Machine Learning and Brain Imaging: Opportunities and Challenges

Martin P Paulus; Rayus Kuplicki; Hung-Wen Yeh

doi:10.1016/j.tins.2019.07.007

Machine Learning and Brain Imaging: Opportunities and Challenges

Trends Neurosci. 2019 Oct;42(10):659-661. doi: 10.1016/j.tins.2019.07.007. Epub 2019 Jul 31.

Authors

Martin P Paulus¹, Rayus Kuplicki², Hung-Wen Yeh³

Affiliations

¹ Laureate Institute for Brain Research, Tulsa, OK, USA; University of Tulsa, Department of Community Medicine, Tulsa, OK, USA. Electronic address: [email protected].
² Laureate Institute for Brain Research, Tulsa, OK, USA; University of Tulsa, Department of Community Medicine, Tulsa, OK, USA.
³ Laureate Institute for Brain Research, Tulsa, OK, USA; Health Services and Outcomes Research, Children's Mercy Hospital, Kansas City, MO, USA.

PMID: 31376925
DOI: 10.1016/j.tins.2019.07.007

Abstract

Machine learning approaches may provide ways to link brain activation patterns to behavior at an individual-subject level. Using a comparative performance analysis, Jollans and colleagues (Neuroimage, 2019) highlight in a recent paper key considerations when applying machine learning algorithms to neuroimaging data.

Keywords: machine learning; neuroimaging; prediction.

Publication types

Research Support, N.I.H., Extramural
Comment

MeSH terms

Algorithms
Brain
Machine Learning*
Neuroimaging*

Abstract

Publication types

MeSH terms

Grants and funding