Brain functional connectivity (FC) derived from resting-state functional magnetic resonance imaging (rs-fMRI) has been widely employed to study neuropsychiatric disorders such as autism spectrum disorder (ASD). Existing studies usually suffer from (1) significant data heterogeneity caused by different scanners or studied populations in multiple sites, (2) curse of dimensionality caused by millions of voxels in each fMRI scan and a very limited number (tens or hundreds) of training samples, and (3) poor interpretability, which hinders the identification of reproducible disease biomarkers. To this end, we propose a Multi-site Clustering and Nested Feature Extraction (MC-NFE) method for fMRI-based ASD detection. Specifically, we first divide multi-site training data into ASD and healthy control (HC) groups. To model inter-site heterogeneity within each category, we use a similarity-driven multiview linear reconstruction model to learn latent representations and perform subject clustering within each group. We then design a nested singular value decomposition (SVD) method to mitigate inter-site heterogeneity and extract FC features by learning both local cluster-shared features across sites within each category and global category-shared features across ASD and HC groups, followed by a linear support vector machine (SVM) for ASD detection. Experimental results on 609 subjects with rs-fMRI from the ABIDE database with 21 imaging sites suggest that the proposed MC-NFE outperforms several state-of-the-art methods in ASD detection. The most discriminative FCs identified by the MC-NFE are mainly located in default mode network, salience network, and cerebellum region, which could be used as potential biomarkers for fMRI-based ASD analysis.

源自静息状态功能磁共振成像 (rs-fMRI) 的脑功能连接 (FC) 已被广泛用于研究神经精神疾病，如自闭症谱系障碍 (ASD)。现有研究通常存在以下问题：（1）由不同扫描仪或多个地点的研究人群引起的显着数据异质性，（2）由每次 fMRI 扫描中数百万体素和非常有限数量（数十或数百）的训练样本引起的维度灾难, 和 (3)可解释性差，这阻碍了可重复的疾病生物标志物的鉴定。为此，我们提出了一种用于基于 fMRI 的 ASD 检测的多站点聚类和嵌套特征提取 (MC-NFE) 方法。具体来说，我们首先将多站点训练数据分为 ASD 和健康控制 (HC) 组。为了对每个类别内的站点间异质性进行建模，我们使用相似性驱动的多视图线性重建模型来学习潜在表示并在每个组内执行主题聚类。然后，我们设计了一种嵌套奇异值分解 (SVD) 方法，通过学习每个类别内跨站点的局部集群共享特征和跨 ASD 和 HC 组的全局类别共享特征，来减轻站点间异质性并提取 FC 特征，然后是用于 ASD 检测的线性支持向量机 (SVM)。来自 ABIDE 数据库的 609 名 rs-fMRI 受试者的实验结果表明，所提出的 MC-NFE 在 ASD 检测中优于几种最先进的方法。MC-NFE 识别出的最具歧视性的 FC 主要位于默认模式网络、显着网络和小脑区域，可用作基于 fMRI 的 ASD 分析的潜在生物标志物。