TY - JOUR
T1 - Accurate prediction of AD patients using cortical thickness networks
AU - Dai, Dai
AU - He, Huiguang
AU - Vogelstein, Joshua T.
AU - Hou, Zengguang
N1 - Funding Information:
This work was supported by the National Natural Science Foundation of China (61271151, 61228103, 61175076), and the Sci. & Tech. Aiding the Disabled Program of the Chinese Academy of Sciences (Grant #KGCX2-YW-618). We thank Dr. Hai Jiang for proof-reading.
PY - 2013/10
Y1 - 2013/10
N2 - It is widely believed that human brain is a complicated network and many neurological disorders such as Alzheimer's disease (AD) are related to abnormal changes of the brain network architecture. In this work, we present a kernel-based method to establish a network for each subject using mean cortical thickness, which we refer to hereafter as the individual's network. We construct individual networks for 83 subjects, including AD patients and normal controls (NC), which are taken from the Open Access Series of Imaging Studies database. The network edge features are used to make prediction of AD/NC through the sophisticated machine learning technology. As the number of edge features is much more than that of samples, feature selection is applied to avoid the adverse impact of high-dimensional data on the performance of classifier. We use a hybrid feature selection that combines filter and wrapper methods, and compare the performance of six different combinations of them. Finally, support vector machines are trained using the selected features. To obtain an unbiased evaluation of our method, we use a nested cross validation framework to choose the optimal hyper-parameters of classifier and evaluate the generalization of the method. We report the best accuracy of 90.4 % using the proposed method in the leave-one-out analysis, outperforming that using the raw cortical thickness data by more than 10 %.
AB - It is widely believed that human brain is a complicated network and many neurological disorders such as Alzheimer's disease (AD) are related to abnormal changes of the brain network architecture. In this work, we present a kernel-based method to establish a network for each subject using mean cortical thickness, which we refer to hereafter as the individual's network. We construct individual networks for 83 subjects, including AD patients and normal controls (NC), which are taken from the Open Access Series of Imaging Studies database. The network edge features are used to make prediction of AD/NC through the sophisticated machine learning technology. As the number of edge features is much more than that of samples, feature selection is applied to avoid the adverse impact of high-dimensional data on the performance of classifier. We use a hybrid feature selection that combines filter and wrapper methods, and compare the performance of six different combinations of them. Finally, support vector machines are trained using the selected features. To obtain an unbiased evaluation of our method, we use a nested cross validation framework to choose the optimal hyper-parameters of classifier and evaluate the generalization of the method. We report the best accuracy of 90.4 % using the proposed method in the leave-one-out analysis, outperforming that using the raw cortical thickness data by more than 10 %.
KW - Alzheimer's disease
KW - Classification
KW - Cortical thickness
KW - Network
UR - http://www.scopus.com/inward/record.url?scp=84885328735&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84885328735&partnerID=8YFLogxK
U2 - 10.1007/s00138-012-0462-0
DO - 10.1007/s00138-012-0462-0
M3 - Article
AN - SCOPUS:84885328735
SN - 0932-8092
VL - 24
SP - 1445
EP - 1457
JO - Machine Vision and Applications
JF - Machine Vision and Applications
IS - 7
ER -