Deep Neural Networks and Kernel Regression Achieve Comparable Accuracies for Functional Connectivity Prediction of Behavior and Demographics
Open accessPreprint — published as 10.1016/j.neuroimage.2019.116276 · Paper page
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.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946 · see citing works
Efficient multi-scale 3D CNN with fully connected CRF for accurate brain lesion segmentation
Kamnitsas, K., Ledig, C., Newcombe, V. F. J., Simpson, J. P., Kane, A. D., Menon, D. K., Rueckert, D., & Glocker, B. (2017) · Medical Image Analysis · doi:10.1016/j.media.2016.10.004 · Cited by 3,498 · cited 3× · see citing works
“…DNNs have been applied as tools to analyze neuroscience data, including lesion and tumor segmentation (Pinto et al., 2016; Havaei et al., 2017; Kamnitsas et al., 2017b; G. Zhao et al., 2018), anatomical segmentation (Wachinger et al., 2018; X. Zhao et al., 2018), image modality/quality…”
BackgroundMethodMultimodal population brain imaging in the UK Biobank prospective epidemiological study
Miller, K. L., Alfaro-Almagro, F., Bangerter, N. K., Thomas, D. L., Yacoub, E., Xu, J., Bartsch, A. J., Jbabdi, S., Sotiropoulos, S. N., Andersson, J. L. R., et al. (2016) · Nature Neuroscience · doi:10.1038/nn.4393 · Cited by 2,020 · see citing works
Cole, J. H., Poudel, R. P. K., Tsagkrasoulis, D., Caan, M. W. A., Steves, C., Spector, T. D., & Montana, G. (2017) · NeuroImage · doi:10.1016/j.neuroimage.2017.07.059 · Cited by 872 · see citing works
Smith, S. M., Nichols, T. E., Vidaurre, D., Winkler, A. M., Behrens, T. E. J., Glasser, M. F., Ugurbil, K., Barch, D. M., Van Essen, D. C., & Miller, K. L. (2015) · Nature Neuroscience · doi:10.1038/nn.4125 · Cited by 859 · see citing works
BrainNetCNN: convolutional neural networks for brain networks; towards predicting neurodevelopment
Kawahara, J., Brown, C. J., Miller, S. P., Booth, B. G., Chau, V., Grunau, R. E., Zwicker, J. G., & Hamarneh, G. (2017) · NeuroImage · doi:10.1016/j.neuroimage.2016.09.046 · Cited by 813 · see citing works
Abnormal functional connectivity of default mode sub-networks in autism spectrum disorder patients
Assaf, M., Jagannathan, K., Calhoun, V. D., Miller, L., Stevens, M. C., Sahl, R., O'Boyle, J. G., Schultz, R. T., & Pearlson, G. D. (2010) · NeuroImage · doi:10.1016/j.neuroimage.2010.05.067 · Cited by 680 · see citing works
Quicksilver: Fast predictive image registration – A deep learning approach
Yang, X., Kwitt, R., Styner, M., & Niethammer, M. (2017) · NeuroImage · doi:10.1016/j.neuroimage.2017.07.008 · Cited by 630 · see citing works
Kell, A. J. E., Yamins, D. L. K., Shook, E. N., Norman-Haignere, S. V., & McDermott, J. H. (2018) · Neuron · doi:10.1016/j.neuron.2018.03.044 · Cited by 544 · see citing works
Imaging-based parcellations of the human brain
Eickhoff, S. B., Yeo, B. T. T., & Genon, S. (2018) · Nature reviews. Neuroscience · doi:10.1038/s41583-018-0071-7 · Cited by 484 · see citing works
Self-citationBertoia, M. L., Mukamal, K. J., Cahill, L. E., Hou, T., Ludwig, D. S., Mozaffarian, D., Willett, W. C., Hu, F. B., & Rimm, E. B. (2015) · PLOS Medicine · doi:10.1371/journal.pmed.1001878 · Cited by 397 · see citing works
Li, J., Kong, R., Liégeois, R., Orban, C., Tan, Y., Sun, N., Holmes, A. J., Sabuncu, M. R., Ge, T., & Yeo, B. T. T. (2019) · NeuroImage · doi:10.1016/j.neuroimage.2019.04.016 · Cited by 380 · see citing works
Self-citation
Flagged first, then by citations
- Authors
- He, T., Kong, R., Holmes, A. J., Nguyen, M., Sabuncu, M. R., Eickhoff, S. B., Bzdok, D., Feng, J., & Yeo, B. T. T.
- Affiliations
- National University of Singapore (SG)
- Yale University (US)
- Cornell University (US)
- Forschungszentrum Jülich (DE)
- Institut national de recherche en sciences et technologies du numérique (FR)
- Corresponding author
- Yeo, B.T. Thomas
- ORCID
- Venue
- bioRxiv (Cold Spring Harbor Laboratory)
- Publisher
- openRxiv
- Published
- 2018-11-19
- OpenAlex
- W2900707608
- Cited by
- 16
- References
- 12
- Citations by year
- 2024: 1 · 2023: 2 · 2022: 1 · 2021: 2 · 2020: 7 · 2019: 3
- Type
- posted content
- Language
- en
- Open access
- green
- doi.org
- Licence
- cc-by
- Locations
- bioRxiv (Cold Spring Harbor Laboratory) (acceptedVersion, cc-by)
- Funders
- Massachusetts General Hospital (1S10RR023401, 1S10RR019307, P41EB015896, 1S10RR023043, 1U54MH091657)
- Nvidia
- National Research Foundation
- National Research Foundation Singapore
- Ministry of Education, India
- Centre d'Imagerie BioMédicale
- National Supercomputing Centre Singapore
- National Institutes of Health (1s10rr019307-01, Tier 2, 1U54‐MH‐091657, 1s10rr023043-01)
- McDonnell Center for Systems Neuroscience (1U54MH091657)
- Athinoula A. Martinos Center for Biomedical Imaging, Massachusetts General Hospital (P41-EB015896, 1S10RR023401, 1S10RR023043, 25163, 1U54MH091657, 1S10RR019307)
- National Medical Research Council (CBRG/0088/2015)
- National Institute of Biomedical Imaging and Bioengineering (P41EB015896)
- National Center for Research Resources (S10RR023401)
- NIH Blueprint for Neuroscience Research (P41EB015896, 1U54-MH-091657, 1S10RR023401, 1S10RR023043, 1S10RR019307)
- Topics
- Life Sciences › Neuroscience › Cognitive Neuroscience › Functional Brain Connectivity Studies
- Health Sciences › Medicine › Radiology, Nuclear Medicine and Imaging › Advanced Neuroimaging Techniques and Applications
- Health Sciences › Medicine › Radiology, Nuclear Medicine and Imaging › Advanced MRI Techniques and Applications
- Keywords
- deep neural network, kernel regression, resting-state functional connectivity, demographic prediction, sample size effects, computational cost, Human Connectome Project, UK Biobank
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
