NeAT: A nonlinear neuroimaging analysis toolbox.

Authors: Adrià Casamitjana, Santi Puch, Asier Aduriz, Verónica Vilaplana, Juando Gispert, José Luis Molinuevo



We implemented a new neuroimaging analysis toolbox for modeling linear and nonlinear effects overcoming the limitations of the standard neuroimaging processing tools that perform statistical inference based only on linear models. NeAT is a modular, exible and user-friendly tool via command line interface that provides a range of statistical and machine learning non-linear methods for model estimation. Several metrics based on curve fitting and complexity are used for model inference. The toolbox includes a graphical user interface (GUI) for visualization of results.

Associated publications

Voxelwise nonlinear regression toolbox for neuroimage analysis; Application to aging and neurodegenerative disease modeling Santi Puch, Asier Aduriz, Adrià Casamitjana, Verónica Vilaplana, Paula Petrone, Grégory Operto, Raffaele Cacciaglia, Stavros Skouras, Carles Falcón, José Luis Molinuevo, and Juan Domingo Gispert NIPS Workshop Machine Learning for Health (ML4H), 2017.