Discriminative analysis of resting-state functional connectivity patterns of schizophrenia using low dimensional embedding of fMRI

Shen, Hui; Wang, Lubin; Liu, Yadong; Hu, Dewen

doi:10.1016/j.neuroimage.2009.11.011

Cited by 336 publications

(299 citation statements)

References 40 publications

Supporting

Mentioning

287

Contrasting

Unclassified

Order By: Relevance

“…Indeed, our classification of patients with child-onset schizophrenia achieved a sensitivity of 90% and specificity of 74%. This finding supports the notion that analysis based on network measures and data mining methods may present a possible strategy for automatic diagnostics for neurological disorders Previous studies on restingstate fMRI achieved similar levels of specificity and accuracy, not only for schizophrenia in adults (Tang et al, 2012;Venkataraman et al, 2012;Shen et al, 2010), but also for other neurological disorders (Welsh et al, 2013;Zeng et al, 2013;Tang et al, 2013).…”

Section: Discussionsupporting

confidence: 83%

“…In adult schizophrenic patients previous studies already illustrated the usefulness of non-invasive diagnosis based on the analysis of restingstate fMRI data. Such analysis of brain network properties achieved values for correct classification of up to 94% with 75% accuracy (Tang et al, 2012;Venkataraman et al, 2012;Shen et al, 2010). However, similar analysis of fMRI data from patients with childonset schizophrenia is currently lacking.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Structure and dynamics of functional networks in child-onset schizophrenia

Arruda

Costa

Schubert³

et al. 2014

Clinical Neurophysiology

View full text Add to dashboard Cite

Section: Discussionsupporting

confidence: 83%

Section: Introductionmentioning

confidence: 99%

Structure and dynamics of functional networks in child-onset schizophrenia

Arruda

Costa

Schubert³

et al. 2014

Clinical Neurophysiology

View full text Add to dashboard Cite

“…In most studies, however, FCGs are treated as vectors in a high-dimensional space (e.g. Shen et al, 2010;Pollolini et al, 2010;Richiardi et al, 2011), an approach that disregards the inherent tabular representation of FCGs and their nature as secondorder tensors. To overcome this limitation, we treat FCGs as tensors and resort to tensor subspace analysis (TSA) for appropriate feature extraction (He and Cai, 2005).…”

Section: Classification Of Fcg Patternsmentioning

confidence: 99%

Altered cross-frequency coupling in resting-state MEG after mild traumatic brain injury

Antonakakis

Dimitriadis

Zervakis

et al. 2016

International Journal of Psychophysiology

122

View full text Add to dashboard Cite

Cross-frequency coupling (CFC) is thought to represent a basic mechanism of functional integration of neural networks across distant brain regions. In this study, we analyzed CFC profiles from resting state Magnetoencephalographic (MEG) recordings obtained from 30 mild traumatic brain injury (mTBI) patients and 50 controls. We used mutual information (MI) to quantify the phase-to-amplitude coupling (PAC) of activity among the recording sensors in six nonoverlapping frequency bands. After forming the CFC-based functional connectivity graphs, we employed a tensor representation and tensor subspace analysis to identify the optimal set of features for subject classification as mTBI or control. Our results showed that controls formed a dense network of stronger local and global connections indicating higher functional integration compared to mTBI patients.Furthermore, mTBI patients could be separated from controls with more than 90% classification accuracy. These findings indicate that analysis of brain networks computed from resting-state MEG with PAC and tensorial representation of connectivity profiles may provide a valuable biomarker for the diagnosis of mTBI.

show abstract

“…Different types of properties, such as local spontaneous activity (ReHo), local network (DMN and/or its anti-correlated network), and whole brain network, derived from SLFF have been taken as features to discriminate patients from normal controls (Table 4). In general, both the sensitivity and specificity of these studies has been above 80% (Greicius et al 2004;Song et al 2006;Wang et al 2006a;Calhoun et al 2008a;Shi et al 2007;Shen et al 2010;Zhou et al 2010), suggesting that the activity patterns of SLFF have the potential to become brain imaging biomarkers to improve the sensitivity and specificity of the current clinical diagnosis of neuropsychiatric disorders. And compared to task-related fMRI, the SLFF within the resting-state network may be more effective at identifying functional pathology associated with AD risk (Fleisher et al 2009).…”

Section: Pilot Studies Of Slff As a Brain Imaging Biomarkermentioning

confidence: 99%

Spontaneous brain activity observed with functional magnetic resonance imaging as a potential biomarker in neuropsychiatric disorders

et al. 2010

View full text Add to dashboard Cite

As functional magnetic resonance imaging (fMRI) studies have yielded increasing amounts of information about the brain's spontaneous activity, they have revealed fMRI's potential to locate changes in brain hemodynamics that are associated with neuropsychiatric disorders. In this paper, we review studies that support the notion that changes in brain spontaneous activity observed by fMRI can be used as potential biomarkers for diagnosis and treatment evaluation in neuropsychiatric disorders. We first review the methods used to study spontaneous activity from the perspectives of (1) the properties of local spontaneous activity, (2) the spatial pattern of spontaneous activity, and (3) the topological properties of brain networks. We also summarize the major findings associated with major neuropsychiatric disorders obtained using these methods. Then we review the pilot studies that have used spontaneous activity to discriminate patients from normal controls. Finally, we discuss current challenges and potential research directions to further elucidate the clinical use of spontaneous brain activity in neuropsychiatric disorders.

show abstract

Discriminative analysis of resting-state functional connectivity patterns of schizophrenia using low dimensional embedding of fMRI

Cited by 336 publications

References 40 publications

Structure and dynamics of functional networks in child-onset schizophrenia

Structure and dynamics of functional networks in child-onset schizophrenia

Altered cross-frequency coupling in resting-state MEG after mild traumatic brain injury

Spontaneous brain activity observed with functional magnetic resonance imaging as a potential biomarker in neuropsychiatric disorders

Contact Info

Product

Resources

About