Search

BackgroundThe brain in resting state has complex dynamic properties and shows frequency dependent characteristics. The frequency-dependent whole-brain dynamic changes of resting state across the scans have been ignored in Alzheimer’s disease (AD).ObjectiveCoactivation pattern (CAP) analysis can identify different brain states. This paper aimed to investigate the dynamic characteristics of frequency dependent whole-brain CAPs in AD.MethodsWe utilized a multiband CAP approach to model the state space and study brain dynamics in both AD and NC. The correlation between the dynamic characteristics and the subjects’ clinical index was further analyzed.ResultsThe results showed similar CAP patterns at different frequency bands, but the occurrence of patterns was different. In addition, CAPs associated with the default mode network (DMN) and the ventral/dorsal visual network (dorsal/ventral VN) were altered significantly between the AD and NC groups. This study also found the correlation between the altered dynamic characteristics of frequency dependent CAPs and the patients’ clinical Mini-Mental State Examination assessment scale scores.ConclusionThis study revealed that while similar CAP spatial patterns appear in different frequency bands, their dynamic characteristics in subbands vary. In addition, delineating subbands was more helpful in distinguishing AD from NC in terms of CAP.

IntroductionAlzheimer’s disease (AD) even nowadays remains a complex neurodegenerative disease and its diagnosis relies mainly on cognitive tests which have many limitations. On the other hand, qualitative imaging will not provide an early diagnosis because the radiologist will perceive brain atrophy on a late disease stage. Therefore, the main objective of this study is to investigate the necessity of quantitative imaging in the assessment of AD by using machine learning (ML) methods. Nowadays, ML methods are used to address high dimensional data, integrate data from different sources, model the etiological and clinical heterogeneity, and discover new biomarkers in the assessment of AD.MethodsIn this study radiomic features from both entorhinal cortex and hippocampus were extracted from 194 normal controls (NC), 284 mild cognitive impairment (MCI) and 130 AD subjects. Texture analysis evaluates statistical properties of the image intensities which might represent changes in MRI image pixel intensity due to the pathophysiology of a disease. Therefore, this quantitative method could detect smaller-scale changes of neurodegeneration. Then the radiomics signatures extracted by texture analysis and baseline neuropsychological scales, were used to build an XGBoost integrated model which has been trained and integrated.ResultsThe model was explained by using the Shapley values produced by the SHAP (SHapley Additive exPlanations) method. XGBoost produced a f1-score of 0.949, 0.818, and 0.810 between NC vs. AD, MC vs. MCI, and MCI vs. AD, respectively.DiscussionThese directions have the potential to help to the earlier diagnosis and to a better manage of the disease progression and therefore, develop novel treatment strategies. This study clearly showed the importance of explainable ML approach in the assessment of AD.

IntroductionResearch on the brain activity during resting state has found that brain activation is centered around three networks, including the default mode network (DMN), the salient network (SN), and the central executive network (CEN), and switches between multiple modes. As a common disease in the elderly, Alzheimer’s disease (AD) affects the state transitions of functional networks in the resting state.MethodsEnergy landscape, as a new method, can intuitively and quickly grasp the statistical distribution of system states and information related to state transition mechanisms. Therefore, this study mainly uses the energy landscape method to study the changes of the triple-network brain dynamics in AD patients in the resting state.ResultsAD brain activity patterns are in an abnormal state, and the dynamics of patients with AD tend to be unstable, with an unusually high flexibility in switching between states. Also , the subjects’ dynamic features are correlated with clinical index.DiscussionThe atypical balance of large-scale brain systems in patients with AD is associated with abnormally active brain dynamics. Our study are helpful for further understanding the intrinsic dynamic characteristics and pathological mechanism of the resting-state brain in AD patients.

BackgroundPrevious studies have explored the application of non-invasive biomarkers of language dysfunction for the early detection of Alzheimer's disease (AD). However, language dysfunction over time may be quite heterogeneous within different diagnostic groups.MethodPatient demographics and clinical data were retrieved from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database for the participants without dementia who had measures of cerebrospinal fluid (CSF) biomarkers and language dysfunction. We analyzed the effect of longitudinal neuropathological and clinical correlates in the pathological process of semantic fluency and confrontation naming. The mediation effects of AD biomarkers were also explored by the mediation analysis.ResultThere were 272 subjects without dementia included in this analysis. Higher rates of decline in semantic fluency and confrontation naming were associated with a higher risk of progression to MCI or AD, and a greater decline in cognitive abilities. Moreover, the rate of change in semantic fluency was significantly associated with Aβ deposition, while confrontation naming was significantly associated with both amyloidosis and tau burden. Mediation analyses revealed that both confrontation naming and semantic fluency were partially mediated by the Aβ aggregation.ConclusionIn conclusion, the changes in language dysfunction may partly stem from the Aβ deposition, while confrontation naming can also partly originate from the increase in tau burden. Therefore, this study sheds light on how language dysfunction is partly constitutive of mild cognitive impairment and dementia and therefore is an important clinical predictor.

Brain iron accumulation, which is indicated in the cerebrospinal fluid (CSF) ferritin, is associated with the development of Alzheimer's Disease (AD). Studies have indicated that iron deposition might participate in Alzheimer's pathology through the induction of microglial activation. A soluble triggering receptor expressed on myeloid cells 2 (sTrem2) in CSF is increasingly recognized as a reliable indicator for microglia activity in the brain and participates in the development of neuroinflammation. However, the association between CSF ferritin and sTrem2 under the AD continuum has not been well-established. We enrolled individuals from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database. Participants were classified into healthy controls (HC, n = 46) and AD continuum (n = 105) in the combined strata of Amyloid/Tau/Neurodegeneration (ATN) mode and Clinical Dementia Rating (CDR) criteria. The associations between CSF ferritin (indicating iron burden) and sTrem2, as well as AD pathology, which is reflected by Aβ42, t-tau, and p-tau in CSF, were explored. CSF ferritin was significantly associated with sTrem2 among all participants (β = 0.517, P < 0.001, FDR < 0.001), HC (β = 0.749, P = 0.006, FDR = 0.010), and AD continuum (β = 0.488, P < 0.001, FDR < 0.001), respectively. However, ferritin predicted the accelerated sTrem2 level in those with high ferritin (β = 0.549, P = 0.036, FDR = 0.045). In conclusion, CSF ferritin serves as a potential biomarker of Trem2-indicated microglia function.

ObjectivesWe proposed a novel deep learning radiomics (DLR) method to distinguish cognitively normal adults at risk of Alzheimer’s disease (AD) from normal control based on T1-weighted structural MRI images.MethodsIn this study, we selected MRI data from the Alzheimer’s Disease Neuroimaging Initiative Database (ADNI), which included 417 cognitively normal adults. These subjects were divided into 181 individuals at risk of Alzheimer’s disease (preAD group) and 236 normal control individuals (NC group) according to standard uptake ratio >1.18 calculated by amyloid Positron Emission Tomography (PET). We further divided the preaAD group into APOE+ and APOE− subgroups according to whether APOE ε4 was positive or not. All data sets were divided into one training/validation group and one independent test group. The proposed DLR method included three steps: (1) the pre-training of basic deep learning (DL) models, (2) the extraction, selection and fusion of DLR features, and (3) classification. The support vector machine (SVM) was used as the classifier. In the comparative experiments, we compared our proposed DLR method with three existing models: hippocampal model, clinical model, and traditional radiomics model. Ten-fold cross-validation was performed with 100 time repetitions.ResultsThe DLR method achieved the best classification performance between preAD and NC than other models with an accuracy of 89.85% ± 1.12%. In comparison, the accuracies of the other three models were 72.44% ± 1.37%, 82.00% ± 4.09% and 79.65% ± 2.21%. In addition, the DLR model also showed the best classification performance (85.45% ± 9.04% and 92.80% ± 2.61%) in the subgroup experiment.ConclusionThe results showed that the DLR method provided a potentially clinical value to distinguish preAD from NC.

Genetic algorithms have a proven capability to explore a large space of solutions, and deal with very large numbers of input features. We hypothesized that the application of these algorithms to 18F-Fluorodeoxyglucose Positron Emission Tomography (FDG-PET) may help in diagnosis of Alzheimer’s disease (AD) and Frontotemporal Dementia (FTD) by selecting the most meaningful features and automating diagnosis. We aimed to develop algorithms for the three main issues in the diagnosis: discrimination between patients with AD or FTD and healthy controls (HC), differential diagnosis between behavioral FTD (bvFTD) and AD, and differential diagnosis between primary progressive aphasia (PPA) variants. Genetic algorithms, customized with K-Nearest Neighbor and BayesNet Naives as the fitness function, were developed and compared with Principal Component Analysis (PCA). K-fold cross validation within the same sample and external validation with ADNI-3 samples were performed. External validation was performed for the algorithms distinguishing AD and HC. Our study supports the use of FDG-PET imaging, which allowed a very high accuracy rate for the diagnosis of AD, FTD, and related disorders. Genetic algorithms identified the most meaningful features with the minimum set of features, which may be relevant for automated assessment of brain FDG-PET images. Overall, our study contributes to the development of an automated, and optimized diagnosis of neurodegenerative disorders using brain metabolism.

Objectives: Neuropsychological tests are an important basis for the memory impairment diagnosis in Alzheimer’s disease (AD). However, multiple memory tests might be conflicting within-subjects and lead to uncertain diagnoses in some cases. This study proposed a framework to diagnose the uncertain cases of memory impairment.Methods: We collected 2,386 samples including AD, mild cognitive impairment (MCI), and cognitive normal (CN) using 18F-fluorodeoxyglucose positron emission tomography (FDG-PET) and three different neuropsychological tests (Mini-Mental State Examination, Alzheimer’s Disease Assessment Scale-Cognitive Subscale, and Clinical Dementia Rating) from the Alzheimer’s Disease Neuroimaging Initiative (ADNI). A deep learning (DL) framework using FDG-PET was proposed to diagnose uncertain memory impairment cases that were conflicting between tests. Subsequent ANOVA, chi-squared, and t-test were used to explain the potential causes of uncertain cases.Results: For certain cases in the testing set, the proposed DL framework outperformed other methods with 95.65% accuracy. For the uncertain cases, its positive diagnoses had a significant (p < 0.001) worse decline in memory function than negative diagnoses in a longitudinal study of 40 months on average. In the memory-impaired group, uncertain cases were mainly explained by an AD metabolism pattern but mild in extent (p < 0.05). In the healthy group, uncertain cases were mainly explained by a non-energetic mental state (p < 0.001) measured using a global deterioration scale (GDS), with a significant depression-related metabolism pattern detected (p < 0.05).Conclusion: A DL framework for diagnosing uncertain cases of memory impairment is proposed. Proved by longitudinal tracing of its diagnoses, it showed clinical validity and had application potential. Its valid diagnoses also provided evidence and explanation of uncertain cases based on the neurodegeneration and depression mental state.

Networks are present in many aspects of our lives, and networks in neuroscience have recently gained much attention leading to novel representations of brain connectivity. The integration of neuroimaging characteristics and genetics data allows a better understanding of the effects of the gene expression on brain structural and functional connections. The current work uses whole-brain tractography in a longitudinal setting, and by measuring the brain structural connectivity changes studies the neurodegeneration of Alzheimer's disease. This is accomplished by examining the effect of targeted genetic risk factors on the most common local and global brain connectivity measures. Furthermore, we examined the extent to which Clinical Dementia Rating relates to brain connections longitudinally, as well as to gene expression. For instance, here we show that the expression of PLAU gene increases the change over time in betweenness centrality related to the fusiform gyrus. We also show that the betweenness centrality metric impact dementia-related changes in distinct brain regions. Our findings provide insights into the complex longitudinal interplay between genetics and brain characteristics and highlight the role of Alzheimer's genetic risk factors in the estimation of regional brain connectivity alterations.

Purpose: To investigate the brain information flow pattern in patients with early mild cognitive impairment (EMCI) and explore its potential ability of differentiation and prediction for EMCI.Methods: In this study, 49 patients with EMCI and 40 age- and sex-matched healthy controls (HCs) with available resting-state functional MRI images and neurological measures [including the neuropsychological evaluation and cerebrospinal fluid (CSF) biomarkers] were included from the Alzheimer's Disease Neuroimaging Initiative. Functional MRI measures including preferred information flow direction between brain regions and preferred information flow index of each brain region parcellated by the Atlas of Intrinsic Connectivity of Homotopic Areas (AICHA) were calculated by using non-parametric multiplicative regression-Granger causality analysis (NPMR-GCA). Edge- and node-wise Student's t-test was conducted for between-group comparison. Support vector classification was performed to differentiate EMCI from HC. The least absolute shrinkage and selection operator (lasso) regression were used to evaluate the predictive ability of information flow measures for the neurological state.Results: Compared to HC, disturbed preferred information flow directions between brain regions involving default mode network (DMN), executive control network (ECN), somatomotor network (SMN), and visual network (VN) were observed in patients with EMCI. An altered preferred information flow index in several brain regions (including the thalamus, posterior cingulate, and precentral gyrus) was also observed. Classification accuracy of 80% for differentiating patients with EMCI from HC was achieved by using the preferred information flow directions. The preferred information flow directions have a good ability to predict memory and executive function, level of amyloid β, tau protein, and phosphorylated tau protein with the high Pearson's correlation coefficients (r > 0.7) between predictive and actual neurological measures.Conclusion: Patients with EMCI were presented with a disturbed brain information flow pattern, which could help clinicians to identify patients with EMCI and assess their neurological state.

Background: Plasma-based biomarkers would be potential biomarkers for early diagnosis of Alzheimer's disease (AD) because they are more available and cost-effective than cerebrospinal fluid (CSF) or neuroimaging. Therefore, we aimed to evaluate whether phosphorylated tau181 (p-tau181) in plasma could be an accurate AD predictor.Methods: Participants from the ADNI database included 185 cognitively unimpaired subjects with negative Aβ (CU–), 66 subjects with pre-clinical AD (CU with positive Aβ), 164 subjects with mild cognitive impairment with negative Aβ (MCI–), 254 subjects with prodromal AD (MCI with positive Aβ), and 98 subjects with dementia. Multiple linear regression models, linear mixed-effects models, and local regression were used to explore cross-sectional and longitudinal associations of plasma p-tau181 with cognition, neuroimaging, or CSF biomarkers adjusted for age, sex, education, and APOE genotype. Besides, Kaplan–Meier and adjusted Cox-regression model were performed to predict the risk of progression to dementia. Receiver operating characteristic analyses were performed to evaluate the predictive value of p-tau181.Results: Plasma p-tau181 level was highest in AD dementia, followed by prodromal AD and pre-clinical AD. In pre-clinical AD, plasma p-tau181 was negatively associated with hippocampal volume (β = −0.031, p-value = 0.017). In prodromal AD, plasma p-tau181 was associated with decreased global cognition, executive function, memory, language, and visuospatial functioning (β range −0.119 to −0.273, p-value < 0.05) and correlated with hippocampal volume (β = −0.028, p-value < 0.005) and white matter hyperintensity volume (WMH) volume (β = 0.02, p-value = 0.01). In AD dementia, increased plasma p-tau181 was associated with worse memory. In the whole group, baseline plasma p-tau181 was significantly associated with longitudinal increases in multiple neuropsychological test z-scores and correlated with AD-related CSF biomarkers and hippocampal volume (p-value < 0.05). Meanwhile, CU or MCI with high plasma p-tau181 carried a higher risk of progression to dementia. The area under the curve (AUC) of the adjusted model (age, sex, education, APOE genotype, and plasma p-tau181) was 0.78; that of additionally included CSF biomarkers was 0.84.Conclusions: Plasma p-tau181 level is related to multiple AD-associated cognitive domains and AD-related CSF biomarkers at the clinical stages of AD. Moreover, plasma p-tau181 level is related to the change rates of cognitive decline and hippocampal atrophy. Thus, this study confirms the utility of plasma p-tau181 as a non-invasive biomarker for early detection and prediction of AD.

Identifying biomarkers that can assess the risk of developing Alzheimer’s Disease (AD) remains a significant challenge. In this study, we investigated the integrity levels of brain white matter in 34 patients with mild cognitive impairment (MCI) who later converted to AD and 53 stable MCI patients. We used diffusion tensor imaging (DTI) and automated fiber quantification to obtain the diffusion properties of 20 major white matter tracts. To identify which tracts and diffusion measures are most relevant to AD conversion, we used support vector machines (SVMs) to classify the AD conversion and non-conversion MCI patients based on the diffusion properties of each tract individually. We found that diffusivity measures from seven white matter tracts were predictive of AD conversion with axial diffusivity being the most predictive diffusion measure. Additional analyses revealed that white matter changes in the central and parahippocampal terminal regions of the right cingulate hippocampal bundle, central regions of the right inferior frontal occipital fasciculus, and posterior and anterior regions of the left inferior longitudinal fasciculus were the best predictors of conversion from MCI to AD. An SVM based on these white matter tract regions achieved an accuracy of 0.75. These findings provide additional potential biomarkers of AD risk in MCI patients.

Methods: Alzheimer's disease and Frontotemporal dementia are the first and third most common forms of dementia. Due to their similar clinical symptoms, they are easily misdiagnosed as each other even with sophisticated clinical guidelines. For disease-specific intervention and treatment, it is essential to develop a computer-aided system to improve the accuracy of their differential diagnosis. Recent advances in deep learning have delivered some of the best performance for medical image recognition tasks. However, its application to the differential diagnosis of AD and FTD pathology has not been explored.Approach: In this study, we proposed a novel deep learning based framework to distinguish between brain images of normal aging individuals and subjects with AD and FTD. Specifically, we combined the multi-scale and multi-type MRI-base image features with Generative Adversarial Network data augmentation technique to improve the differential diagnosis accuracy.Results: Each of the multi-scale, multitype, and data augmentation methods improved the ability for differential diagnosis for both AD and FTD. A 10-fold cross validation experiment performed on a large sample of 1,954 images using the proposed framework achieved a high overall accuracy of 88.28%.Conclusions: The salient contributions of this study are three-fold: (1) our experiments demonstrate that the combination of multiple structural features extracted at different scales with our proposed deep neural network yields superior performance than individual features; (2) we show that the use of Generative Adversarial Network for data augmentation could further improve the discriminant ability of the network regarding challenging tasks such as differentiating dementia sub-types; (3) and finally, we show that ensemble classifier strategy could make the network more robust and stable.

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.

ObjectiveTo examine whether osteoarthritis (OA) is associated with a change in adjusted hippocampal volumes (HpVR: hippocampal/intracranial volume × 103) over time among cognitively normal older people.MethodsWe examined the cross-sectional and longitudinal associations of OA with HpVR among individuals with normal cognition (NC) from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) study. At baseline, a total of 372 individuals with NC were included.ResultsIn the cross-sectional analyses of baseline data, we did not find a significant relationship between OA and HpVR among individuals with NC. However, in the longitudinal analyses, OA was significantly associated with change in HpVR over time among individuals with NC. Specifically, compared with individuals without OA, those with OA showed a faster decline in HpVR over time when controlling for other potential confounders, including age, educational attainment, gender, and APOE4 genotype.ConclusionOA status was significantly associated with a change in HpVR over time among individuals with NC.

Recent evidence shows that neuroinflammation plays a role in many neurological diseases including mild cognitive impairment (MCI) and Alzheimer's disease (AD), and that free water (FW) modeling from clinically acquired diffusion MRI (DTI-like acquisitions) can be sensitive to this phenomenon. This FW index measures the fraction of the diffusion signal explained by isotropically unconstrained water, as estimated from a bi-tensor model. In this study, we developed a simple but powerful whole-brain FW measure designed for easy translation to clinical settings and potential use as a priori outcome measure in clinical trials. These simple FW measures use a “safe” white matter (WM) mask without gray matter (GM)/CSF partial volume contamination (WMsafe) near ventricles and sulci. We investigated if FW inside the WMsafe mask, including and excluding areas of white matter damage such as white matter hyperintensities (WMHs) as shown on T2 FLAIR, computed across the whole white matter could be indicative of diagnostic grouping along the AD continuum. After careful quality control, 81 cognitively normal controls (NC), 103 subjects with MCI and 42 with AD were selected from the ADNIGO and ADNI2 databases. We show that MCI and AD have significantly higher FW measures even after removing all partial volume contamination. We also show, for the first time, that when WMHs are removed from the masks, the significant results are maintained, which demonstrates that the FW measures are not just a byproduct of WMHs. Our new and simple FW measures can be used to increase our understanding of the role of inflammation-associated edema in AD and may aid in the differentiation of healthy subjects from MCI and AD patients.

Alzheimer's disease (AD), including its mild cognitive impairment (MCI) phase that may or may not progress into the AD, is the most ordinary form of dementia. It is extremely important to correctly identify patients during the MCI stage because this is the phase where AD may or may not develop. Thus, it is crucial to predict outcomes during this phase. Thus far, many researchers have worked on only using a single modality of a biomarker for the diagnosis of AD or MCI. Although recent studies show that a combination of one or more different biomarkers may provide complementary information for the diagnosis, it also increases the classification accuracy distinguishing between different groups. In this paper, we propose a novel machine learning-based framework to discriminate subjects with AD or MCI utilizing a combination of four different biomarkers: fluorodeoxyglucose positron emission tomography (FDG-PET), structural magnetic resonance imaging (sMRI), cerebrospinal fluid (CSF) protein levels, and Apolipoprotein-E (APOE) genotype. The Alzheimer's Disease Neuroimaging Initiative (ADNI) baseline dataset was used in this study. In total, there were 158 subjects for whom all four modalities of biomarker were available. Of the 158 subjects, 38 subjects were in the AD group, 82 subjects were in MCI groups (including 46 in MCIc [MCI converted; conversion to AD within 24 months of time period], and 36 in MCIs [MCI stable; no conversion to AD within 24 months of time period]), and the remaining 38 subjects were in the healthy control (HC) group. For each image, we extracted 246 regions of interest (as features) using the Brainnetome template image and NiftyReg toolbox, and later we combined these features with three CSF and two APOE genotype features obtained from the ADNI website for each subject using early fusion technique. Here, a different kernel-based multiclass support vector machine (SVM) classifier with a grid-search method was applied. Before passing the obtained features to the classifier, we have used truncated singular value decomposition (Truncated SVD) dimensionality reduction technique to reduce high dimensional features into a lower-dimensional feature. As a result, our combined method achieved an area under the receiver operating characteristic (AU-ROC) curve of 98.33, 93.59, 96.83, 94.64, 96.43, and 95.24% for AD vs. HC, MCIs vs. MCIc, AD vs. MCIs, AD vs. MCIc, HC vs. MCIc, and HC vs. MCIs subjects which are high relative to single modality results and other state-of-the-art approaches. Moreover, combined multimodal methods have improved the classification performance over the unimodal classification.

The genetic component of many common traits is associated with the gene expression and several variants act as expression quantitative loci, regulating the gene expression in a tissue specific manner. In this work, we applied tissue-specific cis-eQTL gene expression prediction models on the genotype of 808 samples including controls, subjects with mild cognitive impairment, and patients with Alzheimer's Disease. We then dissected the imputed transcriptomic profiles by means of different unsupervised and supervised machine learning approaches to identify potential biological associations. Our analysis suggests that unsupervised and supervised methods can provide complementary information, which can be integrated for a better characterization of the underlying biological system. In particular, a variational autoencoder representation of the transcriptomic profiles, followed by a support vector machine classification, has been used for tissue-specific gene prioritizations. Interestingly, the achieved gene prioritizations can be efficiently integrated as a feature selection step for improving the accuracy of deep learning classifier networks. The identified gene-tissue information suggests a potential role for inflammatory and regulatory processes in gut-brain axis related tissues. In line with the expected low heritability that can be apportioned to eQTL variants, we were able to achieve only relatively low prediction capability with deep learning classification models. However, our analysis revealed that the classification power strongly depends on the network structure, with recurrent neural networks being the best performing network class. Interestingly, cross-tissue analysis suggests a potentially greater role of models trained in brain tissues also by considering dementia-related endophenotypes. Overall, the present analysis suggests that the combination of supervised and unsupervised machine learning techniques can be used for the evaluation of high dimensional omics data.

Background: Despite the increasing availability in brain health related data, clinically translatable methods to predict the conversion from Mild Cognitive Impairment (MCI) to Alzheimer's disease (AD) are still lacking. Although MCI typically precedes AD, only a fraction of 20–40% of MCI individuals will progress to dementia within 3 years following the initial diagnosis. As currently available and emerging therapies likely have the greatest impact when provided at the earliest disease stage, the prompt identification of subjects at high risk for conversion to AD is of great importance in the fight against this disease. In this work, we propose a highly predictive machine learning algorithm, based only on non-invasively and easily in-the-clinic collectable predictors, to identify MCI subjects at risk for conversion to AD.Methods: The algorithm was developed using the open dataset from the Alzheimer's Disease Neuroimaging Initiative (ADNI), employing a sample of 550 MCI subjects whose diagnostic follow-up is available for at least 3 years after the baseline assessment. A restricted set of information regarding sociodemographic and clinical characteristics, neuropsychological test scores was used as predictors and several different supervised machine learning algorithms were developed and ensembled in final algorithm. A site-independent stratified train/test split protocol was used to provide an estimate of the generalized performance of the algorithm.Results: The final algorithm demonstrated an AUROC of 0.88, sensitivity of 77.7%, and a specificity of 79.9% on excluded test data. The specificity of the algorithm was 40.2% for 100% sensitivity.Conclusions: The algorithm we developed achieved sound and high prognostic performance to predict AD conversion using easily clinically derived information that makes the algorithm easy to be translated into practice. This indicates beneficial application to improve recruitment in clinical trials and to more selectively prescribe new and newly emerging early interventions to high AD risk patients.

Recent developments of tau Positron Emission Tomography (PET) allows assessment of regional neurofibrillary tangles (NFTs) deposition in human brain. Among the tau PET molecular probes, 18F-AV1451 is characterized by high selectivity for pathologic tau aggregates over amyloid plaques, limited non-specific binding in white and gray matter, and confined off-target binding. The objectives of the study are (1) to quantitatively characterize regional brain tau deposition measured by 18F-AV1451 PET in cognitively normal older adults (CN), mild cognitive impairment (MCI), and AD participants; (2) to evaluate the correlations between cerebrospinal fluid (CSF) biomarkers or Mini-Mental State Examination (MMSE) and 18F-AV1451 PET standardized uptake value ratio (SUVR); and (3) to evaluate the partial volume effects on 18F-AV1451 brain uptake.Methods: The study included total 115 participants (CN = 49, MCI = 58, and AD = 8) from the Alzheimer's Disease Neuroimaging Initiative (ADNI). Preprocessed 18F-AV1451 PET images, structural MRIs, and demographic and clinical assessments were downloaded from the ADNI database. A reblurred Van Cittertiteration method was used for voxelwise partial volume correction (PVC) on PET images. Structural MRIs were used for PET spatial normalization and region of interest (ROI) definition in standard space. The parametric images of 18F-AV1451 SUVR relative to cerebellum were calculated. The ROI SUVR measurements from PVC and non-PVC SUVR images were compared. The correlation between ROI 18F-AV1451 SUVR and the measurements of MMSE, CSF total tau (t-tau), and phosphorylated tau (p-tau) were also assessed.Results:18F-AV1451 prominently specific binding was found in the amygdala, entorhinal cortex, parahippocampus, fusiform, posterior cingulate, temporal, parietal, and frontal brain regions. Most regional SUVRs showed significantly higher uptake of 18F-AV1451 in AD than MCI and CN participants. SUVRs of small regions like amygdala, entorhinal cortex and parahippocampus were statistically improved by PVC in all groups (p < 0.01). Although there was an increasing tendency of 18F-AV-1451 SUVRs in MCI group compared with CN group, no significant difference of 18F-AV1451 deposition was found between CN and MCI brains with or without PVC (p > 0.05). Declined MMSE score was observed with increasing 18F-AV1451 binding in amygdala, entorhinal cortex, parahippocampus, and fusiform. CSF p-tau was positively correlated with 18F-AV1451 deposition. PVC improved the results of 18F-AV-1451 tau deposition and correlation studies in small brain regions.Conclusion: The typical deposition of 18F-AV1451 tau PET imaging in AD brain was found in amygdala, entorhinal cortex, fusiform and parahippocampus, and these regions were strongly associated with cognitive impairment and CSF biomarkers. Although more deposition was observed in MCI group, the 18F-AV-1451 PET imaging could not differentiate the MCI patients from CN population. More tau deposition related to decreased MMSE score and increased level of CSF p-tau, especially in ROIs of amygdala, entorhinal cortex and parahippocampus. PVC did improve the results of tau deposition and correlation studies in small brain regions and suggest to be routinely used in 18F-AV1451 tau PET quantification.

Introduction: Patients with transient ischemic attack (TIA) and minor stroke demonstrate cognitive impairment, and a four-fold risk of late-life dementia.Aim: To study the extent to which the rates of brain volume loss in TIA patients differ from healthy controls and how they are correlated with cognitive impairment.Methods: TIA or minor stroke patients were tested with a neuropsychological battery and underwent T1 weighted volumetric magnetic resonance imaging scans at fixed intervals over a 3 years period. Linear mixed effects regression models were used to compare brain atrophy rates between groups, and to determine the relationship between atrophy rates and cognitive function in TIA and minor stroke patients.Results: Whole brain atrophy rates were calculated for the TIA and minor stroke patients; n = 38 between 24 h and 18 months, and n = 68 participants between 18 and 36 months, and were compared to healthy controls. TIA and minor stroke patients demonstrated a significantly higher whole brain atrophy rate than healthy controls over a 3 years interval (p = 0.043). Diabetes (p = 0.012) independently predicted higher atrophy rate across groups. There was a relationship between higher rates of brain atrophy and processing speed (composite P = 0.047 and digit symbol coding P = 0.02), but there was no relationship with brain atrophy rates and memory or executive composite scores or individual cognitive tests for language (Boston naming, memory recall, verbal fluency or Trails A or B score).Conclusion: TIA and minor stroke patients experience a significantly higher rate of whole brain atrophy. In this cohort of TIA and minor stroke patients changes in brain volume over time precede cognitive decline.

Introduction: Alzheimer’s disease (AD) is a neurodegenerative disorder with a clinical presentation characterized by memory impairment and executive dysfunction. Our group previously demonstrated significant alterations in white matter microstructural metrics in AD compared to healthy older adults. We aimed to further investigate the relationship between white matter microstructure in AD and cognitive function, including memory and executive function.Methods: Diffusion tensor imaging (DTI) and neuropsychological data were downloaded from the AD Neuroimaging Initiative database for 49 individuals with AD and 48 matched healthy older adults. The relationship between whole-brain fractional anisotropy (FA), mean diffusivity (MD), axial diffusivity (AxD), radial diffusivity (RD), and composite scores of memory and executive function was examined. We also considered voxel-wise relationships using Tract-Based Spatial Statistics.Results: As expected, individuals with AD had lower composite scores on tests of memory and executive function, as well as disrupted white matter integrity (low FA, high MD, AxD, and RD) relative to healthy older adults in widespread regions, including the hippocampus. When the AD and healthy older adult groups were combined, we found significant relationships between DTI metrics (FA/MD/AxD/RD) and memory scores across widespread regions of the brain, including the medial temporal regions. We also found significant relationships between DTI metrics (FA/MD/AxD/RD) and executive function in widespread regions, including the frontal areas in the combined group. However, when the groups were examined separately, no significant relationships were found between DTI metrics (FA/MD/AxD/RD) and memory performance for either group. Further, we did not find any significant relationships between DTI metrics (FA/MD/AxD/RD) and executive function in the AD group, but we did observe significant relationships between FA/RD, and executive function in healthy older adults.Conclusion: White matter integrity is disrupted in AD. In a mixed sample of AD and healthy elderly persons, associations between measures of white matter microstructure and memory and executive cognitive test performance were evident. However, no significant linear relationship between the degree of white matter disruption and level of cognitive functioning (memory and executive abilities) was found in those with AD. Future longitudinal studies of the relations between DTI metrics and cognitive function in AD are required to determine whether DTI has potential to measure progression of AD and/or treatment efficacy.

Predicting progression of mild cognitive impairment (MCI) to Alzheimer’s disease (AD) is clinically important. In this study, we propose a dual-model radiomic analysis with multivariate Cox proportional hazards regression models to investigate promising risk factors associated with MCI conversion to AD. T1 structural magnetic resonance imaging (MRI) and 18F-Fluorodeoxyglucose (FDG) positron emission tomography (PET) data, from the AD Neuroimaging Initiative database, were collected from 131 patients with MCI who converted to AD within 3 years and 132 patients with MCI without conversion within 3 years. These subjects were randomly partition into 70% training dataset and 30% test dataset with multiple times. We fused MRI and PET images by wavelet method. In a subset of subjects, a group comparison was performed using a two-sample t-test to determine regions of interest (ROIs) associated with MCI conversion. 172 radiomic features from ROIs for each individual were established using a published radiomics tool. Finally, L1-penalized Cox model was constructed and Harrell’s C index (C-index) was used to evaluate prediction accuracy of the model. To evaluate the efficacy of our proposed method, we used a same analysis framework to evaluate MRI and PET data separately. We constructed prognostic Cox models with: clinical data, MRI images, PET images, fused MRI/PET images, and clinical variables and fused MRI/PET images in combination. The experimental results showed that captured ROIs significantly associated with conversion to AD, such as gray matter atrophy in the bilateral hippocampus and hypometabolism in the temporoparietal cortex. Imaging model (MRI/PET/fused) provided significant enhancement in prediction of conversion compared to clinical models, especially the fused-modality Cox model. Moreover, the combination of fused-modality imaging and clinical variables resulted in the greatest accuracy of prediction. The average C-index for the clinical/MRI/PET/fused/combined model in the test dataset was 0.69, 0.73, 0.73 and 0.75, and 0.78, respectively. These results suggested that a combination of radiomic analysis and Cox model analyses could be used successfully in survival analysis and may be powerful tools for personalized precision medicine patients with potential to undergo conversion from MCI to AD.

The Plexin-A 4 (PLXNA4) gene, has recently been identified in genome wide association studies (GWAS), as a novel genetic player associated with Alzheimer's disease (AD). Additionally, PLXNA4 genetic variations were also found to increase AD risk by tau pathology in vitro. However, the potential roles of PLXNA4 variants in the amyloid-β (Aβ) pathology, were not evaluated. Five targeted loci capturing the top common variations in PLXNA4, were extracted using tagger methods. Multiple linear regression models were used to explore whether these variations can affect the cerebrospinal fluid (CSF) (Aβ1−42, T-tau, and P-tau) phenotypes in the Alzheimer's disease Neuroimaging Initiative (ADNI) dataset. We detected that two loci (rs6467431, rs67468325) were significantly associated with CSF Aβ1−42 levels in the hybrid population (rs6467431: P = 0.01376, rs67468325: P = 0.006536) and the significance remained after false discovery rate (FDR) correction (rs6467431: Pc = 0.03441, rs67468325: Pc = 0.03268). In the subgroup analysis, we further confirmed the association of rs6467431 in the cognitively normal (CN) subgroup (P = 0.01904, Pc = 0.04761). Furthermore, rs6467431-A carriers and rs67468325-G carriers showed higher CSF Aβ1−42 levels than non-carriers. Nevertheless, we did not detect any significant relationships between the levels of T-tau, P-tau and these PLXNA4 loci. Our findings provided preliminary evidence that PLXNA4 variants can confer AD risk through modulating the Aβ deposition.

Brain aging is a multifaceted process that remains poorly understood. Despite significant advances in technology, progress toward identifying reliable risk factors for suboptimal brain health requires realistically complex analytic methods to explain relationships between genetics, biology, and environment. Here we show the utility of a novel unsupervised machine learning technique – Correlation Explanation (CorEx) – to discover how individual measures from structural brain imaging, genetics, plasma, and CSF markers can jointly provide information on risk for Alzheimer’s disease (AD). We examined 829 participants (Mage: 75.3 ± 6.9 years; 350 women and 479 men) from the Alzheimer’s Disease Neuroimaging Initiative database to identify multivariate predictors of cognitive decline and brain atrophy over a 1-year period. Our sample included 231 cognitively normal individuals, 397 with mild cognitive impairment (MCI), and 201 with AD as their baseline diagnosis. Analyses revealed latent factors based on data-driven combinations of plasma markers and brain metrics, that were aligned with established biological pathways in AD. These factors were able to improve disease prediction along the trajectory from normal cognition and MCI to AD, with an area under the receiver operating curve of up to 99%, and prediction accuracy of up to 89.9% on independent “held out” testing data. Further, the most important latent factors that predicted AD consisted of a novel set of variables that are essential for cardiovascular, immune, and bioenergetic functions. Collectively, these results demonstrate the strength of unsupervised network measures in the detection and prediction of AD.

Background: Predicting the progression of cognitive decline in Alzheimer's disease (AD) is important for treatment selection and patient counseling. Structural MRI markers such as hippocampus or basal forebrain volumes might represent useful instruments for the prediction of cognitive decline. The primary objective was to determine the predictive value of hippocampus and basal forebrain volumes for global and domain specific cognitive decline in AD dementia during cholinergic treatment.Methods: We used MRI and cognitive data from 124 patients with the clinical diagnosis of AD dementia, derived from the ADNI-1 cohort, who were on standard of care cholinesterase inhibitor treatment during a follow-up period between 0.4 and 3.1 years. We used linear mixed effects models with cognitive function as outcome to assess the main effects as well as two-way interactions between baseline volumes and time controlling for age, sex, and total intracranial volume. This model accounts for individual variation in follow-up times.Results: Basal forebrain volume, but not hippocampus volume, was a significant predictor of rates of global cognitive decline. Larger volumes were associated with smaller rates of cognitive decline. Left hippocampus volume had a modest association with rates of episodic memory decline. Baseline performance in global cognition and memory was significantly associated with hippocampus and basal forebrain volumes; in addition, basal forebrain volume was associated with baseline performance in executive function.Conclusions: Our findings indicate that in AD dementia patients, basal forebrain volume may be a useful marker to predict subsequent cognitive decline during cholinergic treatment.

Alzheimer’s disease (AD) prevalence varies by sex, suggesting that sex chromosomes, sex hormones and/or their signaling could potentially modulate AD risk and progression. Low testosterone levels are reported in men with AD. Further, variation in the androgen receptor (AR) gene has been associated with AD risk and cognitive impairment. We assessed measures of plasma testosterone levels as a biomarker of AD in male participants from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) cohort. Baseline testosterone levels were significantly different between clinical diagnosis groups [cognitively normal controls, mild cognitive impairment (MCI), or AD], with the lowest testosterone levels in men with AD. Lower baseline testosterone levels were associated with higher baseline clinical severity. Change in testosterone levels between baseline and 1-year follow-up varied by diagnosis; MCI had the greatest decreases in testosterone levels between baseline and 1-year follow-up. Despite differences by clinical diagnosis, there was no association between plasma testosterone and CSF biomarkers of AD pathology. We also tested single nucleotide polymorphisms (SNPs) in AR for association with AD risk in a separate cohort from ADNI and found 26 SNPs associated with risk for AD. The top associated SNP is predicted to be an expression quantitative trait locus for AR in multiple tissues, including brain, with the AD-associated risk allele predicted to confer lower AR expression. Our findings suggest a link between the androgen pathway and AD through Aβ/tau independent pathways. These effects may be most pronounced during conversion from MCI to dementia.

There is increasing evidence that metabolic dysfunction plays an important role in Alzheimer’s disease (AD). Brain insulin resistance and subsequent impairment of insulin and insulin-like growth factor (IGF) signaling are associated with the neurodegenerative and clinical features of AD. Nevertheless, how the brain insulin/IGF signaling system is altered in AD and the effects of these changes on AD pathobiology are not well understood. IGF binding protein 2 (IGFBP-2) is an abundant cerebral IGF signaling protein and there is early evidence suggesting it associates with AD biomarkers. We evaluated the relationship between protein levels of IGFBP-2 with cerebrospinal fluid (CSF) biomarkers and neuroimaging markers of AD progression in 300 individuals from across the AD spectrum. CSF IGFBP-2 levels were correlated with CSF tau levels and brain atrophy in non-hippocampal regions. To further explore the role of IGFBP2 in tau pathobiology, we evaluated the expression of IGFBP2 in different human and mouse brain cell types and brain tissue from two transgenic mouse models: the P301L-tau model of tauopathy and TASTPM model of AD. We observed significant differential expression of IGFBP2 in both transgenic mouse models relative to wild-type mice in cortex but not in hippocampus. In both humans and mice, IGFBP2 is most highly expressed in astrocytes. Taken together, our findings suggest that IGFBP-2 may be linked to tau pathology and provides further evidence for a relationship between metabolic dysregulation and neurodegeneration. Our results also raise the possibility that this relationship may extend beyond neurons.

Objective: Subjective cognitive decline (SCD), also known as significant memory concern (SMC), has been suggested as a manifestation of Alzheimer’s Disease (AD) preceding mild cognitive impairment (MCI). This study assessed the impact of gender on cognition, amyloid accumulation, the volumes of hippocampus, entorhinal cortex (EC), fusiform and medial temporal lobe (MTA) and cerebrospinal fluid (CSF) pathology biomarkers in patients reporting SMC.Methods: Twenty-nine males (mean age ± SD: 72.3 ± 5.7 years) and 40 females (mean age ± SD: 71.0 ± 5.1 years) with SMC from the AD Neuroimaging Initiative (ADNI) were included in the study. We explored the gender discrepancies in cognition, [18F] AV45 amyloid positivity, volumes of hippocampus, EC, fusiform and MTA and CSF biomarkers.Results: Compared with females, males showed significantly worse performance in Assessment Scale-cognitive subscale 13 (ADAS-13; P = 0.004) and lower amyloid deposition (P < 0.001). However, females showed greater advantage on the task of Rey Auditory Verbal Learning Test-5 (RAVLT-5) sum (P = 0.021), RAVLT-immediate recall (P = 0.010) and reduced volumes of the hippocampus, EC, fusiform and MTA (P = 0.001, P < 0.001, P < 0.001, P = 0.007) than males. No gender differences were found in CSF Aβ42, CSF Tau and CSF P-tau (P = 0.264, P = 0.454, P = 0.353).Conclusions: These findings highlight that gender discrepancies should be considered in the interpretation of cognitive measures when evaluating SMC.

Alzheimer’s disease (AD) is an irreversible brain degenerative disorder affecting people aged older than 65 years. Currently, there is no effective cure for AD, but its progression can be delayed with some treatments. Accurate and early diagnosis of AD is vital for the patient care and development of future treatment. Fluorodeoxyglucose positrons emission tomography (FDG-PET) is a functional molecular imaging modality, which proves to be powerful to help understand the anatomical and neural changes of brain related to AD. Most existing methods extract the handcrafted features from images, and then design a classifier to distinguish AD from other groups. These methods highly depends on the preprocessing of brain images, including image rigid registration and segmentation. Motivated by the success of deep learning in image classification, this paper proposes a new classification framework based on combination of 2D convolutional neural networks (CNN) and recurrent neural networks (RNNs), which learns the intra-slice and inter-slice features for classification after decomposition of the 3D PET image into a sequence of 2D slices. The 2D CNNs are built to capture the features of image slices while the gated recurrent unit (GRU) of RNN is cascaded to learn and integrate the inter-slice features for image classification. No rigid registration and segmentation are required for PET images. Our method is evaluated on the baseline FDG-PET images acquired from 339 subjects including 93 AD patients, 146 mild cognitive impairments (MCI) and 100 normal controls (NC) from Alzheimer’s Disease Neuroimaging Initiative (ADNI) database. Experimental results show that the proposed method achieves an area under receiver operating characteristic curve (AUC) of 95.3% for AD vs. NC classification and 83.9% for MCI vs. NC classification, demonstrating the promising classification performance.

Accurate classification of either patients with Alzheimer's disease (AD) or patients with mild cognitive impairment (MCI), the prodromal stage of AD, from cognitively unimpaired (CU) individuals is important for clinical diagnosis and adequate intervention. The current study focused on distinguishing AD or MCI from CU based on the multi-feature kernel supervised within-Class-similar discriminative dictionary learning algorithm (MKSCDDL), which we introduced in a previous study, demonstrating that MKSCDDL had superior performance in face recognition. Structural magnetic resonance imaging (sMRI), fluorodeoxyglucose (FDG) positron emission tomography (PET), and florbetapir-PET data from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database were all included for classification of AD vs. CU, MCI vs. CU, as well as AD vs. MCI (113 AD patients, 110 MCI patients, and 117 CU subjects). By adopting MKSCDDL, we achieved a classification accuracy of 98.18% for AD vs. CU, 78.50% for MCI vs. CU, and 74.47% for AD vs. MCI, which in each instance was superior to results obtained using several other state-of-the-art approaches (MKL, JRC, mSRC, and mSCDDL). In addition, testing time results outperformed other high quality methods. Therefore, the results suggested that the MKSCDDL procedure is a promising tool for assisting early diagnosis of diseases using neuroimaging data.