TY - JOUR
T1 - Application of deep canonically correlated sparse autoencoder for the classification of schizophrenia
AU - Li, Gang
AU - Han, Depeng
AU - Wang, Chao
AU - Hu, Wenxing
AU - Calhoun, Vince D.
AU - Wang, Yu Ping
N1 - Funding Information:
The research is supported, in part, by the Science and Technology Bureau of Xi'an project (201805045YD23CG29(5)) and the Fundamental Research Funds for the Central Universities (300102329203), CHD.
Funding Information:
The research is supported, in part, by the Science and Technology Bureau of Xi'an project ( 201805045YD23CG29(5) ) and the Fundamental Research Fund s for the Central Universitie s ( 300102329203 ), CHD .
Publisher Copyright:
© 2019
PY - 2020/1
Y1 - 2020/1
N2 - Background and objective: Imaging genetics has been widely used to help diagnose and treat mental illness, e.g., schizophrenia, by combining magnetic resonance imaging of the brain and genomic information for comprehensive and systematic analysis. As a result, utilizing the correlation between magnetic resonance imaging of the brain and genomic information is becoming an important challenge. Methods: In this paper, the joint analysis of single nucleotide polymorphisms and functional magnetic resonance imaging is conducted for comprehensive study of schizophrenia. We developed a deep canonically correlated sparse autoencoder to classify schizophrenia patients from healthy controls, which can address the limitation of many existing methods such as canonical correlation analysis, deep canonical correlation analysis and sparse autoencoder. Results: The proposed deep canonically correlated sparse autoencoder can not only use complex nonlinear transformation and dimension reduction, but also achieve more accurate classifications. Our experiments showed the proposed method achieved an accuracy of 95.65% for SNP data sets and an accuracy of 80.53% for fMRI data sets. Conclusions: Experiments demonstrated higher accuracy of using the proposed method over other conventional models when classifying schizophrenia patients and healthy controls.
AB - Background and objective: Imaging genetics has been widely used to help diagnose and treat mental illness, e.g., schizophrenia, by combining magnetic resonance imaging of the brain and genomic information for comprehensive and systematic analysis. As a result, utilizing the correlation between magnetic resonance imaging of the brain and genomic information is becoming an important challenge. Methods: In this paper, the joint analysis of single nucleotide polymorphisms and functional magnetic resonance imaging is conducted for comprehensive study of schizophrenia. We developed a deep canonically correlated sparse autoencoder to classify schizophrenia patients from healthy controls, which can address the limitation of many existing methods such as canonical correlation analysis, deep canonical correlation analysis and sparse autoencoder. Results: The proposed deep canonically correlated sparse autoencoder can not only use complex nonlinear transformation and dimension reduction, but also achieve more accurate classifications. Our experiments showed the proposed method achieved an accuracy of 95.65% for SNP data sets and an accuracy of 80.53% for fMRI data sets. Conclusions: Experiments demonstrated higher accuracy of using the proposed method over other conventional models when classifying schizophrenia patients and healthy controls.
KW - Canonical correlation analysis
KW - Deep canonically correlated sparse autoencoder
KW - Imaging-genetic associations
KW - Schizophrenia classification
KW - Sparse autoencoder
UR - http://www.scopus.com/inward/record.url?scp=85072091523&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85072091523&partnerID=8YFLogxK
U2 - 10.1016/j.cmpb.2019.105073
DO - 10.1016/j.cmpb.2019.105073
M3 - Article
C2 - 31525548
AN - SCOPUS:85072091523
SN - 0169-2607
VL - 183
JO - Computer Methods and Programs in Biomedicine
JF - Computer Methods and Programs in Biomedicine
M1 - 105073
ER -