BrainMT：一种用于建模功能MRI数据长程依赖的混合Mamba-Transformer架构
BrainMT: A Hybrid Mamba-Transformer Architecture for Modeling Long-Range Dependencies in Functional MRI Data
AI总结：
提出混合框架BrainMT，通过双向Mamba块捕获全局时间交互、Transformer块建模全局空间关系，有效学习fMRI数据长程时空依赖，在性别和智力预测任务上显著优于现有方法。
摘要：
深度学习的最新进展使得直接从功能磁共振成像（fMRI）脑体积中预测表型指标成为可能，这在神经影像学界引发了极大的兴趣。然而，现有的主要基于卷积神经网络或Transformer架构的方法，往往难以对fMRI数据中固有的复杂关系进行建模，受限于其无法捕获长程的空间和时间依赖性。为了克服这些缺陷，我们引入了BrainMT，这是一种新颖的混合框架，旨在高效地学习并整合fMRI数据中的长程时空属性。我们的框架分两个阶段运行：(1) 一个具有时间优先扫描机制的双向Mamba块，以计算高效的方式捕获全局时间交互；(2) 一个利用自注意力机制的Transformer块，对由Mamba块处理的深度特征建模全局空间关系。在两个大规模公开数据集UKBioBank和Human Connectome Project上的大量实验表明，BrainMT在分类（性别预测）和回归（认知智力预测）任务上均取得了最先进的性能，以显著优势超越了现有方法。我们的代码和实现细节将在 https://github.com/arunkumar-kannan/BrainMT-fMRI 公开。
英文摘要：
Recent advances in deep learning have made it possible to predict phenotypic measures directly from functional magnetic resonance imaging (fMRI) brain volumes, sparking significant interest in the neuroimaging community. However, existing approaches, primarily based on convolutional neural networks or transformer architectures, often struggle to model the complex relationships inherent in fMRI data, limited by their inability to capture long-range spatial and temporal dependencies. To overcome these shortcomings, we introduce BrainMT, a novel hybrid framework designed to efficiently learn and integrate long-range spatiotemporal attributes in fMRI data. Our framework operates in two stages: (1) a bidirectional Mamba block with a temporal-first scanning mechanism to capture global temporal interactions in a computationally efficient manner; and (2) a transformer block leveraging self-attention to model global spatial relationships across the deep features processed by the Mamba block. Extensive experiments on two large-scale public datasets, UKBioBank and the Human Connectome Project, demonstrate that BrainMT achieves state-of-the-art performance on both classification (sex prediction) and regression (cognitive intelligence prediction) tasks, outperforming existing methods by a significant margin. Our code and implementation details will be made publicly available at this https://github.com/arunkumar-kannan/BrainMT-fMRI
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
