TY - JOUR
T1 - High-dimensional pattern regression using machine learning
T2 - From medical images to continuous clinical variables
AU - Wang, Ying
AU - Fan, Yong
AU - Bhatt, Priyanka
AU - Davatzikos, Christos
N1 - Funding Information:
This study was financially supported by the NIH grant R01AG14971 . The authors would like to thank Evi Parmpi for her help with data processing.
PY - 2010/5/1
Y1 - 2010/5/1
N2 - This paper presents a general methodology for high-dimensional pattern regression on medical images via machine learning techniques. Compared with pattern classification studies, pattern regression considers the problem of estimating continuous rather than categorical variables, and can be more challenging. It is also clinically important, since it can be used to estimate disease stage and predict clinical progression from images. In this work, adaptive regional feature extraction approach is used along with other common feature extraction methods, and feature selection technique is adopted to produce a small number of discriminative features for optimal regression performance. Then the Relevance Vector Machine (RVM) is used to build regression models based on selected features. To get stable regression models from limited training samples, a bagging framework is adopted to build ensemble basis regressors derived from multiple bootstrap training samples, and thus to alleviate the effects of outliers as well as facilitate the optimal model parameter selection. Finally, this regression scheme is tested on simulated data and real data via cross-validation. Experimental results demonstrate that this regression scheme achieves higher estimation accuracy and better generalizing ability than Support Vector Regression (SVR).
AB - This paper presents a general methodology for high-dimensional pattern regression on medical images via machine learning techniques. Compared with pattern classification studies, pattern regression considers the problem of estimating continuous rather than categorical variables, and can be more challenging. It is also clinically important, since it can be used to estimate disease stage and predict clinical progression from images. In this work, adaptive regional feature extraction approach is used along with other common feature extraction methods, and feature selection technique is adopted to produce a small number of discriminative features for optimal regression performance. Then the Relevance Vector Machine (RVM) is used to build regression models based on selected features. To get stable regression models from limited training samples, a bagging framework is adopted to build ensemble basis regressors derived from multiple bootstrap training samples, and thus to alleviate the effects of outliers as well as facilitate the optimal model parameter selection. Finally, this regression scheme is tested on simulated data and real data via cross-validation. Experimental results demonstrate that this regression scheme achieves higher estimation accuracy and better generalizing ability than Support Vector Regression (SVR).
KW - Adaptive regional clustering
KW - Alzheimer's disease
KW - High-dimensionality pattern regression
KW - MRI
KW - Relevance vector regression
UR - http://www.scopus.com/inward/record.url?scp=77950588524&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=77950588524&partnerID=8YFLogxK
U2 - 10.1016/j.neuroimage.2009.12.092
DO - 10.1016/j.neuroimage.2009.12.092
M3 - Article
C2 - 20056158
AN - SCOPUS:77950588524
SN - 1053-8119
VL - 50
SP - 1519
EP - 1535
JO - NeuroImage
JF - NeuroImage
IS - 4
ER -