A clustering-based method to detect functional connectivity differences

Department of Biophysics, Medical College of Wisconsin, Milwaukee, WI 53226, USA.
NeuroImage (Impact Factor: 6.36). 03/2012; 61(1):56-61. DOI: 10.1016/j.neuroimage.2012.02.064
Source: PubMed


Recently, resting-state functional magnetic resonance imaging (R-fMRI) has emerged as a powerful tool for investigating functional brain organization changes in a variety of neurological and psychiatric disorders. However, the current techniques may need further development to better define the reference brain networks for quantifying the functional connectivity differences between normal and diseased subject groups. In this study, we introduced a new clustering-based method that can clearly define the reference clusters. By employing group difference information to guide the clustering, the voxels within the reference clusters will have homogeneous functional connectivity changes above predefined levels. This method identified functional clusters that were significantly different between the amnestic mild cognitively impaired (aMCI) and age-matched cognitively normal (CN) subjects. The results indicated that the distribution of the clusters and their functionally disconnected regions resembled the altered memory network regions previously identified in task fMRI studies. In conclusion, the new clustering method provides an advanced approach for studying functional brain organization changes associated with brain diseases.

Download full-text


Available from: Piero Antuono
  • Source

    Full-text · Article · May 2013 · Frontiers in Psychiatry
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Rapid advances in neuroimaging techniques have provided an efficient and non-invasive way for exploring the structural and functional connectivity of the human brain. Quantitative measurement of abnormality of brain connectivity in patients with neurodegenerative diseases, such as mild cognitive impairment (MCI) and Alzheimer's disease (AD), have also been widely reported, especially at a group level. Recently, machine learning techniques have been applied to the study of AD and MCI, i.e., to identify the individuals with AD/MCI from the healthy controls (HC). However, most existing methods focus on using only a single property of a connectivity network, although multiple network properties, such as local connectivity and global topological properties, can potentially be used. In this paper, by employing multi-kernel based approach, we propose a novel connectivity based framework to integrate multiple properties of connectivity network for improving the classification performance. Specifically, two different types of kernels (i.e., vector-based kernel and graph kernel) are used to quantify two different yet complementary properties of the network, i.e., local connectivity and global topological properties. Then, multi-kernel learning (MKL) technique is adopted to fuse these heterogeneous kernels for neuroimaging classification. We test the performance of our proposed method on two different data sets. First, we test it on the functional connectivity networks of 12 MCI and 25 HC subjects. The results show that our method achieves significant performance improvement over those using only one type of network property. Specifically, our method achieves a classification accuracy of 91.9%, which is 10.8% better than those by single network-property based methods. Then, we test our method for gender classification on a large set of functional connectivity networks with 133 infants scanned at birth, 1-year-old, and 2-years-old, also demonstrating very promising results.
    Full-text · Article · Oct 2013 · IEEE transactions on bio-medical engineering
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: In this study, we recorded spike trains from brain cortical neurons of several behavioral rats in vivo by using multi-electrode recordings. An NFN was constructed on each trial, obtaining a total of 150 NFNs in this study. The topological characteristics of NFNs were analyzed by using the two most important characteristics of complex networks, namely, small-world structure and community structure. We found that the small-world properties exist in different NFNs constructed in this study. Modular function Q was used to determine the existence of community structure in NFNs, through which we found that community-structure characteristics, which are related to recorded spike train data sets, are more evident in the Y-maze task than in the DM-GM task. Our results can also be used to analyze further the relationship between small-world characteristics and the cognitive behavioral responses of rats.
    Full-text · Article · Aug 2014 · Physics Letters A
Show more