Share Email Print

Proceedings Paper

Tensor-based vs. matrix-based rank reduction in dynamic brain connectivity
Author(s): Fatemeh Mokhtari; Rhiannon E. Mayhugh; Christina E. Hugenschmidt; W. Jack Rejeski; Paul J. Laurienti
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

The spatio-temporal information associated with dynamic connectivity from functional magnetic resonance imaging (fMRI) data can be fully represented using a multi-modal tensorial structure. Following a correlation analysis using a sliding-window, the dynamic connectivity data is represented by a 3rd-order tensor with three modes: 1-2) connectivity and 3) time. In typical dynamic connectivity analysis of fMRI data, the tensor is often flattened into matrix format resulting in mixed information embedded within the different modes. If a tensor-based data analysis is used, the information underlying the data structure is preserved rather than mixed. In this study, data dimension reduction was performed on dynamic brain networks from two fMRI datasets processed using tensor-based higher-order singular value decomposition (HOSVD) and regular matrix-based SVD. In the first dataset, brain networks were used to predict walking speed in a population of older adults enrolled in a weight loss study. For the second dataset, fMRI networks were collected from moderate-heavy alcohol consumers and classification was performed to identify networks associated with resting state vs. an emotional stress task. We hypothesized that the reduced-rank dynamic connectivity from the HOSDV would result in superior classification compared to matrix-based SVD using the same linear support vector machine with a 50 random-sampling cross-validation procedure. Results demonstrated that HOSVD (accuracy > 90% for both datasets) significantly outperformed regular SVD that failed to correctly identify the grouping status (accuracy ~ 50%).

Paper Details

Date Published: 2 March 2018
PDF: 10 pages
Proc. SPIE 10574, Medical Imaging 2018: Image Processing, 105740Z (2 March 2018); doi: 10.1117/12.2293014
Show Author Affiliations
Fatemeh Mokhtari, Wake Forest Univ. School of Medicine (United States)
Virginia Tech-Wake Forest Univ. School of Biomedical Engineering and Sciences (United States)
Rhiannon E. Mayhugh, Wake Forest Univ. School of Medicine (United States)
Christina E. Hugenschmidt, Wake Forest Univ. School of Medicine (United States)
W. Jack Rejeski, Wake Forest Univ. School of Medicine (United States)
Wake Forest Univ. (United States)
Paul J. Laurienti, Wake Forest Univ. School of Medicine (United States)
Wake Forest Univ. (United States)

Published in SPIE Proceedings Vol. 10574:
Medical Imaging 2018: Image Processing
Elsa D. Angelini; Bennett A. Landman, Editor(s)

© SPIE. Terms of Use
Back to Top