Verifying and refining early statuses in Alzheimer's disease progression: a possibility from deep feature comparison.

Defining the early status of Alzheimer's disease is challenging. Theoretically, the statuses in the Alzheimer's disease continuum are expected to share common features. Here, we explore to verify and refine candidature early statuses of Alzheimer's disease with features learned from deep learning. We train models on brain functional networks to accurately classify between amnestic and non-amnestic mild cognitive impairments and between healthy controls and mild cognitive impairments. The trained models are applied to Alzheimer's disease and subjective cognitive decline groups to suggest feature similarities among the statuses and identify informative subpopulations. The amnestic mild cognitive impairment vs non-amnestic mild cognitive impairments classifier believes that 71.8% of Alzheimer's disease are amnestic mild cognitive impairment. And 73.5% of subjective cognitive declines are labeled as mild cognitive impairments, 88.8% of which are further suggested as "amnestic mild cognitive impairment." Further multimodal analyses suggest that the amnestic mild cognitive impairment-like Alzheimer's disease, mild cognitive impairment-like subjective cognitive decline, and amnestic mild cognitive impairment-like subjective cognitive decline exhibit more Alzheimer's disease -related pathological changes (elaborated ß-amyloid depositions, reduced glucose metabolism, and gray matter atrophy) than non-amnestic mild cognitive impairments -like Alzheimer's disease, healthy control-like subjective cognitive decline, and non-amnestic mild cognitive impairments -like subjective cognitive decline. The test-retest reliability of the subpopulation identification is fair to good in general. The study indicates overall similarity among subjective cognitive decline, amnestic mild cognitive impairment, and Alzheimer's disease and implies their progression relationships. The results support "deep feature comparison" as a potential beneficial framework to verify and refine early Alzheimer's disease status.

Segregation, integration, and balance of large-scale resting brain networks configure different cognitive abilities.

Diverse cognitive processes set different demands on locally segregated and globally integrated brain activity. However, it remains an open question how resting brains configure their functional organization to balance the demands on network segregation and integration to best serve cognition. Here we use an eigenmode-based approach to identify hierarchical modules in functional brain networks and quantify the functional balance between network segregation and integration. In a large sample of healthy young adults (n = 991), we combine the whole-brain resting state functional magnetic resonance imaging (fMRI) data with a mean-filed model on the structural network derived from diffusion tensor imaging and demonstrate that resting brain networks are on average close to a balanced state. This state allows for a balanced time dwelling at segregated and integrated configurations and highly flexible switching between them. Furthermore, we employ structural equation modeling to estimate general and domain-specific cognitive phenotypes from nine tasks and demonstrate that network segregation, integration, and their balance in resting brains predict individual differences in diverse cognitive phenotypes. More specifically, stronger integration is associated with better general cognitive ability, stronger segregation fosters crystallized intelligence and processing speed, and an individual's tendency toward balance supports better memory. Our findings provide a comprehensive and deep understanding of the brain's functioning principles in supporting diverse functional demands and cognitive abilities and advance modern network neuroscience theories of human cognition.

Multiscale functional connectome abnormality predicts cognitive outcomes in subcortical ischemic vascular disease.

Subcortical ischemic vascular disease could induce subcortical vascular cognitive impairments (SVCIs), such as amnestic mild cognitive impairment (aMCI) and non-amnestic MCI (naMCI), or sometimes no cognitive impairment (NCI). Previous SVCI studies focused on focal structural lesions such as lacunes and microbleeds, while the functional connectivity networks (FCNs) from functional magnetic resonance imaging are drawing increasing attentions. Considering remarkable variations in structural lesion sizes, we expect that seeking abnormalities in the multiscale hierarchy of brain FCNs could be more informative to differentiate SVCI patients with varied outcomes (NCI, aMCI, and naMCI). Driven by this hypothesis, we first build FCNs based on the atlases at multiple spatial scales for group comparisons and found distributed FCN differences across different spatial scales. We then verify that combining multiscale features in a prediction model could improve differentiation accuracy among NCI, aMCI, and naMCI. Furthermore, we propose a graph convolutional network to integrate the naturally emerged multiscale features based on the brain network hierarchy, which significantly outperforms all other competing methods. In addition, the predictive features derived from our method consistently emphasize the limbic network in identifying aMCI across the different scales. The proposed analysis provides a better understanding of SVCI and may benefit its clinical diagnosis.

Cortex-Wide Dynamics of Intrinsic Electrical Activities: Propagating Waves and Their Interactions.

Cortical circuits generate patterned activities that reflect intrinsic brain dynamics that lay the foundation for any, including stimuli-evoked, cognition and behavior. However, the spatiotemporal organization properties and principles of this intrinsic activity have only been partially elucidated because of previous poor resolution of experimental data and limited analysis methods. Here we investigated continuous wave patterns in the 0.5-4 Hz (delta band) frequency range on data from high-spatiotemporal resolution optical voltage imaging of the upper cortical layers in anesthetized mice. Waves of population activities propagate in heterogeneous directions to coordinate neuronal activities between different brain regions. The complex wave patterns show characteristics of both stereotypy and variety. The location and type of wave patterns determine the dynamical evolution when different waves interact with each other. Local wave patterns of source, sink, or saddle emerge at preferred spatial locations. Specifically, "source" patterns are predominantly found in cortical regions with low multimodal hierarchy such as the primary somatosensory cortex. Our findings reveal principles that govern the spatiotemporal dynamics of spontaneous cortical activities and associate them with the structural architecture across the cortex.SIGNIFICANCE STATEMENT Intrinsic brain activities, as opposed to external stimulus-evoked responses, have increasingly gained attention, but it remains unclear how these intrinsic activities are spatiotemporally organized at the cortex-wide scale. By taking advantage of the high spatiotemporal resolution of optical voltage imaging, we identified five wave pattern types, and revealed the organization properties of different wave patterns and the dynamical mechanisms when they interact with each other. Moreover, we found a relationship between the emergence probability of local wave patterns and the multimodal structure hierarchy across cortical areas. Our findings reveal the principles of spatiotemporal wave dynamics of spontaneous activities and associate them with the underlying hierarchical architecture across the cortex.

Predicting reading ability from brain anatomy and function: From areas to connections.

Reading is a complex task involving different brain areas. As a crystallized ability, reading is also known to have effects on brain structure and function development. However, there are still open questions about what are the elements of the reading networks and how structural and functional brain measures shape the reading ability. The present study used a data-driven approach to investigate whether reading-related brain structural measures of cortical thickness, myelination, sulcus depth and structural connectivity and functional connectivity from the whole brain can predict individual differences in reading skills. It used different brain measures and performance scores from the Oral Reading Recognition Test (ORRT) measuring reading ability from 998 participants. We revealed reading-related brain areas and connections, and evaluated how well area and connection measures predict reading performance. Interestingly, the combination of all brain measures obtained the best predictions. We further grouped reading-related areas into positive and negative networks, each with four different levels (Core Regions, Extended-Regions 1, 2, 3), representing different correlation levels with the reading scores, and the non-correlated Region irrelevant to reading ability. The Core Regions are composed of areas that are most strongly correlated with reading performance. Insular and frontal opercular cortex, lateral temporal cortex, and early auditory cortex occupy the positive Core Region, while inferior temporal and motor cortex occupy the negative Core Region. Aside from those areas, the present study also found more reading-related areas including visual and language-related areas. In addition, connections predicting reading scores are denser inside the reading-related networks than outside. Together, the present study reveals extended reading networks of the brain and provides an extended data-driven analytical framework to study interpretable brain-behavior relationships, which are transferable also to studying other abilities.

Assessing spatiotemporal variability of brain spontaneous activity by multiscale entropy and functional connectivity.

Brain signaling occurs across a wide range of spatial and temporal scales, and analysis of brain signal variability and synchrony has attracted recent attention as markers of intelligence, cognitive states, and brain disorders. However, current technologies to measure brain signals in humans have limited resolutions either in space or in time and cannot fully capture spatiotemporal variability, leaving it untested whether temporal variability and spatiotemporal synchrony are valid and reliable proxy of spatiotemporal variability in vivo. Here we used optical voltage imaging in mice under anesthesia and wakefulness to monitor cortical voltage activity at both high spatial and temporal resolutions to investigate functional connectivity (FC, a measure of spatiotemporal synchronization), Multi-Scale Entropy (MSE, a measure of temporal variability), and their relationships to Regional Entropy (RE, a measure of spatiotemporal variability). We observed that across cortical space, MSE pattern can largely explain RE pattern at small and large temporal scales with high positive and negative correlation respectively, while FC pattern strongly negatively associated with RE pattern. The time course of FC and small scale MSE tightly followed that of RE, while large scale MSE was more loosely coupled to RE. fMRI and EEG data simulated by reducing spatiotemporal resolution of the voltage imaging data or considering hemodynamics yielded MSE and FC measures that still contained information about RE based on the high resolution voltage imaging data. This suggested that MSE and FC could still be effective measures to capture spatiotemporal variability under limitation of imaging modalities applicable to human subjects. Our results support the notion that FC and MSE are effective biomarkers for brain states, and provide a promising viewpoint to unify these two principal domains in human brain data analysis.

Hierarchical Connectome Modes and Critical State Jointly Maximize Human Brain Functional Diversity.

The brain requires diverse segregated and integrated processing to perform normal functions in terms of anatomical structure and self-organized dynamics with critical features, but the fundamental relationships between the complex structural connectome, critical state, and functional diversity remain unknown. Herein, we extend the eigenmode analysis to investigate the joint contribution of hierarchical modular structural organization and critical state to brain functional diversity. We show that the structural modes inherent to the hierarchical modular structural connectome allow a nested functional segregation and integration across multiple spatiotemporal scales. The real brain hierarchical modular organization provides large structural capacity for diverse functional interactions, which are generated by sequentially activating and recruiting the hierarchical connectome modes, and the critical state can best explore the capacity to maximize the functional diversity. Our results reveal structural and dynamical mechanisms that jointly support a balanced segregated and integrated brain processing with diverse functional interactions, and they also shed light on dysfunctional segregation and integration in neurodegenerative diseases and neuropsychiatric disorders.

Dysfunctions of multiscale dynamic brain functional networks in subjective cognitive decline.

Subjective cognitive decline is potentially the earliest symptom of Alzheimer's disease, whose objective neurological basis remains elusive. To explore the potential biomarkers for subjective cognitive decline, we developed a novel deep learning method based on multiscale dynamical brain functional networks to identify subjective cognitive declines. We retrospectively constructed an internal data set (with 112 subjective cognitive decline and 64 healthy control subjects) to develop and internally validate the deep learning model. Conventional deep learning methods based on static and dynamic brain functional networks are compared. After the model is established, we prospectively collect an external data set (26 subjective cognitive decline and 12 healthy control subjects) for testing. Meanwhile, our method provides monitoring of the transitions between normal and abnormal (subjective cognitive decline-related) dynamical functional network states. The features of abnormal dynamical functional network states are quantified by network and variability metrics and associated with individual cognitions. Our method achieves an area under the receiver operating characteristic curve of 0.807 ± 0.046 in the internal validation data set and of 0.707 (P = 0.007) in the external testing data set, which shows improvements compared to conventional methods. The method further suggests that, at the local level, the abnormal dynamical functional network states are characterized by decreased connectivity strength and increased connectivity variability at different spatial scales. At the network level, the abnormal states are featured by scale-specifically altered modularity and all-scale decreased efficiency. Low tendencies to stay in abnormal states and high state transition variabilities are significantly associated with high general, language and executive functions. Overall, our work supports the deficits in multiscale brain dynamical functional networks detected by the deep learning method as reliable and meaningful neural alternation underpinning subjective cognitive decline.

Randomizing Human Brain Function Representation for Brain Disease Diagnosis.

Resting-state fMRI (rs-fMRI) is an effective tool for quantifying functional connectivity (FC), which plays a crucial role in exploring various brain diseases. Due to the high dimensionality of fMRI data, FC is typically computed based on the region of interest (ROI), whose parcellation relies on a pre-defined atlas. However, utilizing the brain atlas poses several challenges including 1) subjective selection bias in choosing from various brain atlases, 2) parcellation of each subject's brain with the same atlas yet disregarding individual specificity; 3) lack of interaction between brain region parcellation and downstream ROI-based FC analysis. To address these limitations, we propose a novel randomizing strategy for generating brain function representation to facilitate neural disease diagnosis. Specifically, we randomly sample brain patches, thus avoiding ROI parcellations of the brain atlas. Then, we introduce a new brain function representation framework for the sampled patches. Each patch has its function description by referring to anchor patches, as well as the position description. Furthermore, we design an adaptive-selection-assisted Transformer network to optimize and integrate the function representations of all sampled patches within each brain for neural disease diagnosis. To validate our framework, we conduct extensive evaluations on three datasets, and the experimental results establish the effectiveness and generality of our proposed method, offering a promising avenue for advancing neural disease diagnosis beyond the confines of traditional atlas-based methods. Our code is available at https://github.com/mjliu2020/RandomFR.

Hierarchical Graph Convolutional Network Built by Multiscale Atlases for Brain Disorder Diagnosis Using Functional Connectivity.

Functional connectivity network (FCN) data from functional magnetic resonance imaging (fMRI) is increasingly used for the diagnosis of brain disorders. However, state-of-the-art studies used to build the FCN using a single brain parcellation atlas at a certain spatial scale, which largely neglected functional interactions across different spatial scales in hierarchical manners. In this study, we propose a novel framework to perform multiscale FCN analysis for brain disorder diagnosis. We first use a set of well-defined multiscale atlases to compute multiscale FCNs. Then, we utilize biologically meaningful brain hierarchical relationships among the regions in multiscale atlases to perform nodal pooling across multiple spatial scales, namely "Atlas-guided Pooling (AP)." Accordingly, we propose a multiscale-atlases-based hierarchical graph convolutional network (MAHGCN), built on the stacked layers of graph convolution and the AP, for a comprehensive extraction of diagnostic information from multiscale FCNs. Experiments on neuroimaging data from 1792 subjects demonstrate the effectiveness of our proposed method in the diagnoses of Alzheimer's disease (AD), the prodromal stage of AD i.e., mild cognitive impairment (MCI), as well as autism spectrum disorder (ASD), with the accuracy of 88.9%, 78.6%, and 72.7%, respectively. All results show significant advantages of our proposed method over other competing methods. This study not only demonstrates the feasibility of brain disorder diagnosis using resting-state fMRI empowered by deep learning but also highlights that the functional interactions in the multiscale brain hierarchy are worth being explored and integrated into deep learning network architectures for a better understanding of the neuropathology of brain disorders. The codes for MAHGCN are publicly available at "https://github.com/MianxinLiu/ MAHGCN-code."

Multilevel and multifaceted brain response features in spiking, ERP and ERD: experimental observation and simultaneous generation in a neuronal network model with excitation-inhibition balance.

Brain as a dynamic system responds to stimulations with specific patterns affected by its inherent ongoing dynamics. The patterns are manifested across different levels of organization-from spiking activity of neurons to collective oscillations in local field potential (LFP) and electroencephalogram (EEG). The multilevel and multifaceted response activities show patterns seemingly distinct and non-comparable from each other, but they should be coherently related because they are generated from the same underlying neural dynamic system. A coherent understanding of the interrelationships between different levels/aspects of activity features is important for understanding the complex brain functions. Here, based on analysis of data from human EEG, monkey LFP and neuronal spiking, we demonstrated that the brain response activities from different levels of neural system are highly coherent: the external stimulus simultaneously generated event-related potentials, event-related desynchronization, and variation in neuronal spiking activities that precisely match with each other in the temporal unfolding. Based on a biologically plausible but generic network of conductance-based integrate-and-fire excitatory and inhibitory neurons with dense connections, we showed that the multiple key features can be simultaneously produced at critical dynamical regimes supported by excitation-inhibition (E-I) balance. The elucidation of the inherent coherency of various neural response activities and demonstration of a simple dynamical neural circuit system having the ability to simultaneously produce multiple features suggest the plausibility of understanding high-level brain function and cognition from elementary and generic neuronal dynamics. Supplementary Information: The online version contains supplementary material available at 10.1007/s11571-022-09889-w.

Individualized Assessment of Brain Aß Deposition With fMRI Using Deep Learning.

PET-based Alzheimer's disease (AD) assessment has many limitations in large-scale screening. Non-invasive techniques such as resting-state functional magnetic resonance imaging (rs-fMRI) have been proven valuable in early AD diagnosis. This study investigated feasibility of using rs-fMRI, especially functional connectivity (FC), for individualized assessment of brain amyloid-ß deposition derived from PET. We designed a graph convolutional networks (GCNs) and random forest (RF) based integrated framework for using rs-fMRI-derived multi-level FC networks to predict amyloid-ß PET patterns with the OASIS-3 (N = 258) and ADNI-2 (N = 291) datasets. Our method achieved satisfactory accuracy not only in Aß-PET grade classification (for negative, intermediate, and positive grades, with accuracy in the three-class classification as 62.8% and 64.3% on two datasets, respectively), but also in prediction of whole-brain region-level Aß-PET standard uptake value ratios (SUVRs) (with the mean square errors as 0.039 and 0.074 for two datasets, respectively). Model interpretability examination also revealed the contributive role of the limbic network. This study demonstrated high feasibility and reproducibility of using low-cost, more accessible magnetic resonance imaging (MRI) to approximate PET-based diagnosis.

Complexity of cortical wave patterns of the wake mouse cortex.

Rich spatiotemporal dynamics of cortical activity, including complex and diverse wave patterns, have been identified during unconscious and conscious brain states. Yet, how these activity patterns emerge across different levels of wakefulness remain unclear. Here we study the evolution of wave patterns utilizing data from high spatiotemporal resolution optical voltage imaging of mice transitioning from barbiturate-induced anesthesia to wakefulness (N = 5) and awake mice (N = 4). We find that, as the brain transitions into wakefulness, there is a reduction in hemisphere-scale voltage waves, and an increase in local wave events and complexity. A neural mass model recapitulates the essential cellular-level features and shows how the dynamical competition between global and local spatiotemporal patterns and long-range connections can explain the experimental observations. These mechanisms possibly endow the awake cortex with enhanced integrative processing capabilities.

Convolutional neural network to predict IDH mutation status in glioma from chemical exchange saturation transfer imaging at 7 Tesla.

Background and goal: Noninvasive prediction of isocitrate dehydrogenase (IDH) mutation status in glioma guides surgical strategies and individualized management. We explored the capability on preoperatively identifying IDH status of combining a convolutional neural network (CNN) and a novel imaging modality, ultra-high field 7.0 Tesla (T) chemical exchange saturation transfer (CEST) imaging. Method: We enrolled 84 glioma patients of different tumor grades in this retrospective study. Amide proton transfer CEST and structural Magnetic Resonance (MR) imaging at 7T were performed preoperatively, and the tumor regions are manually segmented, leading to the "annotation" maps that offers the location and shape information of the tumors. The tumor region slices in CEST and T1 images were further cropped out as samples and combined with the annotation maps, which were inputted to a 2D CNN model for generating IDH predictions. Further comparison analysis to radiomics-based prediction methods was performed to demonstrate the crucial role of CNN for predicting IDH based on CEST and T1 images. Results: A fivefold cross-validation was performed on the 84 patients and 4090 slices. We observed a model based on only CEST achieved accuracy of 74.01% ± 1.15%, and the area under the curve (AUC) of 0.8022 ± 0.0147. When using T1 image only, the prediction performances dropped to accuracy of 72.52% ± 1.12% and AUC of 0.7904 ± 0.0214, which indicates no superiority of CEST over T1. However, when we combined CEST and T1 together with the annotation maps, the performances of the CNN model were further boosted to accuracy of 82.94% ± 1.23% and AUC of 0.8868 ± 0.0055, suggesting the importance of a joint analysis of CEST and T1. Finally, using the same inputs, the CNN-based predictions achieved significantly improved performances above those from radiomics-based predictions (logistic regression and support vector machine) by 10% to 20% in all metrics. Conclusion: 7T CEST and structural MRI jointly offer improved sensitivity and specificity of preoperative non-invasive imaging for the diagnosis of IDH mutation status. As the first study of CNN model on imaging acquired at ultra-high field MR, our results could demonstrate the potential of combining ultra-high-field CEST and CNN for facilitating decision-making in clinical practice. However, due to the limited cases and B1 inhomogeneities, the accuracy of this model will be improved in our further study.

S3R: Shape and Semantics-Based Selective Regularization for Explainable Continual Segmentation Across Multiple Sites.

In clinical practice, it is desirable for medical image segmentation models to be able to continually learn on a sequential data stream from multiple sites, rather than a consolidated dataset, due to storage cost and privacy restrictions. However, when learning on a new site, existing methods struggle with a weak memorizability for previous sites with complex shape and semantic information, and a poor explainability for the memory consolidation process. In this work, we propose a novel Shape and Semantics-based Selective Regularization ( [Formula: see text]) method for explainable cross-site continual segmentation to maintain both shape and semantic knowledge of previously learned sites. Specifically, [Formula: see text] method adopts a selective regularization scheme to penalize changes of parameters with high Joint Shape and Semantics-based Importance (JSSI) weights, which are estimated based on the parameter sensitivity to shape properties and reliable semantics of the segmentation object. This helps to prevent the related shape and semantic knowledge from being forgotten. Moreover, we propose an Importance Activation Mapping (IAM) method for memory interpretation, which indicates the spatial support for important parameters to visualize the memorized content. We have extensively evaluated our method on prostate segmentation and optic cup and disc segmentation tasks. Our method outperforms other comparison methods in reducing model forgetting and increasing explainability. Our code is available at https://github.com/jingyzhang/S3R.

A common spectrum underlying brain disorders across lifespan revealed by deep learning on brain networks.

Brain disorders in the early and late life of humans potentially share pathological alterations in brain functions. However, the key neuroimaging evidence remains unrevealed for elucidating such commonness and the relationships among these disorders. To explore this puzzle, we build a restricted single-branch deep learning model, using multi-site functional magnetic resonance imaging data (N = 4,410, 6 sites), for classifying 5 different early- and late-life brain disorders from healthy controls (cognitively unimpaired). Our model achieves 62.6 ± 1.9% overall classification accuracy and thus supports us in detecting a set of commonly affected functional subnetworks, including default mode, executive control, visual, and limbic networks. In the deep-layer representation of data, we observe young and aging patients with disorders are continuously distributed, which is in line with the clinical concept of the "spectrum of disorders." The relationships among brain disorders from the revealed spectrum promote the understanding of disorder comorbidities and time associations in the lifespan.

Cortex-wide spontaneous activity non-linearly steers propagating sensory-evoked activity in awake mice.

The brain responds highly variably to identical sensory inputs, but there is no consensus on the nature of this variability. We explore this question using cortex-wide optical voltage imaging and whisker stimulation in awake mice. Clustering analysis reveals that the sensory-evoked activity propagates over the cortex via distinct pathways associated with distinct behavioral states. The pathway taken by each trial is independent of the level of primary sensory-evoked activation but is partially predictable by the spatiotemporal features of the preceding cortical spontaneous activity patterns. The sensory inputs reduce trial-to-trial variability in brain activity and alter temporal autocorrelation in spatial activity pattern evolutions, suggesting non-linear interactions between evoked activities and spontaneous activities. Further, evoked activities and spontaneous activities occupy different positions in the state space, suggesting that sensory inputs can intricately interact with the internal state to generate large-scale evoked activity patterns not frequented by spontaneous brain states.

Predicting Brain Amyloid-ß PET Grades with Graph Convolutional Networks Based on Functional MRI and Multi-Level Functional Connectivity.

BACKGROUND: The detection of amyloid-ß (Aß) deposition in the brain provides crucial evidence in the clinical diagnosis of Alzheimer's disease (AD). However, the current positron emission tomography (PET)-based brain Aß examination suffers from the problems of coarse visual inspection (in many cases, with 2-class stratification) and high scanning cost. OBJECTIVE: 1) To characterize the non-binary Aß deposition levels in the AD continuum based on clustering of PET data, and 2) to explore the feasibility of predicting individual Aß deposition grades with non-invasive functional magnetic resonance imaging (fMRI). METHODS: 1) Individual whole-brain Aß-PET images from the OASIS-3 dataset (N = 258) were grouped into three clusters (grades) with t-SNE and k-means. The demographical data as well as global and regional standard uptake value ratios (SUVRs) were compared among the three clusters with Chi-square tests or ANOVA tests. 2) From resting-state fMRI, both conventional functional connectivity (FC) and high-order FC networks were constructed and the topological architectures of the two networks were jointly learned with graph convolutional networks (GCNs) to predict the Aß-PET grades for each individual. RESULTS: We found three clearly separated clusters, indicating three Aß-PET grades. There were significant differences in gender, age, cognitive ability, APOE type, as well as global and regional SUVRs among the three grades we found. The prediction of Aß-PET grades with GCNs on FC for the 258 samples in the AD continuum reached a satisfactory averaged accuracy (78.8%) in the two-class classification tasks. CONCLUSION: The results demonstrated the feasibility of using deep learning on a non-invasive brain functional imaging technique to approximate PET-based Aß deposition grading.

Individual Cortical Entropy Profile: Test-Retest Reliability, Predictive Power for Cognitive Ability, and Neuroanatomical Foundation.

The entropy profiles of cortical activity have become novel perspectives to investigate individual differences in behavior. However, previous studies have neglected foundational aspects of individual entropy profiles, that is, the test-retest reliability, the predictive power for cognitive ability in out-of-sample data, and the underlying neuroanatomical basis. We explored these issues in a large young healthy adult dataset (Human Connectome Project, N = 998). We showed the whole cortical entropy profile from resting-state functional magnetic resonance imaging is a robust personalized measure, while subsystem profiles exhibited heterogeneous reliabilities. The limbic network exhibited lowest reliability. We tested the out-of-sample predictive power for general and specific cognitive abilities based on reliable cortical entropy profiles. The default mode and visual networks are most crucial when predicting general cognitive ability. We investigated the anatomical features underlying cross-region and cross-individual variations in cortical entropy profiles. Cortical thickness and structural connectivity explained spatial variations in the group-averaged entropy profile. Cortical folding and myelination in the attention and frontoparietal networks determined predominantly individual cortical entropy profile. This study lays foundations for brain-entropy-based studies on individual differences to understand cognitive ability and related pathologies. These findings broaden our understanding of the associations between neural structures, functional dynamics, and cognitive ability.

The reliability and psychometric structure of Multi-Scale Entropy measured from EEG signals at rest and during face and object recognition tasks.

BACKGROUND: Multi-Scale Entropy (MSE) is a widely used marker of Brain Signal Complexity (BSC) at multiple temporal scales. METHODOLOGICAL IMPROVEMENT: There is no systematic research addressing the psychometric quality and reliability of MSE. It is unknown how recording conditions of EEG signals affect individual differences in MSE. These gaps can be addressed by means of Structural Equation Modeling (SEM). RESULTS: Based on a large sample of 210 young adults, we estimated measurement models for MSE derived from multiple epochs of EEG signal measured during resting state conditions with closed and open eyes, and during a visual task with multiple experimental manipulations. Factor reliability estimates, quantified by the McDonald's ω coefficient, are high at lower and acceptable at higher time scales. Above individual differences in signal entropy observed across all recording conditions, persons specifically differ with respect to their BSC in open eyes resting state condition as compared with closed eyes state, and in task processing state MSE as compared with resting state. COMPARISON WITH EXISTING METHODS: By means of SEM, we decomposed individual differences in BSC into different factors depending on the recording condition of EEG signals. This goes beyond existing methods that aim at estimating average MSE differences across recording conditions, but do not address whether individual differences are additionally affected by the type of EEG recording condition. CONCLUSION: Eyes closed and open and task conditions strongly influence individual differences in MSE. We provide recommendations for future studies aiming to address BSC using MSE as a neural marker of cognitive abilities.