Toward a Controllable Disentanglement Network.

This article addresses two crucial problems of learning disentangled image representations, namely, controlling the degree of disentanglement during image editing, and balancing the disentanglement strength and the reconstruction quality. To encourage disentanglement, we devise distance covariance-based decorrelation regularization. Further, for the reconstruction step, our model leverages a soft target representation combined with the latent image code. By exploring the real-valued space of the soft target representation, we are able to synthesize novel images with the designated properties. To improve the perceptual quality of images generated by autoencoder (AE)-based models, we extend the encoder-decoder architecture with the generative adversarial network (GAN) by collapsing the AE decoder and the GAN generator into one. We also design a classification-based protocol to quantitatively evaluate the disentanglement strength of our model. The experimental results showcase the benefits of the proposed model.

Nonlinear reconfiguration of network edges, topology and information content during an artificial learning task.

Here, we combine network neuroscience and machine learning to reveal connections between the brain's network structure and the emerging network structure of an artificial neural network. Specifically, we train a shallow, feedforward neural network to classify hand-written digits and then used a combination of systems neuroscience and information-theoretic tools to perform 'virtual brain analytics' on the resultant edge weights and activity patterns of each node. We identify three distinct phases of network reconfiguration across learning, each of which are characterized by unique topological and information-theoretic signatures. Each phase involves aligning the connections of the neural network with patterns of information contained in the input dataset or preceding layers (as relevant). We also observe a process of low-dimensional category separation in the network as a function of learning. Our results offer a systems-level perspective of how artificial neural networks function-in terms of multi-stage reorganization of edge weights and activity patterns to effectively exploit the information content of input data during edge-weight training-while simultaneously enriching our understanding of the methods used by systems neuroscience.

Predicting Prolonged Hospitalization and Supplemental Oxygenation in Patients with COVID-19 Infection from Ambulatory Chest Radiographs using Deep Learning.

RATIONALE AND OBJECTIVES: The clinical prognosis of outpatients with coronavirus disease 2019 (COVID-19) remains difficult to predict, with outcomes including asymptomatic, hospitalization, intubation, and death. Here we determined the prognostic value of an outpatient chest radiograph, together with an ensemble of deep learning algorithms predicting comorbidities and airspace disease to identify patients at a higher risk of hospitalization from COVID-19 infection. MATERIALS AND METHODS: This retrospective study included outpatients with COVID-19 confirmed by reverse transcription-polymerase chain reaction testing who received an ambulatory chest radiography between March 17, 2020 and October 24, 2020. In this study, full admission was defined as hospitalization within 14 days of the COVID-19 test for > 2 days with supplemental oxygen. Univariate analysis and machine learning algorithms were used to evaluate the relationship between the deep learning model predictions and hospitalization for > 2 days. RESULTS: The study included 413 patients, 222 men (54%), with a median age of 51 years (interquartile range, 39-62 years). Fifty-one patients (12.3%) required full admission. A boosted decision tree model produced the best prediction. Variables included patient age, frontal chest radiograph predictions of morbid obesity, congestive heart failure and cardiac arrhythmias, and radiographic opacity, with an internally validated area under the curve (AUC) of 0.837 (95% CI: 0.791-0.883) on a test cohort. CONCLUSION: Deep learning analysis of single frontal chest radiographs was used to generate combined comorbidity and pneumonia scores that predict the need for supplemental oxygen and hospitalization for > 2 days in patients with COVID-19 infection with an AUC of 0.837 (95% confidence interval: 0.791-0.883). Comorbidity scoring may prove useful in other clinical scenarios.

Detecting evolutionary patterns of cancers using consensus trees.

MOTIVATION: While each cancer is the result of an isolated evolutionary process, there are repeated patterns in tumorigenesis defined by recurrent driver mutations and their temporal ordering. Such repeated evolutionary trajectories hold the potential to improve stratification of cancer patients into subtypes with distinct survival and therapy response profiles. However, current cancer phylogeny methods infer large solution spaces of plausible evolutionary histories from the same sequencing data, obfuscating repeated evolutionary patterns. RESULTS: To simultaneously resolve ambiguities in sequencing data and identify cancer subtypes, we propose to leverage common patterns of evolution found in patient cohorts. We first formulate the Multiple Choice Consensus Tree problem, which seeks to select a tumor tree for each patient and assign patients into clusters in such a way that maximizes consistency within each cluster of patient trees. We prove that this problem is NP-hard and develop a heuristic algorithm, Revealing Evolutionary Consensus Across Patients (RECAP), to solve this problem in practice. Finally, on simulated data, we show RECAP outperforms existing methods that do not account for patient subtypes. We then use RECAP to resolve ambiguities in patient trees and find repeated evolutionary trajectories in lung and breast cancer cohorts. AVAILABILITY AND IMPLEMENTATION: https://github.com/elkebir-group/RECAP. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Publisher Correction: Human cognition involves the dynamic integration of neural activity and neuromodulatory systems.

In the version of this article initially published, Kaylena A. Ehgoetz Martens' name was misspelled as Kayla. The error has been corrected in the HTML and PDF versions of the article.

Human cognition involves the dynamic integration of neural activity and neuromodulatory systems.

The human brain integrates diverse cognitive processes into a coherent whole, shifting fluidly as a function of changing environmental demands. Despite recent progress, the neurobiological mechanisms responsible for this dynamic system-level integration remain poorly understood. Here we investigated the spatial, dynamic, and molecular signatures of system-wide neural activity across a range of cognitive tasks. We found that neuronal activity converged onto a low-dimensional manifold that facilitates the execution of diverse task states. Flow within this attractor space was associated with dissociable cognitive functions, unique patterns of network-level topology, and individual differences in fluid intelligence. The axes of the low-dimensional neurocognitive architecture aligned with regional differences in the density of neuromodulatory receptors, which in turn relate to distinct signatures of network controllability estimated from the structural connectome. These results advance our understanding of functional brain organization by emphasizing the interface between neural activity, neuromodulatory systems, and cognitive function.

Decoding brain activity using a large-scale probabilistic functional-anatomical atlas of human cognition.

A central goal of cognitive neuroscience is to decode human brain activity-that is, to infer mental processes from observed patterns of whole-brain activation. Previous decoding efforts have focused on classifying brain activity into a small set of discrete cognitive states. To attain maximal utility, a decoding framework must be open-ended, systematic, and context-sensitive-that is, capable of interpreting numerous brain states, presented in arbitrary combinations, in light of prior information. Here we take steps towards this objective by introducing a probabilistic decoding framework based on a novel topic model-Generalized Correspondence Latent Dirichlet Allocation-that learns latent topics from a database of over 11,000 published fMRI studies. The model produces highly interpretable, spatially-circumscribed topics that enable flexible decoding of whole-brain images. Importantly, the Bayesian nature of the model allows one to "seed" decoder priors with arbitrary images and text-enabling researchers, for the first time, to generate quantitative, context-sensitive interpretations of whole-brain patterns of brain activity.

MRIQC: Advancing the automatic prediction of image quality in MRI from unseen sites.

Quality control of MRI is essential for excluding problematic acquisitions and avoiding bias in subsequent image processing and analysis. Visual inspection is subjective and impractical for large scale datasets. Although automated quality assessments have been demonstrated on single-site datasets, it is unclear that solutions can generalize to unseen data acquired at new sites. Here, we introduce the MRI Quality Control tool (MRIQC), a tool for extracting quality measures and fitting a binary (accept/exclude) classifier. Our tool can be run both locally and as a free online service via the OpenNeuro.org portal. The classifier is trained on a publicly available, multi-site dataset (17 sites, N = 1102). We perform model selection evaluating different normalization and feature exclusion approaches aimed at maximizing across-site generalization and estimate an accuracy of 76%±13% on new sites, using leave-one-site-out cross-validation. We confirm that result on a held-out dataset (2 sites, N = 265) also obtaining a 76% accuracy. Even though the performance of the trained classifier is statistically above chance, we show that it is susceptible to site effects and unable to account for artifacts specific to new sites. MRIQC performs with high accuracy in intra-site prediction, but performance on unseen sites leaves space for improvement which might require more labeled data and new approaches to the between-site variability. Overcoming these limitations is crucial for a more objective quality assessment of neuroimaging data, and to enable the analysis of extremely large and multi-site samples.

What's in a pattern? Examining the type of signal multivariate analysis uncovers at the group level.

Multivoxel pattern analysis (MVPA) has gained enormous popularity in the neuroimaging community over the past few years. At the group level, most MVPA studies adopt an "information based" approach in which the sign of the effect of individual subjects is discarded and a non-directional summary statistic is carried over to the second level. This is in contrast to a directional "activation based" approach typical in univariate group level analysis, in which both signal magnitude and sign are taken into account. The transition from examining effects in one voxel at a time vs. several voxels (univariate vs. multivariate) has thus tacitly entailed a transition from directional to non-directional signal definition at the group level. While a directional group-level MVPA approach implies that individuals have similar multivariate spatial patterns of activity, in a non-directional approach each individual may have a distinct spatial pattern. Using an experimental dataset, we show that directional and non-directional group-level MVPA approaches uncover distinct brain regions with only partial overlap. We propose a method to quantify the degree of spatial similarity in activation patterns over subjects. Applied to an auditory task, we find higher values in auditory regions compared to control regions.

The Dynamics of Functional Brain Networks: Integrated Network States during Cognitive Task Performance.

Higher brain function relies upon the ability to flexibly integrate information across specialized communities of brain regions; however, it is unclear how this mechanism manifests over time. In this study, we used time-resolved network analysis of fMRI data to demonstrate that the human brain traverses between functional states that maximize either segregation into tight-knit communities or integration across otherwise disparate neural regions. Integrated states enable faster and more accurate performance on a cognitive task, and are associated with dilations in pupil diameter, suggesting that ascending neuromodulatory systems may govern the transition between these alternative modes of brain function. Together, our results confirm a direct link between cognitive performance and the dynamic reorganization of the network structure of the brain.

Temporal metastates are associated with differential patterns of time-resolved connectivity, network topology, and attention.

Little is currently known about the coordination of neural activity over longitudinal timescales and how these changes relate to behavior. To investigate this issue, we used resting-state fMRI data from a single individual to identify the presence of two distinct temporal states that fluctuated over the course of 18 mo. These temporal states were associated with distinct patterns of time-resolved blood oxygen level dependent (BOLD) connectivity within individual scanning sessions and also related to significant alterations in global efficiency of brain connectivity as well as differences in self-reported attention. These patterns were replicated in a separate longitudinal dataset, providing additional supportive evidence for the presence of fluctuations in functional network topology over time. Together, our results underscore the importance of longitudinal phenotyping in cognitive neuroscience.

Long-term neural and physiological phenotyping of a single human.

Psychiatric disorders are characterized by major fluctuations in psychological function over the course of weeks and months, but the dynamic characteristics of brain function over this timescale in healthy individuals are unknown. Here, as a proof of concept to address this question, we present the MyConnectome project. An intensive phenome-wide assessment of a single human was performed over a period of 18 months, including functional and structural brain connectivity using magnetic resonance imaging, psychological function and physical health, gene expression and metabolomics. A reproducible analysis workflow is provided, along with open access to the data and an online browser for results. We demonstrate dynamic changes in brain connectivity over the timescales of days to months, and relations between brain connectivity, gene expression and metabolites. This resource can serve as a testbed to study the joint dynamics of human brain and metabolic function over time, an approach that is critical for the development of precision medicine strategies for brain disorders.

Effects of thresholding on correlation-based image similarity metrics.

The computation of image similarity is important for a wide range of analyses in neuroimaging, from decoding to meta-analysis. In many cases the images being compared have empty voxels, but the effects of such empty voxels on image similarity metrics are poorly understood. We present a detailed investigation of the influence of different degrees of image thresholding on the outcome of pairwise image comparison. Given a pair of brain maps for which one of the maps is thresholded, we show that an analysis using the intersection of non-zero voxels across images at a threshold of Z = ±1.0 maximizes accuracy for retrieval of a list of maps of the same contrast, and thresholding up to Z = ±2.0 can increase accuracy as compared to comparison using unthresholded maps. Finally, maps can be thresholded up to to Z = ±3.0 (corresponding to 25% of voxels non-empty within a standard brain mask) and still maintain a lower bound of 90% accuracy. Our results suggest that a small degree of thresholding may improve the accuracy of image similarity computations, and that robust meta-analytic image similarity comparisons can be obtained using thresholded images.

Estimation of dynamic functional connectivity using Multiplication of Temporal Derivatives.

Functional connectivity provides an informative and powerful framework for exploring brain organization. Despite this, few statistical methods are available for the accurate estimation of dynamic changes in functional network architecture. To date, the majority of existing statistical techniques have assumed that connectivity structure is stationary, which is in direct contrast to emerging data that suggests that the strength of connectivity between regions is variable over time. Therefore, the development of statistical methods that enable exploration of dynamic changes in functional connectivity is currently of great importance to the neuroscience community. In this paper, we introduce the 'Multiplication of Temporal Derivatives' (MTD) and then demonstrate the utility of this metric to: (i) detect dynamic changes in connectivity using data from a novel state-switching simulation; (ii) accurately estimate graph structure in a previously-described 'ground-truth' simulated dataset; and (iii) identify task-driven alterations in functional connectivity. We show that the MTD is more sensitive than existing sliding-window methods in detecting dynamic alterations in connectivity structure across a range of correlation strengths and window lengths in simulated data. In addition to the temporal precision offered by MTD, we demonstrate that the metric is also able to accurately estimate stationary network structure in both simulated and real task-based data, suggesting that the method may be used to identify dynamic changes in network structure as they evolve through time.

Identifying candidate disease genes using a trace norm constrained bipartite raking model.

Computational prediction of genes that play roles in human diseases remains an important but challenging task. In this work, we formulate candidate gene prediction as a bipartite ranking problem combining a task-wise ordered observation model with a latent multitask regression function using the matrix-variate Gaussian process (MV-GP). We then use a trace-norm constrained variational inference approach to obtain the bipartite ranking model variables and the parameters of the underlying multitask regression model. We use this model to predict candidate genes from two gene-disease association data sets and show that our model outperforms current state-of-the-art methods. Finally, we demonstrate the practical utility of our method by successfully recovering well characterized gene-disease associations hidden in our training data.

Toward open sharing of task-based fMRI data: the OpenfMRI project.

The large-scale sharing of task-based functional neuroimaging data has the potential to allow novel insights into the organization of mental function in the brain, but the field of neuroimaging has lagged behind other areas of bioscience in the development of data sharing resources. This paper describes the OpenFMRI project (accessible online at http://www.openfmri.org), which aims to provide the neuroimaging community with a resource to support open sharing of task-based fMRI studies. We describe the motivation behind the project, focusing particularly on how this project addresses some of the well-known challenges to sharing of task-based fMRI data. Results from a preliminary analysis of the current database are presented, which demonstrate the ability to classify between task contrasts with high generalization accuracy across subjects, and the ability to identify individual subjects from their activation maps with moderately high accuracy. Clustering analyses show that the similarity relations between statistical maps have a somewhat orderly relation to the mental functions engaged by the relevant tasks. These results highlight the potential of the project to support large-scale multivariate analyses of the relation between mental processes and brain function.