Discriminant analysis of longitudinal cortical thickness changes in Alzheimer's disease using dynamic and network features

Axonal damage and inflammation response are biological correlates of decline in small-world values: a cohort study in autosomal dominant Alzheimer's disease

The grey matter of the brain develops and declines in coordinated patterns during the lifespan. Such covariation patterns of grey matter structure can be quantified as grey matter networks, which can be measured with magnetic resonance imaging. In Alzheimer's disease, the global organization of grey matter networks becomes more random, which is captured by a decline in the small-world coefficient. Such decline in the small-world value has been robustly associated with cognitive decline across clinical stages of Alzheimer's disease. The biological mechanisms causing this decline in small-world values remain unknown. Cerebrospinal fluid (CSF) protein biomarkers are available for studying diverse pathological mechanisms in humans and can provide insight into decline. We investigated the relationships between 10 CSF proteins and small-world coefficient in mutation carriers (N = 219) and non-carriers (N = 136) of the Dominantly Inherited Alzheimer Network Observational study. Abnormalities in Amyloid beta, Tau, synaptic (Synaptosome associated protein-25, Neurogranin) and neuronal calcium-sensor protein (Visinin-like protein-1) preceded loss of small-world coefficient by several years, while increased levels in CSF markers for inflammation (Chitinase-3-like protein 1) and axonal injury (Neurofilament light) co-occurred with decreasing small-world values. This suggests that axonal loss and inflammation play a role in structural grey matter network changes.

Estimating Functional Brain Networks by Low-Rank Representation With Local Constraint

The functional architecture undergoes alterations during the preclinical phase of Alzheimer's disease. Consequently, the primary research focus has shifted towards identifying Alzheimer's disease and its early stages by constructing a functional connectivity network based on resting-state fMRI data. Recent investigations show that as Alzheimer's Disease (AD) progresses, modular tissue and connections in the core brain areas of AD patients diminish. Sparse learning methods are powerful tools for understanding Functional Brain Networks (FBNs) with Regions of Interest (ROIs) and a connectivity matrix measuring functional coherence between them. However, these tools often focus exclusively on functional connectivity measures, neglecting the brain network's modularity. Modularity orchestrates dynamic activities within the FBN to execute intricate cognitive tasks. To provide a comprehensive delineation of the FBN, we propose a local similarity-constrained low-rank sparse representation (LSLRSR) method that encodes modularity information under a manifold-regularized network learning framework and further formulate it as a low-rank sparse graph learning problem, which can be solved by an efficient optimization algorithm. Specifically, for each modularity structure, the Schatten p-norm regularizer reduces the reconstruction error and provides a better approximation of the low-rank constraint. Furthermore, we adopt a manifold-regularized local similarity prior to infer the intricate relationship between subnetwork similarity and modularity, guiding the modeling of FBN. Additionally, the proximal average method approximates the joint solution's proximal map, and the resulting nonconvex optimization problems are solved using the alternating direction multiplier method (ADMM). Compared to state-of-the-art methods for constructing FBNs, our algorithm generates a more modular FBN. This lays the groundwork for further research into alterations in brain network modularity resulting from diseases.

Brain Structure-Function Fusing Representation Learning Using Adversarial Decomposed-VAE for Analyzing MCI

Integrating the brain structural and functional connectivity features is of great significance in both exploring brain science and analyzing cognitive impairment clinically. However, it remains a challenge to effectively fuse structural and functional features in exploring the complex brain network. In this paper, a novel brain structure-function fusing-representation learning (BSFL) model is proposed to effectively learn fused representation from diffusion tensor imaging (DTI) and resting-state functional magnetic resonance imaging (fMRI) for mild cognitive impairment (MCI) analysis. Specifically, the decomposition-fusion framework is developed to first decompose the feature space into the union of the uniform and unique spaces for each modality, and then adaptively fuse the decomposed features to learn MCI-related representation. Moreover, a knowledge-aware transformer module is designed to automatically capture local and global connectivity features throughout the brain. Also, a uniform-unique contrastive loss is further devised to make the decomposition more effective and enhance the complementarity of structural and functional features. The extensive experiments demonstrate that the proposed model achieves better performance than other competitive methods in predicting and analyzing MCI. More importantly, the proposed model could be a potential tool for reconstructing unified brain networks and predicting abnormal connections during the degenerative processes in MCI.

Network-based diagnostic probability estimation from resting-state functional magnetic resonance imaging

Brain functional connectivity is a useful biomarker for diagnosing brain disorders. Connectivity is measured using resting-state functional magnetic resonance imaging (rs-fMRI). Previous studies have used a sequential application of the graphical model for network estimation and machine learning to construct predictive formulas for determining outcomes (e.g., disease or health) from the estimated network. However, the resulting network had limited utility for diagnosis because it was estimated independent of the outcome. In this study, we proposed a regression method with scores from rs-fMRI based on supervised sparse hierarchical components analysis (SSHCA). SSHCA has a hierarchical structure that consists of a network model (block scores at the individual level) and a scoring model (super scores at the population level). A regression model, such as the multiple logistic regression model with super scores as the predictor, was used to estimate diagnostic probabilities. An advantage of the proposed method was that the outcome-related (supervised) network connections and multiple scores corresponding to the sub-network estimation were helpful for interpreting the results. Our results in the simulation study and application to real data show that it is possible to predict diseases with high accuracy using the constructed model.

Topological properties of individual gray matter morphological networks in identifying the preclinical stages of Alzheimer's disease: a preliminary study

Background

Subjective cognitive decline (SCD) and mild cognitive impairment (MCI) are preclinical stages of Alzheimer's disease (AD). Individual biomarkers are essential for evaluating altered neurological outcomes at both SCD and MCI stages for early diagnosis and intervention of AD. In this study, we aimed to investigate the relationships between topological properties of the individual brain morphological network and clinical cognitive performances among healthy controls (HCs) and patients with SCD or MCI.

Methods

The topological measurements of individual morphological networks were analyzed using graph theory, and inter-group differences of standard graph topology were correlated and regressed to scores of clinical cognitive functions.

Results

Compared with HCs, the topology of the individual morphological networks in SCD and MCI patients was significantly altered. At the global level, altered topology was characterized by lower global efficiency, shorter characteristics path length, and normalized characteristics path length [all P<0.05, false discovery rate (FDR) corrected]. In addition, at the regional level, SCD and MCI patients exhibited abnormal degree centrality in the caudate nucleus and nodal efficiency in the caudate nucleus, right insula, lenticular nucleus, and putamen (all P<0.05, FDR corrected).

Conclusions

The topological features of individual gray matter morphological networks may serve as biomarkers to improve disease prognosis and intervention in the early stages of AD, namely SCD and MCI. Moreover, these findings may further elucidate the relationships between brain morphological alterations and cognitive dysfunctions in SCD and MCI.

Axonal damage and astrocytosis are biological correlates of grey matter network integrity loss: a cohort study in autosomal dominant Alzheimer disease

Brain development and maturation leads to grey matter networks that can be measured using magnetic resonance imaging. Network integrity is an indicator of information processing capacity which declines in neurodegenerative disorders such as Alzheimer disease (AD). The biological mechanisms causing this loss of network integrity remain unknown. Cerebrospinal fluid (CSF) protein biomarkers are available for studying diverse pathological mechanisms in humans and can provide insight into decline. We investigated the relationships between 10 CSF proteins and network integrity in mutation carriers (N=219) and noncarriers (N=136) of the Dominantly Inherited Alzheimer Network Observational study. Abnormalities in Aβ, Tau, synaptic (SNAP-25, neurogranin) and neuronal calcium-sensor protein (VILIP-1) preceded grey matter network disruptions by several years, while inflammation related (YKL-40) and axonal injury (NfL) abnormalities co-occurred and correlated with network integrity. This suggests that axonal loss and inflammation play a role in structural grey matter network changes.

Key points

Abnormal levels of fluid markers for neuronal damage and inflammatory processes in CSF are associated with grey matter network disruptions.The strongest association was with NfL, suggesting that axonal loss may contribute to disrupted network organization as observed in AD.Tracking biomarker trajectories over the disease course, changes in CSF biomarkers generally precede changes in brain networks by several years.

Brain disorder prediction with dynamic multivariate spatio-temporal features: Application to Alzheimer’s disease and autism spectrum disorder

The dynamic functional connectivity (dFC) in functional magnetic resonance imaging (fMRI) is beneficial for the analysis and diagnosis of neurological brain diseases. The dFCs between regions of interest (ROIs) are generally delineated by a specific template and clustered into multiple different states. However, these models inevitably fell into the model-driven self-contained system which ignored the diversity at spatial level and the dynamics at time level of the data. In this study, we proposed a spatial and time domain feature extraction approach for Alzheimer’s disease (AD) and autism spectrum disorder (ASD)-assisted diagnosis which exploited the dynamic connectivity among independent functional sub networks in brain. Briefly, independent sub networks were obtained by applying spatial independent component analysis (SICA) to the preprocessed fMRI data. Then, a sliding window approach was used to segment the time series of the spatial components. After that, the functional connections within the window were obtained sequentially. Finally, a temporal signal-sensitive long short-term memory (LSTM) network was used for classification. The experimental results on Alzheimer’s Disease Neuroimaging Initiative (ADNI) and Autism Brain Imaging Data Exchange (ABIDE) datasets showed that the proposed method effectively predicted the disease at the early stage and outperformed the existing algorithms. The dFCs between the different components of the brain could be used as biomarkers for the diagnosis of diseases such as AD and ASD, providing a reliable basis for the study of brain connectomics.

Brain-age is associated with progression to dementia in memory clinic patients

BACKGROUND

Biomarkers for the early detection of dementia risk hold promise for better disease monitoring and targeted interventions. However, most biomarker studies, particularly in neuroimaging, have analysed artificially 'clean' research groups, free from comorbidities, erroneous referrals, contraindications and from a narrow sociodemographic pool. Such biases mean that neuroimaging samples are often unrepresentative of the target population for dementia risk (e.g., people referred to a memory clinic), limiting the generalisation of these studies to real-world clinical settings. To facilitate better translation from research to the clinic, datasets that are more representative of dementia patient groups are warranted.

METHODS

We analysed T1-weighted MRI scans from a real-world setting of patients referred to UK memory clinic services (n = 1140; 60.2 % female and mean [SD] age of 70.0[10.8] years) to derive 'brain-age'. Brain-age is an index of age-related brain health based on quantitative analysis of structural neuroimaging, largely reflecting brain atrophy. Brain-predicted age difference (brain-PAD) was calculated as brain-age minus chronological age. We determined which patients went on to develop dementia between three months and 7.8 years after neuroimaging assessment (n = 476) using linkage to electronic health records.

RESULTS

Survival analysis, using Cox regression, indicated a 3 % increased risk of dementia per brain-PAD year (hazard ratio [95 % CI] = 1.03 [1.02,1.04], p < 0.0001), adjusted for baseline age, age2, sex, Mini Mental State Examination (MMSE) score and normalised brain volume. In sensitivity analyses, brain-PAD remained significant when time-to-dementia was at least 3 years (hazard ratio [95 % CI] = 1.06 [1.02, 1.09], p = 0.0006), or when baseline MMSE score ≥ 27 (hazard ratio [95 % CI] = 1.03 [1.01, 1.05], p = 0.0006).

CONCLUSIONS

Memory clinic patients with older-appearing brains are more likely to receive a subsequent dementia diagnosis. Potentially, brain-age could aid decision-making during initial memory clinic assessment to improve early detection of dementia. Even when neuroimaging assessment was more than 3 years prior to diagnosis and when cognitive functioning was not clearly impaired, brain-age still proved informative. These real-world results support the use of quantitative neuroimaging biomarkers like brain-age in memory clinics.

Multiview Feature Learning With Multiatlas-Based Functional Connectivity Networks for MCI Diagnosis

Functional connectivity (FC) networks built from resting-state functional magnetic resonance imaging (rs-fMRI) has shown promising results for the diagnosis of Alzheimer's disease and its prodromal stage, that is, mild cognitive impairment (MCI). FC is usually estimated as a temporal correlation of regional mean rs-fMRI signals between any pair of brain regions, and these regions are traditionally parcellated with a particular brain atlas. Most existing studies have adopted a predefined brain atlas for all subjects. However, the constructed FC networks inevitably ignore the potentially important subject-specific information, particularly, the subject-specific brain parcellation. Similar to the drawback of the "single view" (versus the "multiview" learning) in medical image-based classification, FC networks constructed based on a single atlas may not be sufficient to reveal the underlying complicated differences between normal controls and disease-affected patients due to the potential bias from that particular atlas. In this study, we propose a multiview feature learning method with multiatlas-based FC networks to improve MCI diagnosis. Specifically, a three-step transformation is implemented to generate multiple individually specified atlases from the standard automated anatomical labeling template, from which a set of atlas exemplars is selected. Multiple FC networks are constructed based on these preselected atlas exemplars, providing multiple views of the FC network-based feature representations for each subject. We then devise a multitask learning algorithm for joint feature selection from the constructed multiple FC networks. The selected features are jointly fed into a support vector machine classifier for multiatlas-based MCI diagnosis. Extensive experimental comparisons are carried out between the proposed method and other competing approaches, including the traditional single-atlas-based method. The results indicate that our method significantly improves the MCI classification, demonstrating its promise in the brain connectome-based individualized diagnosis of brain diseases.

MPC-STANet: Alzheimer's Disease Recognition Method Based on Multiple Phantom Convolution and Spatial Transformation Attention Mechanism

Alzheimer's disease (AD) is a progressive neurodegenerative disease with insidious and irreversible onset. The recognition of the disease stage of AD and the administration of effective interventional treatment are important to slow down and control the progression of the disease. However, due to the unbalanced distribution of the acquired data volume, the problem that the features change inconspicuously in different disease stages of AD, and the scattered and narrow areas of the feature areas (hippocampal region, medial temporal lobe, etc.), the effective recognition of AD remains a critical unmet need. Therefore, we first employ class-balancing operation using data expansion and Synthetic Minority Oversampling Technique (SMOTE) to avoid the AD MRI dataset being affected by classification imbalance in the training. Subsequently, a recognition network based on Multi-Phantom Convolution (MPC) and Space Conversion Attention Mechanism (MPC-STANet) with ResNet50 as the backbone network is proposed for the recognition of the disease stages of AD. In this study, we propose a Multi-Phantom Convolution in the way of convolution according to the channel direction and integrate it with the average pooling layer into two basic blocks of ResNet50: Conv Block and Identity Block to propose the Multi-Phantom Residual Block (MPRB) including Multi-Conv Block and Multi-Identity Block to better recognize the scattered and tiny disease features of Alzheimer's disease. Meanwhile, the weight coefficients are extracted from both vertical and horizontal directions using the Space Conversion Attention Mechanism (SCAM) to better recognize subtle structural changes in the AD MRI images. The experimental results show that our proposed method achieves an average recognition accuracy of 96.25%, F1 score of 95%, and mAP of 93%, and the number of parameters is only 1.69 M more than ResNet50.

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.

MRI Segmentation of Brain Tissue and Course Classification in Alzheimer’s Disease

Alzheimer’s disease (AD) is one of the most common diseases causing cognitive impairment in middle-aged and elderly people, and the high cost of the disease poses a challenge for health systems to cope with the expected increasing number of cases in the future. With the advance of aging of the society, China has the largest number of Alzheimer’s disease patients in the world. Therefore, how to diagnose Alzheimer’s disease early and accurately and intervene positively is an urgent problem. In this paper, the improved MultiRes + UNet network is used to effectively segment the brain tissue in the preprocessing. This method expands the convolutional field by null convolution to integrate the global information, mitigates the differences between encoder–decoder features by using MultiRes block and Res path structure, greatly reducing the memory requirement, and improving its accuracy, applicability, and robustness. The non-local means the attention model is introduced to make the mapped organization categories free from noise interference. In the classification problem, this paper adopts the improved VoxCNN network model for binary classification of AD, EMCI, LMCI, and NC. Experiments showed that the model classification performance and the accuracy rate improved significantly with the combined effect of the improved MultiRes + UNet network and VoxCNN network, the binary classification accuracy was 98.35% for AD vs. NC, 89.46% for AD vs. LMCI, 83.95% for LMCI vs. EMCI, and 88.27% for EMCI vs. NC.

Rich-Club Connectivity of the Structural Covariance Network Relates to Memory Processes in Mild Cognitive Impairment and Alzheimer's Disease

BACKGROUND

Though mediotemporal lobe volume changes are well-known features of Alzheimer's disease (AD), grey matter volume changes may be distributed throughout the brain. These distributed changes are not independent due to the underlying network structure and can be described in terms of a structural covariance network (SCN).

OBJECTIVE

To investigate how the cortical brain organization is altered in AD we studied the mutual connectivity of hubs in the SCN, i.e., the rich-club.

METHODS

To construct the SCNs, cortical thickness was obtained from structural MRI for 97 participants (normal cognition, n = 37; mild cognitive impairment, n = 41; Alzheimer-type dementia, n = 19). Subsequently, rich-club coefficients were calculated from the SCN, and related to memory performance and hippocampal volume using linear regression.

RESULTS

Lower rich-club connectivity was related to lower memory performance as well as lower hippocampal volume.

CONCLUSION

Therefore, this study provides novel evidence of reduced connectivity in hub areas in relation to AD-related cognitive impairments and atrophy.

Repeated measures discriminant analysis using multivariate generalized estimation equations

Discriminant analysis procedures that assume parsimonious covariance and/or means structures have been proposed for distinguishing between two or more populations in multivariate repeated measures designs. However, these procedures rely on the assumptions of multivariate normality which is not tenable in multivariate repeated measures designs which are characterized by binary, ordinal, or mixed types of response distributions. This study investigates the accuracy of repeated measures discriminant analysis (RMDA) based on the multivariate generalized estimating equations (GEE) framework for classification in multivariate repeated measures designs with the same or different types of responses repeatedly measured over time. Monte Carlo methods were used to compare the accuracy of RMDA procedures based on GEE, and RMDA based on maximum likelihood estimators (MLE) under diverse simulation conditions, which included number of repeated measure occasions, number of responses, sample size, correlation structures, and type of response distribution. RMDA based on GEE exhibited higher average classification accuracy than RMDA based on MLE especially in multivariate non-normal distributions. Three repeatedly measured responses namely severity of epilepsy, current number of anti-epileptic drugs, and parent-reported quality of life in children with epilepsy were used to demonstrate the application of these procedures.

Machine learning methods for predicting progression from mild cognitive impairment to Alzheimer's disease dementia: a systematic review

BACKGROUND

An increase in lifespan in our society is a double-edged sword that entails a growing number of patients with neurocognitive disorders, Alzheimer's disease being the most prevalent. Advances in medical imaging and computational power enable new methods for the early detection of neurocognitive disorders with the goal of preventing or reducing cognitive decline. Computer-aided image analysis and early detection of changes in cognition is a promising approach for patients with mild cognitive impairment, sometimes a prodromal stage of Alzheimer's disease dementia.

METHODS

We conducted a systematic review following PRISMA guidelines of studies where machine learning was applied to neuroimaging data in order to predict whether patients with mild cognitive impairment might develop Alzheimer's disease dementia or remain stable. After removing duplicates, we screened 452 studies and selected 116 for qualitative analysis.

RESULTS

Most studies used magnetic resonance image (MRI) and positron emission tomography (PET) data but also magnetoencephalography. The datasets were mainly extracted from the Alzheimer's disease neuroimaging initiative (ADNI) database with some exceptions. Regarding the algorithms used, the most common was support vector machine with a mean accuracy of 75.4%, but convolutional neural networks achieved a higher mean accuracy of 78.5%. Studies combining MRI and PET achieved overall better classification accuracy than studies that only used one neuroimaging technique. In general, the more complex models such as those based on deep learning, combined with multimodal and multidimensional data (neuroimaging, clinical, cognitive, genetic, and behavioral) achieved the best performance.

CONCLUSIONS

Although the performance of the different methods still has room for improvement, the results are promising and this methodology has a great potential as a support tool for clinicians and healthcare professionals.

Regression and Classification of Alzheimers Disease Diagnosis using NMF-TDNet Features from 3D Brain MR Image

With the development of deep learning and medical imaging technology, many researchers use convolutional neural network(CNN) to obtain deep-level features of medical image in order to better classify Alzheimer's disease (AD) and predict clinical scores. The principal component analysis network (PCANet) is a lightweight deep-learning network that mainly uses principal component analysis (PCA) to generate multilevel filter banks for the centralized learning of samples and then performs binarization and generates blockwise histograms to obtain image features. However, the dimensions of the extracted PCANet features reaching tens of thousands or even hundreds of thousands, and the formation of the multilevel filter banks is sample data dependent, reducing the flexibility of PCANet. In this paper, based on the idea of PCANet, we propose a data-independent network called the nonnegative matrix factorization tensor decomposition network (NMF-TDNet), which improves the computational efficiency and solves the data dependence problem of PCANet. In this network, we use nonnegative matrix factorization (NMF) instead of PCA to create multilevel filter banks for sample learning, then uses the learning results to build a higher-order tensor and perform tensor decomposition (TD) to achieve data dimensionality reduction, producing the final image features. Finally, our method use these features as the input of the support vector machine (SVM) for AD classification diagnosis and clinical score prediction. The performance of our method is extensively evaluated on the ADNI-1, ADNI-2 and OASIS datasets. The experimental results show that NMF-TDNet can achieve data dimensionality reduction (the dimensionality of the extracted features numbers only a few hundred dimensions, far less than the hundreds of thousands required by PCANet) and the NMF-TDNet features as input achieved superior performance than using PCANet features as input.

Joint super-resolution and synthesis of 1 mm isotropic MP-RAGE volumes from clinical MRI exams with scans of different orientation, resolution and contrast

Most existing algorithms for automatic 3D morphometry of human brain MRI scans are designed for data with near-isotropic voxels at approximately 1 mm resolution, and frequently have contrast constraints as well-typically requiring T1-weighted images (e.g., MP-RAGE scans). This limitation prevents the analysis of millions of MRI scans acquired with large inter-slice spacing in clinical settings every year. In turn, the inability to quantitatively analyze these scans hinders the adoption of quantitative neuro imaging in healthcare, and also precludes research studies that could attain huge sample sizes and hence greatly improve our understanding of the human brain. Recent advances in convolutional neural networks (CNNs) are producing outstanding results in super-resolution and contrast synthesis of MRI. However, these approaches are very sensitive to the specific combination of contrast, resolution and orientation of the input images, and thus do not generalize to diverse clinical acquisition protocols - even within sites. In this article, we present SynthSR, a method to train a CNN that receives one or more scans with spaced slices, acquired with different contrast, resolution and orientation, and produces an isotropic scan of canonical contrast (typically a 1 mm MP-RAGE). The presented method does not require any preprocessing, beyond rigid coregistration of the input scans. Crucially, SynthSR trains on synthetic input images generated from 3D segmentations, and can thus be used to train CNNs for any combination of contrasts, resolutions and orientations without high-resolution real images of the input contrasts. We test the images generated with SynthSR in an array of common downstream analyses, and show that they can be reliably used for subcortical segmentation and volumetry, image registration (e.g., for tensor-based morphometry), and, if some image quality requirements are met, even cortical thickness morphometry. The source code is publicly available at https://github.com/BBillot/SynthSR.

Tau-related grey matter network breakdown across the Alzheimer's disease continuum

BACKGROUND

Changes in grey matter covariance networks have been reported in preclinical and clinical stages of Alzheimer's disease (AD) and have been associated with amyloid-β (Aβ) deposition and cognitive decline. However, the role of tau pathology on grey matter networks remains unclear. Based on previously reported associations between tau pathology, synaptic density and brain structural measures, tau-related connectivity changes across different stages of AD might be expected. We aimed to assess the relationship between tau aggregation and grey matter network alterations across the AD continuum.

METHODS

We included 533 individuals (178 Aβ-negative cognitively unimpaired (CU) subjects, 105 Aβ-positive CU subjects, 122 Aβ-positive patients with mild cognitive impairment, and 128 patients with AD dementia) from the BioFINDER-2 study. Single-subject grey matter networks were extracted from T1-weighted images and graph theory properties including degree, clustering coefficient, path length, and small world topology were calculated. Associations between tau positron emission tomography (PET) values and global and regional network measures were examined using linear regression models adjusted for age, sex, and total intracranial volume. Finally, we tested whether the association of tau pathology with cognitive performance was mediated by grey matter network disruptions.

RESULTS

Across the whole sample, we found that higher tau load in the temporal meta-ROI was associated with significant changes in degree, clustering, path length, and small world values (all p < 0.001), indicative of a less optimal network organisation. Already in CU Aβ-positive individuals associations between tau burden and lower clustering and path length were observed, whereas in advanced disease stages elevated tau pathology was progressively associated with more brain network abnormalities. Moreover, the association between higher tau load and lower cognitive performance was only partly mediated (9.3 to 9.5%) through small world topology.

CONCLUSIONS

Our data suggest a close relationship between grey matter network disruptions and tau pathology in individuals with abnormal amyloid. This might reflect a reduced communication between neighbouring brain areas and an altered ability to integrate information from distributed brain regions with tau pathology, indicative of a more random network topology across different AD stages.

Predicting MCI to AD Conversation Using Integrated sMRI and rs-fMRI: Machine Learning and Graph Theory Approach

BACKGROUND

Graph theory and machine learning have been shown to be effective ways of classifying different stages of Alzheimer's disease (AD). Most previous studies have only focused on inter-subject classification with single-mode neuroimaging data. However, whether this classification can truly reflect the changes in the structure and function of the brain region in disease progression remains unverified. In the current study, we aimed to evaluate the classification framework, which combines structural Magnetic Resonance Imaging (sMRI) and resting-state functional Magnetic Resonance Imaging (rs-fMRI) metrics, to distinguish mild cognitive impairment non-converters (MCInc)/AD from MCI converters (MCIc) by using graph theory and machine learning.

METHODS

With the intra-subject (MCInc vs. MCIc) and inter-subject (MCIc vs. AD) design, we employed cortical thickness features, structural brain network features, and sub-frequency (full-band, slow-4, slow-5) functional brain network features for classification. Three feature selection methods [random subset feature selection algorithm (RSFS), minimal redundancy maximal relevance (mRMR), and sparse linear regression feature selection algorithm based on stationary selection (SS-LR)] were used respectively to select discriminative features in the iterative combinations of MRI and network measures. Then support vector machine (SVM) classifier with nested cross-validation was employed for classification. We also compared the performance of multiple classifiers (Random Forest, K-nearest neighbor, Adaboost, SVM) and verified the reliability of our results by upsampling.

RESULTS

We found that in the classifications of MCIc vs. MCInc, and MCIc vs. AD, the proposed RSFS algorithm achieved the best accuracies (84.71, 89.80%) than the other algorithms. And the high-sensitivity brain regions found with the two classification groups were inconsistent. Specifically, in MCIc vs. MCInc, the high-sensitivity brain regions associated with both structural and functional features included frontal, temporal, caudate, entorhinal, parahippocampal, and calcarine fissure and surrounding cortex. While in MCIc vs. AD, the high-sensitivity brain regions associated only with functional features included frontal, temporal, thalamus, olfactory, and angular.

CONCLUSIONS

These results suggest that our proposed method could effectively predict the conversion of MCI to AD, and the inconsistency of specific brain regions provides a novel insight for clinical AD diagnosis.

Gray matter structural networks related to 18F-THK5351 retention in cognitively normal older adults and Alzheimer's disease patients

Objective

This study aimed to examine the alterations in gray matter networks related to tau retention in Alzheimer's disease (AD) patients and cognitively normal (CN) older individuals.

Methods

Eighteen amyloid-positive AD patients and 30 age- and sex-matched amyloid-negative CN controls were enrolled. All underwent 3D T1-weighted MRI, amyloid positron-emission tomography imaging (PET) with ¹¹C-Pittsburgh Compound B (PiB), and tau PET with ¹⁸F-THK5351. The structural networks extracted from the T1-weighted MRI data based on cortical similarities within single subjects were analyzed. Based on graph theoretical approach, global and local network properties across the whole brain were computed. Group comparisons of global and local network properties were evaluated between the groups. Then, we correlated the global and local network measures with total cerebral ¹⁸F-THK5351 retention.

Results

AD patients moved toward more randomized global network compared to controls and regional differences were observed in the default mode network (DMN) area. No significant correlations existed between global network properties and tau retention. On a local level, AD and controls showed opposite relationships between network properties and tau retention mainly in the DMN areas; CN controls showed positive correlations, whereas AD showed negative correlations.

Conclusion

We found opposite relationships between local network properties and tau retention between amyloid-positive AD patients and amyloid-negative controls. Our findings suggest that the presence of amyloid and induced exacerbated tau retention alter the relationship of local network properties and tau retention.

•

Correlation of structural network properties and tau retention.

•

Positive correlations between local network properties and tau retention in healthy elderly.

•

Negative correlations between local network properties and tau retention in AD.

Long range early diagnosis of Alzheimer's disease using longitudinal MR imaging data

The enormous social and economic cost of Alzheimer's disease (AD) has driven a number of neuroimaging investigations for early detection and diagnosis. Towards this end, various computational approaches have been applied to longitudinal imaging data in subjects with Mild Cognitive Impairment (MCI), as serial brain imaging could increase sensitivity for detecting changes from baseline, and potentially serve as a diagnostic biomarker for AD. However, current state-of-the-art brain imaging diagnostic methods have limited utility in clinical practice due to the lack of robust predictive power. To address this limitation, we propose a flexible spatial-temporal solution to predict the risk of MCI conversion to AD prior to the onset of clinical symptoms by sequentially recognizing abnormal structural changes from longitudinal magnetic resonance (MR) image sequences. Firstly, our model is trained to sequentially recognize different length partial MR image sequences from different stages of AD. Secondly, our method is leveraged by the inexorably progressive nature of AD. To that end, a Temporally Structured Support Vector Machine (TS-SVM) model is proposed to constrain the partial MR image sequence's detection score to increase monotonically with AD progression. Furthermore, in order to select the best morphological features for enabling classifiers, we propose a joint feature selection and classification framework. We demonstrate that our early diagnosis method using only two follow-up MR scans is able to predict conversion to AD 12 months ahead of an AD clinical diagnosis with 81.75% accuracy.

Predicting Alzheimer's conversion in mild cognitive impairment patients using longitudinal neuroimaging and clinical markers

Patients with mild cognitive impairment (MCI) have a high risk for conversion to Alzheimer's disease (AD). Early diagnose of AD in MCI subjects could help to slow or halt the disease progression. Selecting a set of relevant markers from multimodal data to predict conversion from MCI to probable AD has become a challenging task. The aim of this paper is to quantify the impact of longitudinal predictive models with single- or multisource data for predicting MCI-to-AD conversion and identifying a very small subset of features that are highly predictive of conversion. We developed predictive models of MCI-to-AD progression that combine magnetic resonance imaging (MRI)-based markers (cortical thickness and volume of subcortical structures) with neuropsychological tests. These models were built with longitudinal data and validated using baseline values. By using a linear mixed effects approach, we modeled the longitudinal trajectories of the markers. A set of longitudinal features potentially discriminating between MCI subjects who convert to dementia and those who remain stable over a period of 3 years was obtained. Classifier were trained using the marginal longitudinal trajectory residues from the selected features. Our best models predicted conversion with 77% accuracy at baseline (AUC = 0.855, 84% sensitivity, 70% specificity). As more visits were available, longitudinal predictive models improved their predictions with 84% accuracy (AUC = 0.912, 83% sensitivity, 84% specificity). The proposed approach was developed, trained and evaluated using the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset with a total of 2491 visits from 610 subjects.

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.

Neuroimaging advances regarding subjective cognitive decline in preclinical Alzheimer's disease

Subjective cognitive decline (SCD) is regarded as the first clinical manifestation in the Alzheimer’s disease (AD) continuum. Investigating populations with SCD is important for understanding the early pathological mechanisms of AD and identifying SCD-related biomarkers, which are critical for the early detection of AD. With the advent of advanced neuroimaging techniques, such as positron emission tomography (PET) and magnetic resonance imaging (MRI), accumulating evidence has revealed structural and functional brain alterations related to the symptoms of SCD. In this review, we summarize the main imaging features and key findings regarding SCD related to AD, from local and regional data to connectivity-based imaging measures, with the aim of delineating a multimodal imaging signature of SCD due to AD. Additionally, the interaction of SCD with other risk factors for dementia due to AD, such as age and the Apolipoprotein E (ApoE) ɛ4 status, has also been described. Finally, the possible explanations for the inconsistent and heterogeneous neuroimaging findings observed in individuals with SCD are discussed, along with future directions. Overall, the literature reveals a preferential vulnerability of AD signature regions in SCD in the context of AD, supporting the notion that individuals with SCD share a similar pattern of brain alterations with patients with mild cognitive impairment (MCI) and dementia due to AD. We conclude that these neuroimaging techniques, particularly multimodal neuroimaging techniques, have great potential for identifying the underlying pathological alterations associated with SCD. More longitudinal studies with larger sample sizes combined with more advanced imaging modeling approaches such as artificial intelligence are still warranted to establish their clinical utility.

Tau pathology in early Alzheimer's disease is linked to selective disruptions in neurophysiological network dynamics

Understanding the role of Tau protein aggregation in the pathogenesis of Alzheimer's disease is critical for the development of new Tau-based therapeutic strategies to slow or prevent dementia. We tested the hypothesis that Tau pathology is associated with functional organization of widespread neurophysiological networks. We used electro-magnetoencephalography with [¹⁸F]AV-1451 PET scanning to quantify Tau-dependent network changes. Using a graph theoretical approach to brain connectivity, we quantified nodal measures of functional segregation, centrality, and the efficiency of information transfer and tested them against levels of [¹⁸F]AV-1451. Higher Tau burden in early Alzheimer's disease was associated with a shift away from the optimal small-world organization and a more fragmented network in the beta and gamma bands, whereby parieto-occipital areas were disconnected from the anterior parts of the network. Similarly, higher Tau burden was associated with decreases in both local and global efficiency, especially in the gamma band. The results support the translational development of neurophysiological "signatures" of Alzheimer's disease, to understand disease mechanisms in humans and facilitate experimental medicine studies.

Single-subject grey matter network trajectories over the disease course of autosomal dominant Alzheimer's disease

Structural grey matter covariance networks provide an individual quantification of morphological patterns in the brain. The network integrity is disrupted in sporadic Alzheimer's disease, and network properties show associations with the level of amyloid pathology and cognitive decline. Therefore, these network properties might be disease progression markers. However, it remains unclear when and how grey matter network integrity changes with disease progression. We investigated these questions in autosomal dominant Alzheimer's disease mutation carriers, whose conserved age at dementia onset allows individual staging based upon their estimated years to symptom onset. From the Dominantly Inherited Alzheimer Network observational cohort, we selected T1-weighted MRI scans from 269 mutation carriers and 170 non-carriers (mean age 38 ± 15 years, mean estimated years to symptom onset -9 ± 11), of whom 237 had longitudinal scans with a mean follow-up of 3.0 years. Single-subject grey matter networks were extracted, and we calculated for each individual the network properties which describe the network topology, including the size, clustering, path length and small worldness. We determined at which time point mutation carriers and non-carriers diverged for global and regional grey matter network metrics, both cross-sectionally and for rate of change over time. Based on cross-sectional data, the earliest difference was observed in normalized path length, which was decreased for mutation carriers in the precuneus area at 13 years and on a global level 12 years before estimated symptom onset. Based on longitudinal data, we found the earliest difference between groups on a global level 6 years before symptom onset, with a greater rate of decline of network size for mutation carriers. We further compared grey matter network small worldness with established biomarkers for Alzheimer disease (i.e. amyloid accumulation, cortical thickness, brain metabolism and cognitive function). We found that greater amyloid accumulation at baseline was associated with faster decline of small worldness over time, and decline in grey matter network measures over time was accompanied by decline in brain metabolism, cortical thinning and cognitive decline. In summary, network measures decline in autosomal dominant Alzheimer's disease, which is alike sporadic Alzheimer's disease, and the properties show decline over time prior to estimated symptom onset. These data suggest that single-subject networks properties obtained from structural MRI scans form an additional non-invasive tool for understanding the substrate of cognitive decline and measuring progression from preclinical to severe clinical stages of Alzheimer's disease.

A toolbox for brain network construction and classification (BrainNetClass)

Brain functional network has been increasingly used in understanding brain functions and diseases. While many network construction methods have been proposed, the progress in the field still largely relies on static pairwise Pearson's correlation-based functional network and group-level comparisons. We introduce a "Brain Network Construction and Classification (BrainNetClass)" toolbox to promote more advanced brain network construction methods to the filed, including some state-of-the-art methods that were recently developed to capture complex and high-order interactions among brain regions. The toolbox also integrates a well-accepted and rigorous classification framework based on brain connectome features toward individualized disease diagnosis in a hope that the advanced network modeling could boost the subsequent classification. BrainNetClass is a MATLAB-based, open-source, cross-platform toolbox with both graphical user-friendly interfaces and a command line mode targeting cognitive neuroscientists and clinicians for promoting reliability, reproducibility, and interpretability of connectome-based, computer-aided diagnosis. It generates abundant classification-related results from network presentations to contributing features that have been largely ignored by most studies to grant users the ability of evaluating the disease diagnostic model and its robustness and generalizability. We demonstrate the effectiveness of the toolbox on real resting-state functional MRI datasets. BrainNetClass (v1.0) is available at https://github.com/zzstefan/BrainNetClass.

Medical Conditions Linked to Atherosclerosis Are Associated With Magnified Cortical Thinning in Individuals With Alcohol Use Disorders

AIMS

Magnetic resonance imaging (MRI) studies report widespread cortical thinning in individuals with alcohol use disorder (AUD), but did not consider potential effects of pro-atherogenic conditions such as hypertension, type 2 diabetes mellitus, hepatitis C seropositivity and hyperlipidemia on cortical thickness. The conditions are associated with regional cortical thinning in those without AUD. We predicted that individuals with concurrent AUD and pro-atherogenic conditions demonstrate the greatest regional cortical thinning in areas most vulnerable to decreased perfusion.

METHODS

Treatment-seeking individuals with AUD (n = 126) and healthy controls (CON; n = 49) completed a 1.5 T MRI study. Regional cortical thickness was quantitated via FreeSurfer. Individuals with AUD and pro-atherogenic conditions (Atherogenic+), AUD without pro-atherogenic conditions (Atherogenic-) and CON were compared on regional cortical thickness.

RESULTS

Individuals with AUD showed significant bilateral cortical thinning compared to CON, but Atherogenic+ demonstrated the most widespread and greatest magnitude of regional thinning, while Atherogenic- had reduced thickness primarily in anterior frontal and posterior parietal lobes. Atherogenic+ also showed a thinner cortex than Atherogenic- in lateral orbitofrontal and dorso/dorsolateral frontal cortex, mesial and lateral temporal and inferior parietal regions.

CONCLUSIONS

Our results demonstrate significant bilateral cortical thinning in individuals with AUD relative to CON, but the distribution and magnitude were influenced by comorbid pro-atherogenic conditions. The magnitude of cortical thinning in Atherogenic+ strongly corresponded to cortical watershed areas susceptible to decreased perfusion, which may result in morphometric abnormalities. The findings indicate that pro-atherogenic conditions may contribute to cortical thinning in those seeking treatment for AUD.

A survey on machine and statistical learning for longitudinal analysis of neuroimaging data in Alzheimer's disease

BACKGROUND AND OBJECTIVES

Recently, longitudinal studies of Alzheimer's disease have gathered a substantial amount of neuroimaging data. New methods are needed to successfully leverage and distill meaningful information on the progression of the disease from the deluge of available data. Machine learning has been used successfully for many different tasks, including neuroimaging related problems. In this paper, we review recent statistical and machine learning applications in Alzheimer's disease using longitudinal neuroimaging.

METHODS

We search for papers using longitudinal imaging data, focused on Alzheimer's Disease and published between 2007 and 2019 on four different search engines.

RESULTS

After the search, we obtain 104 relevant papers. We analyze their approach to typical challenges in longitudinal data analysis, such as missing data and variability in the number and extent of acquisitions.

CONCLUSIONS

Reviewed works show that machine learning methods using longitudinal data have potential for disease progression modelling and computer-aided diagnosis. We compare results and models, and propose future research directions in the field.

Relative rate of change in cognitive score network dynamics via Bayesian hierarchical models reveal spatial patterns of neurodegeneration

The degeneration of the human brain is a complex process, which often affects certain brain regions due to healthy aging or disease. This degeneration can be evaluated on regions of interest (ROI) in the brain through probabilistic networks and morphological estimates. Current approaches for finding such networks are limited to analyses at discrete neuropsychological stages, which cannot appropriately account for connectivity dynamics over the onset of cognitive deterioration, and morphological changes are seldom unified with connectivity networks, despite known dependencies. To overcome these limitations, a probabilistic wombling model is proposed to simultaneously estimate ROI cortical thickness and covariance networks contingent on rates of change in cognitive decline. This proposed model was applied to analyze longitudinal data from healthy control (HC) and Alzheimer's disease (AD) groups and found connection differences pertaining to regions, which play a crucial role in lasting cognitive impairment, such as the entorhinal area and temporal regions. Moreover, HC cortical thickness estimates were significantly higher than those in the AD group across all ROIs. The analyses presented in this work will help practitioners jointly analyze brain tissue atrophy at the ROI-level conditional on neuropsychological networks, which could potentially allow for more targeted therapeutic interventions.

Gaussian Graphical Models Reveal Inter-Modal and Inter-Regional Conditional Dependencies of Brain Alterations in Alzheimer's Disease

Alzheimer's disease (AD) is characterized by a sequence of pathological changes, which are commonly assessed in vivo using various brain imaging modalities such as magnetic resonance imaging (MRI) and positron emission tomography (PET). Currently, the most approaches to analyze statistical associations between regions and imaging modalities rely on Pearson correlation or linear regression models. However, these models are prone to spurious correlations arising from uninformative shared variance and multicollinearity. Notably, there are no appropriate multivariate statistical models available that can easily integrate dozens of multicollinear variables derived from such data, being able to utilize the additional information provided from the combination of data sources. Gaussian graphical models (GGMs) can estimate the conditional dependency from given data, which is conceptually expected to closely reflect the underlying causal relationships between various variables. Hence, we applied GGMs to assess multimodal regional brain alterations in AD. We obtained data from N = 972 subjects from the Alzheimer's Disease Neuroimaging Initiative. The mean amyloid load (AV45-PET), glucose metabolism (FDG-PET), and gray matter volume (MRI) were calculated for each of the 108 cortical and subcortical brain regions. GGMs were estimated using a Bayesian framework for the combined multimodal data and the resulted conditional dependency networks were compared to classical covariance networks based on Pearson correlation. Additionally, graph-theoretical network statistics were calculated to determine network alterations associated with disease status. The resulting conditional dependency matrices were much sparser (≈10% density) than Pearson correlation matrices (≈50% density). Within imaging modalities, conditional dependency networks yielded clusters connecting anatomically adjacent regions. For the associations between different modalities, only few region-specific connections were detected. Network measures such as small-world coefficient were significantly altered across diagnostic groups, with a biphasic u-shape trajectory, i.e., increased small-world coefficient in early mild cognitive impairment (MCI), similar values in late MCI, and decreased values in AD dementia patients compared to cognitively normal controls. In conclusion, GGMs removed commonly shared variance among multimodal measures of regional brain alterations in MCI and AD, and yielded sparser matrices compared to correlation networks based on the Pearson coefficient. Therefore, GGMs may be used as alternative to thresholding-approaches typically applied to correlation networks to obtain the most informative relations between variables.

A Survey on Computer-Aided Diagnosis of Brain Disorders through MRI Based on Machine Learning and Data Mining Methodologies with an Emphasis on Alzheimer Disease Diagnosis and the Contribution of the Multimodal Fusion

Computer-aided diagnostic (CAD) systems use machine learning methods that provide a synergistic effect between the neuroradiologist and the computer, enabling an efficient and rapid diagnosis of the patient’s condition. As part of the early diagnosis of Alzheimer’s disease (AD), which is a major public health problem, the CAD system provides a neuropsychological assessment that helps mitigate its effects. The use of data fusion techniques by CAD systems has proven to be useful, they allow for the merging of information relating to the brain and its tissues from MRI, with that of other types of modalities. This multimodal fusion refines the quality of brain images by reducing redundancy and randomness, which contributes to improving the clinical reliability of the diagnosis compared to the use of a single modality. The purpose of this article is first to determine the main steps of the CAD system for brain magnetic resonance imaging (MRI). Then to bring together some research work related to the diagnosis of brain disorders, emphasizing AD. Thus the most used methods in the stages of classification and brain regions segmentation are described, highlighting their advantages and disadvantages. Secondly, on the basis of the raised problem, we propose a solution within the framework of multimodal fusion. In this context, based on quantitative measurement parameters, a performance study of multimodal CAD systems is proposed by comparing their effectiveness with those exploiting a single MRI modality. In this case, advances in information fusion techniques in medical imagery are accentuated, highlighting their advantages and disadvantages. The contribution of multimodal fusion and the interest of hybrid models are finally addressed, as well as the main scientific assertions made, in the field of brain disease diagnosis.

A distributed multitask multimodal approach for the prediction of Alzheimer's disease in a longitudinal study

Predicting the progression of Alzheimer's Disease (AD) has been held back for decades due to the lack of sufficient longitudinal data required for the development of novel machine learning algorithms. This study proposes a novel machine learning algorithm for predicting the progression of Alzheimer's disease using a distributed multimodal, multitask learning method. More specifically, each individual task is defined as a regression model, which predicts cognitive scores at a single time point. Since the prediction tasks for multiple intervals are related to each other in chronological order, multitask regression models have been developed to track the relationship between subsequent tasks. Furthermore, since subjects have various combinations of recording modalities together with other genetic, neuropsychological and demographic risk factors, special attention is given to the fact that each modality may experience a specific sparsity pattern. The model is hence generalized by exploiting multiple individual multitask regression coefficient matrices for each modality. The outcome for each independent modality-specific learner is then integrated with complementary information, known as risk factor parameters, revealing the most prevalent trends of the multimodal data. This new feature space is then used as input to the gradient boosting kernel in search for a more accurate prediction. This proposed model not only captures the complex relationships between the different feature representations, but it also ignores any unrelated information which might skew the regression coefficients. Comparative assessments are made between the performance of the proposed method with several other well-established methods using different multimodal platforms. The results indicate that by capturing the interrelatedness between the different modalities and extracting only relevant information in the data, even in an incomplete longitudinal dataset, will yield minimized prediction errors.

Regional brain atrophy predicts time to conversion to Alzheimer's disease, dependent on baseline volume

A key question for the design of clinical trials for Alzheimer's disease (AD) is whether the timing of conversion from mild cognitive impairment (MCI) to AD can be predicted. This is also an important question for the clinical management of MCI. This study aims to address this question by exploring the contribution of baseline brain volume and annual volume change, using Cox regression, in predicting the time to conversion. Individuals with MCI, who converted to AD (n = 198), reverted to normal (n = 38), or remained stable (n = 96) for at least five years, were included in this study. The results revealed that the volumes of all the brain areas considered were predictive of the time to conversion from MCI to AD. Annual change in volume was also predictive of the time to conversion but only when initial volumes were above a certain threshold. This is important because it suggests that reduction in atrophy rate, which is the outcome of some clinical trials, is not inevitably associated with delay in conversion from MCI to AD.

Sex-Related Reserve Hypothesis in Alzheimer's Disease: Changes in Cortical Thickness with a Five-Year Longitudinal Follow-Up

BACKGROUND

Sex effects on the progression of Alzheimer's disease (AD) have received less attention than other demographic factors, including onset age and education.

OBJECTIVE

The aim of this study was to investigate whether sex affected cortical thinning in the disease progression of AD.

METHODS

We prospectively recruited 36 patients with early-stage AD and 14 people with normal cognition. All subjects were assessed with magnetic resonance imaging at baseline, Year 1, Year 3, and Year 5. We performed cortical thickness analyses using surface-based morphometry on magnetic resonance imaging.

RESULTS

Women with AD showed more rapid cortical thinning in the left dorsolateral frontal cortex, left superior temporal gyrus, bilateral temporo-parietal association cortices, bilateral anterior cingulate gyri, bilateral medial frontal cortices, and bilateral occipital cortices over 5 years than men with AD, even though there was no difference in cortical thickness at baseline. In contrast, there were no regions of significantly more rapid atrophy in men with AD.

CONCLUSIONS

Our findings suggest that women deteriorate faster than men in the progression of AD.

Cortical graph neural network for AD and MCI diagnosis and transfer learning across populations

Combining machine learning with neuroimaging data has a great potential for early diagnosis of mild cognitive impairment (MCI) and Alzheimer's disease (AD). However, it remains unclear how well the classifiers built on one population can predict MCI/AD diagnosis of other populations. This study aimed to employ a spectral graph convolutional neural network (graph-CNN), that incorporated cortical thickness and geometry, to identify MCI and AD based on 3089 T1-weighted MRI data of the ADNI-2 cohort, and to evaluate its feasibility to predict AD in the ADNI-1 cohort (n = 3602) and an Asian cohort (n = 347). For the ADNI-2 cohort, the graph-CNN showed classification accuracy of controls (CN) vs. AD at 85.8% and early MCI (EMCI) vs. AD at 79.2%, followed by CN vs. late MCI (LMCI) (69.3%), LMCI vs. AD (65.2%), EMCI vs. LMCI (60.9%), and CN vs. EMCI (51.8%). We demonstrated the robustness of the graph-CNN among the existing deep learning approaches, such as Euclidean-domain-based multilayer network and 1D CNN on cortical thickness, and 2D and 3D CNNs on T1-weighted MR images of the ADNI-2 cohort. The graph-CNN also achieved the prediction on the conversion of EMCI to AD at 75% and that of LMCI to AD at 92%. The find-tuned graph-CNN further provided a promising CN vs. AD classification accuracy of 89.4% on the ADNI-1 cohort and >90% on the Asian cohort. Our study demonstrated the feasibility to transfer AD/MCI classifiers learned from one population to the other. Notably, incorporating cortical geometry in CNN has the potential to improve classification performance.

Brain network disintegration as a final common pathway for delirium: a systematic review and qualitative meta-analysis

Delirium is an acute neuropsychiatric syndrome characterized by altered levels of attention and awareness with cognitive deficits. It is most prevalent in elderly hospitalized patients and related to poor outcomes. Predisposing risk factors, such as older age, determine the baseline vulnerability for delirium, while precipitating factors, such as use of sedatives, trigger the syndrome. Risk factors are heterogeneous and the underlying biological mechanisms leading to vulnerability for delirium are poorly understood. We tested the hypothesis that delirium and its risk factors are associated with consistent brain network changes. We performed a systematic review and qualitative meta-analysis and included 126 brain network publications on delirium and its risk factors. Findings were evaluated after an assessment of methodological quality, providing N=99 studies of good or excellent quality on predisposing risk factors, N=10 on precipitation risk factors and N=7 on delirium. Delirium was consistently associated with functional network disruptions, including lower EEG connectivity strength and decreased fMRI network integration. Risk factors for delirium were associated with lower structural connectivity strength and less efficient structural network organization. Decreased connectivity strength and efficiency appear to characterize structural brain networks of patients at risk for delirium, possibly impairing the functional network, while functional network disintegration seems to be a final common pathway for the syndrome.

•

Delirium is consistently associated with functional network impairments.

•

Risk factors are associated with lower structural connectivity strength.

•

Risk factors are associated with a less efficient structural network organization.

•

Structural impairments make the functional network more vulnerable to deterioration.

•

Functional network disintegration seems to be a final common pathway for delirium.

Strength and Similarity Guided Group-level Brain Functional Network Construction for MCI Diagnosis

Sparse representation-based brain functional network modeling often results in large inter-subject variability in the network structure. This could reduce the statistical power in group comparison, or even deteriorate the generalization capability of the individualized diagnosis of brain diseases. Although group sparse representation (GSR) can alleviate such a limitation by increasing network similarity across subjects, it could, in turn, fail in providing satisfactory separability between the subjects from different groups (e.g., patients vs. controls). In this study, we propose to integrate individual functional connectivity (FC) information into the GSR-based network construction framework to achieve higher between-group separability while maintaining the merit of within-group consistency. Our method was based on an observation that the subjects from the same group have generally more similar FC patterns than those from different groups. To this end, we propose our new method, namely "strength and similarity guided GSR (SSGSR)", which exploits both BOLD signal temporal correlation-based "low-order" FC (LOFC) and inter-subject LOFC-profile similarity-based "high-order" FC (HOFC) as two priors to jointly guide the GSR-based network modeling. Extensive experimental comparisons are carried out, with the rs-fMRI data from mild cognitive impairment (MCI) subjects and healthy controls, between the proposed algorithm and other state-of-the-art brain network modeling approaches. Individualized MCI identification results show that our method could achieve a balance between the individually consistent brain functional network construction and the adequately maintained inter-group brain functional network distinctions, thus leading to a more accurate classification result. Our method also provides a promising and generalized solution for the future connectome-based individualized diagnosis of brain disease.

RNN-based longitudinal analysis for diagnosis of Alzheimer's disease

Alzheimer's disease (AD) is an irreversible neurodegenerative disorder with progressive impairment of memory and other mental functions. Magnetic resonance images (MRI) have been widely used as an important imaging modality of brain for AD diagnosis and monitoring the disease progression. The longitudinal analysis of sequential MRIs is important to model and measure the progression of the disease along the time axis for more accurate diagnosis. Most existing methods extracted the features capturing the morphological abnormalities of brain and their longitudinal changes using MRIs and then designed a classifier to discriminate different groups. However, these methods have several limitations. First, since the feature extraction and classifier model are independent, the extracted features may not capture the full characteristics of brain abnormalities related to AD. Second, longitudinal MR images may be missing at some time points for some subjects, which results in difficulties for extraction of consistent features for longitudinal analysis. In this paper, we present a classification framework based on combination of convolutional and recurrent neural networks for longitudinal analysis of structural MR images in AD diagnosis. First, Convolutional Neural Networks (CNN) is constructed to learn the spatial features of MR images for the classification task. After that, recurrent Neural Networks (RNN) with cascaded three bidirectional gated recurrent units (BGRU) layers is constructed on the outputs of CNN at multiple time points for extracting the longitudinal features for AD classification. Instead of independently performing feature extraction and classifier training, the proposed method jointly learns the spatial and longitudinal features and disease classifier, which can achieve optimal performance. In addition, the proposed method can model the longitudinal analysis using RNN from the imaging data at various time points. Our method is evaluated with the longitudinal T1-weighted MR images of 830 participants including 198 AD, 403 mild cognitive impairment (MCI), and 229 normal controls (NC) subjects from Alzheimer's Disease Neuroimaging Initiative (ADNI) database. Experimental results show that the proposed method achieves classification accuracy of 91.33% for AD vs. NC and 71.71% for pMCI vs. sMCI, demonstrating the promising performance for longitudinal MR image analysis.

Alterations of Graphic Properties and Related Cognitive Functioning Changes in Mild Alzheimer's Disease Revealed by Individual Morphological Brain Network

Alzheimer’s disease (AD) is one of the most common forms of dementia that has slowly negative impacts on memory and cognition. With the assistance of multimodal brain networks and graph-based analysis approaches, AD-related network disruptions support the hypothesis that AD can be identified as a dysconnectivity syndrome. However, as the recent emerging of individual-based morphological network research of AD, the utilization of multiple morphometric features may provide a broader horizon for locating the lesions. Therefore, the present study applied the newly proposed individual morphological brain network with five commonly used morphometric features (cortical thickness, regional volume, surface area, mean curvature, and fold index) to explore the topological aberrations and their relationship with cognitive functioning alterations in the early stage of AD. A total of 40 right-handed participants were selected from Open Access Series of Imaging Studies Database with 20 AD patients (age ranged from 70 to 79, CDR = 0.5) and 20 age/gender-matched healthy controls. The significantly affected connections (p < 0.05 with FDR correction) were observed across multiple regions, both enhanced and attenuated correlations, primarily related to the left entorhinal cortex (ENT). In addition, profoundly changed Mini Mental State Examination (MMSE) score and global efficiency (p < 0.05) were noted in the AD patients, as well as the pronounced inter-group distinctions of betweenness centrality, global and local efficiency (p < 0.05) in the higher MMSE score zone (28–30), which indicating the potential role of graphic properties in determination of early-stage AD patients. Moreover, the reservations (regions in the occipital and frontal lobes) and alterations (regions in the right temporal lobe and cingulate cortex) of hubs were also detected in the AD patients. Overall, the findings further confirm the selective AD-related disruptions in morphological brain networks and also suggest the feasibility of applying the morphological graphic properties in the discrimination of early-stage AD patients.

Discriminating Alzheimer's disease progression using a new hippocampal marker from T1-weighted MRI: The local surface roughness

Hippocampal atrophy is one of the main hallmarks of Alzheimer's disease (AD). However, there is still controversy about whether this sign is a robust finding during the early stages of the disease, such as in mild cognitive impairment (MCI) and subjective cognitive decline (SCD). Considering this background, we proposed a new marker for assessing hippocampal atrophy: the local surface roughness (LSR). We tested this marker in a sample of 307 subjects (normal control (NC) = 70, SCD = 87, MCI = 137, AD = 13). In addition, 97 patients with MCI were followed-up over a 3-year period and classified as stable MCI (sMCI) (n = 61) or progressive MCI (pMCI) (n = 36). We did not find significant differences using traditional markers, such as normalized hippocampal volumes (NHV), between the NC and SCD groups or between the sMCI and pMCI groups. However, with LSR we found significant differences between the sMCI and pMCI groups and a better ability to discriminate between NC and SCD. The classification accuracy of the LSR for NC and SCD was 68.2%, while NHV had a 57.2% accuracy. In addition, the classification accuracy of the LSR for sMCI and pMCI was 74.3%, and NHV had a 68.3% accuracy. Cox proportional hazards models adjusted for age, sex, and education were used to estimate the relative hazard of progression from MCI to AD based on hippocampal markers and conversion times. The LSR marker showed better prediction of conversion to AD than NHV. These results suggest the relevance of considering the LSR as a new hippocampal marker for the AD continuum.

Interdatabase Variability in Cortical Thickness Measurements

The phenomenon of cortical thinning with age has been well established; however, the measured rate of change varies between studies. The source of this variation could be image acquisition techniques including hardware and vendor specific differences. Databases are often consolidated to increase the number of subjects but underlying differences between these datasets could have undesired effects. We explore differences in cerebral cortex thinning between 4 databases, totaling 1382 subjects. We investigate several aspects of these databases, including: 1) differences between databases of cortical thinning rates versus age, 2) correlation of cortical thinning rates between regions for each database, and 3) regression bootstrapping to determine the effect of the number of subjects included. We also examined the effect of different databases on age prediction modeling. Cortical thinning rates were significantly different between databases in all 68 parcellated regions (ANCOVA, P < 0.001). Subtle differences were observed in correlation matrices and bootstrapping convergence. Age prediction modeling using a leave-one-out cross-validation approach showed varying prediction performance (0.64 < R2 < 0.82) between databases. When a database was used to calibrate the model and then applied to another database, prediction performance consistently decreased. We conclude that there are indeed differences in the measured cortical thinning rates between these large-scale databases.

Automated discrimination of dementia spectrum disorders using extreme learning machine and structural T1 MRI features

The classification of neuroimaging data for the diagnosis of Alzheimer's Disease (AD) is one of the main research goals of the neuroscience and clinical fields. In this study, we performed extreme learning machine (ELM) classifier to discriminate the AD, mild cognitive impairment (MCI) from normal control (NC). We compared the performance of ELM with that of a linear kernel support vector machine (SVM) for 718 structural MRI images from Alzheimer's Disease Neuroimaging Initiative (ADNI) database. The data consisted of normal control, MCI converter (MCI-C), MCI non-converter (MCI-NC), and AD. We employed SVM-based recursive feature elimination (RFE-SVM) algorithm to find the optimal subset of features. In this study, we found that the RFE-SVM feature selection approach in combination with ELM shows the superior classification accuracy to that of linear kernel SVM for structural T1 MRI data.

Stability of graph theoretical measures in structural brain networks in Alzheimer's disease

Graph analysis has become a popular approach to study structural brain networks in neurodegenerative disorders such as Alzheimer's disease (AD). However, reported results across similar studies are often not consistent. In this paper we investigated the stability of the graph analysis measures clustering, path length, global efficiency and transitivity in a cohort of AD (N = 293) and control subjects (N = 293). More specifically, we studied the effect that group size and composition, choice of neuroanatomical atlas, and choice of cortical measure (thickness or volume) have on binary and weighted network properties and relate them to the magnitude of the differences between groups of AD and control subjects. Our results showed that specific group composition heavily influenced the network properties, particularly for groups with less than 150 subjects. Weighted measures generally required fewer subjects to stabilize and all assessed measures showed robust significant differences, consistent across atlases and cortical measures. However, all these measures were driven by the average correlation strength, which implies a limitation of capturing more complex features in weighted networks. In binary graphs, significant differences were only found in the global efficiency and transitivity measures when using cortical thickness measures to define edges. The findings were consistent across the two atlases, but no differences were found when using cortical volumes. Our findings merits future investigations of weighted brain networks and suggest that cortical thickness measures should be preferred in future AD studies if using binary networks. Further, studying cortical networks in small cohorts should be complemented by analyzing smaller, subsampled groups to reduce the risk that findings are spurious.