The objective of this paper is to further validate theoretically and empirically a nonlinear independent component analysis (ICA) algorithm implemented with a deep learning architecture. We first revisited its formulation to verify its consistency with the criterion of minimization of mutual information. Then, we applied the nonlinear independent component estimation algorithm (NICE) to synthetic 2D images that resemble structural magnetic resonance imaging (sMRI) data. This data was generated by mixing spatial components that represent axial slices of sMRI tissue concentration images. Next, we generated the images under linear and mildly nonlinear mixtures, being able to show that NICE matches ICA when the data is generated by using the conventional linear mixture and outperforms ICA for the nonlinear mixture of components. The obtained results are promising and suggest that NICE has potential to find richer brain networks if applied to real sMRI data, provided that small conditioning adjustments are performed along with this approach.