Frequency specific co-activation pattern analysis via sparse nonnegative tensor decomposition

Guoqiang Hu; Deqing Wang; Siwen Luo; Yuxing Hao; Lisa D Nickerson; Fengyu Cong

doi:10.1016/j.jneumeth.2021.109299

Frequency specific co-activation pattern analysis via sparse nonnegative tensor decomposition

J Neurosci Methods. 2021 Oct 1:362:109299. doi: 10.1016/j.jneumeth.2021.109299. Epub 2021 Jul 31.

Authors

Guoqiang Hu¹, Deqing Wang¹, Siwen Luo², Yuxing Hao¹, Lisa D Nickerson³, Fengyu Cong⁴

Affiliations

¹ School of Biomedical Engineering, Faculty of Electronic Information and Electrical Engineering, Dalian University of Technology, Dalian, China.
² Affiliated Zhongshan Hospital of Dalian University, Dalian, China.
³ Brain Imaging Center, Mclean Hospital, Belmont, MA, USA; Department of Psychiatry, Harvard Medical School, Boston, MA, USA.
⁴ School of Biomedical Engineering, Faculty of Electronic Information and Electrical Engineering, Dalian University of Technology, Dalian, China; School of Artificial Intelligence, Faculty of Electronic Information and Electrical Engineering, Dalian University of Technology, Dalian, China; Key Laboratory of Integrated Circuit and Biomedical Electronic System, Liaoning Province. Dalian University of Technology, Dalian, China; Faculty of Information Technology, University of Jyvaskyla, Jyvaskyla, Finland.

PMID: 34339754
DOI: 10.1016/j.jneumeth.2021.109299

Abstract

Background: Traditionally, the diagnosis of Parkinson's disease (PD) has been made based on symptoms. Extensive studies have demonstrated that PD may lead to variation of brain activity in different frequency bands. However, frequency specific dynamic alterations of PD have not yet been explored.

New method: In order to address this gap, a novel sparse nonnegative tensor decomposition (SNTD) method was used to estimate frequency specific co-activation patterns (CAP). The difference between PD and healthy controls (HC) are investigated with the proposed framework.

Result: The difference between PD and HC mainly exists at frequency band 0.04-0.1 Hz in basal ganglia. We also found that the average intensity of PD in this frequency band is significantly correlated with the Hoehn and Yahr scale.

Comparison with existing methods: Compared with conventional CAP approach, SNTD estimates frequency specific CAPs that show alterations in PD patients.

Conclusion: SNTD provides an alternative to K-means clustering used in conventional CAP analysis. With the proposed framework, frequency specific CAPs are extracted, and alterations in PD patients are also successfully discovered.

Keywords: Co-activation pattern; FMRI; Sparse constrained nonnegative tensor decomposition.

Publication types

Research Support, Non-U.S. Gov't

MeSH terms

Basal Ganglia
Brain*
Cluster Analysis
Humans
Parkinson Disease*