Machine learning in brain imaging genomics

J. Yan, L. Du, X. Yao, Li Shen

Research output: Chapter in Book/Report/Conference proceedingChapter

2 Scopus citations

Abstract

Brain imaging genomics is an emerging research topic that has arisen with the advances in high-throughput genotyping and multimodal imaging techniques. Its major task is to examine the association between genetic markers such as single nucleotide polymorphisms and quantitative traits extracted from multimodal neuroimaging data. Bridging imaging and genomic factors and exploring their connections have the potential to provide a better mechanistic understanding of normal or disordered brain functions. In the last decade, statistical and machine learning has been widely employed in this research area and has greatly advanced the association discoveries via univariate, multilocus, and bi-multivariate imaging genomic association analyses, as well as pathway and network enrichment analyses. This chapter describes the traditional and state-of-the-art machine learning models widely used in brain imaging genomic studies.

Original languageEnglish (US)
Title of host publicationMachine Learning and Medical Imaging
PublisherElsevier Inc.
Pages411-434
Number of pages24
ISBN (Electronic)9780128041147
ISBN (Print)9780128040768
DOIs
StatePublished - Aug 9 2016

    Fingerprint

Keywords

  • Canonical correlation analysis
  • Enrichment analysis
  • Genome-wide association study
  • Imaging genomics
  • Regression
  • Sparse learning

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Yan, J., Du, L., Yao, X., & Shen, L. (2016). Machine learning in brain imaging genomics. In Machine Learning and Medical Imaging (pp. 411-434). Elsevier Inc.. https://doi.org/10.1016/B978-0-12-804076-8.00014-1