MnemoDyn：从4万条fMRI序列中学习静息态动力学
MnemoDyn: Learning Resting State Dynamics from 40K FMRI sequences
浏览论文内容
中文总结 AI 辅助
本研究提出基于动力学系统的MnemoDyn模型，通过4万条rs-fMRI序列训练，采用分块脑区多分辨率时间建模，计算高效且泛化性强，在重建质量上优于Transformer方法，适用于神经影像学下游任务及小样本研究。
中文摘要 AI 辅助
我们提出一种基于动力学系统的静息态功能磁共振成像（rs-fMRI）模型，该模型在约4万条rs-fMRI序列组成的数据集上训练，这些序列涵盖了多种公开及需授权获取的数据集。现有多数方案采用Transformer主干网络，而我们利用分块脑区动力学的多分辨率时间建模。研究表明，MnemoDyn计算效率高，且在不同人群和扫描协议中泛化性极强。与当前最先进的基于Transformer的方法对比，MnemoDyn始终展现出更优的重建质量。总体而言，我们发现通过在（非专有）rs-fMRI数据集上进行此类大规模预训练，可得到适用于多种下游任务的高性能模型；研究结果还为该模型在小样本研究中的有效性提供了证据，这对广泛使用rs-fMRI作为常用成像模态的神经影像学研究具有重要意义。
英文摘要
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.
发表机构
- University of Wisconsin–Madison（威斯康星大学麦迪逊分校）
- Pohang University of Science and Technology (POSTECH)（浦项科技大学）
- University of North Carolina at Chapel Hill（北卡罗来纳大学教堂山分校）
机构由 AI 辅助整理，请以论文原文为准。
