% IMPORTANT: The following is UTF-8 encoded.  This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.

@ARTICLE{Frahm:1045526,
      author       = {Frahm, Lennart and Patil, Kaustubh R. and Satterthwaite,
                      Theodore D. and Fox, Peter T. and Eickhoff, Simon B. and
                      Langner, Robert},
      title        = {{P}redictive modeling of significance thresholding in
                      activation likelihood estimation meta-analysis},
      journal      = {Imaging neuroscience},
      volume       = {3},
      issn         = {2837-6056},
      address      = {Cambridge, MA},
      publisher    = {MIT Press},
      reportid     = {FZJ-2025-03531},
      pages        = {$imag_a_00423$},
      year         = {2025},
      note         = {This study was supported by the Deutsche
                      Forschungsgemeinschaft (DFG, EI 816/11-1 and International
                      Research Training Group 2150, 269953372/GRK2150), the
                      National Institute of Mental Health (R01-MH074457), the
                      National Institute of Aging (P30-AG066546), and the
                      Jülich-Aachen Research Alliance (JARA) granting computation
                      time on the supercomputer JURECA (Jülich Supercomputing
                      Centre, 2018) at Forschungszentrum Jülich. Open access
                      funding is enabled and organized by Projekt DEAL.},
      abstract     = {Activation Likelihood Estimation (ALE) employs voxel- or
                      cluster-level family-wise error (vFWE or cFWE) correction or
                      threshold-free cluster enhancement (TFCE) to counter false
                      positives due to multiple comparisons. These corrections
                      utilize Monte-Carlo simulations to approximate a null
                      distribution of spatial convergence, which allows for the
                      determination of a corrected significance threshold. The
                      simulations may take many hours depending on the dataset and
                      the hardware used to run the computations. In this study, we
                      aimed to replace the time-consuming Monte-Carlo simulation
                      procedure with an instantaneous machine-learning prediction
                      based on features of the meta-analysis dataset. These
                      features were created from the number of experiments in the
                      dataset, the number of subjects per experiment, and the
                      number of foci reported per experiment. We simulated 68,100
                      training datasets, containing between 10 and 150 experiments
                      and computed the vFWE, cFWE, and TFCE significance
                      thresholds. We then used this data to train one XGBoost
                      regression model for each thresholding technique. Lastly, we
                      validated the performance of the three models using 11
                      independent real-life datasets (21 contrasts) from
                      previously published ALE meta-analyses. The vFWE model
                      reached near-perfect prediction levels (R² = 0.996), while
                      the TFCE and cFWE models achieved very good prediction
                      accuracies of R² = 0.951 and R² = 0.938, respectively.
                      This means that, on average, the difference between
                      predicted and standard (monte-carlo based) cFWE thresholds
                      was less than two voxels. Given that our model predicts
                      significance thresholds in ALE meta-analyses with very high
                      accuracy, we advocate our efficient prediction approach as a
                      replacement for the currently used Monte-Carlo simulations
                      in future ALE analyses. This will save hours of computation
                      time and reduce energy consumption. Furthermore, the reduced
                      compute time allows for easier implementation of
                      multi-analysis set-ups like leave-one-out sensitivity
                      analysis or subsampling.},
      cin          = {INM-7},
      ddc          = {610},
      cid          = {I:(DE-Juel1)INM-7-20090406},
      pnm          = {5251 - Multilevel Brain Organization and Variability
                      (POF4-525)},
      pid          = {G:(DE-HGF)POF4-5251},
      typ          = {PUB:(DE-HGF)16},
      pubmed       = {40800822},
      UT           = {WOS:001521329000001},
      doi          = {10.1162/imag_a_00423},
      url          = {https://juser.fz-juelich.de/record/1045526},
}