BrainODE: Dynamic Brain Signal Analysis via Graph-Aided Neural Ordinary Differential Equations
This work addresses data quality issues in brain network analysis for clinical applications, representing an incremental improvement in signal processing methods.
The paper tackled the challenges of missing values, irregular samples, and sampling misalignment in fMRI brain signals by proposing BrainODE, a model using neural ODEs for continuous signal reconstruction, which demonstrated superior performance on real-world datasets.
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.