Deep learning encodes robust discriminative neuroimaging representations to outperform standard machine learning

Anees Abrol (), Zening Fu, Mustafa Salman, Rogers Silva, Yuhui Du, Sergey Plis and Vince Calhoun
Additional contact information
Anees Abrol: Georgia State University, Georgia Institute of Technology, Emory University
Zening Fu: Georgia State University, Georgia Institute of Technology, Emory University
Mustafa Salman: Georgia State University, Georgia Institute of Technology, Emory University
Rogers Silva: Georgia State University, Georgia Institute of Technology, Emory University
Yuhui Du: Georgia State University, Georgia Institute of Technology, Emory University
Sergey Plis: Georgia State University, Georgia Institute of Technology, Emory University
Vince Calhoun: Georgia State University, Georgia Institute of Technology, Emory University

Nature Communications, 2021, vol. 12, issue 1, 1-17

Abstract: Abstract Recent critical commentaries unfavorably compare deep learning (DL) with standard machine learning (SML) approaches for brain imaging data analysis. However, their conclusions are often based on pre-engineered features depriving DL of its main advantage — representation learning. We conduct a large-scale systematic comparison profiled in multiple classification and regression tasks on structural MRI images and show the importance of representation learning for DL. Results show that if trained following prevalent DL practices, DL methods have the potential to scale particularly well and substantially improve compared to SML methods, while also presenting a lower asymptotic complexity in relative computational time, despite being more complex. We also demonstrate that DL embeddings span comprehensible task-specific projection spectra and that DL consistently localizes task-discriminative brain biomarkers. Our findings highlight the presence of nonlinearities in neuroimaging data that DL can exploit to generate superior task-discriminative representations for characterizing the human brain.

Date: 2021
References: Add references at CitEc
Citations: View citations in EconPapers (2)

Downloads: (external link)
https://www.nature.com/articles/s41467-020-20655-6 Abstract (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:nat:natcom:v:12:y:2021:i:1:d:10.1038_s41467-020-20655-6

Ordering information: This journal article can be ordered from
https://www.nature.com/ncomms/

DOI: 10.1038/s41467-020-20655-6

Access Statistics for this article

Nature Communications is currently edited by Nathalie Le Bot, Enda Bergin and Fiona Gillespie

More articles in Nature Communications from Nature
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().