Classification of Alzheimer disease, mild cognitive impairment, and normal cognitive status with large-scale network analysis based on resting-state functional MR imaging

Detecting Alzheimer's Disease Stages and Frontotemporal Dementia in Time Courses of Resting-State fMRI Data Using a Machine Learning Approach

Early, accurate diagnosis of neurodegenerative dementia subtypes such as Alzheimer's disease (AD) and frontotemporal dementia (FTD) is crucial for the effectiveness of their treatments. However, distinguishing these conditions becomes challenging when symptoms overlap or the conditions present atypically. Resting-state fMRI (rs-fMRI) studies have demonstrated condition-specific alterations in AD, FTD, and mild cognitive impairment (MCI) compared to healthy controls (HC). Here, we used machine learning to build a diagnostic classification model based on these alterations. We curated all rs-fMRIs and their corresponding clinical information from the ADNI and FTLDNI databases. Imaging data underwent preprocessing, time course extraction, and feature extraction in preparation for the analyses. The imaging features data and clinical variables were fed into gradient-boosted decision trees with fivefold nested cross-validation to build models that classified four groups: AD, FTD, HC, and MCI. The mean and 95% confidence intervals for model performance metrics were calculated using the unseen test sets in the cross-validation rounds. The model built using only imaging features achieved 74.4% mean balanced accuracy, 0.94 mean macro-averaged AUC, and 0.73 mean macro-averaged F1 score. It accurately classified FTD (F1 = 0.99), HC (F1 = 0.99), and MCI (F1 = 0.86) fMRIs but mostly misclassified AD scans as MCI (F1 = 0.08). Adding clinical variables to model inputs raised balanced accuracy to 91.1%, macro-averaged AUC to 0.99, macro-averaged F1 score to 0.92, and improved AD classification accuracy (F1 = 0.74). In conclusion, a multimodal model based on rs-fMRI and clinical data accurately differentiates AD-MCI vs. FTD vs. HC.

Dynamic graph transformer network via dual-view connectivity for autism spectrum disorder identification

Autism Spectrum Disorder (ASD) is a neurodevelopmental disorder that requires objective and accurate identification methods for effective early intervention. Previous population-based methods via functional connectivity (FC) analysis ignore the differences between positive and negative FCs, which provide the potential information complementarity. And they also require additional information to construct a pre-defined graph. Meanwhile, two challenging demand attentions are the imbalance of performance caused by the class distribution and the inherent heterogeneity of multi-site data. In this paper, we propose a novel dynamic graph Transformer network based on dual-view connectivity for ASD Identification. It is based on the Autoencoders, which regard the input feature as individual feature and without any inductive bias. First, a dual-view feature extractor is designed to extract individual and complementary information from positive and negative connectivity. Then Graph Transformer network is innovated with a hot plugging K-Nearest Neighbor (KNN) algorithm module which constructs a dynamic population graph without any additional information. Additionally, we introduce the PolyLoss function and the Vrex method to address the class imbalance and improve the model's generalizability. The evaluation experiment on 1102 subjects from the ABIDE I dataset demonstrates our method can achieve superior performance over several state-of-the-art methods and satisfying generalizability for ASD identification.

A Method to Estimate Longitudinal Change Patterns in Functional Network Connectivity of the Developing Brain Relevant to Psychiatric Problems, Cognition, and Age

Aim: To develop an approach to evaluate multiple overlapping brain functional change patterns (FCPs) in functional network connectivity (FNC) and apply to study developmental changes in brain function. Introduction: FNC, the network analog of functional connectivity (FC), is commonly used to capture the intrinsic functional relationships among brain networks. Ongoing research on longitudinal changes of intrinsic FC across whole-brain functional networks has proven useful for characterizing age-related changes, but to date, there has been little focus on capturing multivariate patterns of FNC change with brain development. Methods: In this article, we introduce a novel approach to evaluate multiple overlapping FCPs by utilizing FNC matrices. We computed FNC matrices from the large-scale Adolescent Brain Cognitive Development data using fully automated spatially constrained independent component analysis (ICA). We next evaluated changes in these patterns for a 2-year period using a second-level ICA on the FNC change maps. Results: Our proposed approach reveals several highly structured (modular) FCPs and significant results including strong brain FC between visual and sensorimotor domains that increase with age. We also find several FCPs that are associated with longitudinal changes of psychiatric problems, cognition, and age in the developing brain. Interestingly, FCP cross-covariation, reflecting coupling between maximally independent FCPs, also shows significant differences between upper and lower quartile loadings for longitudinal changes in age, psychiatric problems, and cognition scores, as well as baseline age in the developing brain. FCP patterns and results were also found to be highly reliable based on analysis of data collected in a separate scan session. Conclusion: In sum, our results show evidence of consistent multivariate patterns of functional change in emerging adolescents and the proposed approach provides a useful and general tool to evaluate covarying patterns of whole-brain functional changes in longitudinal data. Impact statement In this article, we introduce a novel approach utilizing functional network connectivity (FNC) matrices to estimate multiple overlapping brain functional change patterns (FCPs). The findings demonstrate several well-structured FCPs that exhibit significant changes for a 2-year period, particularly in the functional connectivity between the visual and sensorimotor domains. In addition, we discover several FCPs that are associated with psychopathology, cognition, and age. Finally, our proposed approach for studying age-related FCPs represents a pioneering method that provides a valuable tool for assessing interconnected patterns of whole-brain functional changes in longitudinal data and may be useful to study change over time with applicability to many other areas, including the study of longitudinal changes within diagnostic groups, treatment effects, aging effects, and more.

Analyzing 20 years of Resting-State fMRI Research: Trends and collaborative networks revealed

Resting-state functional magnetic resonance imaging (rs-fMRI), initially proposed by Biswal et al. in 1995, has emerged as a pivotal facet of neuroimaging research. Its ability to examine brain activity during the resting state without the need for explicit tasks or stimuli has made it an integral component of brain imaging studies. In recent years, rs-fMRI has witnessed substantial growth and found widespread application in the investigation of functional connectivity within the brain. To delineate the developmental trajectory of rs-fMRI over the past two decades, we conducted a comprehensive analysis using bibliometric tool Citespace. Our analysis encompassed publication trends, authorship networks, institutional affiliations, international collaborations, as well as emergent themes in references and keywords. Our study reveals a remarkable increase in the volume of rs-fMRI publications over the past two decades, underscoring the burgeoning interest and potential within this field. Harvard University stands out as the institution with the highest number of research papers published in the realm of RS-fMRI, while the United States holds the highest overall influence in this domain. The recent emergence of keywords such as "machine learning" and "default mode," coupled with citation surges in reference to rs-fMRI, have paved new avenues for research within this field. Our study underscores the critical importance of integrating machine learning techniques into rs-fMRI investigations, offering valuable insights into brain function and disease diagnosis. These findings hold profound significance for the field of neuroscience and may furnish insights for future research employing rs-fMRI as a diagnostic tool for a wide array of neurological disorders, thus emphasizing its pivotal role and potential as a tool for investigating brain functionality.

The relationship between APOE genotype, CSF Tau and cognition across the Alzheimer's disease spectrum, moderation and mediation role of insula network connectivity

AIMS

To investigate whether insula network connectivity modulates the relationship between apolipoprotein E (APOE) ε4 genotype, cerebrospinal fluid (CSF) biomarkers (Aβ, Tau, and pTau) and cognition across Alzheimer's disease (AD) spectrum.

METHODS

Forty-six cognitive normal (CN), 35 subjective memory complaint (SMC), 41 mild cognitive impairment (MCI), and 32 AD subjects from the Alzheimer's Disease Neuroimaging Initiative (ADNI) were obtained. Multivariable linear regression analyses were conducted to investigate the main effects and interaction of the APOE genotype and disease status on the insula functional connectivity (IFC) network. Mediation and moderation analysis were performed to investigate whether IFC strengths regulate the association between APOE genotype, CSF biomarkers and cognition. Additionally, the support vector machine (SVM) model integrating APOE genotype, CSF biomarkers, and neuroimaging biomarkers (insula volumes and altered regional IFCs) was used to classify the AD spectrum.

RESULTS

The interactive effect of the APOE genotype and disease on the insula network was found in the left medial superior frontal gyrus (SFGmed.L), right anterior medial prefrontal cortex (aMPFC.R), and bilateral thalamus (THA.B). The functional connectivities (FCs) in the left insula (LIns) connecting with the left posterior middle temporal gyrus (pMTG.L), SFGmed.L, and right lingual gyrus (LING.R) were correlated with cognition. LIns-SFGmed.L and LIns-pMTG.L FCs could moderate the effects of Tau on cognition. Furthermore, LIns-SFGmed.L FC may suppress the association between APOE genotype and cognition. More importantly, the integrated biomarkers from the SVM model yielded strong powers for classifying the AD spectrum.

CONCLUSIONS

Insula functional connectivity regulated the association between APOE genotype, CSF Tau and cognition and provided stage-dependent biomarkers for early differentiation of the AD spectrum. The present study used a cross-sectional design. Follow-up studies are needed to validate the relationship.

Causal functional connectivity in Alzheimer's disease computed from time series fMRI data

Functional connectivity between brain regions is known to be altered in Alzheimer's disease and promises to be a biomarker for early diagnosis. Several approaches for functional connectivity obtain an un-directed network representing stochastic associations (correlations) between brain regions. However, association does not necessarily imply causation. In contrast, Causal Functional Connectivity (CFC) is more informative, providing a directed network representing causal relationships between brain regions. In this paper, we obtained the causal functional connectome for the whole brain from resting-state functional magnetic resonance imaging (rs-fMRI) recordings of subjects from three clinical groups: cognitively normal, mild cognitive impairment, and Alzheimer's disease. We applied the recently developed Time-aware PC (TPC) algorithm to infer the causal functional connectome for the whole brain. TPC supports model-free estimation of whole brain CFC based on directed graphical modeling in a time series setting. We compared the CFC outcome of TPC with that of other related approaches in the literature. Then, we used the CFC outcomes of TPC and performed an exploratory analysis of the difference in strengths of CFC edges between Alzheimer's and cognitively normal groups, based on edge-wise p-values obtained by Welch's t-test. The brain regions thus identified are found to be in agreement with literature on brain regions impacted by Alzheimer's disease, published by researchers from clinical/medical institutions.

Textural features of the frontal white matter could be used to discriminate amnestic mild cognitive impairment patients from the normal population

OBJECTIVE

We aim to develop a radiomics model based on 3-dimensional (3D)-T1WI images to discriminate amnestic mild cognitive impairment (aMCI) patients from the normal population by measuring changes in frontal white matter.

METHODS

In this study, 126 patients with aMCI and 174 normal controls (NC) were recruited from the local community. All subjects underwent routine magnetic resonance imaging examination (including 3D-T1WI ). Participants were randomly divided into a training set (n = 242, aMCI:102, NC:140) and a testing set (n = 58, aMCI:24, NC:34). Texture features of the frontal lobe were extracted from 3D-T1WI images. The least absolute shrinkage and selection operator (LASSO) was used to reduce feature dimensions and develop a radiomics signature model. Diagnostic performance was assessed in the training and testing sets using the receiver operating characteristic (ROC) curve analysis. The area under the ROC curve (AUC), sensitivity, and specificity were also calculated. The efficacy of the radiomics model in discriminating aMCI patients from the normal population was assessed by decision curve analysis (DCA).

RESULTS

A total of 108 frontal lobe texture features were extracted from 3D-T1WI images. LASSO selected 58 radiomic features for the final model, including log-sigma (n = 18), original (n = 8), and wavelet (n = 32) features. The performance of radiomic features extracted from 3D T1 imaging for distinguishing aMCI patients from controls was: in the training set, AUC was 1.00, and the accuracy, sensitivity, and specificity were 100%, 98%, and 100%, respectively. In the testing set, AUC was 0.82 (95% CI:0.69-0.95), and the accuracy, sensitivity, and specificity were 69%, 92%, and 55%, respectively. The DCA demonstrated that the model had favorable clinical predictive value.

CONCLUSIONS

Textural features of white matter in the frontal lobe showed potential for distinguishing aMCI from the normal population, which could be a surrogate protocol to aid aMCI screening in clinical setting.

BNLoop-GAN: a multi-loop generative adversarial model on brain network learning to classify Alzheimer's disease

Recent advancements in AI, big data analytics, and magnetic resonance imaging (MRI) have revolutionized the study of brain diseases such as Alzheimer's Disease (AD). However, most AI models used for neuroimaging classification tasks have limitations in their learning strategies, that is batch training without the incremental learning capability. To address such limitations, the systematic Brain Informatics methodology is reconsidered to realize evidence combination and fusion computing with multi-modal neuroimaging data through continuous learning. Specifically, we introduce the BNLoop-GAN (Loop-based Generative Adversarial Network for Brain Network) model, utilizing multiple techniques such as conditional generation, patch-based discrimination, and Wasserstein gradient penalty to learn the implicit distribution of brain networks. Moreover, a multiple-loop-learning algorithm is developed to combine evidence with better sample contribution ranking during training processes. The effectiveness of our approach is demonstrated through a case study on the classification of individuals with AD and healthy control groups using various experimental design strategies and multi-modal brain networks. The BNLoop-GAN model with multi-modal brain networks and multiple-loop-learning can improve classification performance.

Temporal Irreversibility of Large-Scale Brain Dynamics in Alzheimer's Disease

Healthy brain dynamics can be understood as the emergence of a complex system far from thermodynamic equilibrium. Brain dynamics are temporally irreversible and thus establish a preferred direction in time (i.e., arrow of time). However, little is known about how the time-reversal symmetry of spontaneous brain activity is affected by Alzheimer's disease (AD). We hypothesized that the level of irreversibility would be compromised in AD, signaling a fundamental shift in the collective properties of brain activity toward equilibrium dynamics. We investigated the irreversibility from resting-state fMRI and EEG data in male and female human patients with AD and elderly healthy control subjects (HCs). We quantified the level of irreversibility and, thus, proximity to nonequilibrium dynamics by comparing forward and backward time series through time-shifted correlations. AD was associated with a breakdown of temporal irreversibility at the global, local, and network levels, and at multiple oscillatory frequency bands. At the local level, temporoparietal and frontal regions were affected by AD. The limbic, frontoparietal, default mode, and salience networks were the most compromised at the network level. The temporal reversibility was associated with cognitive decline in AD and gray matter volume in HCs. The irreversibility of brain dynamics provided higher accuracy and more distinctive information than classical neurocognitive measures when differentiating AD from control subjects. Findings were validated using an out-of-sample cohort. Present results offer new evidence regarding pathophysiological links between the entropy generation rate of brain dynamics and the clinical presentation of AD, opening new avenues for dementia characterization at different levels.SIGNIFICANCE STATEMENT By assessing the irreversibility of large-scale dynamics across multiple brain signals, we provide a precise signature capable of distinguishing Alzheimer's disease (AD) at the global, local, and network levels and different oscillatory regimes. Irreversibility of limbic, frontoparietal, default-mode, and salience networks was the most compromised by AD compared with more sensory-motor networks. Moreover, the time-irreversibility properties associated with cognitive decline and atrophy outperformed and complemented classical neurocognitive markers of AD in predictive classification performance. Findings were generalized and replicated with an out-of-sample validation procedure. We provide novel multilevel evidence of reduced irreversibility in AD brain dynamics that has the potential to open new avenues for understating neurodegeneration in terms of the temporal asymmetry of brain dynamics.

Diffusion Kernel Attention Network for Brain Disorder Classification

Constructing and analyzing functional brain networks (FBN) has become a promising approach to brain disorder classification. However, the conventional successive construct-and-analyze process would limit the performance due to the lack of interactions and adaptivity among the subtasks in the process. Recently, Transformer has demonstrated remarkable performance in various tasks, attributing to its effective attention mechanism in modeling complex feature relationships. In this paper, for the first time, we develop Transformer for integrated FBN modeling, analysis and brain disorder classification with rs-fMRI data by proposing a Diffusion Kernel Attention Network to address the specific challenges. Specifically, directly applying Transformer does not necessarily admit optimal performance in this task due to its extensive parameters in the attention module against the limited training samples usually available. Looking into this issue, we propose to use kernel attention to replace the original dot-product attention module in Transformer. This significantly reduces the number of parameters to train and thus alleviates the issue of small sample while introducing a non-linear attention mechanism to model complex functional connections. Another limit of Transformer for FBN applications is that it only considers pair-wise interactions between directly connected brain regions but ignores the important indirect connections. Therefore, we further explore diffusion process over the kernel attention to incorporate wider interactions among indirectly connected brain regions. Extensive experimental study is conducted on ADHD-200 data set for ADHD classification and on ADNI data set for Alzheimer's disease classification, and the results demonstrate the superior performance of the proposed method over the competing methods.

Assessing Multi-Site rs-fMRI-Based Connectomic Harmonization Using Information Theory

Several harmonization techniques have recently been proposed for connectomics/networks derived from resting-state functional magnetic resonance imaging (rs-fMRI) acquired at multiple sites. These techniques have the objective of mitigating site-specific biases that complicate its subsequent analysis and, therefore, compromise the quality of the results when these images are analyzed together. Thus, harmonization is indispensable when large cohorts are required in which the data obtained must be independent of the particular condition of each resonator, its make and model, its calibration, and other features or artifacts that may affect the significance of the acquisition. To date, no assessment of the actual efficacy of these harmonization techniques has been proposed. In this work, we apply recently introduced Information Theory tools to analyze the effectiveness of these techniques, developing a methodology that allows us to compare different harmonization models. We demonstrate the usefulness of this methodology by applying it to some of the most widespread harmonization frameworks and datasets. As a result, we are able to show that some of these techniques are indeed ineffective since the acquisition site can still be determined from the fMRI data after the processing.

Convolutional Recurrent Neural Network for Dynamic Functional MRI Analysis and Brain Disease Identification

Dynamic functional connectivity (dFC) networks derived from resting-state functional magnetic resonance imaging (rs-fMRI) help us understand fundamental dynamic characteristics of human brains, thereby providing an efficient solution for automated identification of brain diseases, such as Alzheimer's disease (AD) and its prodromal stage. Existing studies have applied deep learning methods to dFC network analysis and achieved good performance compared with traditional machine learning methods. However, they seldom take advantage of sequential information conveyed in dFC networks that could be informative to improve the diagnosis performance. In this paper, we propose a convolutional recurrent neural network (CRNN) for automated brain disease classification with rs-fMRI data. Specifically, we first construct dFC networks from rs-fMRI data using a sliding window strategy. Then, we employ three convolutional layers and long short-term memory (LSTM) layer to extract high-level features of dFC networks and also preserve the sequential information of extracted features, followed by three fully connected layers for brain disease classification. Experimental results on 174 subjects with 563 rs-fMRI scans from the Alzheimer's Disease Neuroimaging Initiative (ADNI) demonstrate the effectiveness of our proposed method in binary and multi-category classification tasks.

Classification of Alzheimer’s Disease Based on Core-Large Scale Brain Network Using Multilayer Extreme Learning Machine

Various studies suggest that the network deficit in default network mode (DMN) is prevalent in Alzheimer’s disease (AD) and mild cognitive impairment (MCI). Besides DMN, some studies reveal that network alteration occurs in salience network motor networks and large scale network. In this study we performed classification of AD and MCI from healthy control considering the network alterations in large scale network and DMN. Thus, we constructed the brain network from functional magnetic resonance (fMR) images. Pearson’s correlation-based functional connectivity was used to construct the brain network. Graph features of the brain network were converted to feature vectors using Node2vec graph-embedding technique. Two classifiers, single layered extreme learning and multilayered extreme learning machine, were used for the classification together with feature selection approaches. We performed the classification test on the brain network of different sizes including the large scale brain network, the whole brain network and the combined brain network. Experimental results showed that the least absolute shrinkage and selection operator (LASSO) feature selection method generates better classification accuracy on large network size, and that feature selection with adaptive structure learning (FSAL) feature selection technique generates better classification accuracy on small network size.

Changes in a sensorimotor network, occipital network, and psychomotor speed within three months after focal surgical injury in pediatric patients with intracranial space-occupying lesions

BACKGROUND

Studies on cognition and brain networks after various forms of brain injury mainly involve traumatic brain injury, neurological disease, tumours, and mental disease. There are few related studies on surgical injury and even fewer pediatric studies. This study aimed to preliminarily explore the cognitive and brain network changes in children with focal, unilateral, well-bounded intracranial space-occupying lesions (ISOLs) in the short term period after surgery.

METHODS

We enrolled 15 patients (6-14 years old) with ISOLs admitted to the Department of Pediatric Neurosurgery of the Beijing Tiantan Hospital between July 2020 and August 2021. Cognitive assessment and resting-state functional magnetic resonance imaging (rs-fMRI) were performed. Regional homogeneity (Reho), seed-based analysis (SBA) and graph theory analysis (GTA) were performed. Paired T-test was used for statistical analysis of cognitive assessment and rs-fMRI. Gaussian random-field theory correction (voxel p-value < 0.001, cluster p-value < 0.05) was used for Reho and SBA. False discovery rate correction (corrected p value < 0.05) for GTA.

RESULTS

Our results showed that psychomotor speed decreased within three months after surgery. Further, rs-fMRI data analysis suggested that sensorimotor and occipital network activation decreased with low information transmission efficiency.

CONCLUSION

We prudently concluded that the changes in cognitive function and brain network within three months after surgery may be similar to ageing and that the brain is vulnerable during this period.

Alzheimer's Disease Diagnosis and Biomarker Analysis Using Resting-State Functional MRI Functional Brain Network With Multi-Measures Features and Hippocampal Subfield and Amygdala Volume of Structural MRI

Accurate diagnosis of the initial phase of Alzheimer's disease (AD) is essential and crucial. The objective of this research was to employ efficient biomarkers for the diagnostic analysis and classification of AD based on combining structural MRI (sMRI) and resting-state functional MRI (rs-fMRI). So far, several anatomical MRI imaging markers for AD diagnosis have been identified. The use of cortical and subcortical volumes, the hippocampus, and amygdala volume, as well as genetic patterns, has proven to be beneficial in distinguishing patients with AD from the healthy population. The fMRI time series data have the potential for specific numerical information as well as dynamic temporal information. Voxel and graphical analyses have gained popularity for analyzing neurodegenerative diseases, such as Alzheimer's and its prodromal phase, mild cognitive impairment (MCI). So far, these approaches have been utilized separately for the diagnosis of AD. In recent studies, the classification of cases of MCI into those that are not converted for a certain period as stable MCI (MCIs) and those that converted to AD as MCIc has been less commonly reported with inconsistent results. In this study, we verified and validated the potency of a proposed diagnostic framework to identify AD and differentiate MCIs from MCIc by utilizing the efficient biomarkers obtained from sMRI, along with functional brain networks of the frequency range .01-.027 at the resting state and the voxel-based features. The latter mainly included default mode networks (amplitude of low-frequency fluctuation [ALFF], fractional ALFF [ALFF], and regional homogeneity [ReHo]), degree centrality (DC), and salience networks (SN). Pearson's correlation coefficient for measuring fMRI functional networks has proven to be an efficient means for disease diagnosis. We applied the graph theory to calculate nodal features (nodal degree [ND], nodal path length [NL], and between centrality [BC]) as a graphical feature and analyzed the connectivity link between different brain regions. We extracted three-dimensional (3D) patterns to calculate regional coherence and then implement a univariate statistical t-test to access a 3D mask that preserves voxels showing significant changes. Similarly, from sMRI, we calculated the hippocampal subfield and amygdala nuclei volume using Freesurfer (version 6). Finally, we implemented and compared the different feature selection algorithms to integrate the structural features, brain networks, and voxel features to optimize the diagnostic identifications of AD using support vector machine (SVM) classifiers. We also compared the performance of SVM with Random Forest (RF) classifiers. The obtained results demonstrated the potency of our framework, wherein a combination of the hippocampal subfield, the amygdala volume, and brain networks with multiple measures of rs-fMRI could significantly enhance the accuracy of other approaches in diagnosing AD. The accuracy obtained by the proposed method was reported for binary classification. More importantly, the classification results of the less commonly reported MCIs vs. MCIc improved significantly. However, this research involved only the AD Neuroimaging Initiative (ADNI) cohort to focus on the diagnosis of AD advancement by integrating sMRI and fMRI. Hence, the study's primary disadvantage is its small sample size. In this case, the dataset we utilized did not fully reflect the whole population. As a result, we cannot guarantee that our findings will be applicable to other populations.

Extracting ROI-Based Contourlet Subband Energy Feature From the sMRI Image for Alzheimer's Disease Classification

Structural magnetic resonance imaging (sMRI)-based Alzheimer's disease (AD) classification and its prodromal stage-mild cognitive impairment (MCI) classification have attracted many attentions and been widely investigated in recent years. Owing to the high dimensionality, representation of the sMRI image becomes a difficult issue in AD classification. Furthermore, regions of interest (ROI) reflected in the sMRI image are not characterized properly by spatial analysis techniques, which has been a main cause of weakening the discriminating ability of the extracted spatial feature. In this study, we propose a ROI-based contourlet subband energy (ROICSE) feature to represent the sMRI image in the frequency domain for AD classification. Specifically, a preprocessed sMRI image is first segmented into 90 ROIs by a constructed brain mask. Instead of extracting features from the 90 ROIs in the spatial domain, the contourlet transform is performed on each of these ROIs to obtain their energy subbands. And then for an ROI, a subband energy (SE) feature vector is constructed to capture its energy distribution and contour information. Afterwards, SE feature vectors of the 90 ROIs are concatenated to form a ROICSE feature of the sMRI image. Finally, support vector machine (SVM) classifier is used to classify 880 subjects from ADNI and OASIS databases. Experimental results show that the ROICSE approach outperforms six other state-of-the-art methods, demonstrating that energy and contour information of the ROI are important to capture differences between the sMRI images of AD and HC subjects. Meanwhile, brain regions related to AD can also be found using the ROICSE feature, indicating that the ROICSE feature can be a promising assistant imaging marker for the AD diagnosis via the sMRI image. Code and Sample IDs of this paper can be downloaded at https://github.com/NWPU-903PR/ROICSE.git.

Resting-state functional MRI signal fluctuation amplitudes are correlated with brain amyloid- deposition in patients with mild cognitive impairment

Mounting evidence suggests that amyloid-β (Aβ) and vascular etiologies are intertwined in the pathogenesis of Alzheimer's disease (AD). Blood-oxygen-level-dependent (BOLD) signals, measured by resting-state functional MRI (rs-fMRI), are associated with neuronal activity and cerebrovascular hemodynamics. Nevertheless, it is unclear if BOLD fluctuations are associated with Aβ deposition in individuals at high risk of AD. Thirty-three patients with amnestic mild cognitive impairment underwent rs-fMRI and AV45 PET. The AV45 standardized uptake value ratio (AV45-SUVR) was calculated using cerebral white matter as reference, to assess Aβ deposition. The whole-brain normalized amplitudes of low-frequency fluctuations (sALFF) of local BOLD signals were calculated in the frequency band of 0.01-0.08 Hz. Stepwise increasing physiological/vascular signal regressions on the rs-fMRI data examined whether sALFF-AV45 correlations were driven by vascular hemodynamics, neuronal activities, or both. We found that sALFF and AV45-SUVR were negatively correlated in regions of default-mode and visual networks (precuneus, angular, lingual and fusiform gyri). Regions with higher sALFF had less Aβ accumulation. Correlated cluster sizes in MNI space (r ≈ -0.47) were reduced from 3018 mm³ to 1072 mm³ with stronger cardiovascular regression. These preliminary findings imply that local brain blood fluctuations due to vascular hemodynamics or neuronal activity can affect Aβ homeostasis.

Stability Analysis of fMRI BOLD Signals for Disease Diagnosis

Previous studies have demonstrated that the stability changes in physiological signals can reflect individuals' pathological conditions. Apart from this, according to system science theory, a large-scale system can generally be divided into many subsystems whose stability level govern its overall performance. Therefore, this study attempts to investigate the possibility of analyzing the stability of decomposed subsystems of resting-state fMRI (rs-fMRI) BOLD signals in order to assess the overall characteristic of the human brain and individuals' health conditions. We used attention deficit/hyperactive disorder (ADHD) as an example to illustrate our method. Rs-fMRI BOLD signals were first decomposed into dynamic modes (DMs) which can illuminate the patterns of brain subsystems. Each DM is associated with one eigenvalue that determines its stability as well as oscillation frequency. Accordingly, we divided the DMs within common BOLD frequency bands into stable and unstable DMs. Then, the features related to the stability of those DMs were extracted, and nine common classifiers were used to differentiate healthy controls from ADHD patients taken from ADHD-200, a well-known dataset. The results showed that almost all features were statistically significant. Additionally, our proposed approach outperforms all existing methods with the highest possible precision, recall, and area under the receiver operating characteristic curve of 100%. In sum, we are the first to evaluate the stability of BOLD signals and demonstrate its possibility for disease diagnosis. This method can unveil new mechanisms of brain function, and could be widely used in medicine and engineering.

Classification of Alzheimer's disease progression based on sMRI using gray matter volume and lateralization index

Note that identifying Mild Cognitive Impairment (MCI) is crucial to early detection and diagnosis of Alzheimer's disease (AD). This work explores how classification features and experimental algorithms influence classification performances on the ADNI database. Based on structural Magnetic Resonance Images (sMRI), two features including gray matter (GM) volume and lateralization index (LI) are firstly extracted through hypothesis testing. Afterward, several classifier algorithms including Random Forest (RF), Decision Tree (DT), K-Nearest Neighbor(KNN) and Support Vector Machine (SVM) with RBF kernel, Linear kernel or Polynomial kernel are established to realize binary classification among Normal Control (NC), Early Mild Cognitive Impairment (EMCI), Late Mild Cognitive Impairment (LMCI) and AD groups. The main experimental results are as follows. (1) The classification performance in the feature of LI is poor compared with those in the feature of GM volume or the combined feature of LI and GM volume, i.e., the classification accuracies in the feature of LI are relatively low and unstable for most classifier models and subject groups. (2) Comparing with the classification performances in the feature of GM volume and the combined feature of LI and GM volume, the classification accuracy of NC group versus AD group is relatively stable for different classifier models, moreover, the accuracy of AD group versus NC group is almost the highest, with the most classification accuracy of 98.0909%. (3) For different subject groups, the SVM classifier algorithm with Polynomial kernel and the KNN classifier algorithm show relatively stable and high classification accuracy, while DT classifier algorithm shows relatively unstable and lower classification accuracy. (4) Except the groups of EMCI versus LMCI and NC versus EMCI, the classification accuracies are significantly enhanced by emerging the LI into the original feature of GM volume, with the maximum accuracy increase of 5.6364%. These results indicate that various factors of subject data, feature types and experimental algorithms influence classification performances remarkably, especially the newly introduced feature of LI into the feature of GM volume is helpful to improve classification results in some certain extent.

Functional connectome fingerprint of holistic-analytic cultural style

Although research in the field of cultural psychology and cultural neuroscience has revealed that culture is an important factor related to the human behaviors and neural activities in various tasks, it remains unclear how different brain regions organize together to construct a topological network for the representation of individual's cultural tendency. In this study, we examined the hypothesis that resting-state brain network properties can reflect individual's cultural background or tendency. By combining the methods of resting-state magnetic resonance imaging and graph theoretical analysis, significant cultural differences between participants from Eastern and Western cultures were found in the degree and global efficiency of regions mainly within the default mode network and subcortical network. Furthermore, the holistic-analytic thinking style, as a cultural value, provided a partial explanation for the cultural differences on various nodal metrics. Validation analyses further confirmed that these network properties effectively predicted the tendency of holistic-analytic cultural style within a group (r = 0.23) and accurately classified cultural groups (65%). The current study establishes a neural connectome representation of holistic-analytic cultural style including the topological brain network properties of regions in the default mode network, the basal ganglia and amygdala, which enable accurate cultural group membership classification.

Individualized spatial network predictions using Siamese convolutional neural networks: A resting-state fMRI study of over 11,000 unaffected individuals

Individuals can be characterized in a population according to their brain measurements and activity, given the inter-subject variability in brain anatomy, structure-function relationships, or life experience. Many neuroimaging studies have demonstrated the potential of functional network connectivity patterns estimated from resting functional magnetic resonance imaging (fMRI) to discriminate groups and predict information about individual subjects. However, the predictive signal present in the spatial heterogeneity of brain connectivity networks is yet to be extensively studied. In this study, we investigate, for the first time, the use of pairwise-relationships between resting-state independent spatial maps to characterize individuals. To do this, we develop a deep Siamese framework comprising three-dimensional convolution neural networks for contrastive learning based on individual-level spatial maps estimated via a fully automated fMRI independent component analysis approach. The proposed framework evaluates whether pairs of spatial networks (e.g., visual network and auditory network) are capable of subject identification and assesses the spatial variability in different network pairs' predictive power in an extensive whole-brain analysis. Our analysis on nearly 12,000 unaffected individuals from the UK Biobank study demonstrates that the proposed approach can discriminate subjects with an accuracy of up to 88% for a single network pair on the test set (best model, after several runs), and 82% average accuracy at the subcortical domain level, notably the highest average domain level accuracy attained. Further investigation of our network's learned features revealed a higher spatial variability in predictive accuracy among younger brains and significantly higher discriminative power among males. In sum, the relationship among spatial networks appears to be both informative and discriminative of individuals and should be studied further as putative brain-based biomarkers.

APOE genotype moderates the relationship between LRP1 polymorphism and cognition across the Alzheimer's disease spectrum via disturbing default mode network

AIMS

This study aims to investigate the mechanisms by which apolipoprotein E (APOE) genotype modulates the relationship between low-density lipoprotein receptor-related protein 1 (LRP1) rs1799986 variant on the default mode network (DMN) and cognition in Alzheimer's disease (AD) spectrum populations.

METHODS

Cross-sectional 168 subjects of AD spectrum were obtained from Alzheimer's Disease Neuroimaging Initiative database with resting-state fMRI scans and neuropsychological scores data. Multivariable linear regression analysis was adopted to investigate the main effects and interaction of LRP1 and disease on the DMN. Moderation and interactive analyses were performed to assess the relationships among APOE, LRP1, and cognition. A support vector machine model was used to classify AD spectrum with altered connectivity as an objective diagnostic biomarker.

RESULTS

The main effects and interaction of LRP1 and disease were mainly focused on the core hubs of frontal-parietal network. Several brain regions with altered connectivity were correlated with cognitive scores in LRP1-T carriers, but not in non-carriers. APOE regulated the effect of LRP1 on cognitive performance. The functional connectivity of numerous brain regions within LRP1-T carriers yielded strong power for classifying AD spectrum.

CONCLUSION

These findings suggested LRP1 could affect DMN and provided a stage-dependent neuroimaging biomarker for classifying AD spectrum populations.

Distribution-guided Network Thresholding for Functional Connectivity Analysis in fMRI-based Brain Disorder Identification

Brain functional connectivity (FC) networks derived from resting-state functional magnetic resonance imaging (rs-fMRI) have been widely applied to automated identification of brain disorders, such as Alzheimer's disease (AD) and attention deficit hyperactivity disorder (ADHD). To generate compact representations of FC networks, various thresholding strategies have been developed to analyze brain FC networks. However, existing studies usually employ predefined thresholds or percentages of connections to threshold FC networks, thus ignoring the diversity of temporal correlation (particularly strong associations) among brain regions in same/different subject groups. Also, it is usually challenging to decide the optimal threshold or connection percentage in practice. To this end, in this paper, we propose a distribution-guided network thresholding (DNT) method for functional connectivity analysis in brain disorder identification with rs-fMRI. Specifically, for each functional connectivity of a pair of brain regions, we proposed to compute its specific threshold based on the distribution of connection strength (i.e., temporal correlation) between subject groups (e.g., patients and normal controls). The proposed DNT can adaptively yield FC-specific threshold for each connection in brain networks, thus preserving the diversity of temporal correlation among brain regions. Experiment results on both ADNI and ADHD-200 datasets demonstrate the effectiveness of our proposed DNT method in fMRI-based identification of AD and ADHD.

Intrinsic functional connectivity of the frontoparietal network predicts inter-individual differences in the propensity for costly third-party punishment

Humans are motivated to give norm violators their just deserts through costly punishment even as unaffected third parties (i.e., third-party punishment, TPP). A great deal of individual variability exists in costly punishment; however, how this variability particularly in TPP is represented by the brain's intrinsic network architecture remains elusive. Here, we examined whether inter-individual differences in the propensity for TPP can be predicted based on resting-state functional connectivity (RSFC) combining an economic TPP game with task-free functional neuroimaging and a multivariate prediction framework. Our behavioral results revealed that TPP punishment increased with the severity of unfairness for offers. People with higher TPP propensity punished more harshly across norm-violating scenarios. Our neuroimaging findings showed RSFC within the frontoparietal network predicted individual differences in TPP propensity. Our findings contribute to understanding the neural fingerprint for an individual's propensity to costly punish strangers, and shed some light on how social norm enforcement behaviors are represented by the brain's intrinsic network architecture.

Advances in computerized MRI‐based biomarkers in Alzheimer’s disease

The use of neuroimaging examinations is crucial in Alzheimer’s disease (AD), in both research and clinical settings. Over the years, magnetic resonance imaging (MRI)–based computer‐aided diagnosis has been shown to be helpful for early screening and predicting cognitive decline. Meanwhile, an increasing number of studies have adopted machine learning for the classification of AD, with promising results. In this review article, we focus on computerized MRI‐based biomarkers of AD by reviewing representative studies that used computerized techniques to identify AD patients and predict cognitive progression. We categorized these studies based on the following applications: (1) identifying AD from normal control; (2) identifying AD from other dementia types, including vascular dementia, dementia with Lewy bodies, and frontotemporal dementia; and (3) predicting conversion from NC to mild cognitive impairment (MCI) and from MCI to AD. This systematic review could act as a state‐of‐the‐art overview of this emerging field as well as a basis for designing future studies.

Management Based on Multimodal Brain Monitoring May Improve Functional Connectivity and Post-operative Neurocognition in Elderly Patients Undergoing Spinal Surgery

Perioperative neurocognitive disorder (PND) is a common condition in elderly patients undergoing surgery. Sedation, analgesia, regional cerebral oxygen saturation (rSO₂), and body temperature are known to be associated with PND, but few studies have examined the contribution of these factors combined in detail. This prospective, randomized, controlled, double-blinded study investigated whether anesthesia management based on multimodal brain monitoring—an anesthesia management algorithm designed by our group—could improve the post-operative cognitive function and brain functional connectivity (FC) in elderly patients undergoing elective spinal surgery with general anesthesia. The patients (aged ≥65 years) were randomized into two groups [control (Group C), n = 12 and intervention (Group I), n = 14]. Patients in Group I were managed with multimodal brain monitoring (patient state index, spectral edge frequency, analgesia nociception index, rSO₂, and temperature), and those in Group C were managed with routine anesthesia management. All patients were pre- and post-operatively evaluated (7 days after surgery) with the Montreal Cognitive Assessment (MoCA). Amplitude of low-frequency fluctuation (ALFF) and FC were analyzed after resting-state functional MRI. Serum C-reactive protein (CRP) and lipopolysaccharide levels were measured, and the correlation between FC and changes in inflammatory marker levels was analyzed. Mean post-operative MoCA score was higher in Group I (24.80 ± 2.09) than in Group C (22.56 ± 2.24) (p = 0.04), with no difference in PND incidence between groups (28.57 vs. 16.67%; p = 0.47). Group I also showed significantly increased ALFF values in several brain regions after surgery (p < 0.05), and FC between the left hippocampus and left orbital inferior frontal gyrus (FG), left middle FG, left superior temporal gyrus, and left precentral gyrus was enhanced (p < 0.05), which was negatively correlated with the change in serum CRP (pre vs. post-intervention) (R = −0.58, p = 0.01). These results suggest that management of elderly patients undergoing surgery by multimodal brain monitoring may improve post-operative neurocognition and FC by reducing systemic inflammation.

Clinical Trial Registration:http://www.chictr.org.cn/index.aspx, identifier: ChiCTR1900028024.

Identifying Autism Spectrum Disorder From Resting-State fMRI Using Deep Belief Network

With the increasing prevalence of autism spectrum disorder (ASD), it is important to identify ASD patients for effective treatment and intervention, especially in early childhood. Neuroimaging techniques have been used to characterize the complex biomarkers based on the functional connectivity anomalies in the ASD. However, the diagnosis of ASD still adopts the symptom-based criteria by clinical observation. The existing computational models tend to achieve unreliable diagnostic classification on the large-scale aggregated data sets. In this work, we propose a novel graph-based classification model using the deep belief network (DBN) and the Autism Brain Imaging Data Exchange (ABIDE) database, which is a worldwide multisite functional and structural brain imaging data aggregation. The remarkable connectivity features are selected through a graph extension of K -nearest neighbors and then refined by a restricted path-based depth-first search algorithm. Thanks to the feature reduction, lower computational complexity could contribute to the shortening of the training time. The automatic hyperparameter-tuning technique is introduced to optimize the hyperparameters of the DBN by exploring the potential parameter space. The simulation experiments demonstrate the superior performance of our model, which is 6.4% higher than the best result reported on the ABIDE database. We also propose to use the data augmentation and the oversampling technique to identify further the possible subtypes within the ASD. The interpretability of our model enables the identification of the most remarkable autistic neural correlation patterns from the data-driven outcomes.

Altered hippocampal functional connectivity patterns in patients with cognitive impairments following ischaemic stroke: A resting-state fMRI study

BACKGROUND

Ischemic stroke with cognitive impairment is a considerable risk factor for developing dementia. Identifying imaging markers of cognitive impairment following ischemic stroke will help to develop prevention strategies against post-stroke dementia.

METHODS

We investigated the hippocampal functional connectivity (FC) pattern following ischemic stroke, using resting-state fMRI (rs-fMRI). Thirty-three cognitively impaired patients after ischemic stroke and sixteen age-matched controls with no known history of neurological disorder were recruited for the study. No patient had a direct ischaemic insult to hippocampus on the examination of brain imaging. Seven subfields of hippocampus were used as seeds region for FC analyses.

RESULTS

Across all hippocampal subfields, FC with the inferior parietal lobule was reduced in stroke patients as compared with healthy controls. This decreased FC included both supramarginal gyrus and angular gyrus. The FC of hippocampal subfields with cerebellum was increased. Importantly, the degree of the altered FC between hippocampal subfields and inferior parietal lobule was associated with their impaired memory function.

CONCLUSION

Our results demonstrated that decreased hippocampal-inferior parietal lobule connectivity was associated with cognitive impairment in patients with ischemic stroke. These findings provide novel insights into the role of hippocampus in cognitive impairment following ischemic stroke.

Pathogenic Factors Identification of Brain Imaging and Gene in Late Mild Cognitive Impairment

Mild cognitive impairment (MCI) is a dangerous signal of severe cognitive decline. It can be separated into two steps: early MCI (EMCI) and late MCI (LMCI). As the post-state of MCI and pre-state of Alzheimer's disease (AD), LMCI receives insufficient attention in the field of brain science, causing the internal mechanism of LMCI has not been well understood. To better explore the focus and pathological mechanism of LMCI, a method called genetic evolved random forest (GERF) is applied. Resting functional magnetic resonance imaging (rfMRI) and gene data are obtained from 62 subjects (36 LMCI and 26 normal controls), and Pearson correlation analysis is adopted to perform the multimodal fusion of two types of data to construct fusion features. We identified pathogenic brain regions and genes that are highly related to LMCI using GERF and achieves a good effect. Compared with the normal control (NC) group, the abnormal brain regions of LMCI are PUT.L, PreCG.L, IFGtriang.R, REC.R, DCG.R, PoCG.L, and HES.L, and the pathogenic genes are FHIT, RF00019, FRMD4A, PTPRD, and RBFOX1. More importantly, most of these risk genes and abnormal brain regions have been confirmed to be related to AD and MCI in previous studies. In this study, we mapped them to LMCI with higher accuracies, so as to provide a more robust understanding of the physiological mechanism of MCI.

Statistical and Machine Learning Link Selection Methods for Brain Functional Networks: Review and Comparison

Network-based representations have introduced a revolution in neuroscience, expanding the understanding of the brain from the activity of individual regions to the interactions between them. This augmented network view comes at the cost of high dimensionality, which hinders both our capacity of deciphering the main mechanisms behind pathologies, and the significance of any statistical and/or machine learning task used in processing this data. A link selection method, allowing to remove irrelevant connections in a given scenario, is an obvious solution that provides improved utilization of these network representations. In this contribution we review a large set of statistical and machine learning link selection methods and evaluate them on real brain functional networks. Results indicate that most methods perform in a qualitatively similar way, with NBS (Network Based Statistics) winning in terms of quantity of retained information, AnovaNet in terms of stability and ExT (Extra Trees) in terms of lower computational cost. While machine learning methods are conceptually more complex than statistical ones, they do not yield a clear advantage. At the same time, the high heterogeneity in the set of links retained by each method suggests that they are offering complementary views to the data. The implications of these results in neuroscience tasks are finally discussed.

Preventing Failures by Dataset Shift Detection in Safety-Critical Graph Applications

Dataset shift refers to the problem where the input data distribution may change over time (e.g., between training and test stages). Since this can be a critical bottleneck in several safety-critical applications such as healthcare, drug-discovery, etc., dataset shift detection has become an important research issue in machine learning. Though several existing efforts have focused on image/video data, applications with graph-structured data have not received sufficient attention. Therefore, in this paper, we investigate the problem of detecting shifts in graph structured data through the lens of statistical hypothesis testing. Specifically, we propose a practical two-sample test based approach for shift detection in large-scale graph structured data. Our approach is very flexible in that it is suitable for both undirected and directed graphs, and eliminates the need for equal sample sizes. Using empirical studies, we demonstrate the effectiveness of the proposed test in detecting dataset shifts. We also corroborate these findings using real-world datasets, characterized by directed graphs and a large number of nodes.

Diagnosis of early Alzheimer's disease based on dynamic high order networks

Machine learning methods have been widely used for early diagnosis of Alzheimer's disease (AD) via functional connectivity networks (FCNs) analysis from neuroimaging data. The conventional low-order FCNs are obtained by time-series correlation of the whole brain based on resting-state functional magnetic resonance imaging (R-fMRI). However, FCNs overlook inter-region interactions, which limits application to brain disease diagnosis. To overcome this drawback, we develop a novel framework to exploit the high-level dynamic interactions among brain regions for early AD diagnosis. Specifically, a sliding window approach is employed to generate some R-fMRI sub-series. The correlations among these sub-series are then used to construct a series of dynamic FCNs. High-order FCNs based on the topographical similarity between each pair of the dynamic FCNs are then constructed. Afterward, a local weight clustering method is used to extract effective features of the network, and the least absolute shrinkage and selection operation method is chosen for feature selection. A support vector machine is employed for classification, and the dynamic high-order network approach is evaluated on the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset. Our experimental results demonstrate that the proposed approach not only achieves promising results for AD classification, but also successfully recognizes disease-related biomarkers.

A Deep Learning Approach to Predict Autism Spectrum Disorder Using Multisite Resting-State fMRI

Autism spectrum disorder (ASD) is a complex and degenerative neuro-developmental disorder. Most of the existing methods utilize functional magnetic resonance imaging (fMRI) to detect ASD with a very limited dataset which provides high accuracy but results in poor generalization. To overcome this limitation and to enhance the performance of the automated autism diagnosis model, in this paper, we propose an ASD detection model using functional connectivity features of resting-state fMRI data. Our proposed model utilizes two commonly used brain atlases, Craddock 200 (CC200) and Automated Anatomical Labelling (AAL), and two rarely used atlases Bootstrap Analysis of Stable Clusters (BASC) and Power. A deep neural network (DNN) classifier is used to perform the classification task. Simulation results indicate that the proposed model outperforms state-of-the-art methods in terms of accuracy. The mean accuracy of the proposed model was 88%, whereas the mean accuracy of the state-of-the-art methods ranged from 67% to 85%. The sensitivity, F1-score, and area under receiver operating characteristic curve (AUC) score of the proposed model were 90%, 87%, and 96%, respectively. Comparative analysis on various scoring strategies show the superiority of BASC atlas over other aforementioned atlases in classifying ASD and control.

Machine Learning Analytics of Resting-State Functional Connectivity Predicts Survival Outcomes of Glioblastoma Multiforme Patients

Glioblastoma multiforme (GBM) is the most frequently occurring brain malignancy. Due to its poor prognosis with currently available treatments, there is a pressing need for easily accessible, non-invasive techniques to help inform pre-treatment planning, patient counseling, and improve outcomes. In this study we determined the feasibility of resting-state functional connectivity (rsFC) to classify GBM patients into short-term and long-term survival groups with respect to reported median survival (14.6 months). We used a support vector machine with rsFC between regions of interest as predictive features. We employed a novel hybrid feature selection method whereby features were first filtered using correlations between rsFC and OS, and then using the established method of recursive feature elimination (RFE) to select the optimal feature subset. Leave-one-subject-out cross-validation evaluated the performance of models. Classification between short- and long-term survival accuracy was 71.9%. Sensitivity and specificity were 77.1 and 65.5%, respectively. The area under the receiver operating characteristic curve was 0.752 (95% CI, 0.62–0.88). These findings suggest that highly specific features of rsFC may predict GBM survival. Taken together, the findings of this study support that resting-state fMRI and machine learning analytics could enable a radiomic biomarker for GBM, augmenting care and planning for individual patients.

White matter of perinatally HIV infected older youths shows low frequency fluctuations that may reflect glial cycling

In perinatally HIV-infected (PHIV) children, neurodevelopment occurs in the presence of HIV-infection, and even with combination antiretroviral therapy (cART) the brain can be a reservoir for latent HIV. Consequently, patients often demonstrate long-term cognitive deficits and developmental delay, which may be reflected in altered functional brain activity. Our objective was to examine brain function in PHIV on cART by quantifying the amplitude of low frequency fluctuations (ALFF) and regional homogeneity (ReHo). Further, we studied ALFF and ReHo changes with neuropsychological performance and measures of immune health including CD4 count and viral loads in the HIV-infected youths. We found higher ALFF and ReHo in cerebral white matter in the medial orbital lobe for PHIV (N = 11, age mean ± sd = 22.5 ± 2.9 years) compared to controls (N = 16, age = 22.5 ± 3.0 years), with age and gender as co-variates. Bilateral cerebral white matter showed increased spontaneous regional activity in PHIV compared to healthy controls. No brain regions showed lower ALFF or ReHo in PHIV compared to controls. Higher log10 viral load was associated with higher ALFF and ReHo in PHIV in bilateral cerebral white matter and right cerebral white matter respectively after masking the outcomes intrinsic to the brain regions that showed significantly higher ALFF and ReHo in the PHIV compared to the control. Reductions in social cognition and abstract thinking in PHIV were correlated with higher ALFF at the left cerebral white matter in the left medial orbital gyrus and higher ReHo at the right cerebral white matter in the PHIV patients. Although neuroinflammation and associated neuro repair were not directly measured, the findings support their potential role in PHIV impacting neurodevelopment and cognition.

Dynamic Connectivity Alteration Facilitates Cognitive Decline in Alzheimer's Disease Spectrum

Introduction: It is unknown the alterations in the dynamic networks of the brain and the underlying molecular pathological mechanism of Alzheimer's disease (AD) spectrum. Here, we aim to explore the association between alterations in the dynamic brain networks' trajectory and cognitive decline in the AD spectrum. Methods: One hundred sixty subjects were recruited from the ADNI database, including 49 early mild cognitive impairment, 28 late mild cognitive impairment, 24 AD patients, and 59 cognitively normal. All participants completed the resting-state functional magnetic resonance imaging scan and neuropsychological tests. We integrated a new method combining large-scale network analysis and canonical correlation analysis to explore the dynamic spatiotemporal patterns within- and between resting-state networks (RSNs) and their significance in the AD spectrum. Results: All RSNs represented an increase in connectivity within networks by enhancing inner cohesive ability, while 7 out of 10 RSNs were characterized by a decrease in connectivity between networks, which indicated a weakened connector among networks from the early stage to dementia. This dichotomous mode presenting large-scale dynamic network abnormality was significantly correlated with the levels of molecular biomarkers of AD, and cognitive performance, as well as with the accumulating effects of 10 identified AD-related genetic risk factors. Discussion: These findings deepen our understanding of the associated mechanism underlying large-scale network disruption, linking known molecular biomarkers and phenotypic variations in the AD spectrum.

A multilayer multimodal detection and prediction model based on explainable artificial intelligence for Alzheimer's disease

Alzheimer's disease (AD) is the most common type of dementia. Its diagnosis and progression detection have been intensively studied. Nevertheless, research studies often have little effect on clinical practice mainly due to the following reasons: (1) Most studies depend mainly on a single modality, especially neuroimaging; (2) diagnosis and progression detection are usually studied separately as two independent problems; and (3) current studies concentrate mainly on optimizing the performance of complex machine learning models, while disregarding their explainability. As a result, physicians struggle to interpret these models, and feel it is hard to trust them. In this paper, we carefully develop an accurate and interpretable AD diagnosis and progression detection model. This model provides physicians with accurate decisions along with a set of explanations for every decision. Specifically, the model integrates 11 modalities of 1048 subjects from the Alzheimer's Disease Neuroimaging Initiative (ADNI) real-world dataset: 294 cognitively normal, 254 stable mild cognitive impairment (MCI), 232 progressive MCI, and 268 AD. It is actually a two-layer model with random forest (RF) as classifier algorithm. In the first layer, the model carries out a multi-class classification for the early diagnosis of AD patients. In the second layer, the model applies binary classification to detect possible MCI-to-AD progression within three years from a baseline diagnosis. The performance of the model is optimized with key markers selected from a large set of biological and clinical measures. Regarding explainability, we provide, for each layer, global and instance-based explanations of the RF classifier by using the SHapley Additive exPlanations (SHAP) feature attribution framework. In addition, we implement 22 explainers based on decision trees and fuzzy rule-based systems to provide complementary justifications for every RF decision in each layer. Furthermore, these explanations are represented in natural language form to help physicians understand the predictions. The designed model achieves a cross-validation accuracy of 93.95% and an F1-score of 93.94% in the first layer, while it achieves a cross-validation accuracy of 87.08% and an F1-Score of 87.09% in the second layer. The resulting system is not only accurate, but also trustworthy, accountable, and medically applicable, thanks to the provided explanations which are broadly consistent with each other and with the AD medical literature. The proposed system can help to enhance the clinical understanding of AD diagnosis and progression processes by providing detailed insights into the effect of different modalities on the disease risk.

A study of regional homogeneity of resting-state Functional Magnetic Resonance Imaging in mild cognitive impairment

Mild cognitive impairment (MCI) is considered to be the early stage of Alzheimer's disease (AD), but the diagnostic predictive markers for MCI patients are still unclear. Here we have identified the brain function activity changes in MCI patients by using the resting-state functional magnetic resonance imaging (rs-fMRI). A total of 28 MCI patients and 38 age- and gender-matched healthy controls from the Wuxi Mental Health Center were recruited, and their abnormal spontaneous brain activities in the MCI were examined. The results showed that, compared with the healthy controls, MCI patients exhibited reduced regional homogeneity (ReHo) in the right superior temporal gyrus, right middle temporal gyrus, left angular gyrus and superior marginal gyrus. In addition, the correlation analysis revealed that ReHo in these regions were not correlated with the AD Assessment Scale-Cognitive score in MCI. We concluded abnormalities in the right superior temporal gyrus, right middle temporal gyrus, left angular gyrus and superior marginal gyrus with MCI, suggesting that the right language network may be impaired in MCI, which may provide a better understanding of dementia progression and potentially comprehensive treatment in MCI.

Multi-Scale Time-Series Kernel-Based Learning Method for Brain Disease Diagnosis

The functional magnetic resonance imaging (fMRI) is a noninvasive technique for studying brain activity, such as brain network analysis, neural disease automated diagnosis and so on. However, many existing methods have some drawbacks, such as limitations of graph theory, lack of global topology characteristic, local sensitivity of functional connectivity, and absence of temporal or context information. In addition to many numerical features, fMRI time series data also cover specific contextual knowledge and global fluctuation information. Here, we propose multi-scale time-series kernel-based learning model for brain disease diagnosis, based on Jensen-Shannon divergence. First, we calculate correlation value within and between brain regions over time. In addition, we extract multi-scale synergy expression probability distribution (interactional relation) between brain regions. Also, we produce state transition probability distribution (sequential relation) on single brain regions. Then, we build time-series kernel-based learning model based on Jensen-Shannon divergence to measure similarity of brain functional connectivity. Finally, we provide an efficient system to deal with brain network analysis and neural disease automated diagnosis. On Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset, our proposed method achieves accuracy of 0.8994 and AUC of 0.8623. On Major Depressive Disorder (MDD) dataset, our proposed method achieves accuracy of 0.9166 and AUC of 0.9263. Experiments show that our proposed method outperforms other existing excellent neural disease automated diagnosis approaches. It shows that our novel prediction method performs great accurate for identification of brain diseases as well as existing outstanding prediction tools.

Deep multi-kernel auto-encoder network for clustering brain functional connectivity data

In this study, we propose a deep-learning network model called the deep multi-kernel auto-encoder clustering network (DMACN) for clustering functional connectivity data for brain diseases. This model is an end-to-end clustering algorithm that can learn potentially advanced features and cluster disease categories. Unlike other auto-encoders, DMACN has an added self-expression layer and standard back-propagation is used to learn the features that are beneficial for clustering brain functional connectivity data. In the self-expression layer, the kernel matrix is constructed to extract effective features and a new loss function is proposed to constrain the clustering portion, which enables the training of a deep neural learning network that tends to cluster. To test the performance of the proposed algorithm, we applied the end-to-end deep unsupervised clustering algorithm to brain connectivity data. We then conducted experiments based on four public brain functional connectivity data sets and our own functional connectivity data set. The DMACN algorithm yielded good results in various evaluations compared with the existing clustering algorithm for brain functional connectivity data, the deep auto-encoder clustering algorithm, and several other relevant clustering algorithms. The deep-learning-based clustering algorithm has great potential for use in the unsupervised recognition of brain diseases.

A diagnostic unified classification model for classifying multi-sized and multi-modal brain graphs using graph alignment

BACKGROUND

Presence of multimodal brain graphs derived from different neuroimaging modalities is inarguably one of the most critical challenges in building unified classification models that can be trained and tested on any brain graph regardless of its size and the modality it was derived from.

EXISTING METHODS

One solution is to learn a model for each modality independently, which is cumbersome and becomes more time-consuming as the number of modalities increases. Another traditional solution is to build a model inputting multimodal brain graphs for the target prediction task; however, this is only applicable to datasets where all samples have joint neuro-modalities.

NEW METHOD

In this paper, we propose to build a unified brain graph classification model trained on unpaired multimodal brain graphs, which can classify any brain graph of any size. This is enabled by incorporating a graph alignment step where all multi-modal graphs of different sizes and heterogeneous distributions are mapped to a common template graph. Next, we design a graph alignment strategy to the target fixed-size template and further apply linear discriminant analysis (LDA) to the aligned graphs as a supervised dimensionality reduction technique for the target classification task.

RESULTS

We tested our method on unpaired autistic and healthy brain connectomes derived from functional and morphological MRI datasets (two modalities).

CONCLUSION

Our results showed that our unified model method not only has great promise in solving such a challenging problem but achieves comparable performance to models trained on each modality independently.

Identification of early mild cognitive impairment using multi-modal data and graph convolutional networks

BACKGROUND

The identification of early mild cognitive impairment (EMCI), which is an early stage of Alzheimer's disease (AD) and is associated with brain structural and functional changes, is still a challenging task. Recent studies show great promises for improving the performance of EMCI identification by combining multiple structural and functional features, such as grey matter volume and shortest path length. However, extracting which features and how to combine multiple features to improve the performance of EMCI identification have always been a challenging problem. To address this problem, in this study we propose a new EMCI identification framework using multi-modal data and graph convolutional networks (GCNs). Firstly, we extract grey matter volume and shortest path length of each brain region based on automated anatomical labeling (AAL) atlas as feature representation from T1w MRI and rs-fMRI data of each subject, respectively. Then, in order to obtain features that are more helpful in identifying EMCI, a common multi-task feature selection method is applied. Afterwards, we construct a non-fully labelled subject graph using imaging and non-imaging phenotypic measures of each subject. Finally, a GCN model is adopted to perform the EMCI identification task.

RESULTS

Our proposed EMCI identification method is evaluated on 210 subjects, including 105 subjects with EMCI and 105 normal controls (NCs), with both T1w MRI and rs-fMRI data from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database. Experimental results show that our proposed framework achieves an accuracy of 84.1% and an area under the receiver operating characteristic (ROC) curve (AUC) of 0.856 for EMCI/NC classification. In addition, by comparison, the accuracy and AUC values of our proposed framework are better than those of some existing methods in EMCI identification.

CONCLUSION

Our proposed EMCI identification framework is effective and promising for automatic diagnosis of EMCI in clinical practice.

Default Mode Network Connectivity Moderates the Relationship Between the APOE Genotype and Cognition and Individualizes Identification Across the Alzheimer's Disease Spectrum

Although previous studies have investigated the effects of the apolipoprotein E (APOE) ɛ4 genotype on the default mode network (DMN) in the Alzheimer's disease (AD) spectrum, it is still unclear how the APOE genotype regulates the DMN and subsequently affects cognitive decline in the AD spectrum. One hundred sixty-nine subjects with resting-state functional magnetic resonance imaging data and neuropsychological test scores were selected from the Alzheimer's Disease Neuroimaging Initiative. The main effects and interaction of the APOE genotype and disease status on the DMN were explored. A moderation analysis was performed to investigate the relationship among the APOE genotype, DMN connectivity, and cognition. Additionally, the pair-wised DMN connectivity was used to classify AD spectrum, and the classification accuracy was validated. Compared to APOEɛ4 non-carriers, APOEɛ4 carriers showed the opposite trajectory of DMN connectivity across the AD spectrum. Specifically, the strengths in the posterior cingulate cortex (PCC) connecting with the right precuneus, insular, and fusiform area (FFA) were positively correlated with Mini-Mental State Examination (MMSE) scores in APOEɛ4 non-carriers but not in APOEɛ4 carriers. Furthermore, PCC-right FFA connectivity could moderate the effects of the APOE genotype on MMSE scores across the disease groups. More importantly, using a receiver operating characteristic analysis, these altered connectivities yielded strong classification powers in a pathological stage-dependent manner in the AD spectrum. These findings first identified the intrinsic DMN connectivity moderating the effect of the APOE genotype on cognition and provided a pathological stage-dependent neuroimaging biomarker for early differentiation of the AD spectrum.

Investigation on the Alteration of Brain Functional Network and Its Role in the Identification of Mild Cognitive Impairment

Mild cognitive impairment (MCI) is generally regarded as a prodromal stage of Alzheimer’s disease (AD). In coping with the challenges caused by AD, we analyzed resting-state functional magnetic resonance imaging data of 82 MCI subjects and 93 normal controls (NCs). The alteration of brain functional network in MCI was investigated on three scales, including global metrics, nodal characteristics, and modular properties. The results supported the existence of small worldness, hubs, and community structure in the brain functional networks of both groups. Compared with NCs, the network altered in MCI over all the three scales. In scale I, we found significantly decreased characteristic path length and increased global efficiency in MCI. Moreover, altered global network metrics were associated with cognitive level evaluated by neuropsychological assessments. In scale II, the nodal betweenness centrality of some global hubs, such as the right Crus II of cerebellar hemisphere (CERCRU2.R) and fusiform gyrus (FFG.R), changed significantly and associated with the severity and cognitive impairment in MCI. In scale III, although anatomically adjacent regions tended to be clustered into the same module regardless of group, discrepancies existed in the composition of modules in both groups, with a prominent separation of the cerebellum and a less localized organization of community structure in MCI compared with NC. Taking advantages of random forest approach, we achieved an accuracy of 91.4% to discriminate MCI patients from NCs by integrating cognitive assessments and network analysis. The importance of the used features fed into the classifier further validated the nodal characteristics of CERCRU2.R and FFG.R could be potential biomarkers in the identification of MCI. In conclusion, the present study demonstrated that the brain functional connectome data altered at the stage of MCI and could assist the automatic diagnosis of MCI patients.

Early-Stage Identification and Pathological Development of Alzheimer's Disease Using Multimodal MRI

Alzheimer's disease (AD) is one of the most common progressive and irreversible neurodegenerative diseases. The study of the pathological mechanism of AD and early-stage diagnosis is essential and important. Subjective cognitive decline (SCD), the first at-risk stage of AD occurring prior to amnestic mild cognitive impairment (aMCI), is of great research value and has gained our interest. To investigate the entire pathological development of AD pathology efficiently, we proposed a machine learning classification method based on a multimodal support vector machine (SVM) to investigate the structural and functional connectivity patterns of the three stages of AD (SCD, aMCI, and AD). Our experiments achieved an accuracy of 98.58% in the AD group, 97.76% in the aMCI group, and 80.24% in the SCD group. Moreover, in our experiments, we identified the most discriminating brain regions, which were mainly located in the default mode network and subcortical structures (SCS). Notably, with the development of AD pathology, SCS regions have become increasingly important, and structural connectivity has shown more discriminative power than functional connectivity. The current study may shed new light on the pathological mechanism of AD and suggests that whole-brain connectivity may provide potential effective biomarkers for the early-stage diagnosis of AD.