TY - JOUR
T1 - Application of principal component analysis to distinguish patients with schizophrenia from healthy controls based on fractional anisotropy measurements
AU - Caprihan, A.
AU - Pearlson, G. D.
AU - Calhoun, V. D.
N1 - Funding Information:
This research was supported by the NIH (1R01EB006841, 1R01EB005846) and NSF (0612076) to Dr. Calhoun and by NIMH, 2 RO1MH43775 (MERIT Award), 5 RO1 MH52886; NIDA, 1 R01 DA020709; by NIAAA, 1 RO1 AA015615 and a NARSAD Distinguished Investigator Award, to Dr. Pearlson.
PY - 2008/8/15
Y1 - 2008/8/15
N2 - Principal component analysis (PCA) is often used to reduce the dimension of data before applying more sophisticated data analysis methods such as non-linear classification algorithms or independent component analysis. This practice is based on selecting components corresponding to the largest eigenvalues. If the ultimate goal is separation of data in two groups, then these set of components need not have the most discriminatory power. We measured the distance between two such populations using Mahalanobis distance and chose the eigenvectors to maximize it, a modified PCA method, which we call the discriminant PCA (DPCA). DPCA was applied to diffusion tensor-based fractional anisotropy images to distinguish age-matched schizophrenia subjects from healthy controls. The performance of the proposed method was evaluated by the one-leave-out method. We show that for this fractional anisotropy data set, the classification error with 60 components was close to the minimum error and that the Mahalanobis distance was twice as large with DPCA, than with PCA. Finally, by masking the discriminant function with the white matter tracts of the Johns Hopkins University atlas, we identified left superior longitudinal fasciculus as the tract which gave the least classification error. In addition, with six optimally chosen tracts the classification error was zero.
AB - Principal component analysis (PCA) is often used to reduce the dimension of data before applying more sophisticated data analysis methods such as non-linear classification algorithms or independent component analysis. This practice is based on selecting components corresponding to the largest eigenvalues. If the ultimate goal is separation of data in two groups, then these set of components need not have the most discriminatory power. We measured the distance between two such populations using Mahalanobis distance and chose the eigenvectors to maximize it, a modified PCA method, which we call the discriminant PCA (DPCA). DPCA was applied to diffusion tensor-based fractional anisotropy images to distinguish age-matched schizophrenia subjects from healthy controls. The performance of the proposed method was evaluated by the one-leave-out method. We show that for this fractional anisotropy data set, the classification error with 60 components was close to the minimum error and that the Mahalanobis distance was twice as large with DPCA, than with PCA. Finally, by masking the discriminant function with the white matter tracts of the Johns Hopkins University atlas, we identified left superior longitudinal fasciculus as the tract which gave the least classification error. In addition, with six optimally chosen tracts the classification error was zero.
UR - http://www.scopus.com/inward/record.url?scp=47949115223&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=47949115223&partnerID=8YFLogxK
U2 - 10.1016/j.neuroimage.2008.04.255
DO - 10.1016/j.neuroimage.2008.04.255
M3 - Article
C2 - 18571937
AN - SCOPUS:47949115223
SN - 1053-8119
VL - 42
SP - 675
EP - 682
JO - NeuroImage
JF - NeuroImage
IS - 2
ER -