TY - GEN
T1 - A deep learning fusion model for brain disorder classification
T2 - 11th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics, BCB 2020
AU - Du, Yuhui
AU - Li, Bang
AU - Hou, Yuliang
AU - Calhoun, Vince D.
N1 - Funding Information:
This work was supported by National Natural Science Foundation of China (Grant No. 61703253 to YHD), National Institutes of Health grants 5P20RR021938/P20GM103472 & R01EB020407 and National Science Foundation grant 1539067 (to VDC), and the 1331 Engineering Project of Shanxi Province, China.
Publisher Copyright:
© 2020 ACM.
PY - 2020/9/21
Y1 - 2020/9/21
N2 - Deep learning has shown a great promise in classifying brain disorders due to its powerful ability in learning optimal features by nonlinear transformation. However, given the high-dimension property of neuroimaging data, how to jointly exploit complementary information from multimodal neuroimaging data in deep learning is difficult. In this paper, we propose a novel multilevel convolutional neural network (CNN) fusion method that can effectively combine different types of neuroimage-derived features. Importantly, we incorporate a sequential feature selection into the CNN model to increase the feature interpretability. To evaluate our method, we classified two symptom-related brain disorders using large-sample multi-site data from 335 schizophrenia (SZ) patients and 380 autism spectrum disorder (ASD) patients within a cross-validation procedure. Brain functional networks, functional network connectivity, and brain structural morphology were employed to provide possible features. As expected, our fusion method outperformed the CNN model using only single type of features, as our method yielded higher classification accuracy (with mean accuracy >85%) and was more reliable across multiple runs in differentiating the two groups. We found that the default mode, cognitive control, and subcortical regions contributed more in their distinction. Taken together, our method provides an effective means to fuse multimodal features for the diagnosis of different psychiatric and neurological disorders.
AB - Deep learning has shown a great promise in classifying brain disorders due to its powerful ability in learning optimal features by nonlinear transformation. However, given the high-dimension property of neuroimaging data, how to jointly exploit complementary information from multimodal neuroimaging data in deep learning is difficult. In this paper, we propose a novel multilevel convolutional neural network (CNN) fusion method that can effectively combine different types of neuroimage-derived features. Importantly, we incorporate a sequential feature selection into the CNN model to increase the feature interpretability. To evaluate our method, we classified two symptom-related brain disorders using large-sample multi-site data from 335 schizophrenia (SZ) patients and 380 autism spectrum disorder (ASD) patients within a cross-validation procedure. Brain functional networks, functional network connectivity, and brain structural morphology were employed to provide possible features. As expected, our fusion method outperformed the CNN model using only single type of features, as our method yielded higher classification accuracy (with mean accuracy >85%) and was more reliable across multiple runs in differentiating the two groups. We found that the default mode, cognitive control, and subcortical regions contributed more in their distinction. Taken together, our method provides an effective means to fuse multimodal features for the diagnosis of different psychiatric and neurological disorders.
KW - Classification
KW - Deep learning
KW - Fusion
KW - Multimodal neuroimaging
UR - http://www.scopus.com/inward/record.url?scp=85096980818&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85096980818&partnerID=8YFLogxK
U2 - 10.1145/3388440.3412478
DO - 10.1145/3388440.3412478
M3 - Conference contribution
C2 - 33363290
AN - SCOPUS:85096980818
T3 - Proceedings of the 11th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics, BCB 2020
BT - Proceedings of the 11th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics, BCB 2020
PB - Association for Computing Machinery, Inc
Y2 - 21 September 2020 through 24 September 2020
ER -