Locally Linear Embedding and fMRI Feature Selection in Psychiatric Classification

  title={Locally Linear Embedding and fMRI Feature Selection in Psychiatric Classification},
  author={G. Sidhu},
  journal={IEEE Journal of Translational Engineering in Health and Medicine},
  • G. Sidhu
  • Published 2019
  • Computer Science, Medicine
  • IEEE Journal of Translational Engineering in Health and Medicine
Background: Functional magnetic resonance imaging (fMRI) provides non-invasive measures of neuronal activity using an endogenous Blood Oxygenation-Level Dependent (BOLD) contrast. This article introduces a nonlinear dimensionality reduction (Locally Linear Embedding) to extract informative measures of the underlying neuronal activity from BOLD time-series. The method is validated using the Leave-One-Out-Cross-Validation (LOOCV) accuracy of classifying psychiatric diagnoses using resting-state… Expand
3 Citations
The Laplacian eigenmaps dimensionality reduction of fMRI data for discovering stimulus-induced changes in the resting-state brain activity
This study used functional magnetic resonance imaging of RS brain activity before and after the acquisition and extinction of experimental conditioned fear to develop an unbiased method to detect changes in the RS activity after exposure to emotionally meaningful stimuli. Expand
Applicable features of electroencephalogram for ADHD diagnosis
Purpose Attention-deficit/hyperactivity disorder (ADHD) is a neuro-developmental and psychiatric disorder, which affects 11% of children around the world. Several linear and nonlinear biomarkers fromExpand
Neuroimaging-Based Deep Learning in Autism Spectrum Disorder and Attention-Deficit/Hyperactivity Disorder
Here, a review of studies that combine neurodevelopmental disorder neuroimaging and DL techniques to explore the strengths, limitations, and future directions of this research area. Expand


Dimensionality reduction of fMRI time series data using locally linear embedding
The non-linear locally linear embedding (LLE) algorithm is introduced for dimensionality reduction of fMRI time series data and consistently found task-related components as well as known resting-state networks and the algorithm compared well to PCA. Expand
A Review of Challenges in the Use of fMRI for Disease Classification / Characterization and A Projection Pursuit Application from A Multi-site fMRI Schizophrenia Study
Functional magnetic resonance imaging (fMRI) is a fairly new technique that has the potential to characterize and classify brain disorders such as schizophrenia. It has the possibility of playing aExpand
Principal component analysis of the dynamic response measured by fMRI: a generalized linear systems framework.
A generalized linear systems framework for PCA based on the singular value decomposition (SVD) model for representation of spatio-temporal fMRI data sets is presented and illustrated in the setting of dynamic time-series response data from fMRI experiments involving pharmacological stimulation of the dopaminergic nigro-striatal system in primates. Expand
Neurophysiological investigation of the basis of the fMRI signal
These findings suggest that the BOLD contrast mechanism reflects the input and intracortical processing of a given area rather than its spiking output, and that LFPs yield a better estimate of BOLD responses than the multi-unit responses. Expand
The history, developments and current status of FSL are written about, and some descriptions of parts of F SL that are not well covered in the existing literature are included. Expand
What we can do and what we cannot do with fMRI
An overview of the current state of fMRI is given, and the current understanding of the haemodynamic signals and the constraints they impose on neuroimaging data interpretation are presented. Expand
Patterns of cerebral blood flow in schizophrenia.
Analysis of correlations between syndrome scores and rCBF revealed that each syndrome was associated with a specific pattern of perfusion in paralimbic and association cortex, and in related subcortical nuclei, suggesting that the abnormalities of brain function underlying each of the three syndromes are not confined to single loci, but involve distributed neuronal networks. Expand
Temporal lobe dysfunction in childhood autism: a PET study. Positron emission tomography.
PET and voxel-based image analysis revealed a localized dysfunction of the temporal lobes in school-aged children with idiopathic autism and the relationships between these temporal abnormalities and the perceptive, cognitive, and emotional developmental abnormalities characteristic of this disorder are clarified. Expand
Brain magnetic resonance imaging with contrast dependent on blood oxygenation.
It is demonstrated that in vivo images of brain microvasculature with image contrast reflecting the blood oxygen level can be used to provide in vivo real-time maps of blood oxygenation in the brain under normal physiological conditions. Expand
Distribution of cerebral activity in chronic schizophrenia.
Abstract Measurements of regional cerebral blood-flow (R.C.B.F.) show that patients with schizophrenia have normal mean hemisphere flows, but that there is a shift in R.C.B.F. distribution so thatExpand