LEICA: Laplacian eigenmaps for group ICA decomposition of fMRI data

Abstract

Independent component analysis (ICA) is a data-driven method that has been increasingly used for analyzing functional Magnetic Resonance Imaging (fMRI) data. However, generalizing ICA to multi-subject studies is non-trivial due to the high-dimensionality of the data, the complexity of the underlying neuronal processes, the presence of various noise sources, and inter-subject variability. Current group ICA based approaches typically use several forms of the Principal Component Analysis (PCA) method to extend ICA for generating group inferences. However, linear dimensionality reduction techniques have serious limitations including the fact that the underlying BOLD signal is a complex function of several nonlinear processes. In this paper, we propose an effective non-linear ICA-based model for extracting group-level spatial maps from multi-subject fMRI datasets. We use a non-linear dimensionality reduction algorithm based on Laplacian eigenmaps to identify a manifold subspace common to the group, such that this mapping preserves the correlation among voxels' time series as much as possible. These eigenmaps are modeled as linear mixtures of a set of group-level spatial features, which are then extracted using ICA. The resulting algorithm is called LEICA (Laplacian Eigenmaps for group ICA decomposition). We introduce a number of methods to evaluate LEICA using 100-subject resting state and 100-subject working memory task fMRI datasets from the Human Connectome Project (HCP). The test results show that the extracted spatial maps from LEICA are meaningful functional networks similar to those produced by some of the best known methods. Importantly, relative to state-of-the-art methods, our algorithm compares favorably in terms of the functional cohesiveness of the spatial maps generated, as well as in terms of the reproducibility of the results.

Machine Learning pipeline for discovering neuroimaging-based biomarkers in neurology and psychiatry

“…The most popular model of high-dimensional data, which occupy a small part of observation space, is a Manifold model in accordance with which the data is located near an unknown Data manifold of lower dimension, embedded in an ambient high-dimensional input space Vapnik; this manifold model can effectively represent the brain anatomy as well Gareth et al. Dimensionality reduction algorithms under this model, called Manifold learning Bishop are widely used for medical data preprocessing including MRI/fMRI data Liu et al (2017); Shen and Meyer (2008).…”

Class-Similarity Based Label Smoothing for Confidence Calibration

“…Machine learning algorithms have progressed rapidly in recent years and are becoming the critical component in a wide variety of technologies [9] such as object detection [26], machine translation [1], medical diagnosis [16,25], and autonomous driving vehicles [5]. In most of these applications, making wrong decisions could lead to very high costs, including significant business losses or even severe human injuries [3].…”

The Laplacian eigenmaps dimensionality reduction of fMRI data for discovering stimulus-induced changes in the resting-state brain activity

“…The Laplacian eigenmaps (LE) method 19 is a tool developed to solve this problem. It has been used to cluster and classify neuronal activity 20,21 and applied to fMRI data to highlight areas of interest 22 , improve the accuracy of functional network discrimination 23 , analyze fMRI data using diffusion-based spatial priors 24 and classify brain activity in Alzheimer's disease 25 . A thorough investigation of machine learning methods in application to resting-state fMRI data can be found in the review of Khosla et al 26 In this study, we tested the LE dimensionality reduction method compared to the linear reduction approach via PCA for revealing stimulus-dependent changes in resting-state brain activity before and immediately after fear conditioning and fear extinction in healthy volunteers 27 .…”