Please use this identifier to cite or link to this item:
Title: Deep neural networks and kernel regression achieve comparable accuracies for functional connectivity prediction of behavior and demographics
Authors: He, T.
Kong, R. 
Holmes, A.J.
Nguyen, M. 
Sabuncu, M.R.
Eickhoff, S.B.
Bzdok, D.
Feng, J. 
Yeo, B.T.T. 
Keywords: Deep learning
Graph convolutional neural network
Kernel ridge regression
Resting-state fMRI
Issue Date: 2020
Publisher: Academic Press Inc.
Citation: He, T., Kong, R., Holmes, A.J., Nguyen, M., Sabuncu, M.R., Eickhoff, S.B., Bzdok, D., Feng, J., Yeo, B.T.T. (2020). Deep neural networks and kernel regression achieve comparable accuracies for functional connectivity prediction of behavior and demographics. NeuroImage 206 : 116276. ScholarBank@NUS Repository.
Rights: Attribution-NonCommercial-NoDerivatives 4.0 International
Abstract: There is significant interest in the development and application of deep neural networks (DNNs) to neuroimaging data. A growing literature suggests that DNNs outperform their classical counterparts in a variety of neuroimaging applications, yet there are few direct comparisons of relative utility. Here, we compared the performance of three DNN architectures and a classical machine learning algorithm (kernel regression) in predicting individual phenotypes from whole-brain resting-state functional connectivity (RSFC) patterns. One of the DNNs was a generic fully-connected feedforward neural network, while the other two DNNs were recently published approaches specifically designed to exploit the structure of connectome data. By using a combined sample of almost 10,000 participants from the Human Connectome Project (HCP) and UK Biobank, we showed that the three DNNs and kernel regression achieved similar performance across a wide range of behavioral and demographic measures. Furthermore, the generic feedforward neural network exhibited similar performance to the two state-of-the-art connectome-specific DNNs. When predicting fluid intelligence in the UK Biobank, performance of all algorithms dramatically improved when sample size increased from 100 to 1000 subjects. Improvement was smaller, but still significant, when sample size increased from 1000 to 5000 subjects. Importantly, kernel regression was competitive across all sample sizes. Overall, our study suggests that kernel regression is as effective as DNNs for RSFC-based behavioral prediction, while incurring significantly lower computational costs. Therefore, kernel regression might serve as a useful baseline algorithm for future studies. © 2019 Elsevier Inc.
Source Title: NeuroImage
ISSN: 1053-8119
DOI: 10.1016/j.neuroimage.2019.116276
Rights: Attribution-NonCommercial-NoDerivatives 4.0 International
Appears in Collections:Elements
Staff Publications

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
10_1016_j_neuroimage_2019_116276.pdf1.77 MBAdobe PDF




checked on May 21, 2022


checked on Oct 6, 2021

Page view(s)

checked on May 26, 2022

Google ScholarTM



This item is licensed under a Creative Commons License Creative Commons