College of Computer and Information Sciences, Imam Mohammad Ibn Saud Islamic University, 11564, Riyadh, Saudi Arabia.
Faculty of Integrated Technologies, Universiti Brunei Darussalam, Bandar Seri Begawan, BE1410, Brunei.
Sci Rep. 2024 Aug 17;14(1):19070. doi: 10.1038/s41598-024-69647-2.
Independent component analysis (ICA) and dictionary learning (DL) are the most successful blind source separation (BSS) methods for functional magnetic resonance imaging (fMRI) data analysis. However, ICA to higher and DL to lower extent may suffer from performance degradation by the presence of anomalous observations in the recovered time courses (TCs) and high overlaps among spatial maps (SMs). This paper addressed both problems using a novel three-layered sparse DL (TLSDL) algorithm that incorporated prior information in the dictionary update process and recovered full-rank outlier-free TCs from highly corrupted measurements. The associated sequential DL model involved factorizing each subject's data into a multi-subject (MS) dictionary and MS sparse code while imposing a low-rank and a sparse matrix decomposition restriction on the dictionary matrix. It is derived by solving three layers of feature extraction and component estimation. The first and second layers captured brain regions with low and moderate spatial overlaps, respectively. The third layer that segregated regions with significant spatial overlaps solved a sequence of vector decomposition problems using the proximal alternating linearized minimization (PALM) method and solved a decomposition restriction using the alternating directions method (ALM). It learned outlier-free dynamics that integrate spatiotemporal diversities across brains and external information. It differs from existing DL methods owing to its unique optimization model, which incorporates prior knowledge, subject-wise/multi-subject representation matrices, and outlier handling. The TLSDL algorithm was compared with existing dictionary learning algorithms using experimental and synthetic fMRI datasets to verify its performance. Overall, the mean correlation value was found to be higher for the TLSDL than for the state-of-the-art subject-wise sequential DL (swsDL) technique.
独立成分分析 (ICA) 和字典学习 (DL) 是功能磁共振成像 (fMRI) 数据分析中最成功的盲源分离 (BSS) 方法。然而，ICA 在更高程度上，DL 在更低程度上，可能会因恢复的时间序列 (TCs) 中存在异常观测值和空间图谱 (SMs) 之间的高度重叠而导致性能下降。本文使用一种新颖的三层稀疏 DL (TLSDL) 算法解决了这两个问题，该算法在字典更新过程中结合了先验信息，并从高度受污染的测量中恢复了全秩无异常的 TCs。相关的顺序 DL 模型涉及将每个受试者的数据分解为一个多受试者 (MS) 字典和 MS 稀疏码，同时对字典矩阵施加低秩和稀疏矩阵分解限制。它是通过求解三层特征提取和成分估计得到的。第一层和第二层分别捕获具有低和中等空间重叠的脑区。第三层，即分离具有显著空间重叠的区域，使用近端交替线性化最小化 (PALM) 方法解决了一系列向量分解问题，并使用交替方向法 (ALM) 解决了分解限制。它学习了无异常的动力学，这些动力学整合了跨大脑和外部信息的时空多样性。它与现有的 DL 方法不同，因为它具有独特的优化模型，该模型结合了先验知识、受试者/多受试者表示矩阵和异常处理。使用实验和合成 fMRI 数据集将 TLSDL 算法与现有的字典学习算法进行了比较，以验证其性能。总的来说，TLSDL 的平均相关值高于最先进的基于受试者的顺序 DL (swsDL) 技术。
