Rogers F. Silva

A Baseline for the Multivariate Comparison of Resting-State Networks

As the size of functional and structural MRI datasets expands, it becomes increasingly important to establish a baseline from which diagnostic relevance may be determined, a processing strategy that efficiently prepares data for analysis, and a statistical approach that identifies important effects in a manner that is both robust and reproducible. In this paper, we introduce a multivariate analytic approach that optimizes sensitivity and reduces unnecessary testing. We demonstrate the utility of this mega-analytic approach by identifying the effects of age and gender on the resting-state networks (RSNs) of 603 healthy adolescents and adults (mean age: 23.4 years, range: 12–71 years). Data were collected on the same scanner, preprocessed using an automated analysis pipeline based in SPM, and studied using group independent component analysis. RSNs were identified and evaluated in terms of three primary outcome measures: time course spectral power, spatial map intensity, and functional network connectivity. Results revealed robust effects of age on all three outcome measures, largely indicating decreases in network coherence and connectivity with increasing age. Gender effects were of smaller magnitude but suggested stronger intra-network connectivity in females and more inter-network connectivity in males, particularly with regard to sensorimotor networks. These findings, along with the analysis approach and statistical framework described here, provide a useful baseline for future investigations of brain networks in health and disease.

Independent Component Analysis for Brain fMRI Does Indeed Select for Maximal Independence

A recent paper by Daubechies et al. claims that two independent component analysis (ICA) algorithms, Infomax and FastICA, which are widely used for functional magnetic resonance imaging (fMRI) analysis, select for sparsity rather than independence. The argument was supported by a series of experiments on synthetic data. We show that these experiments fall short of proving this claim and that the ICA algorithms are indeed doing what they are designed to do: identify maximally independent sources.

THE TENTH ANNUAL MLSP COMPETITION: SCHIZOPHRENIA CLASSIFICATION CHALLENGE

For the 24th Machine Learning for Signal Processing competition, participants were asked to automatically diagnose schizophrenia using multimodal features derived from MRI scans. The objective of the classification task was to achieve the best possible schizophrenia diagnosis prediction based only on the multimodal features derived from brain MRI scans. A total of 2087 entries from 291 participants with active Kaggle.com accounts were made. Each participant developed a classifier, with optional feature selection, that combined functional and structural magnetic resonance imaging features. Here we review details about the competition setup, the winning strategies, and provide basic analyses of the submitted entries. We conclude with a discussion of the advances made to the neuroimaging and machine learning fields.

Multidataset independent subspace analysis extends independent vector analysis

Despite its multivariate nature, independent component analysis (ICA) is generally limited to univariate latents in the sense that each latent component is a scalar process. Independent subspace analysis (ISA), or multidimensional ICA (MICA), is a generalization of ICA which identifies latent independent vector components instead. While ISA/MICA considers multidimensional latent components within a single dataset, our work specifically considers the case of multiple datasets. Independent vector analysis (IVA) is a related technique that also considers multiple datasets explicitly but with a fixed and constrained model. Here, we first show that 1) ISA/MICA naturally extends to the case of multiple datasets (which we call MISA), and that 2) IVA is a special case of this extension. Then we develop an algorithm for MISA and demonstrate its performance on both IVA- and MISA-type problems. The benefit of these extensions is that the vector sources (or subspaces) capture higher order statistical dependence across datasets while retaining independence between subspaces. This is a promising model that can explore complex latent relations across multiple datasets and help identify novel biological traits for intricate mental illnesses such as schizophrenia.

Comparison of PCA approaches for very large group ICA

Large data sets are becoming more common in fMRI and, with the advent of faster pulse sequences, memory efficient strategies for data reduction via principal component analysis (PCA) turn out to be extremely useful, especially for widely used approaches like group independent component analysis (ICA). In this commentary, we discuss results and limitations from a recent paper on the topic and attempt to provide a more complete perspective on available approaches as well as discussing various issues to consider related to PCA for very large group ICA. We also provide an analysis of computation time, memory use, and number of dataloads for a variety of approaches under multiple scenarios of small and extremely large data sets.

Large scale collaboration with autonomy: Decentralized data ICA

Data sharing for collaborative research systems may not be able to use contemporary architectures that collect and store data in centralized data centers. Research groups often wish to control their data locally but are willing to share access to it for collaborations. This may stem from research culture as well as privacy concerns. To leverage the potential of these aggregated larger data sets, we would like tools that perform joint analyses without transmitting the data. Ideally, these analyses would have similar performance and ease of use as current team-based research structures. In this paper we design, implement, and evaluate a decentralized data independent component analysis (ICA) that meets these criteria. We validate our method on temporal ICA for functional magnetic resonance imaging (fMRI) data; this method shares only intermediate statistics and may be amenable to further privacy protections via differential privacy.

Blind Source Separation for Unimodal and Multimodal Brain Networks: A Unifying Framework for Subspace Modeling

In the past decade, numerous advances in the study of the human brain were fostered by successful applications of blind source separation (BSS) methods to a wide range of imaging modalities. The main focus has been on extracting “networks” represented as the underlying latent sources. While the broad success in learning latent representations from multiple datasets has promoted the wide presence of BSS in modern neuroscience, it also introduced a wide variety of objective functions, underlying graphical structures, and parameter constraints for each method. Such diversity, combined with a host of datatype-specific know-how, can cause a sense of disorder and confusion, hampering a practitioners judgment and impeding further development. We organize the diverse landscape of BSS models by exposing its key features and combining them to establish a novel unifying view of the area. In the process, we unveil important connections among models according to their properties and subspace structures. Consequently, a high-level descriptive structure is exposed, ultimately helping practitioners select the right model for their applications. Equipped with that knowledge, we review the current state of BSS applications to neuroimaging. The gained insight into model connections elicits a broader sense of generalization, highlighting several directions for model development. In light of that, we discuss emerging multidataset multidimensional models and summarize their benefits for the study of the healthy brain and disease-related changes.

Memory Efficient PCA Methods for Large Group ICA.

Principal component analysis (PCA) is widely used for data reduction in group independent component analysis (ICA) of fMRI data. Commonly, group-level PCA of temporally concatenated datasets is computed prior to ICA of the group principal components. This work focuses on reducing very high dimensional temporally concatenated datasets into its group PCA space. Existing randomized PCA methods can determine the PCA subspace with minimal memory requirements and, thus, are ideal for solving large PCA problems. Since the number of dataloads is not typically optimized, we extend one of these methods to compute PCA of very large datasets with a minimal number of dataloads. This method is coined multi power iteration (MPOWIT). The key idea behind MPOWIT is to estimate a subspace larger than the desired one, while checking for convergence of only the smaller subset of interest. The number of iterations is reduced considerably (as well as the number of dataloads), accelerating convergence without loss of accuracy. More importantly, in the proposed implementation of MPOWIT, the memory required for successful recovery of the group principal components becomes independent of the number of subjects analyzed. Highly efficient subsampled eigenvalue decomposition techniques are also introduced, furnishing excellent PCA subspace approximations that can be used for intelligent initialization of randomized methods such as MPOWIT. Together, these developments enable efficient estimation of accurate principal components, as we illustrate by solving a 1600-subject group-level PCA of fMRI with standard acquisition parameters, on a regular desktop computer with only 4 GB RAM, in just a few hours. MPOWIT is also highly scalable and could realistically solve group-level PCA of fMRI on thousands of subjects, or more, using standard hardware, limited only by time, not memory. Also, the MPOWIT algorithm is highly parallelizable, which would enable fast, distributed implementations ideal for big data analysis. Implications to other methods such as expectation maximization PCA (EM PCA) are also presented. Based on our results, general recommendations for efficient application of PCA methods are given according to problem size and available computational resources. MPOWIT and all other methods discussed here are implemented and readily available in the open source GIFT software.

A statistically motivated framework for simulation of stochastic data fusion models applied to multimodal neuroimaging.

Multimodal fusion is becoming more common as it proves to be a powerful approach to identify complementary information from multimodal datasets. However, simulation of joint information is not straightforward. Published approaches mostly employ limited, provisional designs that often break the link between the model assumptions and the data for the sake of demonstrating properties of fusion techniques. This work introduces a new approach to synthetic data generation which allows full-compliance between data and model while still representing realistic spatiotemporal features in accordance with the current neuroimaging literature. The focus is on the simulation of joint information for the verification of stochastic linear models, particularly those used in multimodal data fusion of brain imaging data. Our first goal is to obtain a benchmark ground-truth in which estimation errors due to model mismatch are minimal or none. Then we move on to assess how estimation is affected by gradually increasing model discrepancies toward a more realistic dataset. The key aspect of our approach is that it permits complete control over the type and level of model mismatch, allowing for more educated inferences about the limitations and caveats of select stochastic linear models. As a result, impartial comparison of models is possible based on their performance in multiple different scenarios. Our proposed method uses the commonly overlooked theory of copulas to enable full control of the type and level of dependence/association between modalities, with no occurrence of spurious multimodal associations. Moreover, our approach allows for arbitrary single-modality marginal distributions for any fixed choice of dependence/association between multimodal features. Using our simulation framework, we can rigorously challenge the assumptions of several existing multimodal fusion approaches. Our study brings a new perspective to the problem of simulating multimodal data that can be used for ground-truth verification of various stochastic multimodal models available in the literature, and reveals some important aspects that are not captured or are overlooked by ad hoc simulations that lack a firm statistical motivation.

Identification of Multimodal MRI and EEG Biomarkers using Joint-ICA and Divergence Criteria

The acquisition of multiple brain imaging types for a given study is a very common practice. However these data are typically examined in separate analyses, rather than in a combined model. We propose a novel methodology to perform joint independent component analysis across image modalities, including structural MRI data, functional MRI activation data and EEG data, and to visualize the results via a joint histogram visualization technique. Evaluation of which combination of fused data is most useful is determined by using several information theoretic divergence measures. We demonstrate our method on a data set composed of functional MRI data from two tasks, structural MRI data, and EEG data collected on patients with schizophrenia and healthy controls. Our method provides a way to improve feature selection and even preprocessing. We show that combining data types can improve our ability to distinguish differences between groups.