TY - GEN
T1 - Disease classification and prediction via semi-supervised dimensionality reduction
AU - Batmanghelich, Kayhan N.
AU - Ye, Dong H.
AU - Pohl, Kilian M.
AU - Taskar, Ben
AU - Davatzikos, Christos
PY - 2011
Y1 - 2011
N2 - We present a new semi-supervised algorithmfor dimensionality reduction which exploits information of unlabeled data in order to improve the accuracy of image-based disease classification based on medical images. We perform dimensionality reduction by adopting the formalismof constrainedmatrix decomposition of [1] to semi-supervised learning. In addition, we add a new regularization term to the objective function to better captur the affinity between labeled and unlabeled data. We apply our method to a data set consisting of medical scans of subjects classified as Normal Control (CN) and Alzheimer (AD). The unlabeled data are scans of subjects diagnosedwith Mild Cognitive Impairment (MCI), which are at high risk to develop AD in the future. We measure the accuracy of our algorithm in classifying scans as AD and NC. In addition, we use the classifier to predict which subjects with MCI will converge to AD and compare those results to the diagnosis given at later follow ups. The experiments highlight that unlabeled data greatly improves the accuracy of our classifier.
AB - We present a new semi-supervised algorithmfor dimensionality reduction which exploits information of unlabeled data in order to improve the accuracy of image-based disease classification based on medical images. We perform dimensionality reduction by adopting the formalismof constrainedmatrix decomposition of [1] to semi-supervised learning. In addition, we add a new regularization term to the objective function to better captur the affinity between labeled and unlabeled data. We apply our method to a data set consisting of medical scans of subjects classified as Normal Control (CN) and Alzheimer (AD). The unlabeled data are scans of subjects diagnosedwith Mild Cognitive Impairment (MCI), which are at high risk to develop AD in the future. We measure the accuracy of our algorithm in classifying scans as AD and NC. In addition, we use the classifier to predict which subjects with MCI will converge to AD and compare those results to the diagnosis given at later follow ups. The experiments highlight that unlabeled data greatly improves the accuracy of our classifier.
KW - Alzheimer's disease
KW - Basis Learning
KW - Matrix factorization
KW - Mild Cognitive Impairment (MCI)
KW - Optimization
KW - Semi-supervised Learning
UR - http://www.scopus.com/inward/record.url?scp=80055037586&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=80055037586&partnerID=8YFLogxK
U2 - 10.1109/ISBI.2011.5872590
DO - 10.1109/ISBI.2011.5872590
M3 - Conference contribution
C2 - 28603581
AN - SCOPUS:80055037586
SN - 9781424441280
T3 - Proceedings - International Symposium on Biomedical Imaging
SP - 1086
EP - 1090
BT - 2011 8th IEEE International Symposium on Biomedical Imaging
T2 - 2011 8th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI'11
Y2 - 30 March 2011 through 2 April 2011
ER -