Dataset Information

Generative embedding for model-based classification of fMRI data.

ABSTRACT: Decoding models, such as those underlying multivariate classification algorithms, have been increasingly used to infer cognitive or clinical brain states from measures of brain activity obtained by functional magnetic resonance imaging (fMRI). The practicality of current classifiers, however, is restricted by two major challenges. First, due to the high data dimensionality and low sample size, algorithms struggle to separate informative from uninformative features, resulting in poor generalization performance. Second, popular discriminative methods such as support vector machines (SVMs) rarely afford mechanistic interpretability. In this paper, we address these issues by proposing a novel generative-embedding approach that incorporates neurobiologically interpretable generative models into discriminative classifiers. Our approach extends previous work on trial-by-trial classification for electrophysiological recordings to subject-by-subject classification for fMRI and offers two key advantages over conventional methods: it may provide more accurate predictions by exploiting discriminative information encoded in 'hidden' physiological quantities such as synaptic connection strengths; and it affords mechanistic interpretability of clinical classifications. Here, we introduce generative embedding for fMRI using a combination of dynamic causal models (DCMs) and SVMs. We propose a general procedure of DCM-based generative embedding for subject-wise classification, provide a concrete implementation, and suggest good-practice guidelines for unbiased application of generative embedding in the context of fMRI. We illustrate the utility of our approach by a clinical example in which we classify moderately aphasic patients and healthy controls using a DCM of thalamo-temporal regions during speech processing. Generative embedding achieves a near-perfect balanced classification accuracy of 98% and significantly outperforms conventional activation-based and correlation-based methods. This example demonstrates how disease states can be detected with very high accuracy and, at the same time, be interpreted mechanistically in terms of abnormalities in connectivity. We envisage that future applications of generative embedding may provide crucial advances in dissecting spectrum disorders into physiologically more well-defined subgroups.

SUBMITTER: Brodersen KH

PROVIDER: S-EPMC3121683 | biostudies-literature | 2011 Jun

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Generative embedding for model-based classification of fMRI data.

Brodersen Kay H KH Schofield Thomas M TM Leff Alexander P AP Ong Cheng Soon CS Lomakina Ekaterina I EI Buhmann Joachim M JM Stephan Klaas E KE

PLoS computational biology 20110623 6

Decoding models, such as those underlying multivariate classification algorithms, have been increasingly used to infer cognitive or clinical brain states from measures of brain activity obtained by functional magnetic resonance imaging (fMRI). The practicality of current classifiers, however, is restricted by two major challenges. First, due to the high data dimensionality and low sample size, algorithms struggle to separate informative from uninformative features, resulting in poor generalizati ...[more]

PMID: 21731479

Similar Datasets

Project description:Hemodynamic responses, in general, and the blood oxygenation level-dependent (BOLD) fMRI signal, in particular, provide an indirect measure of neuronal activity. There is strong evidence that the BOLD response correlates well with post-synaptic changes, induced by changes in the excitatory and inhibitory (E-I) balance between active neuronal populations. Typical BOLD responses exhibit transients, such as the early-overshoot and post-stimulus undershoot, that can be linked to transients in neuronal activity, but they can also result from vascular uncoupling between cerebral blood flow (CBF) and venous cerebral blood volume (venous CBV). Recently, we have proposed a novel generative hemodynamic model of the BOLD signal within the dynamic causal modeling framework, inspired by physiological observations, called P-DCM (Havlicek et al., 2015). We demonstrated the generative model's ability to more accurately model commonly observed neuronal and vascular transients in single regions but also effective connectivity between multiple brain areas (Havlicek et al., 2017b). In this paper, we additionally demonstrate the versatility of the generative model to jointly explain dynamic relationships between neuronal and hemodynamic physiological variables underlying the BOLD signal using multi-modal data. For this purpose, we utilized three distinct data-sets of experimentally induced responses in the primary visual areas measured in human, cat, and monkey brain, respectively: (1) CBF and BOLD responses; (2) CBF, total CBV, and BOLD responses (Jin and Kim, 2008); and (3) positive and negative neuronal and BOLD responses (Shmuel et al., 2006). By fitting the generative model to the three multi-modal experimental data-sets, we showed that the presence or absence of dynamic features in the BOLD signal is not an unambiguous indication of presence or absence of those features on the neuronal level. Nevertheless, the generative model that takes into account the dynamics of the physiological mechanisms underlying the BOLD response allowed dissociating neuronal from vascular transients and deducing excitatory and inhibitory neuronal activity time-courses from BOLD data alone and from multi-modal data.

Project description:Patients with major depressive disorder (MDD) show heterogeneous treatment response and highly variable clinical trajectories: while some patients experience swift recovery, others show relapsing-remitting or chronic courses. Predicting individual clinical trajectories at an early stage is a key challenge for psychiatry and might facilitate individually tailored interventions. So far, however, reliable predictors at the single-patient level are absent. Here, we evaluated the utility of a machine learning strategy - generative embedding (GE) - which combines interpretable generative models with discriminative classifiers. Specifically, we used functional magnetic resonance imaging (fMRI) data of emotional face perception in 85 MDD patients from the NEtherlands Study of Depression and Anxiety (NESDA) who had been followed up over two years and classified into three subgroups with distinct clinical trajectories. Combining a generative model of effective (directed) connectivity with support vector machines (SVMs), we could predict whether a given patient would experience chronic depression vs. fast remission with a balanced accuracy of 79%. Gradual improvement vs. fast remission could still be predicted above-chance, but less convincingly, with a balanced accuracy of 61%. Generative embedding outperformed classification based on conventional (descriptive) features, such as functional connectivity or local activation estimates, which were obtained from the same data and did not allow for above-chance classification accuracy. Furthermore, predictive performance of GE could be assigned to a specific network property: the trial-by-trial modulation of connections by emotional content. Given the limited sample size of our study, the present results are preliminary but may serve as proof-of-concept, illustrating the potential of GE for obtaining clinical predictions that are interpretable in terms of network mechanisms. Our findings suggest that abnormal dynamic changes of connections involved in emotional face processing might be associated with higher risk of developing a less favorable clinical course.

Project description:Modern machine learning algorithms are increasingly being used in neuroimaging studies, such as the prediction of Alzheimer's disease (AD) from structural MRI. However, finding a good representation for multivariate brain MRI features in which their essential structure is revealed and easily extractable has been difficult. We report a successful application of a machine learning framework that significantly improved the use of brain MRI for predictions. Specifically, we used the unsupervised learning algorithm of local linear embedding (LLE) to transform multivariate MRI data of regional brain volume and cortical thickness to a locally linear space with fewer dimensions, while also utilizing the global nonlinear data structure. The embedded brain features were then used to train a classifier for predicting future conversion to AD based on a baseline MRI. We tested the approach on 413 individuals from the Alzheimer's Disease Neuroimaging Initiative (ADNI) who had baseline MRI scans and complete clinical follow-ups over 3 years with the following diagnoses: cognitive normal (CN; n=137), stable mild cognitive impairment (s-MCI; n=93), MCI converters to AD (c-MCI, n=97), and AD (n=86). We found that classifications using embedded MRI features generally outperformed (p<0.05) classifications using the original features directly. Moreover, the improvement from LLE was not limited to a particular classifier but worked equally well for regularized logistic regressions, support vector machines, and linear discriminant analysis. Most strikingly, using LLE significantly improved (p=0.007) predictions of MCI subjects who converted to AD and those who remained stable (accuracy/sensitivity/specificity: =0.68/0.80/0.56). In contrast, predictions using the original features performed not better than by chance (accuracy/sensitivity/specificity: =0.56/0.65/0.46). In conclusion, LLE is a very effective tool for classification studies of AD using multivariate MRI data. The improvement in predicting conversion to AD in MCI could have important implications for health management and for powering therapeutic trials by targeting non-demented subjects who later convert to AD.

Dataset Information

Generative embedding for model-based classification of fMRI data.

Publications

Generative embedding for model-based classification of fMRI data.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets