Explore the vast range of titles available.

•Release of OpenBHB, new large-scale brain MRI benchmark with pre-processed data•Representation learning challenge for brain age prediction with site-effect removal•Online platform with leaderboard based on new metric for debiasing and age regression•DNN representation are all biased by acquisition setting for predicting age [Display omitted] Prediction of chronological age from neuroimaging in the healthy population is an important issue because the deviations from normal brain age may highlight abnormal trajectories towards brain disorders. As a first step, ML models have emerged to predict chronological age from brain MRI, as a proxy measure of biological age. However, there is currently no consensus w.r.t which Machine Learning (ML) model is best suited for this task, largely because of a lack of public benchmark. Furthermore, new large emerging population neuroimaging datasets are often biased by the acquisition center images are coming from. This bias heavily deteriorates models generalization capacities, especially for Deep Learning (DL) algorithms that are known to overfit rapidly on the simplest features (known as simplicity bias). Here we propose a new public benchmarking resource, namely Open Big Healthy Brains (OpenBHB), along with a challenge for both brain age prediction and site-effect removal through a representation learning framework. OpenBHB is large-scale, gathering >5K 3D T1 brain MRI from Healthy Controls (HC) and highly multi-sites, aggregating >60 centers worldwide and 10 studies. OpenBHB is expected to grow both in terms of available modalities and number of subjects. All OpenBHB datasets are uniformly preprocessed, including quality check, with container technologies that consist in: 3D Voxel-Based Morphometry maps (VBM from CAT12), quasi-raw (simple linear alignment of images), and Surface-Based Morphometry indices (SBM, from FreeSurfer). The OpenBHB challenge is permanent and we provide all tools, materials and tutorials for participants to easily submit and benchmark their model against each other on a public leaderboard.

Recent advances highlight the limitations of classification strategies in machine learning that rely on a single data source for understanding, diagnosing and predicting psychiatric syndromes. Moreover, approaches based solely on clinician labels often fail to capture the complexity and variability of these conditions. Recent research underlines the importance of considering multiple dimensions that span across different psychiatric syndromes. These developments have led to more comprehensive approaches to studying psychiatric conditions that incorporate diverse data sources such as imaging, genetics, and symptom reports. Multi-view unsupervised learning frameworks, particularly deep learning models, present promising solutions for integrating and analysing complex datasets. Such models contain generative capabilities which facilitate the exploration of relationships between different data views. In this study, we propose a robust framework for interpreting these models that combines digital avatars with stability selection to assess these relationships. We apply this framework to the Healthy Brain Network cohort which includes clinical behavioural scores and brain imaging features, uncovering a consistent set of brain-behaviour interactions. These associations link cortical measurements obtained from structural MRI with clinical reports evaluating psychiatric symptoms. Our framework effectively identifies relevant and stable associations, even with incomplete datasets, while isolating variability of interest from confounding factors.

Functional connectivity (FC) of resting-state fMRI time series can be estimated using methods that differ in their temporal sensitivity (static vs. dynamic) and the number of regions included in the connectivity estimation (derived from a prior atlas). This paper presents a novel framework for identifying and quantifying resting-state networks using resting-state fMRI recordings. The study employs a linear latent variable model to generate spatially distinct brain networks and their associated activities. It specifically addresses the atlas selection problem, and the statistical inference and multivariate analysis of the obtained brain network activities. The approach is demonstrated on a dataset of resting-state fMRI recordings from monkeys under different anesthetics using static FC. Our results suggest that two networks, one fronto-parietal and cingular and another temporo-parieto-occipital (posterior brain) strongly influences shifts in consciousness, especially between anesthesia and wakefulness. Interestingly, this observation aligns with the two prominent theories of consciousness: the global neural workspace and integrated information theories of consciousness. The proposed method is also able to decipher the level of anesthesia from the brain network activities. Overall, we provide a framework that can be effectively applied to other datasets and may be particularly useful for the study of disorders of consciousness.

The perspective of personalized medicine for brain disorders requires efficient learning models for anatomical neuroimaging-based prediction of clinical conditions. There is now a consensus on the benefit of deep learning (DL) in addressing many medical imaging tasks, such as image segmentation. However, for single-subject prediction problems, recent studies yielded contradictory results when comparing DL with Standard Machine Learning (SML) on top of classical feature extraction. Most existing comparative studies were limited in predicting phenotypes of little clinical interest, such as sex and age, and using a single dataset. Moreover, they conducted a limited analysis of the employed image pre-processing and feature selection strategies. This paper extensively compares DL and SML prediction capacity on five multi-site problems, including three increasingly complex clinical applications in psychiatry namely schizophrenia, bipolar disorder, and Autism Spectrum Disorder (ASD) diagnosis. To compensate for the relative scarcity of neuroimaging data on these clinical datasets, we also evaluate three pre-training strategies for transfer learning from brain imaging of the general healthy population: self-supervised learning, generative modeling and supervised learning with age. Overall, we find similar performance between randomly initialized DL and SML for the three clinical tasks and a similar scaling trend for sex prediction. This was replicated on an external dataset. We also show highly correlated discriminative brain regions between DL and linear ML models in all problems. Nonetheless, we demonstrate that self-supervised pre-training on large-scale healthy population imaging datasets (N≈10k), along with Deep Ensemble, allows DL to learn robust and transferable representations to smaller-scale clinical datasets (N≤1k). It largely outperforms SML on 2 out of 3 clinical tasks both in internal and external test sets. These findings suggest that the improvement of DL over SML in anatomical neuroimaging mainly comes from its capacity to learn meaningful and useful abstract representations of the brain anatomy, and it sheds light on the potential of transfer learning for personalized medicine in psychiatry •Deep models achieve predictive performance similar to linear models on clinical tasks.•Self-supervised pretraining improves deep representations of neuroanatomical features.•Combining transfer learning and deep ensemble achieves SOTA results on 2 datasets.

Genetic factors and socioeconomic status (SES) inequalities play a large role in educational attainment, and both have been associated with variations in brain structure and cognition. However, genetics and SES are correlated, and no prior study has assessed their neural associations independently. Here we used a polygenic score for educational attainment (EduYears-PGS), as well as SES, in a longitudinal study of 551 adolescents to tease apart genetic and environmental associations with brain development and cognition. Subjects received a structural MRI scan at ages 14 and 19. At both time points, they performed three working memory (WM) tasks. SES and EduYears-PGS were correlated (r = 0.27) and had both common and independent associations with brain structure and cognition. Specifically, lower SES was related to less total cortical surface area and lower WM. EduYears-PGS was also related to total cortical surface area, but in addition had a regional association with surface area in the right parietal lobe, a region related to nonverbal cognitive functions, including mathematics, spatial cognition, and WM. SES, but not EduYears-PGS, was related to a change in total cortical surface area from age 14 to 19. This study demonstrates a regional association of EduYears-PGS and the independent prediction of SES with cognitive function and brain development. It suggests that the SES inequalities, in particular parental education, are related to global aspects of cortical development, and exert a persistent influence on brain development during adolescence.

Decoding states of consciousness from brain activity is a central challenge in neuroscience. Dynamic functional connectivity (dFC) allows the study of short-term temporal changes in functional connectivity (FC) between distributed brain areas. By clustering dFC matrices from resting-state fMRI, we previously described “brain patterns” that underlie different functional configurations of the brain at rest. The networks associated with these patterns have been extensively analyzed. However, the overall dynamic organization and how it relates to consciousness remains unclear. We hypothesized that deep learning networks would help to model this relationship. Recent studies have used low-dimensional variational autoencoders (VAE) to learn meaningful representations that can help explaining consciousness. Here, we investigated the complexity of selecting such a generative model to study brain dynamics, and extended the available methods for latent space characterization and modeling. Therefore, our contributions are threefold. First, compared with probabilistic principal component analysis and sparse VAE, we showed that the selected low-dimensional VAE exhibits balanced performance in reconstructing dFCs and classifying brain patterns. We then explored the organization of the obtained low-dimensional dFC latent representations. We showed how these representations stratify the dynamic organization of the brain patterns as well as the experimental conditions. Finally, we proposed to delve into the proposed brain computational model. We first applied a receptive field analysis to identify preferred directions in the latent space to move from one brain pattern to another. Then, an ablation study was achieved where we virtually inactivated specific brain areas. We demonstrated the model’s efficiency in summarizing consciousness-specific information encoded in key inter-areal connections, as described in the global neuronal workspace theory of consciousness. The proposed framework advocates the possibility of developing an interpretable computational brain model of interest for disorders of consciousness, paving the way for a dynamic diagnostic support tool.

Exposure to maltreatment during childhood is associated with structural changes throughout the brain. However, the structural differences that are most strongly associated with maltreatment remain unclear given the limited number of whole-brain studies. The present study used machine learning to identify if and how brain structure distinguished young adults with and without a history of maltreatment. Young adults (ages 18–21, n = 384) completed an assessment of childhood trauma exposure and a structural MRI as part of the IMAGEN study. Elastic net regularized regression was used to identify the structural features that identified those with a history of maltreatment. A generalizable model that included 7 cortical thicknesses, 15 surface areas, and 5 subcortical volumes was identified (area under the receiver operating characteristic curve = 0.71, p < 0.001). Those with a maltreatment history had reduced surface areas and cortical thicknesses primarily in fronto-temporal regions. This group also had larger cortical thicknesses in occipital regions and surface areas in frontal regions. The results suggest childhood maltreatment is associated with multiple measures of structure throughout the brain. The use of a large sample without exposure to adulthood trauma provides further evidence for the unique contribution of childhood trauma to brain structure. The identified regions overlapped with regions associated with psychopathology in adults with maltreatment histories, which offers insights as to how these disorders manifest.

Non-human primate functional MRI (fMRI) is a growing field in neuroscience. However, there is no standardized method for monkey fMRI data analysis, specifically for data preprocessing. The preprocessing of monkey fMRI data is challenged by several technical and experimental specificities of the monkey research such as artifacts related to body movements or to intracranial leads. Here we propose to address these challenges by developing a new versatile pipeline for macaque fMRI preprocessing. We developed a Python module, Pypreclin, to process raw images using state of the art algorithms embedded in a fully automatic pipeline. To evaluate its robustness, we applied Pypreclin to fMRI data acquired at 3T in both awake and anesthetized macaques, with or without iron oxide contrast agent, using single loop or multichannel phased-array coils, combined or not with intracranial implanted electrodes. We performed both resting-state and auditory evoked fMRI and compared the results of Pypreclin to a previously employed preprocessing pipeline. Pypreclin successfully achieved the registration of the fMRI data to the macaque brain template in all the experimental conditions. Moreover, Pypreclin enables more accurate locations of auditory evoked activations in relation to the gray matter at corrected level in the awake fMRI condition. Finally, using the Primate neuroimaging Data-Exchange open access platform, we could further validate Pypreclin for monkey fMRI images that were acquired at ultra-high fields, from other institutions and using different protocols. Pypreclin is a validated preprocessing tool that adapts to diverse experimental and technical situations of monkey fMRI. Pypreclin code is available on open source data sharing platform. [Display omitted] •Preprocessing of monkey fMRI data is challenged by several technical and experimental specificities of the monkey research.•Pypreclin achieved robust preprocessing on a diverse fMRI data collection as compared to a previous pipeline.•Pypreclin is a new flexible and automatic tool for preprocessing of macaque fMRI data available for the growing community of primate fMRI.

Schizophrenia (SZ) and bipolar disorder (BD) are often conceptualized as “disconnection syndromes,” with substantial evidence of abnormalities in deep white matter tracts, forming the substrates of long-range connectivity, seen in both disorders. However, the study of superficial white matter (SWM) U-shaped short-range tracts remained challenging until recently, although findings from postmortem studies suggest they are likely integral components of SZ and BD neuropathology. This diffusion weighted imaging (DWI) study aimed to investigate SWM microstructure in vivo in both SZ and BD for the first time. We performed whole brain tractography in 31 people with SZ, 32 people with BD and 54 controls using BrainVISA and Connectomist 2.0. Segmentation and labeling of SWM tracts were performed using a novel, comprehensive U-fiber atlas. Analysis of covariances yielded significant generalized fractional anisotropy (gFA) differences for 17 SWM bundles in frontal, parietal, and temporal cortices. Post hoc analyses showed gFA reductions in both patient groups as compared with controls in bundles connecting regions involved in language processing, mood regulation, working memory, and motor function (pars opercularis, insula, anterior cingulate, precentral gyrus). We also found increased gFA in SZ patients in areas overlapping the default mode network (inferior parietal, middle temporal, precuneus), supporting functional hyperconnectivity of this network evidenced in SZ. We thus illustrate that short U-fibers are vulnerable to the pathological processes in major psychiatric illnesses, encouraging improved understanding of their anatomy and function.

Replicating results (i.e. obtaining consistent results using a new independent dataset) is an essential part of good science. As replicability has consequences for theories derived from empirical studies, it is of utmost importance to better understand the underlying mechanisms influencing it. A popular tool for non-invasive neuroimaging studies is functional magnetic resonance imaging (fMRI). While the effect of underpowered studies is well documented, the empirical assessment of the interplay between sample size and replicability of results for task-based fMRI studies remains limited. In this work, we extend existing work on this assessment in two ways. Firstly, we use a large database of 1400 subjects performing four types of tasks from the IMAGEN project to subsample a series of independent samples of increasing size. Secondly, replicability is evaluated using a multi-dimensional framework consisting of 3 different measures: (un)conditional test-retest reliability, coherence and stability. We demonstrate not only a positive effect of sample size, but also a trade-off between spatial resolution and replicability. When replicability is assessed voxelwise or when observing small areas of activation, a larger sample size than typically used in fMRI is required to replicate results. On the other hand, when focussing on clusters of voxels, we observe a higher replicability. In addition, we observe variability in the size of clusters of activation between experimental paradigms or contrasts of parameter estimates within these.