Regularized aggregation of statistical parametric maps.

Journal: Human brain mapping
Published Date: Sep 5, 2018

Abstract

Combining statistical parametric maps (SPM) from individual subjects is the goal in some types of group-level analyses of functional magnetic resonance imaging data. Brain maps are usually combined using a simple average across subjects, making them susceptible to subjects with outlying values. Furthermore, t tests are prone to false positives and false negatives when outlying values are observed. We propose a regularized unsupervised aggregation method for SPMs to find an optimal weight for aggregation, which aids in detecting and mitigating the effect of outlying subjects. We also present a bootstrap-based weighted t test using the optimal weights to construct an activation map robust to outlying subjects. We validate the performance of the proposed aggregation method and test using simulated and real data examples. Results show that the regularized aggregation approach can effectively detect outlying subjects, lower their weights, and produce robust SPMs.

Authors

  • Li-Yu Wang
    Department of Statistics, University of Georgia, Athens, Georgia.
  • Jongik Chung
    Department of Statistics, University of Georgia, Athens, Georgia.
  • Cheolwoo Park
    Department of Statistics, University of Georgia, Athens, Georgia.
  • Hosik Choi
    Department of Applied Statistics, Kyonggi University, Suwon, South Korea.
  • Amanda L Rodrigue
    Department of Psychology, University of Georgia, Athens, Georgia.
  • Jordan E Pierce
    Department of Psychology, University of Georgia, Athens, Georgia.
  • Brett A Clementz
    Department of Psychology, University of Georgia, Athens, Georgia.
  • Jennifer E McDowell
    Department of Psychology, University of Georgia, Athens, Georgia.

Keywords

External Resources

Popular Topics
Recent Journals