Nonlinear dimensionality reduction of CT histogram based feature space for predicting recurrence-free survival in non-small-cell lung cancer.
Yoshiki KawataNoboru NikiHironobu OhmatsuKeiju AokageMasahiko KusumotoTakaaki TsuchidaKenji EguchiM. KanekoPublished in: Medical Imaging: Computer-Aided Diagnosis (2015)
Keyphrases
- lung cancer
- nonlinear dimensionality reduction
- survival prediction
- feature space
- diagnosis of lung cancer
- low dimensional
- dimensionality reduction
- cancer cells
- manifold learning
- mean shift
- pulmonary nodules
- riemannian manifolds
- lymph nodes
- lung cancer patients
- pet ct
- high dimensional data
- high dimensional
- dimension reduction
- ct images
- locally linear embedding
- ground glass opacity
- high dimensionality
- data points
- computed tomography
- x ray
- gene selection
- feature vectors
- gene expression
- dimensionality reduction methods
- semi supervised
- medical images
- three dimensional
- shape analysis
- pattern recognition
- input image
- principal component analysis
- graph cuts
- kernel pca
- linear discriminant analysis
- ct scans
- feature selection