iMINDBench：iEEG 多机构神经解码基准
iMINDBench: iEEG Multi-Institution Neural Decoding Benchmark
浏览论文内容
中文总结 AI 辅助
iMINDBench 是一个多机构 iEEG 神经解码基准，通过十五个任务和标准化预处理评估模型，发现预训练系统优于基线但扩展数据增益有限，凸显了改进预处理基线和跨机构数据利用的需求。
中文摘要 AI 辅助
颅内脑电图（iEEG）广泛用于直接从人脑内部的电极记录电活动，使其成为神经解码的一种有吸引力的模态。然而，iEEG 解码的进展，尤其是朝向通用基础模型的进展，仍然难以可靠地衡量：数据集是特定于任务或机构的，限制了跨任务和记录环境泛化的证据，并且预处理选择会强烈影响性能，使得模型改进难以与预处理增益区分开来。因此，我们引入了 iMINDBench，一个 iEEG 多机构神经解码基准，它在三个自然电影观看数据集上评估模型，共包含十五个解码任务。该基准还定义了标准化的预处理流程和固定的评估划分，以支持一致的模型比较。使用 iMINDBench，我们发现所评估的预训练系统在其各自的预处理流程内通常优于基线，而强大的频谱基线在机构数据集上仍然具有竞争力。在我们的扩展研究中，添加来自其他受试者或机构的多达 25 倍的监督数据，相对于会话内训练仅产生微小或任务相关的增益。总之，这些发现强调了需要改进强预处理基线并更有效地利用跨受试者和机构数据的 iEEG 模型。项目网站：此 https URL
英文摘要
Intracranial electroencephalography (iEEG) is widely used to record electrical activity directly from electrodes inside the human brain, making it an attractive modality for neural decoding. However, progress in iEEG decoding, especially toward general-purpose foundation models, remains difficult to measure reliably: datasets are task- or institution-specific, limiting evidence of generalization across tasks and recording environments, and preprocessing choices can strongly influence performance, making model improvements difficult to distinguish from preprocessing gains. Thus, we introduce iMINDBench, an iEEG Multi-Institution Neural Decoding Benchmark that evaluates models on a shared suite of fifteen decoding tasks across three naturalistic movie-watching datasets. The benchmark additionally defines standardized preprocessing tracks and fixed evaluation splits to support consistent model comparisons. Using iMINDBench, we find that the evaluated pretrained systems generally outperform baselines within their respective preprocessing tracks, while strong spectral baselines remain competitive across institutional datasets. In our scaling study, adding up to 25 times more supervised data from other subjects or institutions yields only small or task-dependent gains over within-session training. Together, these findings highlight the need for iEEG models that improve on strong preprocessing baselines and make more effective use of data across subjects and institutions. Project website: https://imindbench.github.io/
发表机构
- Caltech（加州理工学院）
- USC（南加州大学）
- Seoul National University（首尔国立大学）
- CMU（卡内基梅隆大学）
- MIT（麻省理工学院）
机构由 AI 辅助整理，请以论文原文为准。
