Estimating Brain Functional Networks Based on Adaptively-Weighted fMRI Signals for MCI Identification

Abstract

Brain functional network (BFN) analysis is becoming a crucial way to explore the inherent organized pattern of the brain and reveal potential biomarkers for diagnosing neurological or psychological disorders. In so doing, a well-estimated BFN is of great concern. In practice, however, noises or artifacts involved in the observed data (i.e., fMRI time series in this paper) generally lead to a poor estimation of BFN, and thus a complex preprocessing pipeline is often used to improve the quality of the data prior to BFN estimation. One of the popular preprocessing steps is data-scrubbing that aims at removing “bad” volumes from the fMRI time series according to the amplitude of the head motion. Despite its helpfulness in general, this traditional scrubbing scheme cannot guarantee that the removed volumes are necessarily unhelpful, since such a step is fully independent to the subsequent BFN estimation task. Moreover, the removal of volumes would reduce the statistical power, and different numbers of volumes are generally scrubbed for different subjects, resulting in an inconsistency or bias in the estimated BFNs. To address these issues, we develop a new learning framework that conducts BFN estimation and data-scrubbing simultaneously by an alternating optimization algorithm. The newly developed algorithm adaptively weights volumes (instead of removing them directly) for the task of BFN estimation. As a result, the proposed method can not only reduce the difficulty of threshold selection involved in the traditional scrubbing scheme, but also provide a more flexible framework that scrubs the data in the subsequent FBN estimation model. Finally, we validate the proposed method by identifying subjects with mild cognitive impairment (MCI) from normal controls based on the estimated BFNs, achieving an 80.22% classification accuracy, which significantly improves the baseline methods.

Estimating Functional Brain Network with Low-Rank Structure via Matrix Factorization for MCI/ASD Identification

“…As exhibited in Table 4, the results achieved by our method are overall better than the four SOTA methods. Note that, even if the SEN and AUC respectively reported in [11] and [41] are better than our method, their performances was on account of a relatively smaller dataset compared with our study.…”

Fusing Multiview Functional Brain Networks by Joint Embedding for Brain Disease Identification

“…First , we estimate the initial FBNs for each subject using four conventional methods, i.e., PC, SR, MI, and CC. Note that many other FBN estimation methods can also be used here, such as some improved strategies that incorporate specific prior information [ 36 , 46 , 47 ]. Since this paper is focused on fusing multiview FBNs, we choose four simple and representative estimation methods.…”

“…For the PC, MI, and CC methods, their constructed FBNs are dense. Thus, we empirically select different thresholds to remove a proportion of edges in the range of [ 46 , 47 ]. For SR, the sparsity of the estimated FBN can be controlled by the values of the regularization parameter that are searched in the range of [ 47 ].…”

Multi-Scale Graph Representation Learning for Autism Identification With Functional MRI

“…Previous studies usually extract node statistics or edge weights from functional brain networks to represent each subject and mine the correlation of temporal and spatial information between brain regions. For example, Chen et al used Pearson's correlation (PC) coefficient to compute edge weights for FCNs construction (Chen et al, 2020 ). Hhimilon et al extracted both global and node-level statistics (such as local clustering coefficients) as FCN attributes (Hamilton, 2020 ).…”