Citations

Accurate prediction of progression in subjects at risk of Alzheimer's disease is crucial for enrolling the right subjects in clinical trials. However, a prospective comparison of state-of-the-art algorithms for predicting disease onset and progression is currently lacking. We present the findings of "The Alzheimer's Disease Prediction Of Longitudinal Evolution" (TADPOLE) Challenge, which compared the performance of 92 algorithms from 33 international teams at predicting the future trajectory of 219 individuals at risk of Alzheimer's disease. Challenge participants were required to make a prediction, for each month of a 5-year future time period, of three key outcomes: clinical diagnosis, Alzheimer's Disease Assessment Scale Cognitive Subdomain (ADAS-Cog13), and total volume of the ventricles. The methods used by challenge participants included multivariate linear regression, machine learning methods such as support vector machines and deep neural networks, as well as disease progression models. No single submission was best at predicting all three outcomes. For clinical diagnosis and ventricle volume prediction, the best algorithms strongly outperform simple baselines in predictive ability. However, for ADAS-Cog13 no single submitted prediction method was significantly better than random guesswork. Two ensemble methods based on taking the mean and median over all predictions, obtained top scores on almost all tasks. Better than average performance at diagnosis prediction was generally associated with the additional inclusion of features from cerebrospinal fluid (CSF) samples and diffusion tensor imaging (DTI). On the other hand, better performance at ventricle volume prediction was associated with inclusion of summary statistics, such as the slope or maxima/minima of patient-specific biomarkers. On a limited, cross-sectional subset of the data emulating clinical trials, performance of the best algorithms at predicting clinical diagnosis decreased only slightly (2 percentage points) compared to the full longitudinal dataset. The submission system remains open via the website https://tadpole.grand-challenge.org, while TADPOLE SHARE (https://tadpole-share.github.io/) collates code for submissions. TADPOLE's unique results suggest that current prediction algorithms provide sufficient accuracy to exploit biomarkers related to clinical diagnosis and ventricle volume, for cohort refinement in clinical trials for Alzheimer's disease. However, results call into question the usage of cognitive test scores for patient selection and as a primary endpoint in clinical trials.

Background: Alzheimer’s disease (AD) is the most common type of age-related dementia, affecting 6.2 million people aged 65 or older according to CDC data. It is commonly agreed that discovering an effective AD diagnosis biomarker could have enormous public health benefits, potentially preventing or delaying up to 40% of dementia cases. Tau neurofibrillary tangles are the primary driver of downstream neurodegeneration and subsequent cognitive impairment in AD, resulting in structural deformations such as hippocampal atrophy that can be observed in magnetic resonance imaging (MRI) scans. Objective: To build a surface-based model to 1) detect differences between APOE subgroups in patterns of tau deposition and hippocampal atrophy, and 2) use the extracted surface-based features to predict cognitive decline. Methods: Using data obtained from different institutions, we develop a surface-based federated Chow test model to study the synergistic effects of APOE, a previously reported significant risk factor of AD, and tau on hippocampal surface morphometry. Results: We illustrate that the APOE-specific morphometry features correlate with AD progression and better predict future AD conversion than other MRI biomarkers. For example, a strong association between atrophy and abnormal tau was identified in hippocampal subregion cornu ammonis 1 (CA1 subfield) and subiculum in e4 homozygote cohort. Conclusion: Our model allows for identifying MRI biomarkers for AD and cognitive decline prediction and may uncover a corner of the neural mechanism of the influence of APOE and tau deposition on hippocampal morphology.

Background: Amyloid-β (Aβ) plaques and tau protein tangles in the brain are the defining ‘A’ and ‘T’ hallmarks of Alzheimer’s disease (AD), and together with structural atrophy detectable on brain magnetic resonance imaging (MRI) scans as one of the neurodegenerative (‘N’) biomarkers comprise the “ATN framework” of AD. Current methods to detect Aβ/tau pathology include cerebrospinal fluid (invasive), positron emission tomography (PET; costly and not widely available), and blood-based biomarkers (promising but mainly still in development). Objective: To develop a non-invasive and widely available structural MRI-based framework to quantitatively predict the amyloid and tau measurements. Methods: With MRI-based hippocampal multivariate morphometry statistics (MMS) features, we apply our Patch Analysis-based Surface Correntropy-induced Sparse coding and max-pooling (PASCS-MP) method combined with the ridge regression model to individual amyloid/tau measure prediction. Results: We evaluate our framework on amyloid PET/MRI and tau PET/MRI datasets from the Alzheimer’s Disease Neuroimaging Initiative. Each subject has one pair consisting of a PET image and MRI scan, collected at about the same time. Experimental results suggest that amyloid/tau measurements predicted with our PASCP-MP representations are closer to the real values than the measures derived from other approaches, such as hippocampal surface area, volume, and shape morphometry features based on spherical harmonics. Conclusion: The MMS-based PASCP-MP is an efficient tool that can bridge hippocampal atrophy with amyloid and tau pathology and thus help assess disease burden, progression, and treatment effects.

Background: A univariate neurodegeneration biomarker (UNB) based on MRI with strong statistical discrimination power would be highly desirable for studying hippocampal surface morphological changes associated with APOE ɛ4 genetic risk for AD in the cognitively unimpaired (CU) population. However, existing UNB work either fails to model large group variances or does not capture AD induced changes. Objective: We proposed a subspace decomposition method capable of exploiting a UNB to represent the hippocampal morphological changes related to the APOE ɛ4 dose effects among the longitudinal APOE ɛ4 homozygotes (HM, N = 30), heterozygotes (HT, N = 49) and non-carriers (NC, N = 61). Methods: Rank minimization mechanism combined with sparse constraint considering the local continuity of the hippocampal atrophy regions is used to extract group common structures. Based on the group common structures of amyloid-β (Aβ) positive AD patients and Aβ negative CU subjects, we identified the regions-of-interest (ROI), which reflect significant morphometry changes caused by the AD development. Then univariate morphometry index (UMI) is constructed from these ROIs. Results: The proposed UMI demonstrates a more substantial statistical discrimination power to distinguish the longitudinal groups with different APOE ɛ4 genotypes than the hippocampal volume measurements. And different APOE ɛ4 allele load affects the shrinkage rate of the hippocampus, i.e., HM genotype will cause the largest atrophy rate, followed by HT, and the smallest is NC. Conclusion: The UMIs may capture the APOE ɛ4 risk allele-induced brain morphometry abnormalities and reveal the dose effects of APOE ɛ4 on the hippocampal morphology in cognitively normal individuals.

Background: Besides their other roles, brain imaging and other biomarkers of Alzheimer’s disease (AD) have the potential to inform a cognitively unimpaired (CU) person’s likelihood of progression to mild cognitive impairment (MCI) and benefit subject selection when evaluating promising prevention therapies. We previously described that among baseline FDG-PET and MRI measures known to be preferentially affected in the preclinical and clinical stages of AD, hippocampal volume was the best predictor of incident MCI within 2 years (79%sensitivity/78%specificity), using standard automated MRI volumetric algorithmic programs, binary logistic regression, and leave-one-out procedures. Objective: To improve the same prediction by using different hippocampal features and machine learning methods, cross-validated via two independent and prospective cohorts (Arizona and ADNI). Methods: Patch-based sparse coding algorithms were applied to hippocampal surface features of baseline TI-MRIs from 78 CU adults who subsequently progressed to amnestic MCI in approximately 2 years (“progressors”) and 80 matched adults who remained CU for at least 4 years (“nonprogressors”). Nonprogressors and progressors were matched for age, sex, education, and apolipoprotein E4 allele dose. We did not include amyloid or tau biomarkers in defining MCI. Results: We achieved 92%prediction accuracy in the Arizona cohort, 92%prediction accuracy in the ADNI cohort, and 90%prediction accuracy when combining the two demographically distinct cohorts, as compared to 79%(Arizona) and 72%(ADNI) prediction accuracy using hippocampal volume. Conclusion: Surface multivariate morphometry and sparse coding, applied to individual MRIs, may accurately predict imminent progression to MCI even in the absence of other AD biomarkers.

Background: Disease progression prediction based on neuroimaging biomarkers is vital in Alzheimer’s disease (AD) research. Convolutional neural networks (CNN) have been proved to be powerful for various computer vision research by refining reliable and high-level feature maps from image patches. Objective: A key challenge in applying CNN to neuroimaging research is the limited labeled samples with high dimensional features. Another challenge is how to improve the prediction accuracy by joint analysis of multiple data sources (i.e., multiple time points or multiple biomarkers). To address these two challenges, we propose a novel multi-task learning framework based on CNN. Methods: First, we pre-trained CNN on the ImageNet dataset and transferred the knowledge from the pre-trained model to neuroimaging representation. We used this deep model as feature extractor to generate high-level feature maps of different tasks. Then a novel unsupervised learning method, termed Multi-task Stochastic Coordinate Coding (MSCC), was proposed for learning sparse features of multi-task feature maps by using shared and individual dictionaries. Finally, Lasso regression was performed on these multi-task sparse features to predict AD progression measured by the Mini-Mental State Examination (MMSE) and the Alzheimer’s Disease Assessment Scale cognitive subscale (ADAS-Cog). Results: We applied this novel CNN-MSCC system on the Alzheimer’s Disease Neuroimaging Initiative dataset to predict future MMSE/ADAS-Cog scales. We found our method achieved superior performances compared with seven other methods. Conclusion: Our work may add new insights into data augmentation and multi-task deep model research and facilitate the adoption of deep models in neuroimaging research.