Abstract
High-order correlation has recently been proposed to model brain functional connectivity network (FCN) for identifying neurological disorders, such as mild cognitive impairment (MCI) and autism spectrum disorder (ASD). In practice, the high-order FCN (HoFCN) can be derived from multiple low-order FCNs that are estimated separately in a series of sliding windows, and thus it in fact provides a way of integrating dynamic information encoded in a sequence of low-order FCNs. However, the estimation of low-order FCN may be unreliable due to the fact that the use of limited volumes/samples in a sliding window can significantly reduce the statistical power, which in turn affects the reliability of the resulted HoFCN. To address this issue, we propose to enhance HoFCN based on a regularized learning framework. More specifically, we first calculate an initial HoFCN using a recently developed method based on maximum likelihood estimation. Then, we learn an optimal neighborhood network of the initially estimated HoFCN with sparsity and modularity priors as regularizers. Finally, based on the improved HoFCNs, we conduct experiments to identify MCI and ASD patients from their corresponding normal controls. Experimental results show that the proposed methods outperform the baseline methods, and the improved HoFCNs with modularity prior consistently achieve the best performance.
Highlights
Resting state functional magnetic resonance imaging, which treats blood oxygen level dependent (BOLD) signals as indirect measures of neural activities, has been widely used in the fields of medicine and neuroscience (Liu et al, 2008; van den Heuvel and Hulshoff Pol, 2010; Liu F. et al, 2013)
We first evaluate the proposed method by identifying subjects with mild cognitive impairment (MCI) from normal controls (NCs) based on ADNI dataset, and conduct an autism spectrum disorder (ASD) identification task based on ABIDE database for further illustrating the generalization of the proposed method
For the three high-order FCN (HoFCN) methods, we report the best result based on different sizes of sliding windows (N = 50, s = 1 for HoFCNMLE; N = 70, s = 2 for S-HoFCN; and N = 70, s = 6 for M-HoFCN)
Summary
Resting state functional magnetic resonance imaging (rs-fMRI), which treats blood oxygen level dependent (BOLD) signals as indirect measures of neural activities, has been widely used in the fields of medicine and neuroscience (Liu et al, 2008; van den Heuvel and Hulshoff Pol, 2010; Liu F. et al, 2013). Many studies adopted a regularizer in the model for more reliable partial correlation estimation (Friedman et al, 2008; Huang et al, 2009; Varoquaux et al, 2010). L1-norm regularizer is commonly used for encoding sparsity prior of FCN (Lee et al, 2011), and trace norm regularizer is used for low-rank prior (Liu G. et al, 2013; Qiao et al, 2016). Most of the correlation-based FCN models can be formulated by a matrix-regularized learning framework, where different data fitting terms and regularized terms are combined for estimating FCNs. Please see Table 1 in section Related Methods for more details
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
