Multimodal fusion of brain signals for robust prediction of psychosis transition.

The prospective study of youths at clinical high risk (CHR) for psychosis, including neuroimaging, can identify neural signatures predictive of psychosis outcomes using algorithms that integrate complex information. Here, to identify risk and psychosis conversion, we implemented multiple kernel learning (MKL), a multimodal machine learning approach allowing patterns from each modality to inform each other. Baseline multimodal scans (n = 74, 11 converters) included structural, resting-state functional imaging, and diffusion-weighted data. Multimodal MKL outperformed unimodal models (AUC = 0.73 vs. 0.66 in predicting conversion). Moreover, patterns learned by MKL were robust to training set variations, suggesting it can identify cross-modality redundancies and synergies to stabilize the predictive pattern. We identified many predictors consistent with the literature, including frontal cortices, cingulate, thalamus, and striatum. This highlights the advantage of methods that leverage the complex pathophysiology of psychosis.

Fusion of biomedical imaging studies for increased sample size and diversity: a case study of brain MRI.

Data collection, curation, and cleaning constitute a crucial phase in Machine Learning (ML) projects. In biomedical ML, it is often desirable to leverage multiple datasets to increase sample size and diversity, but this poses unique challenges, which arise from heterogeneity in study design, data descriptors, file system organization, and metadata. In this study, we present an approach to the integration of multiple brain MRI datasets with a focus on homogenization of their organization and preprocessing for ML. We use our own fusion example (approximately 84,000 images from 54,000 subjects, 12 studies, and 88 individual scanners) to illustrate and discuss the issues faced by study fusion efforts, and we examine key decisions necessary during dataset homogenization, presenting in detail a database structure flexible enough to accommodate multiple observational MRI datasets. We believe our approach can provide a basis for future similarly-minded biomedical ML projects.

Predictive Modeling of Huntington's Disease Unfolds Thalamic and Caudate Atrophy Dissociation.

BACKGROUND: Atrophy in the striatum is a hallmark of Huntington's disease (HD), including the period before clinical motor diagnosis (before-CMD), but it extends to other subcortical structures. The study of the covariation of these structures could improve the detection of disease-related longitudinal progression before-CMD, provide mechanistic insights of the disease, and potentially be used to obtain accurate prospective estimates of atrophy before-CMD and early after-CMD. METHODS: We analyzed data from 337 before-CMD individuals, 236 healthy control subjects, and 95 early after-CMD individuals from three studies, and we used nine subcortical regions volumes in two analyses. First, we discriminated before-CMD from healthy control trajectories by integrating volume changes from these regions. Second, we estimated prospective atrophy before-CMD and early after-CMD by considering the influence of a region's present volume over the future volume of another one. RESULTS: Before-CMD progression was robustly detected across studies. Indeed, detection of before-CMD progression improved when multiple structures were integrated, as opposed to analyzing the striatum alone, likely because of the reduced partial correlation between caudate and thalamic volume change before-CMD. Our multivariate atrophy prediction model found a thalamus-caudate association that is consistent with this pattern, which yields an improved caudate atrophy prediction in early after-CMD. CONCLUSIONS: This study is the first attempt to validate before-CMD multivariate subcortical change detection across studies and to do multivariate prospective atrophy prediction in HD. These models achieve improved performance by detecting a dissociation between caudate and thalamic atrophy trajectories, and they provide a possible mechanistic understanding of the dynamics of HD. © 2022 International Parkinson and Movement Disorder Society.

Learning Brain Dynamics With Coupled Low-Dimensional Nonlinear Oscillators and Deep Recurrent Networks.

Many natural systems, especially biological ones, exhibit complex multivariate nonlinear dynamical behaviors that can be hard to capture by linear autoregressive models. On the other hand, generic nonlinear models such as deep recurrent neural networks often require large amounts of training data, not always available in domains such as brain imaging; also, they often lack interpretability. Domain knowledge about the types of dynamics typically observed in such systems, such as a certain type of dynamical systems models, could complement purely data-driven techniques by providing a good prior. In this work, we consider a class of ordinary differential equation (ODE) models known as van der Pol (VDP) oscil lators and evaluate their ability to capture a low-dimensional representation of neural activity measured by different brain imaging modalities, such as calcium imaging (CaI) and fMRI, in different living organisms: larval zebrafish, rat, and human. We develop a novel and efficient approach to the nontrivial problem of parameters estimation for a network of coupled dynamical systems from multivariate data and demonstrate that the resulting VDP models are both accurate and interpretable, as VDP's coupling matrix reveals anatomically meaningful excitatory and inhibitory interactions across different brain subsystems. VDP outperforms linear autoregressive models (VAR) in terms of both the data fit accuracy and the quality of insight provided by the coupling matrices and often tends to generalize better to unseen data when predicting future brain activity, being comparable to and sometimes better than the recurrent neural networks (LSTMs). Finally, we demonstrate that our (generative) VDP model can also serve as a data-augmentation tool leading to marked improvements in predictive accuracy of recurrent neural networks. Thus, our work contributes to both basic and applied dimensions of neuroimaging: gaining scientific insights and improving brain-based predictive models, an area of potentially high practical importance in clinical diagnosis and neurotechnology.

Loss of nucleus accumbens low-frequency fluctuations is a signature of chronic pain.

Chronic pain is a highly prevalent disease with poorly understood pathophysiology. In particular, the brain mechanisms mediating the transition from acute to chronic pain remain largely unknown. Here, we identify a subcortical signature of back pain. Specifically, subacute back pain patients who are at risk for developing chronic pain exhibit a smaller nucleus accumbens volume, which persists in the chronic phase, compared to healthy controls. The smaller accumbens volume was also observed in a separate cohort of chronic low-back pain patients and was associated with dynamic changes in functional connectivity. At baseline, subacute back pain patients showed altered local nucleus accumbens connectivity between putative shell and core, irrespective of the risk of transition to chronic pain. At follow-up, connectivity changes were observed between nucleus accumbens and rostral anterior cingulate cortex in the patients with persistent pain. Analysis of the power spectral density of nucleus accumbens resting-state activity in the subacute and chronic back pain patients revealed loss of power in the slow-5 frequency band (0.01 to 0.027 Hz) which developed only in the chronic phase of pain. This loss of power was reproducible across two cohorts of chronic low-back pain patients obtained from different sites and accurately classified chronic low-back pain patients in two additional independent datasets. Our results provide evidence that lower nucleus accumbens volume confers risk for developing chronic pain and altered nucleus accumbens activity is a signature of the state of chronic pain.

Resting-state connectivity stratifies premanifest Huntington's disease by longitudinal cognitive decline rate.

Patient stratification is critical for the sensitivity of clinical trials at early stages of neurodegenerative disorders. In Huntington's disease (HD), genetic tests make cognitive, motor and brain imaging measurements possible before symptom manifestation (pre-HD). We evaluated pre-HD stratification models based on single visit resting-state functional MRI (rs-fMRI) data that assess observed longitudinal motor and cognitive change rates from the multisite Track-On HD cohort (74 pre-HD, 79 control participants). We computed longitudinal performance change on 10 tasks (including visits from the preceding TRACK-HD study when available), as well as functional connectivity density (FCD) maps in single rs-fMRI visits, which showed high test-retest reliability. We assigned pre-HD subjects to subgroups of fast, intermediate, and slow change along single tasks or combinations of them, correcting for expectations based on aging; and trained FCD-based classifiers to distinguish fast- from slow-progressing individuals. For robustness, models were validated across imaging sites. Stratification models distinguished fast- from slow-changing participants and provided continuous assessments of decline applicable to the whole pre-HD population, relying on previously-neglected white matter functional signals. These results suggest novel correlates of early deterioration and a robust stratification strategy where a single MRI measurement provides an estimate of multiple ongoing longitudinal changes.

Baseline multimodal information predicts future motor impairment in premanifest Huntington's disease.

In Huntington's disease (HD), accurate estimates of expected future motor impairments are key for clinical trials. Individual prognosis is only partially explained by genetics. However, studies so far have focused on predicting the time to clinical diagnosis based on fixed impairment levels, as opposed to predicting impairment in time windows comparable to the duration of a clinical trial. Here we evaluate an approach to both detect atrophy patterns associated with early degeneration and provide a prognosis of motor impairment within 3 years, using data from the TRACK-HD study on 80 premanifest HD (pre-HD) individuals and 85 age- and sex-matched healthy controls. We integrate anatomical MRI information from gray matter concentrations (estimated via voxel-based morphometry) together with baseline data from demographic, genetic and motor domains to distinguish individuals at high risk of developing pronounced future motor impairment from those at low risk. We evaluate the ability of models to distinguish between these two groups solely using baseline imaging data, as well as in combination with longitudinal imaging or non-imaging data. Our models show improved performance for motor prognosis through the incorporation of imaging features to non-imaging data, reaching 88% cross-validated accuracy when using baseline non-longitudinal information, and detect informative correlates in the caudate nucleus and the thalamus both for motor prognosis and early atrophy detection. These results show the plausibility of using baseline imaging and basic demographic/genetic measures for early detection of individuals at high risk of severe future motor impairment in relatively short timeframes.

Learning stable and predictive network-based patterns of schizophrenia and its clinical symptoms.

Schizophrenia is often associated with disrupted brain connectivity. However, identifying specific neuroimaging-based patterns pathognomonic for schizophrenia and related symptom severity remains a challenging open problem requiring large-scale data-driven analyses emphasizing not only statistical significance but also stability across multiple datasets, contexts and cohorts. Accurate prediction on previously unseen subjects, or generalization, is also essential for any useful biomarker of schizophrenia. In order to build a predictive model based on functional network feature patterns, we studied whole-brain fMRI functional networks, both at the voxel level and lower-resolution supervoxel level. Targeting Auditory Oddball task data on the FBIRN fMRI dataset (n = 95), we considered node-degree and link-weight network features and evaluated stability and generalization accuracy of statistically significant feature sets in discriminating patients vs. CONTROLS: We also applied sparse multivariate regression (elastic net) to whole-brain functional connectivity features, for the first time, to derive stable predictive features for symptom severity. Whole-brain link-weight features achieved 74% accuracy in identifying patients and were more stable than voxel-wise node-degrees. Link-weight features predicted severity of several negative and positive symptom scales, including inattentiveness and bizarre behavior. The most-significant, stable and discriminative functional connectivity changes involved increased correlations between thalamus and primary motor/primary sensory cortex, and between precuneus (BA7) and thalamus, putamen, and Brodmann areas BA9 and BA44. Precuneus, along with BA6 and primary sensory cortex, was also involved in predicting severity of several symptoms. Overall, the proposed multi-step methodology may help identify more reliable multivariate patterns allowing for accurate prediction of schizophrenia and its symptoms severity.

Faces in motion: selectivity of macaque and human face processing areas for dynamic stimuli.

Face recognition mechanisms need to extract information from static and dynamic faces. It has been hypothesized that the analysis of dynamic face attributes is performed by different face areas than the analysis of static facial attributes. To date, there is no evidence for such a division of labor in macaque monkeys. We used fMRI to determine specializations of macaque face areas for motion. Face areas in the fundus of the superior temporal sulcus responded to general object motion; face areas outside of the superior temporal sulcus fundus responded more to facial motion than general object motion. Thus, the macaque face-processing system exhibits regional specialization for facial motion. Human face areas, processing the same stimuli, exhibited specializations for facial motion as well. Yet the spatial patterns of facial motion selectivity differed across species, suggesting that facial dynamics are analyzed differently in humans and macaques.

Parsing a perceptual decision into a sequence of moments of thought.

Theoretical, computational, and experimental studies have converged to a model of decision-making in which sensory evidence is stochastically integrated to a threshold, implementing a shift from an analog to a discrete form of computation. Understanding how this process can be chained and sequenced - as virtually all real-life tasks involve a sequence of decisions - remains an open question in neuroscience. We reasoned that incorporating a virtual continuum of possible behavioral outcomes in a simple decision task - a fundamental ingredient of real-life decision-making - should result in a progressive sequential approximation to the correct response. We used real-time tracking of motor action in a decision task, as a measure of cognitive states reflecting an internal decision process. We found that response trajectories were spontaneously segmented into a discrete sequence of explorations separated by brief stops (about 200 ms) - which remained unconscious to the participants. The characteristics of these stops were indicative of a decision process - a "moment of thought": their duration correlated with the difficulty of the decision and with the efficiency of the subsequent exploration. Our findings suggest that simple navigation in an abstract space involves a discrete sequence of explorations and stops and, moreover, that these stops reveal a fingerprint of moments of thought.