting-state networks, which selected by Independent Component Analysis (ICA) of the fMRI data. Although ICA decomposition in fMRI is widely used to identify networks, is still no unique standard selection criterion to determine networks with potential functional connectivity. One of the main difficulties with component analysis is the automatic selection of the ICA features related to brain activity. In this paper, we describe an implementation of PICA-based algorithm for automatically select resting-state functional networks on Digital Lab Platform, including data processing on the Kurchatov Institute Supercomputer and Data Analysis Module, which can used to detect neural networks and reduce subjectivity in ICA component assessment. In this work were used rest-fMRI data sets, obtained on a Siemens Verio Magnetom 3T Tomograph of the Kurchatov Institute Resource Center.