Literature DB >> 33957159

Disjoint subspaces for common and distinct component analysis: Application to the fusion of multi-task FMRI data.

M A B S Akhonda1, Ben Gabrielson2, Suchita Bhinge2, Vince D Calhoun3, Tülay Adali2.   

Abstract

BACKGROUND: Data-driven methods such as independent component analysis (ICA) makes very few assumptions on the data and the relationships of multiple datasets, and hence, are attractive for the fusion of medical imaging data. Two important extensions of ICA for multiset fusion are the joint ICA (jICA) and the multiset canonical correlation analysis and joint ICA (MCCA-jICA) techniques. Both approaches assume identical mixing matrices, emphasizing components that are common across the multiple datasets. However, in general, one would expect to have components that are both common across the datasets and distinct to each dataset. NEW
METHOD: We propose a general framework, disjoint subspace analysis using ICA (DS-ICA), which identifies and extracts not only the common but also the distinct components across multiple datasets. A key component of the method is the identification of these subspaces and their separation before subsequent analyses, which helps establish better model match and provides flexibility in algorithm and order choice. COMPARISON: We compare DS-ICA with jICA and MCCA-jICA through both simulations and application to multiset functional magnetic resonance imaging (fMRI) task data collected from healthy controls as well as patients with schizophrenia.
RESULTS: The results show DS-ICA estimates more components discriminative between healthy controls and patients than jICA and MCCA-jICA, and with higher discriminatory power showing activation differences in meaningful regions. When applied to a classification framework, components estimated by DS-ICA results in higher classification performance for different dataset combinations than the other two methods.
CONCLUSION: These results demonstrate that DS-ICA is an effective method for fusion of multiple datasets.
Copyright © 2021 Elsevier B.V. All rights reserved.

Entities:  

Keywords:  Common and distinct components; Data fusion; FMRI; ICA; IVA

Mesh:

Year:  2021        PMID: 33957159      PMCID: PMC8217295          DOI: 10.1016/j.jneumeth.2021.109214

Source DB:  PubMed          Journal:  J Neurosci Methods        ISSN: 0165-0270            Impact factor:   2.987


  35 in total

1.  JOINT AND INDIVIDUAL VARIATION EXPLAINED (JIVE) FOR INTEGRATED ANALYSIS OF MULTIPLE DATA TYPES.

Authors:  Eric F Lock; Katherine A Hoadley; J S Marron; Andrew B Nobel
Journal:  Ann Appl Stat       Date:  2013-03-01       Impact factor: 2.083

Review 2.  A Review of the Functional and Anatomical Default Mode Network in Schizophrenia.

Authors:  Mao-Lin Hu; Xiao-Fen Zong; J John Mann; Jun-Jie Zheng; Yan-Hui Liao; Zong-Chang Li; Ying He; Xiao-Gang Chen; Jin-Song Tang
Journal:  Neurosci Bull       Date:  2016-12-19       Impact factor: 5.203

3.  Three-way (N-way) fusion of brain imaging data based on mCCA+jICA and its application to discriminating schizophrenia.

Authors:  Jing Sui; Hao He; Godfrey D Pearlson; Tülay Adali; Kent A Kiehl; Qingbao Yu; Vince P Clark; Eduardo Castro; Tonya White; Bryon A Mueller; Beng C Ho; Nancy C Andreasen; Vince D Calhoun
Journal:  Neuroimage       Date:  2012-10-26       Impact factor: 6.556

4.  The dynamics of contour integration: A simultaneous EEG-fMRI study.

Authors:  Bogdan Mijović; Maarten De Vos; Katrien Vanderperren; Bart Machilsen; Stefan Sunaert; Sabine Van Huffel; Johan Wagemans
Journal:  Neuroimage       Date:  2013-11-21       Impact factor: 6.556

5.  Hyperactivity and hyperconnectivity of the default network in schizophrenia and in first-degree relatives of persons with schizophrenia.

Authors:  Susan Whitfield-Gabrieli; Heidi W Thermenos; Snezana Milanovic; Ming T Tsuang; Stephen V Faraone; Robert W McCarley; Martha E Shenton; Alan I Green; Alfonso Nieto-Castanon; Peter LaViolette; Joanne Wojcik; John D E Gabrieli; Larry J Seidman
Journal:  Proc Natl Acad Sci U S A       Date:  2009-01-21       Impact factor: 11.205

6.  Feature-based fusion of medical imaging data.

Authors:  Vince D Calhoun; Tülay Adali
Journal:  IEEE Trans Inf Technol Biomed       Date:  2008-04-22

Review 7.  Multisubject independent component analysis of fMRI: a decade of intrinsic networks, default mode, and neurodiagnostic discovery.

Authors:  Vince D Calhoun; Tülay Adalı
Journal:  IEEE Rev Biomed Eng       Date:  2012

8.  High classification accuracy for schizophrenia with rest and task FMRI data.

Authors:  Wei Du; Vince D Calhoun; Hualiang Li; Sai Ma; Tom Eichele; Kent A Kiehl; Godfrey D Pearlson; Tülay Adali
Journal:  Front Hum Neurosci       Date:  2012-06-04       Impact factor: 3.169

9.  Investigation of relationships between fMRI brain networks in the spectral domain using ICA and Granger causality reveals distinct differences between schizophrenia patients and healthy controls.

Authors:  Oguz Demirci; Michael C Stevens; Nancy C Andreasen; Andrew Michael; Jingyu Liu; Tonya White; Godfrey D Pearlson; Vincent P Clark; Vince D Calhoun
Journal:  Neuroimage       Date:  2009-02-23       Impact factor: 6.556

10.  Independent vector analysis for common subspace analysis: Application to multi-subject fMRI data yields meaningful subgroups of schizophrenia.

Authors:  Qunfang Long; Suchita Bhinge; Vince D Calhoun; Tülay Adali
Journal:  Neuroimage       Date:  2020-04-28       Impact factor: 6.556

View more
  1 in total

1.  Association of Neuroimaging Data with Behavioral Variables: A Class of Multivariate Methods and Their Comparison Using Multi-Task FMRI Data.

Authors:  M A B S Akhonda; Yuri Levin-Schwartz; Vince D Calhoun; Tülay Adali
Journal:  Sensors (Basel)       Date:  2022-02-05       Impact factor: 3.576

  1 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.