建模大脑的语法：ROI 引导的 fMRI 预训练用于可迁移与可解释的视觉解码
Modeling the Brain's Grammar: ROI-Guided fMRI Pretraining for Transferable and Interpretable Vision Decoding
把 Matryoshka 式嵌套嵌入压缩与 ROI 级稀疏上下文融合用于跨被试 fMRI 预训练，为视觉解码提供可迁移、可按脑区归因的表征；做脑-视觉对齐或多被试表征对齐的研究者可直接借用其 ROI 级 token 化与嵌套压缩思路。
原文依据 Inspired by Matryoshka Representation Learning (MRL), we design an embedding compression scheme that prioritizes the most informative visual components first
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论近期 fMRI 预训练的进展通过利用跨被试神经影像数据集显著提升了视觉解码的准确率。主流策略是使用被试特定的适配器将个体 fMRI 信号对齐到共享特征空间，随后接一个共享解码器。然而，这种无结构的特征空间忽略了体素之间的冗余性与功能相关性，也未能纳入以感兴趣区域（ROI）为核心的大脑内在功能架构。为解决这些局限，我们提出 ROITok，一个 ROI 引导的 fMRI 预训练框架。该方法引入稀疏 ROI 上下文融合来学习 ROI 级视觉表征，并从跨被试数据中捕捉 ROI 之间的功能协同。受 Matryoshka 表征学习（MRL）启发，我们设计了一种嵌入压缩方案，优先编码信息量最大的视觉成分，后续 token 则逐步补充更精细但仍然有用的细节。ROITok 在 NSD 与 GOD 数据集上取得很强的迁移学习性能，并对高层加性噪声表现出很强的鲁棒性，同时提供更好的可解释性。它能够定量评估每个脑区对解码任务的贡献。我们的分析表明，基于 ROI 的预训练可以自动学习大脑的视觉层级结构。不同 ROI 可为解码任务提供互补的上下文；将它们组合起来可提升解码的鲁棒性。
英文原文摘要 1475 字符
Recent advances in fMRI pretraining have significantly improved visual decoding accuracy by leveraging cross-subject neuroimaging datasets. A prevailing strategy aligns individual fMRI signals into a shared feature space using subject-specific adapters, followed by a shared decoder. However, this unstructured feature space overlooks the redundancy and functional correlations among voxels and fails to incorporate the brain's intrinsic functional architecture centered on regions of interest (ROIs). To address these limitations, we propose ROITok, an ROI-guided fMRI pretraining framework. Our method introduces Sparse ROI Context Fusion to learn ROI-level visual representations and captures functional synergy between ROIs from cross-subject data. Inspired by Matryoshka Representation Learning (MRL), we design an embedding compression scheme that prioritizes the most informative visual components first, with later tokens adding progressively finer but still useful details. ROITok achieves strong transfer learning performance on the NSD and GOD datasets and shows strong resilience against high-level additive noises, while offering better interpretability. It allows for quantitative assessment of each brain region's contribution to decoding tasks. Our analysis shows that ROI-based pretraining can automatically learn the brain's visual hierarchy. Different ROIs can provide complementary contexts for decoding tasks; combining them improves decoding robustness.