Hybrid High-order Functional Connectivity Networks Using Resting-state Functional MRI for Mild Cognitive Impairment Diagnosis

Seong-Whan Lee,Xiaobo Chen,Dinggang Shen,Yu Zhang,Han Zhang

doi:10.1038/s41598-017-06509-0

Abstract

Conventional functional connectivity (FC), referred to as low-order FC, estimates temporal correlation of the resting-state functional magnetic resonance imaging (rs-fMRI) time series between any pair of brain regions, simply ignoring the potentially high-level relationship among these brain regions. A high-order FC based on “correlation’s correlation” has emerged as a new approach for abnormality detection of brain disease. However, separate construction of the low- and high-order FC networks overlooks information exchange between the two FC levels. Such a higher-level relationship could be more important for brain diseases study. In this paper, we propose a novel framework, namely “hybrid high-order FC networks” by exploiting the higher-level dynamic interaction among brain regions for early mild cognitive impairment (eMCI) diagnosis. For each sliding window-based rs-fMRI sub-series, we construct a whole-brain associated high-order network, by estimating the correlations between the topographical information of the high-order FC sub-network from one brain region and that of the low-order FC sub-network from another brain region. With multi-kernel learning, complementary features from multiple time-varying FC networks constructed at different levels are fused for eMCI classification. Compared with other state-of-the-art methods, the proposed framework achieves superior diagnosis accuracy, and hence could be promising for understanding pathological changes of brain connectome.

Highlights

Rs-fMRI is an in vivo brain functional imaging modality, measuring blood oxygen level-dependent (BOLD) signals[22] when subjects are in natural rest
One of our hypotheses is that, with features extracted from our newly developed associated high-order functional connectivity (FC) networks, early mild cognitive impairment (eMCI) classification could be more accurate, compared with those extracted using either the traditional low-order or high-order FC. Another hypothesis is that our computational framework of the hybrid high-order FC networks could effectively conduct multi-kernel fusion of the three types of brain dynamic networks and further boost classification performance
Consistent with our hypotheses, the main results are: 1) The high-order FC networks enhanced the classification performance and our associated high-order FC networks gained the highest one if only single type of FC network was used; 2) Integrating all the three types of networks with multi-kernel learning, eMCI classification yielded better performance compared to that using only single type of networks; and 3) The classifications based on the dynamic FC networks consistently outperformed those based on the static FC networks, indicating the necessity of integrating dynamic FC into classification

Summary

Introduction

Rs-fMRI is an in vivo brain functional imaging modality, measuring blood oxygen level-dependent (BOLD) signals[22] when subjects are in natural rest. Previous studies on rs-fMRI based AD early diagnosis often utilized calculated FC by measuring inter-regional BOLD signal temporal synchronization with Pearson’s correlation or, more generally, with sparse representation[8, 33,34,35]. This type of networks is low-order by definition because they characterize BOLD signal synchronizations and are insufficient to characterize high-level inter-regional interactions. Experimental results indicate that our method achieves superior performance than those using only the static FC or only the traditional low- and high-order FC networks

Methods

Results

Conclusion