peaks2maps: reconstructing unthresholded statistical maps from peak coordinates using deep neural networks
Year: 2019
Type: other
Abstract: Image based meta analysis (IBMA) has been long shown to outperform peak coordinate based meta analysis (CBMA). However, despite efforts to promote sharing of unthresholded maps many papers are still published only with coordinate data available. CBMA methods attempt to reconstruct spatial patterns of underlying maps via convolution with 3D gaussians or spheres; however this approach does not take into account delineation of brain region borders or coactivation patterns. In this work we present a novel data driven approach for reconstructing unthresholded statistical maps from peak coordinates. Code available at https://github.com/chrisfilo/peaks2maps
Institution: Stanford University
Language: English
Subfield: Cognitive Neuroscience
Field: Neuroscience
Domain: Life Sciences
Open Access status: gold
OpenAlex ID: W2936359661