用大脑解剖结构提升脑影像解码效率和精度
NeurIPS: Neuro-anatomical Inductive Priors for Sphere-based Brain Decoding
- 将解剖结构作为先验信息，优化表面编码的几何效率
- 在自然场景数据集上达到新最优，训练速度提升60倍
- 适合需要快速适配新受试者或扩展数据集的研究者
当前功能磁共振解码器在性能与保真度之间存在权衡，高效的1D编码器表现优于几何保真的表面模型。我们指出这部分源于表面标记化效率低下以及未能利用解剖结构作为预测信号。本文提出NeurIPS框架，通过将解剖变异从干扰因素转变为强大先验，改进表面解码。该框架融合两项创新：选择性区域球面标记器（SRST）实现高效几何编码；结构引导混合专家（SG-MoE）显式利用皮层特征建模个体解剖差异。在自然场景数据集上，NeurIPS实现了表面解码的新基准，并达到与强1D基线相当的性能。模型收敛速度显著加快（仅需10轮对比基线600轮），支持仅用20%数据快速适配新受试者，并具备良好可扩展性。消融实验证明性能提升源自对皮层特征的利用，而非记忆受试者ID。NeurIPS为实现鲁棒、泛化性强的脑解码提供了系统性路径。
原文摘要 · Abstract (English)
Current fMRI decoders face a performance-fidelity trade-off where efficient ID encoders outperform geometrically faithful surface-based models. We argue this is partly driven by inefficient surface tokenization and the failure to use anatomy as a predictive signal. We present NeurIPS, a framework that improves surface-based decoding by reframing anatomical variation from a nuisance to a powerful inductive prior. NeurIPS unites two innovations: a Selective ROI Spherical Tokenizer (SRST) for efficient geometric encoding, and a Structure-Guided Mixture of Experts (SG-MoE) that explicitly models individual anatomy using cortical features. On the Natural Scenes Dataset, NeurIPS establishes a new state-of-the-art for surface decoders and achieves performance comparable to strong 1D baselines. This is achieved with unprecedented efficiency, as the model converges dramatically faster (10 vs. 600 epochs). This efficiency enables rapid adaptation to new subjects using only 20% of data and ensures robust scalability as the training cohort is expanded. Ablations provide causal evidence that these gains are driven by the model's use of cortical features, not by memorizing subject IDs. By leveraging anatomical priors, NeurIPS provides a principled and scalable path toward robust, generalizable brain decoding.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。