Search papers, labs, and topics across Lattice.
This paper introduces MnemoDyn, a dynamical-systems based model for analyzing resting-state fMRI (rs-fMRI) data, trained on a substantial dataset of approximately 40,000 sequences. Unlike existing methods that rely on transformer architectures, MnemoDyn employs multi-resolution temporal modeling to capture brain dynamics across parcellated regions, demonstrating superior reconstruction quality and efficiency. The model's performance across diverse populations and scanning protocols suggests its potential for enhancing neuroimaging studies, particularly in small sample size contexts.
MnemoDyn outperforms state-of-the-art transformer models in reconstructing resting-state fMRI data, revealing new insights into brain dynamics.
We present a dynamical-systems based model for resting-state functional magnetic resonance imaging (rs-fMRI), trained on a dataset of roughly 40K rs-fMRI sequences covering a wide variety of public and available-by-permission datasets. While most existing proposals use transformer backbones, we utilize multi-resolution temporal modeling of the dynamics across parcellated brain regions. We show that MnemoDyn is compute efficient and generalizes very well across diverse populations and scanning protocols. When benchmarked against current state-of-the-art transformer-based approaches, MnemoDyn consistently delivers superior reconstruction quality. Overall, we find that with such large-scale pre-training on (non-proprietary) rs-fMRI datasets, we get a highly performant model for various downstream tasks. Our results also provide evidence of the efficacy of the model on small sample size studies which has implications for neuroimaging studies at large where resting state fMRI is a commonly acquired imaging modality.
