Independent component analysis (ICA) aiming at detecting the functional connectivity among discrete cortical brain regions, has been extensively used to explore the fMRI data. Although the independent components (IC) were with relatively high quality, the noise embedding in ICs has great impact on the true active/inactive region inference and the reproducibility, in post-processing stage, e.g., the extraction of statistical parametrical maps (SPM). In this paper, a novel brain networks enhancement model (BNEM) is proposed, which mainly consists of two key techniques: (i) 3D wavelet noise filter (3DWNF) for the meaningful ICs, which greatly suppresses noise and enforces the real activation inference of SPMs; (ii) a spatial reproducibility enhancement algorithm (SREA), aiming to improve the reproducibility of SPMs.
The simulated experiment demonstrated that the post-filtering signals by 3DWNF were with higher correlation and less normalized mean square error to the ground truths than the pre-filtering ones; SREA could further enhance the quality of most post-filtering ones, preserving the consistency with 3DWNF. The real data experiments also revealed that (i) 3DWNF could lead to more accurate preservation of the true positive voxels by correctly identifying the high proportionally misclassified voxels of the non-enhanced SPMs; (ii) SREA could further improve the classification accuracy of the active/inactive voxels of SPMs corresponding to the 3DWNF de-noised ICs; (iii) both 3DWNF and SREA contribute to the reproducibility enhancement of the reproduced SPMs by BNEM. Thus, BNEM is expected to have wide applicability in the neuroscience and clinical domain.