TY - JOUR
T1 - Functional network connectivity (FNC)-based generative adversarial network (GAN) and its applications in classification of mental disorders
AU - Zhao, Jianlong
AU - Huang, Jinjie
AU - Zhi, Dongmei
AU - Yan, Weizheng
AU - Ma, Xiaohong
AU - Yang, Xiao
AU - Li, Xianbin
AU - Ke, Qing
AU - Jiang, Tianzi
AU - Calhoun, Vince D.
AU - Sui, Jing
N1 - Publisher Copyright:
© 2020 Elsevier B.V.
PY - 2020/7/15
Y1 - 2020/7/15
N2 - As a popular deep learning method, generative adversarial networks (GAN) have achieved outstanding performance in multiple classifications and segmentation tasks. However, the application of GANs to fMRI data is relatively rare. In this work, we proposed a functional network connectivity (FNC) based GAN for classifying psychotic disorders from healthy controls (HCs), in which FNC matrices were calculated by correlation of time courses derived from non-artefactual fMRI independent components (ICs). The proposed GAN model consisted of one discriminator (real FNCs) and one generator (fake FNCs), each has four fully-connected layers. The generator was trained to match the discriminator in the intermediate layers while simultaneously a new objective loss was determined for the generator to improve the whole classification performance. In a case for classifying 269 major depressive disorder (MDD) patients from 286 HCs, an average accuracy of 70.1% was achieved in 10-fold cross-validation, with at least 6% higher compared to the other 6 popular classification approaches (54.5–64.2%). In another application to discriminating 558 schizophrenia patients from 542 HCs from 7 sites, the proposed GAN model achieved 80.7% accuracy in leave-one-site-out prediction, outperforming support vector machine (SVM) and deep neural net (DNN) by 3%–6%. More importantly, we are able to identify the most contributing FNC nodes and edges with the strategy of leave-one-FNC-out recursively. To the best of our knowledge, this is the first attempt to apply the GAN model on the FNC-based classification of mental disorders. Such a framework promises wide utility and great potential in neuroimaging biomarker identification.
AB - As a popular deep learning method, generative adversarial networks (GAN) have achieved outstanding performance in multiple classifications and segmentation tasks. However, the application of GANs to fMRI data is relatively rare. In this work, we proposed a functional network connectivity (FNC) based GAN for classifying psychotic disorders from healthy controls (HCs), in which FNC matrices were calculated by correlation of time courses derived from non-artefactual fMRI independent components (ICs). The proposed GAN model consisted of one discriminator (real FNCs) and one generator (fake FNCs), each has four fully-connected layers. The generator was trained to match the discriminator in the intermediate layers while simultaneously a new objective loss was determined for the generator to improve the whole classification performance. In a case for classifying 269 major depressive disorder (MDD) patients from 286 HCs, an average accuracy of 70.1% was achieved in 10-fold cross-validation, with at least 6% higher compared to the other 6 popular classification approaches (54.5–64.2%). In another application to discriminating 558 schizophrenia patients from 542 HCs from 7 sites, the proposed GAN model achieved 80.7% accuracy in leave-one-site-out prediction, outperforming support vector machine (SVM) and deep neural net (DNN) by 3%–6%. More importantly, we are able to identify the most contributing FNC nodes and edges with the strategy of leave-one-FNC-out recursively. To the best of our knowledge, this is the first attempt to apply the GAN model on the FNC-based classification of mental disorders. Such a framework promises wide utility and great potential in neuroimaging biomarker identification.
KW - Classification
KW - Deep learning
KW - Generative adversarial networks (GAN)
KW - Major depressive disorders
KW - Resting-state fMRI
KW - Schizophrenia
UR - http://www.scopus.com/inward/record.url?scp=85084434203&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85084434203&partnerID=8YFLogxK
U2 - 10.1016/j.jneumeth.2020.108756
DO - 10.1016/j.jneumeth.2020.108756
M3 - Article
C2 - 32380227
AN - SCOPUS:85084434203
SN - 0165-0270
VL - 341
JO - Journal of Neuroscience Methods
JF - Journal of Neuroscience Methods
M1 - 108756
ER -