Remodeling Pearson's Correlation for Functional Brain Network Estimation and Autism Spectrum Disorder Identification

Public Deposited
Analytics

Downloadable Content

Download PDF
Request Version for Screen Reader
Creator
  • Li, Weikai
    • Other Affiliation: College of Information Science and Engineering; Chongqing Jiaotong University
  • Wang, Zhengxia
    • Other Affiliation: College of Information Science and Engineering; Chongqing Jiaotong University
  • Zhang, Limei
    • Other Affiliation: School of Mathematics; Liaocheng University
  • Qiao, Lishan
    • Other Affiliation: School of Mathematics; Liaocheng University
  • Shen, Dinggang
    • Affiliation: School of Medicine, Department of Radiology
    • Other Affiliation: Department of Brain and Cognitive Engineering; Korea University
Abstract
  • Functional brain network (FBN) has been becoming an increasingly important way to model the statistical dependence among neural time courses of brain, and provides effective imaging biomarkers for diagnosis of some neurological or psychological disorders. Currently, Pearson's Correlation (PC) is the simplest and most widely-used method in constructing FBNs. Despite its advantages in statistical meaning and calculated performance, the PC tends to result in a FBN with dense connections. Therefore, in practice, the PC-based FBN needs to be sparsified by removing weak (potential noisy) connections. However, such a scheme depends on a hard-threshold without enough flexibility. Different from this traditional strategy, in this paper, we propose a new approach for estimating FBNs by remodeling PC as an optimization problem, which provides a way to incorporate biological/physical priors into the FBNs. In particular, we introduce an L1-norm regularizer into the optimization model for obtaining a sparse solution. Compared with the hard-threshold scheme, the proposed framework gives an elegant mathematical formulation for sparsifying PC-based networks. More importantly, it provides a platform to encode other biological/physical priors into the PC-based FBNs. To further illustrate the flexibility of the proposed method, we extend the model to a weighted counterpart for learning both sparse and scale-free networks, and then conduct experiments to identify autism spectrum disorders (ASD) from normal controls (NC) based on the constructed FBNs. Consequently, we achieved an 81.52% classification accuracy which outperforms the baseline and state-of-the-art methods.
Date of publication
Keyword
DOI
Identifier
Resource type
  • Article
Rights statement
  • In Copyright
Journal title
  • Frontiers in Neuroinformatics
Journal volume
  • 11
Language
  • English
ISSN
  • 1662-5196

Relations

Parents:

This work has no parents.

In Collection:

Items

Thumbnail Title Date Uploaded Visibility Actions
file details PubMedCentral-PMC5583214.pdf 2017 Public Download