Learning Image Derived PDE-Phenotypes from fMRI Data
Abstract
Partial Differential Equations (PDEs) model various physical phenomena, such as electromagnetic fields and fluid mechanics. Methods like Sparse Identification of Nonlinear Dynamics (SINDy) and PDE-Net 2.0 have been developed to identify and model PDEs based on data using sparse optimization and deep neural networks, respectively. While PDE models are less commonly applied to fMRI data, they hold the potential for uncovering hidden connections and essential components in brain activity. Using the ADHD200 dataset, we applied Canonical Independent Component Analysis (CanICA) and Uniform Manifold Approximation (UMAP) for dimensionality reduction of fMRI data. We then used Sparse Ridge Regression to identify PDEs from the reduced data, achieving high accuracy in classifying attention deficit hyperactivity disorder (ADHD). The study demonstrates a novel approach to extracting meaningful features from fMRI data for neurological disorder analysis to understand the role of oxygen transport (delivery consumption) in the brain during neural activity relevant for studying intracranial pathologies.
Keywords
Cite
@article{arxiv.2410.18110,
title = {Learning Image Derived PDE-Phenotypes from fMRI Data},
author = {Ion Bica and Ryan Trang and Rui Hu and Wanhua Su and Zhichun Zhai and Qingrun Zhang},
journal= {arXiv preprint arXiv:2410.18110},
year = {2024}
}
Comments
The study demonstrates a novel approach to extracting meaningful PDE-features from fMRI data for neurological disorder analysis to understand the role of oxygen transport (delivery $\&$ consumption) in the brain during neural activity relevant for studying intracranial pathologies