发表机构
Inria Saclay Île-de-France, CEA, Université Paris-Saclay; Sigma Nova（法国国家信息与自动化研究所萨克雷-法兰西岛，法国原子能委员会，巴黎萨克雷大学; Sigma Nova）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究通过谱滤波器重新校准FC特征值，提升KRR预测性能，并据此预训练小型fMRI编码器，以更少参数达到与最佳脑基础模型相当的性能。
AI 中文摘要
自监督预训练重塑了语言和视觉领域的预测，脑基础模型（BFMs）继承了其前景。从大型未标记语料库中学习的表示应能捕捉个体功能动态并跨队列泛化。然而，在功能连接（FC）矩阵上拟合的核岭回归（KRR）在预测个体表型方面仍比我们测试的任何BFM更准确。在本文中，我们表明KRR由FC的特征值加权，而这些特征值对于表型预测而言校准不当。我们应用一种高效的谱滤波器来重新校准每个受试者FC矩阵的特征值，使模型能够利用更多的个体间方差。在我们测试的5个数据集、11个分区和6个预测目标中，我们匹配或超过了KRR基线。基于这一发现，我们在约4,000小时的来自162个开放数据集的fMRI上预训练了一个小型编码器模型，通过将记录片段的嵌入之间的成对相似性与重新校准的连接组之间的成对相似性对齐。我们的模型与我们测试的6个已发表BFM中最好的模型表现相当，同时参数数量少一个数量级。我们的编码器在短扫描和较小队列中表现优于FC，特别是在指纹识别方面。我们发布了预训练模型权重、代码以及预处理和分区后的预训练数据。
英文摘要
Self-supervised pretraining reshaped prediction in language and vision, and brain foundation models (BFMs) inherited its promise. Representations learned from large unlabelled corpora should capture individual functional dynamics and generalise across cohorts. However, kernel ridge regression (KRR) fitted on functional connectivity (FC) matrices still predicts individual phenotypes more accurately than any BFM we tested. In this paper, we show that KRR is weighted by the eigenvalues of the FC which are miscalibrated for phenotype prediction. We apply an efficient spectral filter to recalibrate the eigenvalues of each subject's FC matrix, enabling the model to exploit more inter-individual variance. Across the 5 datasets, 11 parcellations and 6 prediction targets we tested, we match or exceed the KRR baseline. Based on this finding, we then pretrain a small encoder model on about 4,000 hours of fMRI from 162 open datasets, whereby we align the pairwise similarities between the embeddings of recording snippets with those between the recalibrated connectomes. Our model performs on par with the best of the 6 published BFMs we tested while having an order of magnitude fewer parameters. Our encoder performs better than FC on short scans and in smaller cohorts, especially in fingerprinting. We release the pretrained model weights, the code and the pretraining data, preprocessed and parcellated.
