BrainODE: Dynamic Brain Signal Analysis via Graph-Aided Neural Ordinary Differential Equations

TL;DR

BrainODE is a novel neural ODE-based model that effectively reconstructs and analyzes irregular, missing, and misaligned brain signals from fMRI data, improving brain network analysis and clinical predictions.

Contribution

It introduces BrainODE, a continuous-time neural ODE model that handles irregular and incomplete brain signals, advancing neuroimaging analysis methods.

Findings

Outperforms existing methods on real neuroimaging datasets.

Successfully reconstructs brain signals at arbitrary time points.

Addresses missing data, irregular sampling, and misalignment challenges.

Abstract

Brain network analysis is vital for understanding the neural interactions regarding brain structures and functions, and identifying potential biomarkers for clinical phenotypes. However, widely used brain signals such as Blood Oxygen Level Dependent (BOLD) time series generated from functional Magnetic Resonance Imaging (fMRI) often manifest three challenges: (1) missing values, (2) irregular samples, and (3) sampling misalignment, due to instrumental limitations, impacting downstream brain network analysis and clinical outcome predictions. In this work, we propose a novel model called BrainODE to achieve continuous modeling of dynamic brain signals using Ordinary Differential Equations (ODE). By learning latent initial values and neural ODE functions from irregular time series, BrainODE effectively reconstructs brain signals at any time point, mitigating the aforementioned three data challenges of brain signals altogether. Comprehensive experimental results on real-world neuroimaging datasets demonstrate the superior performance of BrainODE and its capability of addressing the three data challenges.