ROI-Based Transformation of Neuroimages into High-Dimensional Data Frames R package MRIreduce version 1.0.0 Converts NIfTI format T1/FL neuroimages into structured, high-dimensional 2D data frames with a focus on region of interest (ROI) based processing. The package incorporates the partition algorithm, which offers a flexible framework for agglomerative partitioning based on the Direct-Measure-Reduce approach. This method ensures that each reduced variable maintains a user-specified minimum level of information while remaining interpretable, as each maps uniquely to one variable in the reduced dataset. The partition framework is described in Millstein et al. (2020) <doi:10.1093/bioinformatics/btz661>. The package allows customization in variable selection, measurement of information loss, and data reduction methods for neuroimaging analysis and machine learning workflows. Software Depends: R (>= 3.5.0) Imports: R6, Rcpp, fslr, neurobase, oro.nifti, parallel, partition, reshape2, reticulate LinkingTo: Rcpp Suggests: DT, EveTemplate, knitr, rmarkdown, testthat (>= 3.0.0) Jinyao Tian <jinyaoti@usc.edu> Comprehensive R Archive Network (CRAN) Joshua Milstein [aut], Jinyao Tian [aut, cre] MIT + file LICENSE (https://CRAN.R-project.org/package=MRIreduce/LICENSE) 2026-04-21 application/tgz https://CRAN.R-project.org/package=MRIreduce doi:10.32614/CRAN.package.MRIreduce en-US