bioRxiv Science⌕ Search

Biology subjects

Bellec, P.

Publications and source records attributed to Bellec, P..

At least 19 recordsLinked to original sources
bioRxiv2023

Behavioral Imitation with Artificial Neural Networks Leads to Personalized Models of Brain Dynamics During Videogame Play

Videogames provide a promising framework to understand brain activity in a rich, engaging, and active environment, in contrast to mostly passive tasks currently dominating the field, such as image viewing. Analyzing videogames neuroimaging data is however challenging, and relies on time-intensive manual annotations of game events, based on somewhat arbitrary rules. Here, we introduce an innovative approach using Artificial Neural networks (ANN) and brain encoding techniques to generate activation maps associated with videogame behaviour using functional magnetic resonance imaging (fMRI). As individual behavior is highly variable across subjects in complex environments, we hypothesized that ANNs need to account for subject-specific behavior to properly capture brain dynamics. In this study, we used data collected while subjects played Shinobi III: Return of the Ninja Master (Sega, 1993), an action-platformer videogame. Using imitation learning, we trained an ANN to play the game while closely replicating the unique gameplay style of individual participants. We found that hidden layers of our imitation learning model successfully encoded task-relevant neural representations, and predicted individual brain dynamics with higher accuracy than models trained on other subjects gameplay. Individual-specific models also outperformed a number of baselines to predict brain activity, such as pixel inputs, or button presses. The highest correlations between layer activations and brain signals were observed in biologically plausible brain areas, i.e. somatosensory, attention, and visual networks. Our results demonstrate that training subject-specific ANNs can successfully uncover brain correlates of complex behaviour. This new method combining imitation learning, brain imaging, and videogames opens new research avenues to study decision-making and psychomotor task solving in naturalistic and complex environments.

neuroscience↗
bioRxiv2023

Aligning the activity of artificial and biological neural networks to build personalised models of auditory processing in a massive individual fMRI dataset

Artificial neural networks trained in the field of artificial intelligence (AI) have emerged as key tools to model brain processes, sparking the idea of aligning network representations with brain dynamics to enhance performance on AI tasks. While this concept has gained support in the visual domain, we investigate here the feasibility of creating auditory artificial neural models directly aligned with individual brain activity. This objective raises major computational challenges, as models have to be trained directly with brain data, which is typically collected at a much smaller scale than data used to train AI models. We aimed to answer two key questions: (1) Can brain alignment of auditory models lead to improved brain encoding for novel, previously unseen stimuli? (2) Can brain alignment lead to generalisable representations of auditory signals that are useful for solving a variety of complex auditory tasks? To answer these questions, we relied on two massive datasets: a deep phenotyping dataset from the Courtois neuronal modelling project, where six subjects watched four seasons (36 hours) of the Friends TV series in functional magnetic resonance imaging and the HEAR benchmark, a large battery of downstream auditory tasks. We fine-tuned SoundNet, a small pretrained convolutional neural network with [~]2.5M parameters. Aligning SoundNet with brain data from three seasons of Friends led to substantial improvement in brain encoding in the fourth season, extending beyond auditory and visual cortices. We also observed consistent performance gains on the HEAR benchmark, particularly for tasks with limited training data, where brain-aligned models performed comparably to the best-performing models regardless of size. We finally compared individual and group models, finding that individual models often matched or outperformed group models in both brain encoding and downstream task performance, highlighting the data efficiency of fine-tuning with individual brain data. Our results demonstrate the feasibility of aligning artificial neural network representations with individual brain activity during auditory processing, and suggest that this alignment is particularly beneficial for tasks with limited training data. Future research is needed to establish whether larger models can achieve even better performance and whether the observed gains extend to other tasks, particularly in the context of few shot learning.

neuroscience↗
bioRxiv2023

A reproducible benchmark of resting-state fMRI denoising strategies using fMRIPrep and Nilearn

Reducing contributions from non-neuronal sources is a crucial step in functional magnetic resonance imaging (fMRI) connectivity analyses. Many viable strategies for denoising fMRI are used in the literature, and practitioners rely on denoising benchmarks for guidance in the selection of an appropriate choice for their study. However, fMRI denoising software is an ever-evolving field, and the benchmarks can quickly become obsolete as the techniques or implementations change. In this work, we present a denoising benchmark featuring a range of denoising strategies, datasets and evaluation metrics for connectivity analyses, based on the popular fMRIprep software. The benchmark is implemented in a fully reproducible framework, where the provided research objects enable readers to reproduce or modify core computations, as well as the figures of the article using the Jupyter Book project and the Neurolibre reproducible preprint server (https://neurolibre.org/). We demonstrate how such a reproducible benchmark can be used for continuous evaluation of research software, by comparing two versions of the fMRIprep software package. The majority of benchmark results were consistent with prior literature. Scrubbing, a technique which excludes time points with excessive motion, combined with global signal regression, is generally effective at noise removal. Scrubbing however disrupts the continuous sampling of brain images and is incompatible with some statistical analyses, e.g. auto-regressive modeling. In this case, a simple strategy using motion parameters, average activity in select brain compartments, and global signal regression should be preferred. Importantly, we found that certain denoising strategies behave inconsistently across datasets and/or versions of fMRIPrep, or had a different behavior than in previously published benchmarks. This work will hopefully provide useful guidelines for the fMRIprep users community, and highlight the importance of continuous evaluation of research methods. Our reproducible benchmark infrastructure will facilitate such continuous evaluation in the future, and may also be applied broadly to different tools or even research fields.

neuroscience↗
bioRxiv2022

Interpretable brain decoding from sensations to cognition to action: graph neural networks reveal the representational hierarchy of human cognition

Inter-subject modeling of cognitive processes has been a challenging task due to large individual variability in brain structure and function. Graph neural networks (GNNs) provide a potential way to project subject-specific neural responses onto a common representational space by effectively combining local and distributed brain activity through connectome-based constraints. Here we provide in-depth interpretations of biologically-constrained GNNs (BGNNs) that reach state-of-the-art performance in several decoding tasks and reveal inter-subject aligned neural representations underpinning cognitive processes. Specifically, the model not only segregates brain responses at different stages of cognitive tasks, e.g. motor preparation and motor execution, but also uncovers functional gradients in neural representations, e.g. a gradual progression of visual working memory (VWM) from sensory processing to cognitive control and towards behavioral abstraction. Moreover, the multilevel representations of VWM exhibit better inter-subject alignment in brain responses, higher decoding of cognitive states, and strong phenotypic and genetic correlations with individual behavioral performance. Our work demonstrates that biologically constrained deep-learning models have the potential towards both cognitive and biological fidelity in cognitive modeling, and open new avenues to interpretable functional gradients of brain cognition in a wide range of cognitive neuroscience questions. HighlightsO_LIBGNN improves inter-subject alignment in task-evoked responses and promotes brain decoding C_LIO_LIBGNN captures functional gradients of brain cognition, transforming from sensory processing to cognition to representational abstraction. C_LIO_LIBGNNs with diffusion or functional connectome constraints better predict human behaviors compared to other graph architectures C_LI Graphic Abstract O_FIG O_LINKSMALLFIG WIDTH=200 HEIGHT=181 SRC="FIGDIR/small/510241v1_ufig1.gif" ALT="Figure 1"> View larger version (71K): org.highwire.dtl.DTLVardef@1b34a13org.highwire.dtl.DTLVardef@1c45ca2org.highwire.dtl.DTLVardef@9db47dorg.highwire.dtl.DTLVardef@1b4916d_HPS_FORMAT_FIGEXP M_FIG C_FIG Multilevel representational learning of cognitive processes using BGNN

neuroscience↗
bioRxiv2021

Deep learning models of cognitive processes constrained by human brain connectomes

Decoding cognitive processes from recordings of brain activity has been an active topic in neuroscience research for decades. Traditional decoding studies focused on pattern classification in specific regions of interest and averaging brain activity over many trials. Recently, brain decoding with graph neural networks has been shown to scale at fine temporal resolution and on the full brain, achieving state-of-the-art performance on the human connectome project benchmark. The reason behind this success is likely the strong inductive connectome prior that enables the integration of distributed patterns of brain activity. Yet, the nature of such inductive bias is still poorly understood. In this work, we investigate the impact of the inclusion of multiple path lengths (through high-order graph convolution), the homogeneity of brain parcels (graph nodes), and the type of interactions (graph edges). We evaluate the decoding models on a large population of 1200 participants, under 21 different experimental conditions, acquired from the Human Connectome Project database. Our findings reveal that the optimal choice for large-scale cognitive decoding is to propagate neural dynamics within empirical functional connectomes and integrate brain dynamics using high-order graph convolutions. In this setting, the model exhibits high decoding accuracy and robustness against adversarial attacks on the graph architecture, including randomization in functional connectomes and lesions in targeted brain regions and networks. The trained model relies on biologically meaningful features for the prediction of cognitive states and generates task-specific graph representations resembling task-evoked activation maps. These results demonstrate that a full-brain integrative model is critical for the large-scale brain decoding. Our study establishes principles of how to effectively leverage human connectome constraints in deep graph neural networks, providing new avenues to study the neural substrates of human cognition at scale.

neuroscience↗
bioRxiv2021

Representational learning of brain responses in executive function and higher-order cognition using deep graph convolutions

Brain decoding aims to infer human cognition from recordings of neural activity using modern neuroimaging techniques. Studies so far often concentrated on a limited number of cognitive states and aimed to classifying patterns of brain activity within a local area. This procedure demonstrated a great success on classifying motor and sensory processes but showed limited power over higher cognitive functions. In this work, we investigate a high-order graph convolution model, named ChebNet, to model the segregation and integration organizational principles in neural dynamics, and to decode brain activity across a large number of cognitive domains. By leveraging our prior knowledge on brain organization using a graph-based model, ChebNet graph convolution learns a new representation from task-evoked neural activity, which demonstrates a highly predictive signature of cognitive states and task performance. Our results reveal that between-network integration significantly boosts the decoding of high-order cognition such as visual working memory tasks, while the segregation of localized brain activity is sufficient to classify motor and sensory processes. Using twin and family data from the Human Connectome Project (n = 1,070), we provide evidence that individual variability in the graph representations of working-memory tasks are under genetic control and strongly associated with participants in-scanner behaviors. These findings uncover the essential role of functional integration in brain decoding, especially when decoding high-order cognition other than sensory and motor functions. TeaserO_LIModelling functional integration through graph convolution is a necessary step towards decoding high-order human cognition. C_LI Significance statementOver the past two decades, many studies have applied multivariate pattern analysis to decode what task a human participant is performing, based on a scan of her brain. The vast majority of these studies have however concentrated on select regions and a specific domain, because of the computational complexity of handling full brain data in a multivariate model. With the fast progress in the field of deep learning, it is now possible to decode a variety of cognitive domains simultaneously using a full-brain model. By leveraging our prior knowledge on brain organization using a graph-based model, we uncovered different organizational principles in brain decoding for motor execution and high-order cognition by modelling functional integration through graph convolution.

neuroscience↗
bioRxiv2020

Transferability of Brain decoding using GraphConvolutional Networks

Transfer learning has been a very active research topic in natural image processing. But few studies have reported notable benefits of transfer learning on medical imaging. In this study, we sought to investigate the transferability of deep artificial neural networks (DNN) in brain decoding, i.e. inferring brain state using fMRI brain response over a short window. Instead of using pretrained models from ImageNet, we trained our base model on a large-scale neuroimaging dataset using graph convolutional networks (GCN). The transferability of learned graph representations were evaluated under different circumstances, including knowledge transfer across cognitive domains, between different groups of subjects, and among different sites using distinct scanning sequences. We observed a significant performance boost via transfer learning either from the same cognitive domain or from other task domains. But the transferability was highly impacted by the scanner site effect. Specifically, for datasets acquired from the same site using the same scanning sequences, using transferred features highly improved the decoding performance. By contrast, the transferability of representations highly decreased between different sites, with the performance boost reducing from 20% down to 7% for the Motor task and decreasing from 15% to 5% for Working-memory tasks. Our results indicate that in contrast to natural images, the scanning condition, instead of task domain, has a larger impact on feature transfer for medical imaging. With other advanced tools such as layer-wise fine-tuning, the decoding performance can be further improved through learning more site-specific high-level features while retaining the transferred low-level representations of brain dynamics.

neuroscience↗
bioRxiv2020

Predicting future cognitive decline from non-brain and multimodal brain imaging data in healthy and pathological aging

Cognitive decline occurs in healthy and pathological aging, and both may be preceded by subtle changes in the brain -- offering a basis for cognitive predictions. Previous work has largely focused on predicting a diagnostic label from structural brain imaging. Our study broadens the scope of applications to cognitive decline in healthy aging by predicting future decline as a continuous trajectory, rather than a diagnostic label. Furthermore, since brain structure as well as function changes in aging, it is reasonable to expect predictive gains when using multiple brain imaging modalities. Here, we tested whether baseline multimodal neuroimaging data improve the prediction of future cognitive decline in healthy and pathological aging. Non-brain data (including demographics and clinical and neuropsychological scores) were combined with structural and functional connectivity MRI data from the OASIS-3 project (N = 662; age = 46 - 96y). The combined input data was entered into cross-validated multi-target random forest models to predict future cognitive decline (measured by the Clinical Dementia Rating and the Mini-Mental State Examination), on average 5.8y into the future. The analysis was preregistered and all analysis code is publicly available. We found that combining non-brain with structural data improved the continuous prediction of future cognitive decline (best test-set performance: R2 = 0.42) and that cognitive performance, daily functioning, and subcortical volume drove the performance of our model. In contrast, including functional connectivity did not improve predictive accuracy. In the future, the prognosis of age-related cognitive decline may enable earlier and more effective cognitive, pharmacological, and behavioral interventions to be tailored to the individual.

neuroscience↗
bioRxiv2020

Reproducible functional connectivity endophenotype confers high risk of ASD diagnosis in a subset of individuals

Functional connectivity (FC) analyses of individuals with autism spectrum disorder (ASD) have established robust alterations of brain connectivity at the group level. Yet, the translation of these imaging findings into robust markers of individual risk is hampered by the extensive heterogeneity among ASD individuals. Here, we report an FC endophenotype that confers a greater than 7-fold risk increase of ASD diagnosis, yet is still identified in an estimated 1 in 200 individuals in the general population. By focusing on a subset of individuals with ASD and highly predictive FC alterations, we achieved a greater than 3-fold increase in risk over previous predictive models. The identified FC risk endophenotype was characterized by underconnectivity of transmodal brain networks and generalized to independent data. Our results demonstrate the ability of a highly targeted prediction model to meaningfully decompose part of the heterogeneity of the autism spectrum. The identified FC signature may help better delineate the multitude of etiological pathways and behavioural symptoms that challenge our understanding of the autism spectrum.

neuroscience↗
bioRxiv2020

Functional Annotation of Human Cognitive States using Deep Graph Convolution

A key goal in neuroscience is to understand brain mechanisms of cognitive functions. An emerging approach is "brain decoding", which consists of inferring a set of experimental conditions performed by a participant, using pattern classification of brain activity. Few works so far have attempted to train a brain decoding model that would generalize across many different cognitive tasks drawn from multiple cognitive domains. To tackle this problem, we proposed a multidomain brain decoder that automatically learns the spatiotemporal dynamics of brain response within a short time window using a deep learning approach. We evaluated the decoding model on a large population of 1200 participants, under 21 different experimental conditions spanning six different cognitive domains, acquired from the Human Connectome Project task-fMRI database. Using a 10s window of fMRI response, the 21 cognitive states were identified with a test accuracy of 90% (chance level 4.8%). Performance remained good when using a 6s window (82%). It was even feasible to decode cognitive states from a single fMRI volume (720ms), with the performance following the shape of the hemodynamic response. Moreover, a saliency map analysis demonstrated that the high decoding performance was driven by the response of biologically meaningful brain regions. Together, we provide an automated tool to annotate human brain activity with fine temporal resolution and fine cognitive granularity. Our model shows potential applications as a reference model for domain adaptation, possibly making contributions in a variety of domains, including neurological and psychiatric disorders.

neuroscience↗
bioRxiv2020

Subtypes of functional connectivity associate robustly with ASD diagnosis

Our understanding of the changes in functional brain organization in autism is hampered by the extensive heterogeneity that characterizes this neurodevelopmental disorder. Data driven clustering offers a straightforward way to decompose this heterogeneity into subtypes of distinguishable connectivity types and promises an unbiased framework to investigate behavioural symptoms and causative genetic factors. Yet the robustness and generalizability of these imaging subtypes is unknown. Here, we show that unsupervised functional connectivity subtypes are moderately associated with the clinical diagnosis of autism, and that these associations generalize to independent replication data. We found that subtypes identified robust patterns of functional connectivity, but that a discrete assignment of individuals to these subtypes was not supported by the data. Our results support the use of data driven subtyping as a data dimensionality reduction technique, rather than to establish clinical categories.

neuroscience↗
bioRxiv2020

Creation of an Open Science Dataset from PREVENT-AD, a Longitudinal Cohort Study of Pre-symptomatic Alzheimer's Disease.

To move Alzheimer Disease (AD) research forward it is essential to collect data from large cohorts, but also make such data available to the global research community. We describe the creation of an open science dataset from the PREVENT-AD (PResymptomatic EValuation of Experimental or Novel Treatments for AD) cohort, composed of cognitively unimpaired older individuals with a parental or multiple-sibling history of AD. From 2011 to 2017, 386 participants were enrolled (mean age 63 years old {+/-} 5) for sustained investigation among whom 349 have retrospectively agreed to share their data openly. Repositories are findable through the unified interface of the Canadian Open Neuroscience Platform (https://portal.conp.ca/) and contain up to five years of longitudinal imaging data, cerebral fluid biochemistry, neurosensory capacities, cognitive, genetic, and medical information. Imaging data can be accessed openly at https://openpreventad.loris.ca while most of the other information, sensitive by nature, is accessible by qualified researchers at https://registeredpreventad.loris.ca. In addition to being a living resource for continued data acquisition, PREVENT-AD offers opportunities to facilitate understanding of AD pathogenesis.

neuroscience↗
bioRxiv2020

Unraveling reproducible dynamic states of individual brain functional parcellation

Data-driven parcellations are widely used for exploring the functional organization of the brain, and also for reducing the high dimensionality of fMRI data. Despite the flurry of methods proposed in the literature, functional brain parcellations are not highly reproducible at the level of individual subjects, even with very long acquisitions. Some brain areas are also more difficult to parcellate than others, with association heteromodal cortices being the most challenging. An important limitation of classical parcellations is that they are static, i.e. they neglect dynamic reconfigurations of brain networks. In this paper, we proposed a new method to identify dynamic states of parcellations, which we hypothesized would improve reproducibility over static parcellation approaches. For a series of seed voxels in the brain, we applied a cluster analysis to regroup short (3 minutes) time windows into "states" with highly similar seed parcels. We splitted individual time series of the Midnight scan club sample into two independent sets of 2.5 hours (test and retest). We found that average within-state parcellations, called stability maps, were highly reproducible (over .9 test-retest spatial correlation in many instances) and subject specific (fingerprinting accuracy over 70% on average) between test and retest. Consistent with our hypothesis, seeds in heteromodal cortices (posterior and anterior cingulate) showed a richer repertoire of states than unimodal (visual) cortex. Taken together, our results indicate that static functional parcellations are incorrectly averaging well-defined and distinct dynamic states of brain parcellations. This work calls to revisit previous methods based on static parcellations, which includes the majority of published network analyses of fMRI data. Our method may, thus, impact how researchers model the rich interactions between brain networks in health and disease.

neuroscience↗
bioRxiv2019

Neuropsychiatric mutations delineate functional brain connectivity dimensions contributing to autism and schizophrenia

16p11.2 and 22q11.2 Copy Number Variants (CNVs) confer high risk for Autism Spectrum Disorder (ASD), schizophrenia (SZ), and Attention-Deficit-Hyperactivity-Disorder (ADHD), but their impact on functional connectivity (FC) remains unclear. We analyzed resting-state functional magnetic resonance imaging data from 101 CNV carriers, 755 individuals with idiopathic ASD, SZ, or ADHD and 1,072 controls. We used CNV FC-signatures to identify dimensions contributing to complex idiopathic conditions. CNVs had large mirror effects on FC at the global and regional level. Thalamus, somatomotor, and posterior insula regions played a critical role in dysconnectivity shared across deletions, duplications, idiopathic ASD, SZ but not ADHD. Individuals with higher similarity to deletion FC-signatures exhibited worse cognitive and behavioral symptoms. Deletion similarities identified at the connectivity level could be related to the redundant associations observed genome-wide between gene expression spatial patterns and FC-signatures. Results may explain why many CNVs affect a similar range of neuropsychiatric symptoms.

neuroscience↗
bioRxiv2018

Multivariate consistency of resting-state fMRI connectivity maps acquired on a single individual over 2.5 years, 13 sites and 3 vendors

Studies using resting-state functional magnetic resonance imaging (rsfMRI) are increasingly collecting data at multiple sites in order to speed up recruitment or increase sample size. The main objective of this study was to assess the long-term consistency of rsfMRI connectivity maps derived at multiple sites and vendors using the Canadian Dementia Imaging Protocol (CDIP, www.cdip-pcid.ca). Nine to ten minutes of functional BOLD images were acquired from an adult cognitively healthy volunteer scanned repeatedly at 13 Canadian sites on three scanner makes (General Electric, Philips and Siemens) over the course of 2.5 years. The consistency (spatial Pearsons correlation) of rsfMRI connectivity maps for seven canonical networks ranged from about 0.4-0.8 (intra-site) to 0.3-0.8 (inter-vendor), with a negligible effect of time. We noted systematic differences in data quality across vendors, which may also explain some of these results. We also pooled the long-term longitudinal data with a single-site, short-term (1 month) data sample acquired on 26 subjects (10 scans per subject), called HNU1. Using randomly selected pairs of scans from each subject, we quantified the ability of a data-driven unsupervised cluster analysis to match two scans of the same subjects. In this \"fingerprinting\" experiment, we found that scans from the Canadian subject (Csub) could be matched with high accuracy intra-site (>95% for some networks), but that the accuracy decreased substantially for scans drawn from different sites and vendors, while still remaining in the range of accuracies observed in HNU1. Overall, our results demonstrate good multivariate stability of rsfMRI measures over several years, but substantial impact of scanning site and vendors. How detrimental these effects are will depend on the application, yet improving methods for harmonizing multisite analysis is an important area for future work.\n\nHIGHLIGHTSO_LIConsistency of rsfMRI connectivity over 2.5 years, 13 sites and 3 scanner vendors\nC_LIO_LITime elapsed between scans had negligible effect on consistency\nC_LIO_LIConsistency decreased due to site and vendor differences\nC_LIO_LIAccuracy of connectivity fingerprints decreased due to site and vendor differences\nC_LI\n\n\n\nO_FIG O_LINKSMALLFIG WIDTH=181 HEIGHT=200 SRC=\"FIGDIR/small/497743v2_ufig1.gif\" ALT=\"Figure 1\">\nView larger version (54K):\norg.highwire.dtl.DTLVardef@109bab7org.highwire.dtl.DTLVardef@1c1720corg.highwire.dtl.DTLVardef@12678e2org.highwire.dtl.DTLVardef@ca494d_HPS_FORMAT_FIGEXP M_FIG Graphical Abstract\n\nC_FIG

neuroscience↗
bioRxiv2018

A signature of cognitive deficits and brain atrophy that is highly predictive of progression to Alzheimer’s dementia

Patients with mild cognitive impairment (MCI) are at risk of progressing to Alzheimers dementia, yet only a fraction of them do. We explore here whether a very high-risk MCI subgroup can be identified using cognitive assessments and structural neuroimaging. A multimodal signature of Alzheimers dementia was first extracted using machine learning tools in the ADNI1 sample, and was comprised of cognitive deficits across multiple domains as well as atrophy in temporal, parietal and occipital regions. We then validated the predictive value of this signature on two MCI cohorts. In ADNI1 (N=235), the presence of the signature predicted progression to dementia over three years with 80.4% positive predictive value, adjusted for a \"typical\" MCI baseline rate of 33% (95.6% specificity, 55.1% sensitivity). These results were replicated in ADNI2 (N=235), with 87.8% adjusted positive predictive value (96.7% specificity, 47.3% sensitivity). Our results demonstrate that, even for widely used markers, marked improvement in positive predictive value over the literature can be achieved by focusing on a subgroup of individuals with similar brain characteristics. The signature can be readily applied for the enrichment of clinical trials.

neuroscience↗
bioRxiv2018

Improving Corticostriatal Parcellation Through Multilevel Bagging with PyBASC

Increasing the reproducibility of neuroimaging measurement addresses a central impediment to the advancement of human neuroscience and its clinical applications. Recent efforts demonstrating variance in functional brain organization within and between individuals shows a need for improving reproducibility of functional parcellations without long scan times. We apply bootstrap aggregation, or bagging, to the problem of improving reproducibility in functional parcellation. We use two large datasets to demonstrate that compared to a standard clustering framework, bagging improves the reproducibility and test-retest reliability of both cortical and subcortical functional parcellations across a range of sites, scanners, samples, scan lengths, clustering algorithms, and clustering parameters (e.g., number of clusters, spatial constraints). With as little as six minutes of scan time, bagging creates more reproducible group and individual level parcellations than standard approaches with twice as much data. This suggests that regardless of the specific parcellation strategy employed, bagging may be a key method for improving functional parcellation and bringing functional neuroimaging-based measurement closer to clinical impact.

neuroscience↗
bioRxiv2018

Data-driven approaches improve Tau-PET biomarkers in Alzheimer’s disease

Previous positron emission tomography (PET) studies have quantified filamentous tau pathology using regions-of-interest (ROIs) based on observations of the topographical distribution of neurofibrillary tangles in post-mortem tissue. However, such approaches may not take full advantage of information contained in neuroimaging data. The present study employs an unsupervised data-driven method to identify spatial patterns of tau-PET distribution, and to compare these patterns to previously published \"pathology-driven\" ROIs. Tau-PET patterns were identified from a discovery sample comprised of 123 normal controls and patients with mild cognitive impairment or Alzheimers disease (AD) dementia from the Swedish BioFINDER cohort, who underwent [18F]AV1451 PET scanning. Associations with cognition were tested in a separate sample of 90 individuals from ADNI. BioFINDER [18F]AV1451 images were entered into a robust voxelwise stable clustering algorithm, which resulted in five clusters. Mean [18F]AV1451 uptake in the data-driven clusters, and in 35 previously published pathology-driven ROIs, was extracted from ADNI [18F]AV1451 scans. We performed linear models comparing [18F]AV1451 signal across all 40 ROIs to several tests of global cognition, adjusting for age, sex and education. Two data-driven ROIs consistently demonstrated the strongest or near-strongest effect sizes across all cognitive tests. Inputting all regions plus demographics into a feature selection routine resulted in selection of two ROIs (one data-driven, one pathology-driven) and education, which together explained 28% of the variance of a global cognitive composite score. Our findings suggest that [18F]AV1451-PET data naturally clusters into spatial patterns that are biologically meaningful and that may offer advantages as clinical tools.

neuroscience↗