功能磁共振成像(functional Magnetic Resonance Imaging,fMRI)研究面临的主要挑战之一是不同被试者fMRI数据的异质性.一方面,多被试数据分析对于确定所生成结果跨被试的通用性和有效性至关重要.另一方面,分析多被试者fMRI数据需要在不同被试者的神经活动之间进行准确的解剖和功能校准,以提升最终结果的性能.然而,现有大多数功能校准研究都采用浅层模型来处理多被试者间的复杂关系,这严重束缚了多被试信息的建模能力.为此,提出了一种基于多视图自编码器的功能校准(Multi-view Auto-encoder Functional Alignment,MAFA)方法.具体地,该方法通过重构不同被试者的响应空间来学习节点嵌入,捕获不同被试者之间共享的特征表示,从而创建一个公共的响应空间.此外,通过引入自训练聚类目标,利用高置信度节点作为软标签来监督图聚类过程.在4个数据集上的实验结果表明,相比其他多被试者脑影像功能校准方法,所提方法在解码精度方面取得了最佳效果.
Abstract
One of the major challenges in functional magnetic resonance imaging(fMRI)research is the heterogeneity of fMRI da-ta across different subjects.On the one hand,analyzing multi-subject data is crucial for determining the generalizability and effec-tiveness of the generated results across subjects.On the other hand,analyzing multi-subject fMRI data requires accurate anatomi-cal and functional alignment among the neural activities of different subjects to enhance the performance of the final results.How-ever,most existing functional alignment studies employ shallow models to handle the complex relationships among multiple sub-jects,severely limiting the modeling capacity for multi-subject information.To solve this problem,this paper proposes a multi-view auto-encoder functional alignment(MAFA)method based on multi-view auto-encoders.Specifically,our method learns node embedding by reconstructing the response spaces of different subjects,capturing shared feature representations among subjects,and creating a common response space.We also introduce the graph clustering process by introducing self-training clustering ob-jectives using high-confidence nodes as soft labels.Experimental results on four datasets demonstrate that the proposed method achieves the best decoding accuracy compared to other multi-subject fMRI functional alignment methods.
关键词
功能磁共振成像/功能校准/多视图表示学习/多被试分析/脑解码
Key words
Functional magnetic resonance imaging/Functional alignment/Multi-view representation learning/Multi-subject analysis/Brain decoding
维普
万方数据