Denoise Functional Magnetic Resonance Imaging With Random Matrix Theory Based Principal Component Analysis.
Wei ZhuXiaodong MaXiao-Hong ZhuKâmil UgurbilWei ChenXiaoping WuPublished in: IEEE Trans. Biomed. Eng. (2022)
Keyphrases
- functional magnetic resonance imaging
- random matrix theory
- principal component analysis
- covariance matrix
- correlation matrix
- human brain
- brain activity
- principal components
- brain imaging
- data analysis
- correlation analysis
- denoising
- pattern classification
- clinical diagnosis
- dimensionality reduction
- singular value decomposition
- human subjects
- activation patterns
- independent component analysis
- high dimensional
- face recognition
- brain images
- functional connectivity
- brain activation
- spatial correlation
- discriminant analysis
- brain regions
- linear discriminant analysis
- cerebral blood flow
- statistical parametric mapping
- feature extraction
- activation detection
- general linear model
- least squares
- feature space
- computer vision