Predicting Brain Amyloid Using Multivariate Morphometry Statistics, Sparse Coding, and Correntropy: Validation in 1,101 Individuals From the ADNI and OASIS Databases

INTRODUCTIONWe investigated the prevalence of amyloid beta (Aβ) positivity (+) and cognitive trajectories in Koreans and non‐Hispanic Whites (NHWs).METHODSWe included 5121 Koreans from multiple centers across South Korea and 929 NHWs from the Alzheimer's Disease Neuroimaging Initiative (ADNI). Participants underwent Aβ positron emission tomography and were categorized into cognitively unimpaired (CU), mild cognitive impairment (MCI), and dementia stages. Age, sex, education, and apolipoprotein E. genotype were adjusted using multivariable logistic regression and stabilized inverse probability of treatment weights based on the propensity scores to mitigate imbalances in these variables.RESULTSThe prevalence of Aβ+ was lower in CU Koreans than in CU NHWs (adjusted odds ratio 0.60). Aβ+ Koreans showed a faster cognitive decline than Aβ+ NHWs in the CU (B = −0.314, p = .004) and MCI stages (B = −0.385, p < .001).DISCUSSIONEthnic characteristics of Aβ biomarkers should be considered in research and clinical application of Aβ‐targeted therapies in diverse populations.HighlightsKoreans have a lower prevalence of Aβ positivity compared to NHWs in the CU stage.The effects of Alzheimer's risk factors on Aβ positivity differ between Koreans and NHWs.Aβ‐positive (Aβ+) Koreans show faster cognitive decline than Aβ+ NHWs in the CU and MCI stages.

ABSTRACTMultimodal neuroimaging, combining data from different sources, has shown promise in the classification of the Alzheimer's disease (AD) stage. Existing multimodal neuroimaging fusion methods exhibit certain limitations, which require advancements to enhance their objective performance, sensitivity, and specificity for AD classification. This study uses the use of a Pareto‐optimal cosine color map to enhance classification performance and visual clarity of fused images. A mobile vision transformer (ViT) model, incorporating the swish activation function, is introduced for effective feature extraction and classification. Fused images from the Alzheimer's Disease Neuroimaging Initiative (ADNI), the Whole Brain Atlas (AANLIB), and Open Access Series of Imaging Studies (OASIS) datasets, obtained through optimized transposed convolution, are utilized for model training, while evaluation is achieved using images that have not been fused from the same databases. The proposed model demonstrates high accuracy in AD classification across different datasets, achieving 98.76% accuracy for Early Mild Cognitive Impairment (EMCI) versus LMCI, 98.65% for Late Mild Cognitive Impairment (LMCI) versus AD, 98.60% for EMCI versus AD, and 99.25% for AD versus Cognitive Normal (CN) in the ADNI dataset. Similarly, on OASIS and AANLIB, the precision of the AD versus CN classification is 99.50% and 96.00%, respectively. Evaluation metrics showcase the model's precision, recall, and F1 score for various binary classifications, emphasizing its robust performance.

Purpose: Hard-to-interpret Black-box Machine Learning (ML) were often used for early Alzheimer's Disease (AD) detection. Methods: To interpret eXtreme Gradient Boosting (XGBoost), Random Forest (RF), and Support Vector Machine (SVM) black-box models a workflow based on Shapley values was developed. All models were trained on the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset and evaluated for an independent ADNI test set, as well as the external Australian Imaging and Lifestyle flagship study of Ageing (AIBL), and Open Access Series of Imaging Studies (OASIS) datasets. Shapley values were compared to intuitively interpretable Decision Trees (DTs), and Logistic Regression (LR), as well as natural and permutation feature importances. To avoid the reduction of the explanation validity caused by correlated features, forward selection and aspect consolidation were implemented. Results: Some black-box models outperformed DTs and LR. The forward-selected features correspond to brain areas previously associated with AD. Shapley values identified biologically plausible associations with moderate to strong correlations with feature importances. The most important RF features to predict AD conversion were the volume of the amygdalae, and a cognitive test score. Good cognitive test performances and large brain volumes decreased the AD risk. The models trained using cognitive test scores significantly outperformed brain volumetric models ($p<0.05$). Cognitive Normal (CN) vs. AD models were successfully transferred to external datasets. Conclusion: In comparison to previous work, improved performances for ADNI and AIBL were achieved for CN vs. Mild Cognitive Impairment (MCI) classification using brain volumes. The Shapley values and the feature importances showed moderate to strong correlations.

Develop a cerebrospinal fluid biomarker signature for mild Alzheimer's disease (AD) in Alzheimer's Disease Neuroimaging Initiative (ADNI) subjects. Amyloid-beta 1 to 42 peptide (A beta(1-42)), total tau (t-tau), and tau phosphorylated at the threonine 181 were measured in (1) cerebrospinal fluid (CSF) samples obtained during baseline evaluation of 100 mild AD, 196 mild cognitive impairment, and 114 elderly cognitively normal (NC) subjects in ADNI; and (2) independent 56 autopsy-confirmed AD cases and 52 age-matched elderly NCs using a multiplex immunoassay. Detection of an AD CSF profile for t-tau and A beta(1-42) in ADNI subjects was achieved using receiver operating characteristic cut points and logistic regression models derived from the autopsy-confirmed CSF data. CSF A beta(1-42) was the most sensitive biomarker for AD in the autopsy cohort of CSF samples: receiver operating characteristic area under the curve of 0.913 and sensitivity for AD detection of 96.4%. In the ADNI cohort, a logistic regression model for A beta(1-42), t-tau, and APO epsilon 4 allele count provided the best assessment delineation of mild AD. An AD-like baseline CSF profile for t-tau/A beta(1-42) was detected in 33 of 37 ADNI mild cognitive impairment subjects who converted to probable AD during the first year of the study. The CSF biomarker signature of AD defined by A beta(1-42) and t-tau in the autopsy-confirmed AD cohort and confirmed in the cohort followed in ADNI for 12 months detects mild AD in a large, multisite, prospective clinical investigation, and this signature appears to predict conversion from mild cognitive impairment to AD.

INTRODUCTIONCerebrovascular injury is common in Alzheimer's disease (AD), but its timing in relation to Aβ and tau pathology and cognitive decline remains unclear.METHODSWe measured baseline vascular marker levels in cerebrospinal fluid (CSF) and serum from 75 Alzheimer's Disease Neuroimaging Initiative (ADNI) study participants, stratified into cognitively unimpaired (CU), mild cognitive impairment (MCI), and AD groups (n = 25/group) and investigated associations with disease pathology (CSF and positron emission tomography [PET] amyloid beta [Aβ] and tau) and cognition (Clinical Dementia Rating scale [CDR], Montreal Cognitive Assessment, Mini‐Mental State Examination, and Alzheimer's Disease Assessment Scale).RESULTSCSF markers of endothelial (placental growth factor, angiopoietin 2, angiotensin‐converting enzyme‐1 [ACE‐1]) and pericyte (soluble platelet‐derived growth factor receptor beta [sPDGFRβ]) injury were elevated in AD. Most were also higher in CDR 0.5 than CDR 0 and correlated with CSF tau and cognitive impairment in CU and MCI groups, particularly in PET Aβ‐positive (Aβ+) participants. Serum sPDGFRβ, tyrosine kinase with immunoglobulin and epidermal growth factor homology domains‐2 (TIE‐2), and ACE‐1 correlated with CSF measurements.DISCUSSIONCerebrovascular injury precedes the development of dementia and, particularly in PET Aβ+ individuals, progresses in close association with CSF tau and cognitive decline.HighlightsWe measured the levels of multiple markers of neurovascular injury in serum and CSF taken at baseline from CU, MCI, and AD participants in the ADNI study and investigated associations with CSF and PET markers of disease pathology and with cognitive decline.CSF markers of neurovascular injury, particularly PlGF, are elevated in very early stages of AD, including in MCI and in PET Aβ+ CU individuals. The levels are closely related to CSF t‐tau and p‐tau and to cognitive declineLevels of only a few neurovascular markers in serum correlate with those in CSF: sPDGFRβ, TIE‐2, and ACE‐1.

Plasma biomarkers for Alzheimer's disease (AD) are increasingly being used to assist in making an etiological diagnosis for cognitively impaired (CI) individuals or to identify cognitively unimpaired (CU) individuals with AD pathology who may be eligible for prevention trials. However, a better understanding of the timing of plasma biomarker changes is needed to optimize their use in clinical and research settings. The aim of this study was to evaluate the timing of change of key AD plasma biomarkers (Aβ42/Aβ40, p-tau217, p-tau181, GFAP and NfL) from six different companies, along with established AD biomarkers, using AD progression timelines based on amyloid and tau PET. We used data from the Alzheimer's Disease Neuroimaging Initiative (ADNI), including 784 individuals with longitudinal 18 F-florbetapir amyloid PET and 359 individuals with longitudinal 18 F-flortaucipir tau PET, to estimate age at amyloid and tau positivity, defined as the age at the first positive PET scan. Of these, longitudinal plasma biomarker measures were available from 190 individuals with an estimated age at amyloid positivity and 70 individuals with an estimated age at tau positivity. Age at tau positivity was a stronger predictor of symptom onset than age at amyloid positivity in 17 individuals who progressed from CU to CI during their participation in the ADNI study (Adj R 2 = 0.86 vs. Adj R 2 = 0.38), and therefore was used to estimate symptom onset age for all individuals with an estimated age at tau positivity. Generalized additive mixed models (GAMMs) were used to model biomarker trajectories across years since amyloid positivity, tau positivity, and symptom onset, and to identify the earliest timepoint of biomarker abnormality when compared to a reference group of amyloid- and tau-negative CU individuals, as well as time periods of significant change in biomarkers. All plasma biomarkers except NfL became abnormal prior to amyloid and tau positivity. Plasma Aβ42/Aβ40 was the first biomarker to reach abnormality consistently across timelines and plasma GFAP became abnormal early in the tau timeline. Plasma Aβ42/Aβ40 levels reached a plateau, while plasma p-tau217, p-tau181, GFAP and NfL increased throughout disease progression. Some differences in the timing of change were observed across biomarker assays. The primary utility of plasma Aβ42/Aβ40 may lie in early identification of individuals at high risk of AD. In contrast, p-tau217, p-tau181, GFAP and NfL increase throughout the estimated timelines, supporting their potential as biomarkers for staging and monitoring disease progression.

In this work, we present a probabilistic information fusion approach for the diagnosis of dementia from cross-sectional magnetic resonance (MR) images. The approach relies on first mapping the outputs of a support vector classifier (SVM) trained on image features to probabilities and then on combining these probabilities with the class-conditional distributions of neuropsychiatric test scores, such as the mini-mental state examination (MMSE). The SVM classifier is trained and tested on 121 subjects drawn from the Open Access Series of Imaging Studies (OASIS) database. Two independent sets of MMSE related statistics are estimated from data, one from the training set in OASIS and the other from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database. The probabilistic fusion of image-based SVM decisions with no visual MMSE information exhibits very steep receiver operating characteristic curves on the test set; giving, at the equal error rate operating point, 92% accuracy.

Optimization of VGG16 utilizing the Arithmetic Optimization Algorithm for early detection of Alzheimer’s disease

The Alzheimer's Disease Neuroimaging Initiative (ADNI) is an ongoing, longitudinal, multicenter study designed to develop clinical, imaging, genetic, and biochemical biomarkers for the early detection and tracking of Alzheimer's disease (AD). The study aimed to enroll 400 subjects with early mild cognitive impairment (MCI), 200 subjects with early AD, and 200 normal control subjects; $67 million funding was provided by both the public and private sectors, including the National Institute on Aging, 13 pharmaceutical companies, and 2 foundations that provided support through the Foundation for the National Institutes of Health. This article reviews all papers published since the inception of the initiative and summarizes the results as of February 2011. The major accomplishments of ADNI have been as follows: (1) the development of standardized methods for clinical tests, magnetic resonance imaging (MRI), positron emission tomography (PET), and cerebrospinal fluid (CSF) biomarkers in a multicenter setting; (2) elucidation of the patterns and rates of change of imaging and CSF biomarker measurements in control subjects, MCI patients, and AD patients. CSF biomarkers are consistent with disease trajectories predicted by β-amyloid cascade (Hardy, J Alzheimers Dis 2006;9(Suppl 3):151-3) and tau-mediated neurodegeneration hypotheses for AD, whereas brain atrophy and hypometabolism levels show predicted patterns but exhibit differing rates of change depending on region and disease severity; (3) the assessment of alternative methods of diagnostic categorization. Currently, the best classifiers combine optimum features from multiple modalities, including MRI, [(18)F]-fluorodeoxyglucose-PET, CSF biomarkers, and clinical tests; (4) the development of methods for the early detection of AD. CSF biomarkers, β-amyloid 42 and tau, as well as amyloid PET may reflect the earliest steps in AD pathology in mildly symptomatic or even nonsymptomatic subjects, and are leading candidates for the detection of AD in its preclinical stages; (5) the improvement of clinical trial efficiency through the identification of subjects most likely to undergo imminent future clinical decline and the use of more sensitive outcome measures to reduce sample sizes. Baseline cognitive and/or MRI measures generally predicted future decline better than other modalities, whereas MRI measures of change were shown to be the most efficient outcome measures; (6) the confirmation of the AD risk loci CLU, CR1, and PICALM and the identification of novel candidate risk loci; (7) worldwide impact through the establishment of ADNI-like programs in Europe, Asia, and Australia; (8) understanding the biology and pathobiology of normal aging, MCI, and AD through integration of ADNI biomarker data with clinical data from ADNI to stimulate research that will resolve controversies about competing hypotheses on the etiopathogenesis of AD, thereby advancing efforts to find disease-modifying drugs for AD; and (9) the establishment of infrastructure to allow sharing of all raw and processed data without embargo to interested scientific investigators throughout the world. The ADNI study was extended by a 2-year Grand Opportunities grant in 2009 and a renewal of ADNI (ADNI-2) in October 2010 through to 2016, with enrollment of an additional 550 participants.

An elevated neutrophil-lymphocyte ratio (NLR) in blood has been associated with Alzheimer's disease (AD). However, an elevated NLR has also been implicated in many other conditions that are risk factors for AD, prompting investigation into whether the NLR is directly linked with AD pathology or a result of underlying comorbidities. Herein, we explored the relationship between the NLR and AD biomarkers in the cerebrospinal fluid (CSF) of cognitively unimpaired (CU) subjects. Adjusting for sociodemographics, APOE4, and common comorbidities, we investigated these associations in two cohorts: the Alzheimer's Disease Neuroimaging Initiative (ADNI) and the M.J. de Leon CSF repository at NYU. Specifically, we examined associations between the NLR and cross-sectional measures of amyloid-β42 (Aβ42), total tau (t-tau), and phosphorylated tau181 (p-tau), as well as the trajectories of these CSF measures obtained longitudinally. A total of 111 ADNI and 190 NYU participants classified as CU with available NLR, CSF, and covariate data were included. Compared to NYU, ADNI participants were older (73.79 vs. 61.53, p < 0.001), had a higher proportion of males (49.5% vs. 36.8%, p = 0.042), higher BMIs (27.94 vs. 25.79, p < 0.001), higher prevalence of hypertensive history (47.7% vs. 16.3%, p < 0.001), and a greater percentage of Aβ-positivity (34.2% vs. 20.0%, p = 0.009). In the ADNI cohort, we found cross-sectional associations between the NLR and CSF Aβ42 (β = -12.193, p = 0.021), but not t-tau or p-tau. In the NYU cohort, we found cross-sectional associations between the NLR and CSF t-tau (β = 26.812, p = 0.019) and p-tau (β = 3.441, p = 0.015), but not Aβ42. In the NYU cohort alone, subjects classified as Aβ + (n = 38) displayed a stronger association between the NLR and t-tau (β = 100.476, p = 0.037) compared to Aβ- subjects or the non-stratified cohort. In both cohorts, the same associations observed in the cross-sectional analyses were observed after incorporating longitudinal CSF data. We report associations between the NLR and Aβ42 in the older ADNI cohort, and between the NLR and t-tau and p-tau in the younger NYU cohort. Associations persisted after adjusting for comorbidities, suggesting a direct link between the NLR and AD. However, changes in associations between the NLR and specific AD biomarkers may occur as part of immunosenescence.

Efficient multimodel method based on transformers and CoAtNet for Alzheimer's diagnosis

Multimodal neuroimaging has gained traction in Alzheimer's Disease (AD) diagnosis by integrating information from multiple imaging modalities to enhance classification accuracy. However, effectively handling heterogeneous data sources and overcoming the challenges posed by multiscale transform methods remains a significant hurdle. This article proposes a novel approach to address these challenges. To harness the power of diverse neuroimaging data, we employ a strategy that leverages optimized convolution techniques. These optimizations include varying kernel sizes and the incorporation of instance normalization, both of which play crucial roles in feature extraction from magnetic resonance imaging (MRI) and positron emission tomography (PET) images. Specifically, varying kernel sizes allow us to adapt the receptive field to different image characteristics, enhancing the model's ability to capture relevant information. Furthermore, we employ transposed convolution, which increases spatial resolution of feature maps, and it is optimized with varying kernel sizes and instance normalization. This heightened resolution facilitates the alignment and integration of data from disparate MRI and PET data. The use of larger kernels and strides in transposed convolution expands the receptive field, enabling the model to capture essential cross-modal relationships. Instance normalization, applied to each modality during the fusion process, mitigates potential biases stemming from differences in intensity, contrast, or scale between modalities. This enhancement contributes to improved model performance by reducing complexity and ensuring robust fusion. The performance of the proposed fusion method is assessed on three distinct neuroimaging datasets, which include: Alzheimer's Disease Neuroimaging Initiative (ADNI), consisting of 50 participants each at various stages of AD for both MRI and PET (Cognitive Normal, AD, and Early Mild Cognitive); Open Access Series of Imaging Studies (OASIS), consisting of 50 participants each at various stages of AD for both MRI and PET (Cognitive Normal, Mild Dementia, Very Mild Dementia); and whole-brain atlas neuroimaging (AANLIB) (consisting of 50 participants each at various stages of AD for both MRI and PET (Cognitive Normal, AD). To evaluate the quality of the fused images generated via our method, we employ a comprehensive set of evaluation metrics, including Structural Similarity Index Measurement (SSIM), which assesses the structural similarity between two images; Peak Signal-to-Noise Ratio (PSNR), which measures how closely the generated image resembles the ground truth; Entropy (E), which assesses the amount of information preserved or lost during fusion; the Feature Similarity Indexing Method (FSIM), which assesses the structural and feature similarities between two images; and Edge-Based Similarity (EBS), which measures the similarity of edges between the fused and ground truth images. The obtained fused image is further evaluated using a Mobile Vision Transformer. In the classification of AD vs. Cognitive Normal, the model achieved an accuracy of 99.00%, specificity of 99.00%, and sensitivity of 98.44% on the AANLIB dataset.

Artificially low mild cognitive impairment to normal reversion rate in the Alzheimer's Disease Neuroimaging Initiative

The Accurate and the early detection of the neurodegenerative brain disorders such as the Alzheimer’s disease(AD) is crucial today for an effective patient care and prevention of disease progression. Computer Assisted Diagnosis (CAD) based on the neuroimaging data is an active research that was enhanced recent years by the deep learning methods. Brain modalities hold the key to achieve a comprehensive understanding of the brain changes and disorders. Magnetic Resonance Imaging(MRI) is a powerful brain modality and biomarker to capture the brain changes. It has been widely adopted for the AD diagnosis. Most of the recent studies are based on the Convolution Neural Network (CNN)using the MRI modality for the AD detection. However the CNN requires a huge amount of data. Furthermore, current CNN models cannot provide a good feature representation due to the lack of an adaptive channel weighting. The main drawback of the CNN network is its inability to learns the importance of the image features and the main correlations among them. Current methods that are based on the CNN does not ensure a valuable information extraction about which brain regions are related to the AD detection. To deal with these challenges, we proposed 2 contributions. Firstly, we used a Deep Convolution Generative Adversarial neural network(DCGAN) for data augmentation to enhance the training and to tackle the lack of data. We proposed also a new method for AD detection based on the integration of the Efficient Channel Attention(ECA-Net) into the Residual network. The ECA module improve the residual network by an attention mechanism to extract the most relevant features and ensure an adaptive weighting channel mechanism. Our method provide an efficient feature representation and extraction with low computational cost. The proposed method was validated using the ADNI (Alzheimer’s disease neuroimaging initiative) and the Open Access Series of Imaging Studies (OASIS). The experimental results outlines that our proposed method achieved the highest classification accuracy comparing with different methods by reaching an accuracy rate of 95%KeywordsAlzheimer’s diseaseData augmentationAttention mechanismDCGANECA-ResNet101

Fluid and imaging biomarkers of Alzheimer disease (AD) are often used interchangeably, but some biomarkers may reveal earlier stages of disease. To characterize individuals with tau abnormality indicated by cerebrospinal fluid (CSF) assay or positron emission tomography (PET). Between 2010 and 2019, 322 participants in the Alzheimer's Disease Neuroimaging Initiative (ADNI) underwent CSF and PET assessments of tau pathology. Data-driven, clinically relevant thresholds for CSF phosphorylated tau (P-tau) (≥26.64 pg/mL) and flortaucipir-PET meta-regions of interest (ROI) (standard uptake value ratio ≥1.37) indicated participants' tau status as CSF-/PET-, CSF+/PET-, CSF-/PET+, and CSF+/PET+. Of 1659 ADNI participants with a CSF or flortaucipir assessment, 588 had both measures (1071 were excluded). Among these, 266 were further excluded because they did not have flortaucipir and CSF testing within less than 25 months, leaving 322 for analysis. Of these, 213 were cognitively unimpaired (CU); 98 had mild cognitive impairment (MCI); and 11 had AD dementia. We compared tau-positive vs tau-negative groups as indicated by either modality or demographic and clinical variables, amyloid β-PET burden, and flortaucipir-PET binding across Braak stage-related ROIs. We also compared 5-year rates of CSF P-tau accumulation and cognitive decline prior to flortaucipir-PET scanning. Among the 322 study participants, 180 were women (56%), and the mean (SD) age was 73.08 (7.37) years. Two hundred ten participants were CSF-/PET- (65%); 63 were CSF+/PET- (19.5%); 15 were CSF-/PET+ (4.6%); and 34 were CSF+/PET+ (10.5%). Most CSF-/PET+ participants had measures near CSF or PET tau thresholds. The CSF+/PET- participants showed faster 5-year accrual of P-tau and increased flortaucipir-PET binding in early Braak ROIs but similar memory decline compared with CSF-/PET- participants. Tau-positive individuals by either measure showed increased amyloid β-PET burden. All CSF+/PET+ individuals were amyloid-positive, and 26 had MCI or AD dementia (76%). Compared with the CSF-/PET- group, CSF+/PET+ individuals had experienced faster 5-year accrual of CSF P-tau and decline in memory and executive function, resulting in reduced cognitive abilities at the time of flortaucipir-PET assessment. Suprathreshold CSF P-tau without flortaucipir-PET abnormality may indicate a stage of AD development characterized by early tau abnormality without measurable loss in cognitive performance. Persons with both tau CSF and PET abnormality appear to have reduced cognitive capacities resulting from faster antecedent cognitive decline. Elevation of CSF P-tau appears to precede flortaucipir-PET positivity in the progression of AD pathogenesis and related cognitive decline.