skip to main content


The NSF Public Access Repository (NSF-PAR) system and access will be unavailable from 11:00PM ET on Friday, December 15 until 2:00 AM ET on Saturday, December 16 due to maintenance. We apologize for the inconvenience.

Title: PET Imaging of Tau Pathology and Amyloid-β, and MRI for Alzheimer’s Disease Feature Fusion and Multimodal Classification
Background: Machine learning is a promising tool for biomarker-based diagnosis of Alzheimer’s disease (AD). Performing multimodal feature selection and studying the interaction between biological and clinical AD can help to improve the performance of the diagnosis models. Objective: This study aims to formulate a feature ranking metric based on the mutual information index to assess the relevance and redundancy of regional biomarkers and improve the AD classification accuracy. Methods: From the Alzheimer’s Disease Neuroimaging Initiative (ADNI), 722 participants with three modalities, including florbetapir-PET, flortaucipir-PET, and MRI, were studied. The multivariate mutual information metric was utilized to capture the redundancy and complementarity of the predictors and develop a feature ranking approach. This was followed by evaluating the capability of single-modal and multimodal biomarkers in predicting the cognitive stage. Results: Although amyloid-β deposition is an earlier event in the disease trajectory, tau PET with feature selection yielded a higher early-stage classification F1-score (65.4%) compared to amyloid-β PET (63.3%) and MRI (63.2%). The SVC multimodal scenario with feature selection improved the F1-score to 70.0% and 71.8% for the early and late-stage, respectively. When age and risk factors were included, the scores improved by 2 to 4%. The Amyloid-Tau-Neurodegeneration [AT(N)] framework helped to interpret the classification results for different biomarker categories. Conclusion: The results underscore the utility of a novel feature selection approach to reduce the dimensionality of multimodal datasets and enhance model performance. The AT(N) biomarker framework can help to explore the misclassified cases by revealing the relationship between neuropathological biomarkers and cognition.  more » « less
Award ID(s):
2018611 1920182
Author(s) / Creator(s):
; ; ; ; ; ; ;
Date Published:
Journal Name:
Journal of Alzheimer's Disease
Page Range / eLocation ID:
1497 to 1514
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. null (Ed.)
    Introduction: Alzheimer’s disease (AD) causes progressive irreversible cognitive decline and is the leading cause of dementia. Therefore, a timely diagnosis is imperative to maximize neurological preservation. However, current treatments are either too costly or limited in availability. In this project, we explored using retinal vasculature as a potential biomarker for early AD diagnosis. This project focuses on stage 3 of a three-stage modular machine learning pipeline which consisted of image quality selection, vessel map generation, and classification [1]. The previous model only used support vector machine (SVM) to classify AD labels which limited its accuracy to 82%. In this project, random forest and gradient boosting were added and, along with SVM, combined into an ensemble classifier, raising the classification accuracy to 89%. Materials and Methods: Subjects classified as AD were those who were diagnosed with dementia in “Dementia Outcome: Alzheimer’s disease” from the UK Biobank Electronic Health Records. Five control groups were chosen with a 5:1 ratio of control to AD patients where the control patients had the same age, gender, and eye side image as the AD patient. In total, 122 vessel images from each group (AD and control) were used. The vessel maps were then segmented from fundus images through U-net. A t-test feature selection was first done on the training folds and the selected features was fed into the classifiers with a p-value threshold of 0.01. Next, 20 repetitions of 5-fold cross validation were performed where the hyperparameters were solely tuned on the training data. An ensemble classifier consisting of SVM, gradient boosting tree, and random forests was built and the final prediction was made through majority voting and evaluated on the test set. Results and Discussion: Through ensemble classification, accuracy increased by 4-12% relative to the individual classifiers, precision by 9-15%, sensitivity by 2-9%, specificity by at least 9-16%, and F1 score by 712%. Conclusions: Overall, a relatively high classification accuracy was achieved using machine learning ensemble classification with SVM, random forest, and gradient boosting. Although the results are very promising, a limitation of this study is that the requirement of needing images of sufficient quality decreased the amount of control parameters that can be implemented. However, through retinal vasculature analysis, this project shows machine learning’s high potential to be an efficient, more cost-effective alternative to diagnosing Alzheimer’s disease. Clinical Application: Using machine learning for AD diagnosis through retinal images will make screening available for a broader population by being more accessible and cost-efficient. Mobile device based screening can also be enabled at primary screening in resource-deprived regions. It can provide a pathway for future understanding of the association between biomarkers in the eye and brain. 
    more » « less
  2. null (Ed.)
    This study introduces a new multimodal deep regression method to predict cognitive test score in a 5-year longitudinal study on Alzheimer’s disease (AD). The proposed model takes advantage of multimodal data that includes cerebrospinal fluid (CSF) levels of tau and beta-amyloid, structural measures from magnetic resonance imaging (MRI), functional and metabolic measures from positron emission tomography (PET), and cognitive scores from neuropsychological tests (Cog), all with the aim of achieving highly accurate predictions of future Mini-Mental State Examination (MMSE) test scores up to five years after baseline biomarker collection. A novel data augmentation technique is leveraged to increase the numbers of training samples without relying on synthetic data. With the proposed method, the best and most encompassing regressor is shown to achieve better than state-of-the-art correlations of 85.07%(SD=1.59) for 6 months in the future, 87.39% (SD =1.48) for 12 months, 84.78% (SD=2.66) for 18 months, 85.13% (SD=2.19) for 24 months, 81.15% (SD=5.48) for 30 months, 81.17% (SD=4.44) for 36 months, 79.25% (SD=5.85) for 42 months, 78.98% (SD=5.79) for 48 months, 78.93%(SD=5.76) for 54 months, and 74.96% (SD=7.54) for 60 months. 
    more » « less
  3. Abstract Background

    Tau positron emission tomography (PET) is increasing in popularity for biomarker characterization of Alzheimer’s disease (AD), and recent frameworks rely on tau PET cut-points to stage individuals along the AD continuum. Given the lack of standardization in tau PET thresholding methods, this study sought to systematically canvass and characterize existing studies that have derived tau PET cut-points and then directly assess different methods of tau PET thresholding in terms of their concurrent validity.


    First, a literature search was conducted in PubMed to identify studies of AD and related clinical phenotypes that used the Flortaucipir (AV-1451) tau PET tracer to derive a binary cut-point for tau positivity. Of 540 articles screened and 47 full-texts reviewed, 23 cohort studies met inclusion criteria with a total of 6536 participants. Second, we derived and compared tau PET cut-points in a 2 × 2 × 2 design that systematically varied region (temporal meta-ROI and entorhinal cortex), analytic method (receiver operating characteristics and 2 standard deviations above comparison group), and criterion/comparison variable (amyloid-beta negative cognitively unimpaired or cognitively unimpaired only) using a sample of 453 older adults from the Alzheimer’s Disease Neuroimaging Initiative.


    For the systematic review, notable variability in sample characteristics, preprocessing methods, region of interest, and analytic approach were observed, which were accompanied by discrepancy in proposed tau PET cut points. The empirical follow-up indicated the cut-point derived based on 2 standard deviations above a either comparison group in either ROI best differentiated tau positive and negative groups on cerebrospinal fluid phosphorylated tau, Mini-Mental State Examination score, and delayed memory performance.


    Given the impact of discrepant thresholds on tau positivity rates, biomarker staging, and eligibility for future clinical treatment trials, recommendations are offered to select cut-point derivations based on the unique goals and priorities of different studies.

    more » « less
  4. Abstract Background

    In Alzheimer’s Diseases (AD) research, multimodal imaging analysis can unveil complementary information from multiple imaging modalities and further our understanding of the disease. One application is to discover disease subtypes using unsupervised clustering. However, existing clustering methods are often applied to input features directly, and could suffer from the curse of dimensionality with high-dimensional multimodal data. The purpose of our study is to identify multimodal imaging-driven subtypes in Mild Cognitive Impairment (MCI) participants using a multiview learning framework based on Deep Generalized Canonical Correlation Analysis (DGCCA), to learn shared latent representation with low dimensions from 3 neuroimaging modalities.


    DGCCA applies non-linear transformation to input views using neural networks and is able to learn correlated embeddings with low dimensions that capture more variance than its linear counterpart, generalized CCA (GCCA). We designed experiments to compare DGCCA embeddings with single modality features and GCCA embeddings by generating 2 subtypes from each feature set using unsupervised clustering. In our validation studies, we found that amyloid PET imaging has the most discriminative features compared with structural MRI and FDG PET which DGCCA learns from but not GCCA. DGCCA subtypes show differential measures in 5 cognitive assessments, 6 brain volume measures, and conversion to AD patterns. In addition, DGCCA MCI subtypes confirmed AD genetic markers with strong signals that existing late MCI group did not identify.


    Overall, DGCCA is able to learn effective low dimensional embeddings from multimodal data by learning non-linear projections. MCI subtypes generated from DGCCA embeddings are different from existing early and late MCI groups and show most similarity with those identified by amyloid PET features. In our validation studies, DGCCA subtypes show distinct patterns in cognitive measures, brain volumes, and are able to identify AD genetic markers. These findings indicate the promise of the imaging-driven subtypes and their power in revealing disease structures beyond early and late stage MCI.

    more » « less
  5. Abstract Alzheimer’s disease (AD) is a neurogenerative condition characterized by sharp cognitive decline with no confirmed effective treatment or cure. This makes it critically important to identify the symptoms of Alzheimer’s disease in its early stages before significant cognitive deterioration has taken hold and even before any brain morphology and neuropathology are noticeable. In this study, five different multimodal deep neural networks (MDNN), with different architectures, in search of an optimal model for predicting the cognitive test scores for the Mini-Mental State Examination (MMSE) and the modified Alzheimer’s Disease Assessment Scale (ADAS-CoG13) over a span of 60 months (5 years). The multimodal data utilized to train and test the proposed models were obtained from the Alzheimer’s Disease Neuroimaging Initiative study and includes cerebrospinal fluid (CSF) levels of tau and beta-amyloid, structural measures from magnetic resonance imaging (MRI), functional and metabolic measures from positron emission tomography (PET), and cognitive scores from the neuropsychological tests (Cog). The models developed herein delve into two main issues: (1) application merits of single-task vs. multitask for predicting future cognitive scores and (2) whether time-varying input data are better suited than specific timepoints for optimizing prediction results. This model yields a high of 90.27% (SD = 1.36) prediction accuracy (correlation) at 6 months after the initial visit to a lower 79.91% (SD = 8.84) prediction accuracy at 60 months. The analysis provided is comprehensive as it determines the predictions at all other timepoints and all MDNN models include converters in the CN and MCI groups (CNc, MCIc) and all the unstable groups in the CN and MCI groups (CNun and MCIun) that reverted to CN from MCI and to MCI from AD, so as not to bias the results. The results show that the best performance is achieved by a multimodal combined single-task long short-term memory (LSTM) regressor with an input sequence length of 2 data points (2 visits, 6 months apart) augmented with a pretrained Neural Network Estimator to fill in for the missing values. 
    more » « less