Search

Contains fulltext : 202546pub.pdf (Publisher’s version ) (Closed access) Abstract Women neuroscientists (please note that we refer to all who identify as such) are still underrepresented in various aspects of academic life. The efforts of the community to mitigate this issue are growing but can elicit adverse reactions (Moghaddam & Gur, 2016). In this opinion paper, we discuss the different approaches that have been taken at institutional, organizational and individual levels to counter gender bias and aim at addressing unfavorable comments. We base our reasoning on empirical data and on the feedback received after the release of the Women in Neuroscience Repository (WiNRepo, see Supplementary Table S1.a), an initiative we created to increase the visibility of women in neuroscience. While this feedback originated mainly from oral conversations and was not rigorously quantified, we believe the frequency of the comments justify their discussion, as performed in (Moghaddam & Gur, 2016). The aim of this piece (supported by a list of signatories, see Supplementary Table S2) is therefore to ‘debunk the myths’ related to gender bias and to affirmative actions in academia, as well as to propose concrete measures that can been implemented to counter such bias. This article is protected by copyright. All rights reserved.

Recurrent Neural Networks (RNNs) are often used for sequential modeling of adverse outcomes in electronic health records (EHRs) due to their ability to encode past clinical states. These deep, recurrent architectures have displayed increased performance compared to other modeling approaches in a number of tasks, fueling the interest in deploying deep models in clinical settings. One of the key elements in ensuring safe model deployment and building user trust is model explainability. Testing with Concept Activation Vectors (TCAV) has recently been introduced as a way of providing human-understandable explanations by comparing high-level concepts to the network's gradients. While the technique has shown promising results in real-world imaging applications, it has not been applied to structured temporal inputs. To enable an application of TCAV to sequential predictions in the EHR, we propose an extension of the method to time series data. We evaluate the proposed approach on an open EHR benchmark from the intensive care unit, as well as synthetic data where we are able to better isolate individual effects.

ObjectiveMultitask learning (MTL) using electronic health records allows concurrent prediction of multiple endpoints. MTL has shown promise in improving model performance and training efficiency; however, it often suffers from negative transfer – impaired learning if tasks are not appropriately selected. We introduce a sequential subnetwork routing (SeqSNR) architecture that uses soft parameter sharing to find related tasks and encourage cross-learning between them.Materials and MethodsUsing the MIMIC-III (Medical Information Mart for Intensive Care-III) dataset, we train deep neural network models to predict the onset of 6 endpoints including specific organ dysfunctions and general clinical outcomes: acute kidney injury, continuous renal replacement therapy, mechanical ventilation, vasoactive medications, mortality, and length of stay. We compare single-task (ST) models with naive multitask and SeqSNR in terms of discriminative performance and label efficiency.ResultsSeqSNR showed a modest yet statistically significant performance boost across 4 of 6 tasks compared with ST and naive multitasking. When the size of the training dataset was reduced for a given task (label efficiency), SeqSNR outperformed ST for all cases showing an average area under the precision-recall curve boost of 2.1%, 2.9%, and 2.1% for tasks using 1%, 5%, and 10% of labels, respectively.ConclusionsThe SeqSNR architecture shows superior label efficiency compared with ST and naive multitasking, suggesting utility in scenarios in which endpoint labels are difficult to ascertain.

State-of-the-art approaches in Schizophrenia research investigate neuroanatomical biomarkers using structural Magnetic Resonance Imaging. However, current models are 1) voxel-wise, 2) difficult to interpret in biologically meaningful ways, and 3) difficult to replicate across studies. Here, we propose a machine learning framework that enables the identification of sparse, region-wise grey matter neuroanatomical biomarkers and their underlying biological substrates by integrating well-established statistical and machine learning approaches. We address the computational issues associated with application of machine learning on structural MRI data in Schizophrenia, as discussed in recent reviews, while promoting transparent science using widely available data and software. In this work, a cohort of patients with Schizophrenia and healthy controls was used. It was found that the cortical thickness in left pars orbitalis seems to be the most reliable measure for distinguishing patients with Schizophrenia from healthy controls.HighlightsWe present a sparse machine learning framework to identify biologically meaningful neuroanatomical biomarkers for SchizophreniaOur framework addresses methodological pitfalls associated with application of machine learning on structural MRI data in Schizophrenia raised by several recent reviewsOur pipeline is easy to replicate using widely available software packagesThe presented framework is geared towards identification of specific changes in brain regions that relate directly to the pathology rather than classification per se

Since machine learning models have been applied to neuroimaging data, researchers have drawn conclusions from the derived weight maps. In particular, weight maps of classifiers between two conditions are often described as a proxy for the underlying signal differences between the conditions. Recent studies have however suggested that such weight maps could not reliably recover the source of the neural signals and even led to false positives (FP). In this work, we used semi-simulated data from ElectroCorticoGraphy (ECoG) to investigate how the signal-to-noise ratio and sparsity of the neural signal affect the similarity between signal and weights. We show that not all cases produce FP and that it is unlikely for FP features to have a high weight in most cases., conference article

Pattern recognition models have been increasingly applied to neuroimaging data over the last two decades. These applications have ranged from cognitive neuroscience to clinical problems. A common limitation of these approaches is that they do not incorporate previous knowledge about the brain structure and function into the models. Previous knowledge can be embedded into pattern recognition models by imposing a grouping structure based on anatomically or functionally defined brain regions. In this work, we present a novel approach that uses group sparsity to model the whole brain multivariate pattern as a combination of regional patterns. More specifically, we use a sparse version of Multiple Kernel Learning (MKL) to simultaneously learn the contribution of each brain region, previously defined by an atlas, to the decision function. Our application of MKL provides two beneficial features: (1) it can lead to improved overall generalisation performance when the grouping structure imposed by the atlas is consistent with the data; (2) it can identify a subset of relevant brain regions for the predictive model. In order to investigate the effect of the grouping in the proposed MKL approach we compared the results of three different atlases using three different datasets. The method has been implemented in the new version of the open-source Pattern Recognition for Neuroimaging Toolbox (PRoNTo).

Evidence for intrinsic functional connectivity (FC) within the human brain is largely from neuroimaging studies of hemodynamic activity. Data are lacking from anatomically precise electrophysiological recordings in the most widely studied nodes of human brain networks. Here we used a combination of fMRI and electrocorticography (ECoG) in five human neurosurgical patients with electrodes in the canonical “default” (medial prefrontal and posteromedial cortex), “dorsal attention” (frontal eye fields and superior parietal lobule), and “frontoparietal control” (inferior parietal lobule and dorsolateral prefrontal cortex) networks. In this unique cohort, simultaneous intracranial recordings within these networks were anatomically matched across different individuals. Within each network and for each individual, we found a positive, and reproducible, spatial correlation for FC measures obtained from resting-state fMRI and separately recorded ECoG in the same brains. This relationship was reliably identified for electrophysiological FC based on slow (SIGNIFICANCE STATEMENTThe study of human brain networks during wakeful “rest”, largely with fMRI, is now a major focus in both cognitive and clinical neuroscience. However, little is known about the neurophysiology of these networks and their dynamics. We studied neural activity during wakeful rest and sleep within neurosurgical patients with directly implanted electrodes. We found that network activity patterns showed striking similarities between fMRI and direct recordings in the same brains. With improved resolution of direct recordings, we also found that networks were best characterized with specific activity frequencies and that different frequencies show different profiles of within-network activity over time. Our work clarifies how networks spontaneously organize themselves across individuals, brain networks, and behavioral states.

Multivariate classification is used in neuroimaging studies to infer brain activation or in medical applications to infer diagnosis. Their results are often assessed through either a binomial or a permutation test. Here, we simulated classification results of generated random data to assess the influence of the cross-validation scheme on the significance of results. Distributions built from classification of random data with cross-validation did not follow the binomial distribution. The binomial test is therefore not adapted. On the contrary, the permutation test was unaffected by the cross-validation scheme. The influence of the cross-validation was further illustrated on real-data from a brain–computer interface experiment in patients with disorders of consciousness and from an fMRI study on patients with Parkinson disease. Three out of 16 patients with disorders of consciousness had significant accuracy on binomial testing, but only one showed significant accuracy using permutation testing. In the fMRI experiment, the mental imagery of gait could discriminate significantly between idiopathic Parkinson's disease patients and healthy subjects according to the permutation test but not according to the binomial test. Hence, binomial testing could lead to biased estimation of significance and false positive or negative results. In our view, permutation testing is thus recommended for clinical application of classification with cross-validation., Highlights • We assess the influence of cross-validation on significance of classification results. • Classification of random data did not follow binomial distribution. • The permutation test was unaffected by the cross-validation scheme. • Results are illustrated on real-data from BCI and fMRI studies.

Most available pattern recognition methods in neuroimaging address binary classification problems. Here, we used relevance vector machine (RVM) in combination with booststrap resampling (‘bagging’) for non-hierarchical multiclass classification. The method was tested on 120 cerebral 18fluorodeoxyglucose (FDG) positron emission tomography (PET) scans performed in patients who exhibited parkinsonian clinical features for 3.5 years on average but that were outside the prevailing perception for Parkinson's disease (PD). A radiological diagnosis of PD was suggested for 30 patients at the time of PET imaging. However, at follow-up several years after PET imaging, 42 of them finally received a clinical diagnosis of PD. The remaining 78 APS patients were diagnosed with multiple system atrophy (MSA, N = 31), progressive supranuclear palsy (PSP, N = 26) and corticobasal syndrome (CBS, N = 21), respectively. With respect to this standard of truth, classification sensitivity, specificity, positive and negative predictive values for PD were 93% 83% 75% and 96%, respectively using binary RVM (PD vs. APS) and 90%, 87%, 79% and 94%, respectively, using multiclass RVM (PD vs. MSA vs. PSP vs. CBS). Multiclass RVM achieved 45%, 55% and 62% classification accuracy for, MSA, PSP and CBS, respectively. Finally, a majority confidence ratio was computed for each scan on the basis of class pairs that were the most frequently assigned by RVM. Altogether, the results suggest that automatic multiclass RVM classification of FDG PET scans achieves adequate performance for the early differentiation between PD and APS on the basis of cerebral FDG uptake patterns when the clinical diagnosis is felt uncertain. This approach cannot be recommended yet as an aid for distinction between the three APS classes under consideration., Highlights • Multiclass classification is one of the challenges of computer-aided diagnosis. • This was addressed here using relevance vector machine and bootstrap aggregation. • Performance was tested on FDG-PET scans from 120 parkinsonian patients. • Four diagnostic classes under consideration as defined on average 3.5 years after PET. • Confusion matrices, majority confidence ratio and discriminant maps were computed.

Brain areas within the lateral parietal cortex (LPC) and ventral temporal cortex (VTC) have been shown to code for abstract quantity representations and for symbolic numerical representations, respectively. To explore the fast dynamics of activity within each region and the interaction between them, we used electrocorticography recordings from 16 neurosurgical subjects implanted with grids of electrodes over these two regions and tracked the activity within and between the regions as subjects performed three different numerical tasks. Although our results reconfirm the presence of math-selective hubs within the VTC and LPC, we report here a remarkable heterogeneity of neural responses within each region at both millimeter and millisecond scales. Moreover, we show that the heterogeneity of response profiles within each hub mirrors the distinct patterns of functional coupling between them. Our results support the existence of multiple bidirectional functional loops operating between discrete populations of neurons within the VTC and LPC during the visual processing of numerals and the performance of arithmetic functions. These findings reveal information about the dynamics of numerical processing in the brain and also provide insight into the fine-grained functional architecture and connectivity within the human brain.

Introduction The mildly invasive 18F-fluorodeoxyglucose positron emission tomography (FDG-PET) is a well-established imaging technique to measure ‘resting state’ cerebral metabolism. This technique made it possible to assess changes in metabolic activity in clinical applications, such as the study of severe brain injury and disorders of consciousness. Objective We assessed the possibility of creating functional MRI activity maps, which could estimate the relative levels of activity in FDG-PET cerebral metabolic maps. If no metabolic absolute measures can be extracted, our approach may still be of clinical use in centers without access to FDG-PET. It also overcomes the problem of recognizing individual networks of independent component selection in functional magnetic resonance imaging (fMRI) resting state analysis. Methods We extracted resting state fMRI functional connectivity maps using independent component analysis and combined only components of neuronal origin. To assess neuronality of components a classification based on support vector machine (SVM) was used. We compared the generated maps with the FDG-PET maps in 16 healthy controls, 11 vegetative state/unresponsive wakefulness syndrome patients and four locked-in patients. Results The results show a significant similarity with ρ = 0.75 ± 0.05 for healthy controls and ρ = 0.58 ± 0.09 for vegetative state/unresponsive wakefulness syndrome patients between the FDG-PET and the fMRI based maps. FDG-PET, fMRI neuronal maps, and the conjunction analysis show decreases in frontoparietal and medial regions in vegetative patients with respect to controls. Subsequent analysis in locked-in syndrome patients produced also consistent maps with healthy controls. Conclusions The constructed resting state fMRI functional connectivity map points toward the possibility for fMRI resting state to estimate relative levels of activity in a metabolic map.

Summary This study characterizes hypnagogic hallucinations reported during a polygraphically recorded 90-min daytime nap following or preceding practice of the computer game Tetris. In the experimental group (N = 16), participants played Tetris in the morning for 2 h during three consecutive days, while in a first control group (N = 13, controlling the effect of experience) participants did not play any game, and in a second control group (N = 14, controlling the effect of anticipation) participants played Tetris after the nap. During afternoon naps, participants were repetitively awakened 15, 45, 75, 120 or 180 s after the onset of S1, and were asked to report their mental content. Reports content was scored by three judges (inter-rater reliability 85%). In the experimental group, 48 out of 485 (10%) sleep-onset reports were Tetris-related. They mostly consisted of images and sounds with very little emotional content. They exactly reproduced Tetris elements or mixed them with other mnemonic components. By contrast, in the first control group, only one report out of 107 was scored as Tetris-related (1%), and in the second control group only three reports out of 112 were scored as Tetris-related (3%; between-groups comparison; P = 0.006). Hypnagogic hallucinations were more consistently induced by experience than by anticipation (P = 0.039), and they were predominantly observed during the transition of wakefulness to sleep. The observed attributes of experience-related hypnagogic hallucinations are consistent with the particular organization of regional brain activity at sleep onset, characterized by high activity in sensory cortices and in the default-mode network.

Machine learning research is interested in building models based on a training set that can then be applied to new data, whether this unseen data comes from new examples (e.g. New subjects, other tasks) or new features (e.g. Different modalities). In this work, we present a simple approach to transfer learning using intracranial EEG (also known as electrocorticographic, ECoG) data from three patients. More specifically, we aimed at detecting numerical processing during naturalistic settings based on a model trained with controlled experimental conditions. Our results showed significant prediction accuracy of numerical events in naturalistic settings when considering a priori knowledge of the target task.

Recently machine learning models have been applied to neuroimaging data, which allow predictions about a variable of interest based on the pattern of activation or anatomy over a set of voxels. These pattern recognition based methods present clear benefits over classical (univariate) techniques, by providing predictions for unseen data, as well as the weights of each feature in the model. Machine learning methods have been applied to a range of data, from MRI to EEG. However, these multivariate techniques have scarcely been applied to electrocorticography (ECoG) data to investigate cognitive neuroscience questions. In this work, we used previously published ECoG data from 8 subjects to show that machine learning techniques can complement univariate techniques and be more sensitive to certain effects.

Memories are consolidated during sleep by two apparently antagonistic processes: (1) reinforcement of memory-specific cortical interactions and (2) homeostatic reduction in synaptic efficiency. Using fMRI, we assessed whether episodic memories are processed during sleep by either or both mechanisms, by comparing recollection before and after sleep. We probed whether LTP influences these processes by contrasting two groups of individuals prospectively recruited based on BDNF rs6265 (Val66Met) polymorphism. Between immediate retrieval and delayed testing scheduled after sleep, responses to recollection increased significantly more in Val/Val individuals than in Met carriers in parietal and occipital areas not previously engaged in retrieval, consistent with “systems-level consolidation.” Responses also increased differentially between allelic groups in regions already activated before sleep but only in proportion to slow oscillation power, in keeping with “synaptic downscaling.” Episodic memories seem processed at both synaptic and systemic levels during sleep by mechanisms involving LTP.

While Multi-Variate Pattern Analysis techniques based on machine learning have now been regularly applied to neuroimaging data, decoding brain activity is usually performed in highly controlled experimental paradigms. In more realistic conditions, the number, sequence and duration of mental states are unpredictably generated by the individual, resulting in complex and imbalanced fMRI data sets. Moreover, in the case of spontaneous brain activity, the mental states can not be linked to any external or internal stimulation, which makes it a highly difficult condition to decode. This study tests the classification of brain activity, acquired on 14 volunteers using fMRI, during mental imagery, a condition in which the number and duration of mental events were not externally imposed but self-generated. Application of the obtained model on rest sessions allowed classifying spontaneous brain activity linked to the task which, overall, correlated with their behavioural performance to the task.

Advanced mathematical tools are still under development to allow the classification of more complicated experimental data sets, such as examining the content of mind wandering or detecting the state of consciousness of a patient showing no response to a command. Nevertheless, in view of the recent advances in multivariate pattern analysis, brain decoding techniques will certainly become more common in the study of consciousness. Their application as a diagnostic tool to differentiate patients presents obvious advantages such as objectiveness, automation and the fact that a posterior probability can be provided with the final prediction, compared to current time-consuming and subjective criteria.

This study characterizes hypnagogic hallucinations reported during a polygraphically recorded 90-min daytime nap following or preceding practice of the computer game Tetris. In the experimental group (N = 16), participants played Tetris in the morning for 2 h during three consecutive days, while in a first control group (N = 13, controlling the effect of experience) participants did not play any game, and in a second control group (N = 14, controlling the effect of anticipation) participants played Tetris after the nap. During afternoon naps, participants were repetitively awakened 15, 45, 75, 120 or 180 s after the onset of S1, and were asked to report their mental content. Reports content was scored by three judges (inter-rater reliability 85%). In the experimental group, 48 out of 485 (10%) sleep-onset reports were Tetris-related. They mostly consisted of images and sounds with very little emotional content. They exactly reproduced Tetris elements or mixed them with other mnemonic components. By contrast, in the first control group, only one report out of 107 was scored as Tetris-related (1%), and in the second control group only three reports out of 112 were scored as Tetris-related (3%; between-groups comparison; P = 0.006). Hypnagogic hallucinations were more consistently induced by experience than by anticipation (P = 0.039), and they were predominantly observed during the transition of wakefulness to sleep. The observed attributes of experience-related hypnagogic hallucinations are consistent with the particular organization of regional brain activity at sleep onset, characterized by high activity in sensory cortices and in the default-mode network.

We started writing the “fMRI artefact rejection and sleep scoring toolbox”, or “FAST”, to process our sleep EEG-fMRI data, that is, the simultaneous recording of electroencephalographic and functional magnetic resonance imaging data acquired while a subject is asleep. FAST tackles three crucial issues typical of this kind of data: (1) data manipulation (viewing, comparing, chunking, etc.) of long continuous M/EEG recordings, (2) rejection of the fMRI-induced artefact in the EEG signal, and (3) manual sleep-scoring of the M/EEG recording. Currently, the toolbox can efficiently deal with these issues via a GUI, SPM8 batching system or hand-written script. The tools developed are, of course, also useful for other EEG applications, for example, involving simultaneous EEG-fMRI acquisition, continuous EEG eye-balling, and manipulation. Even though the toolbox was originally devised for EEG data, it will also gracefully handle MEG data without any problem. “FAST” is developed in Matlab as an add-on toolbox for SPM8 and, therefore, internally uses its SPM8-meeg data format. “FAST” is available for free, under the GNU-GPL.

Dans le domaine des neurosciences, deux des questions fondamentales sont: comment l’information est distribuee au travers de differentes structures cerebrales, et comment cette information se modifie au cours du temps. Divers outils, tels que l’Imagerie par Resonance Magnetique (IRM) et la Tomographie par Emission de Positon (TEP), ont ete developpes au cours de ces dernieres decennies pour enregistrer l’activite cerebrale et repondre a ces deux questions. En particulier, l’IRM fonctionnelle (IRMf) mesure les modifications du niveau d’oxygenation du sang (signal BOLD [Blood Oxygenation Level-Dependent]) qui est un bon indicateur de l’activite cerebrale (1), avec une resolution spatiale de quelques millimetres cube et une resolution temporelle typiquement de l’ordre de la seconde. Jusqu’a recemment, les methodes generalement utilisees pour analyser des donnees IRMf ou TEP se concentraient sur la caracterisation de la relation individuelle entre un etat cognitif ou perceptuel et chaque voxel1, suivant une approche statistique massivement univariee. Ce type d’approche permet notamment la construction d’une cartographie parametrique statistique (2), reposant sur un modele lineaire general (3), permettant de detecter les voxels qui presentent une reponse statistiquement significative a la condition experimentale d’interet (ou une combinaison de celles-ci). Cependant, le fait d’examiner les voxels un par un individuellement contraint ce qui peut etre infere a propos de la representation cerebrale de l’information. Par exemple, il est possible que plusieurs voxels distribues spatialement soient evalues individuellement comme non significativement actives par une condition experimentale selon une analyse univariee, alors que la consideration de l’ensemble de leurs signaux pourrait caracteriser la presence (ou l’absence) de cette condition experimentale. De plus, les approches classiques voxel-par-voxel sont principalement concues pour comparer des differences entre conditions ou groupes de sujets, et ne permettent donc pas d’evaluer ou de predire l’evolution d’une maladie ou l’etat de conscience d’un seul sujet. D’autre part, les techniques d’analyse de formes multi-voxel (ou Multi-Voxel Pattern Analysis) (4–6) permettent d’augmenter la sensibilite de detection d’une representation mentale particuliere. Ces approches multivariees, connues aussi sous les noms de decodage cerebral (brain decoding) ou lecture de l’esprit (mind reading), visent a relier un etat cognitif, perceptuel, comportemental ou medical, a une distribution specifique de l’activite des voxels. L’application de ces methodes a permis de decoder, a partir de l’activite cerebrale mesuree par imagerie, la categorie d’un objet presente visuellement (7–9) ou l’orientation d’un ensemble de lignes vues par un sujet (10, 11). L’evolution des algorithmes de reconnaissance de formes a aussi permis le decodage d’activite cerebrale moins controlee, telle que des tâches de recuperation mnesique (12, 13).

Consciousness has been related to the amount of integrated information that the brain is able to generate. In this paper, we tested the hypothesis that the loss of consciousness caused by propofol anesthesia is associated with a significant reduction in the capacity of the brain to integrate information. To assess the functional structure of the whole brain, functional integration and partial correlations were computed from fMRI data acquired from 18 healthy volunteers during resting wakefulness and propofol-induced deep sedation. Total integration was significantly reduced from wakefulness to deep sedation in the whole brain as well as within and between its constituent networks (or systems). Integration was systematically reduced within each system (i.e., brain or networks), as well as between networks. However, the ventral attentional network maintained interactions with most other networks during deep sedation. Partial correlations further suggested that functional connectivity was particularly affected between parietal areas and frontal or temporal regions during deep sedation. Our findings suggest that the breakdown in brain integration is the neural correlate of the loss of consciousness induced by propofol. They stress the important role played by parietal and frontal areas in the generation of consciousness.

Predicting a particular cognitive state from a specific pattern of fMRI voxel values is still a methodological challenge. Decoding brain activity is usually performed in highly controlled experimental paradigms characterized by a series of distinct states induced by a temporally constrained experimental design. In more realistic conditions, the number, sequence and duration of mental states are unpredictably generated by the individual, resulting in complex and imbalanced fMRI data sets. This study tests the classification of brain activity, acquired on 16 volunteers using fMRI, during mental imagery, a condition in which the number and duration of mental events were not externally imposed but self-generated. To deal with these issues, two classification techniques were considered (Support Vector Machines, SVM, and Gaussian Processes, GP), as well as different feature extraction methods (General Linear Model, GLM and SVM). These techniques were combined in order to identify the procedures leading to the highest accuracy measures. Our results showed that 12 data sets out of 16 could be significantly modeled by either SVM or GP. Model accuracies tended to be related to the degree of imbalance between classes and to task performance of the volunteers. We also conclude that the GP technique tends to be more robust than SVM to model unbalanced data sets.

In the past years,mass univariate statistical analyses of neuroimaging data have been complemented by the use of multivariate pattern analyses, especially based on machine learning models. While these allow an increased sensitivity or the detection of spatially distributed effects compared to univariate techniques, they lack an established and accessible software framework. The goal of this work was to build a toolbox comprising all the necessary functionalities for multi- variate analyses of neuroimaging data, based on machine learn- ing models. The “Pattern Recognition for Neuroimaging Toolbox” (PRoNTo) is open-source, cross-platform, MATLAB-based and SPM compatible, therefore being suitable for both cognitive and clinical neuroscience research. In addi- tion, it is designed to facilitate novel contributions from devel- opers, aiming to improve the interaction between the neuroimaging and machine learning communities. Here, we introduce PRoNTo by presenting examples of possible research questions that can be addressed with the machine learning framework implemented in PRoNTo, and cannot be easily investigated with mass univariate statistical analysis.