English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Continuous improvement in medical imaging techniques allows the acquisitionof higher-resolution images. When these are used in a predictive setting, agreater number of explanatory variables are potentially related to thedependent variable (the response). Meanwhile, the number of acquisitions perexperiment remains limited. In such high dimension/small sample size setting,it is desirable to find the explanatory variables that are truly related to theresponse while controlling the rate of false discoveries. To achieve this goal,novel multivariate inference procedures, such as knockoff inference, have beenproposed recently. However, they require the feature covariance to bewell-defined, which is impossible in high-dimensional settings. In this paper,we propose a new algorithm, called Ensemble of Clustered Knockoffs, that allowsto select explanatory variables while controlling the false discovery rate(FDR), up to a prescribed spatial tolerance. The core idea is thatknockoff-based inference can be applied on groups (clusters) of voxels, whichdrastically reduces the problem's dimension; an ensembling step then removesthe dependence on a fixed clustering and stabilizes the results. We benchmarkthis algorithm and other FDR-controlling methods on brain imaging datasets andobserve empirical gains in sensitivity, while the false discovery rate iscontrolled at the nominal level.

ECKO: Ensemble of Clustered Knockoffs for multivariate inference on fMRI data