TY - GEN
T1 - Classification for Alzheimer's disease from structural MRI by general n-dimensional principal component analysis
AU - Tang, Song Yuan
PY - 2013
Y1 - 2013
N2 - In this paper, we propose a classification method for Alzheimer's disease from structural MRI. In the method, a specific template is firstly constructed. Then all data are registered to the template and the corresponding Jacobians are calculated. And then, a general n-dimensional principal component analysis (GND-PCA) based method is adopted to extract features from the Jacobians and the features are enhanced by the linear discriminant analysis (LDA). Finally, the enhanced features are used for the support vector machines (SVMs) classifiers. The proposed method classifies AD and normal controls (NC) well.
AB - In this paper, we propose a classification method for Alzheimer's disease from structural MRI. In the method, a specific template is firstly constructed. Then all data are registered to the template and the corresponding Jacobians are calculated. And then, a general n-dimensional principal component analysis (GND-PCA) based method is adopted to extract features from the Jacobians and the features are enhanced by the linear discriminant analysis (LDA). Finally, the enhanced features are used for the support vector machines (SVMs) classifiers. The proposed method classifies AD and normal controls (NC) well.
KW - Alzheimer's disease
KW - Generalized N-dimensional principal component analysis (GND-PCA)
KW - Magnetic resonance imaging (MRI)
KW - Support vector machines (SVMs)
UR - http://www.scopus.com/inward/record.url?scp=84883038629&partnerID=8YFLogxK
U2 - 10.4028/www.scientific.net/AMM.336-338.2316
DO - 10.4028/www.scientific.net/AMM.336-338.2316
M3 - Conference contribution
AN - SCOPUS:84883038629
SN - 9783037857519
T3 - Applied Mechanics and Materials
SP - 2316
EP - 2319
BT - Industrial Instrumentation and Control Systems II
T2 - 2013 2nd International Conference on Measurement, Instrumentation and Automation, ICMIA 2013
Y2 - 23 April 2013 through 24 April 2013
ER -