Citations

Abstract Given the prevalence of dementia and the development of pathology-specific disease-modifying therapies, high-value biomarker strategies to inform medical decision-making are critical. In vivo tau-PET is an ideal target as a biomarker for Alzheimer’s disease diagnosis and treatment outcome measure. However, tau-PET is not currently widely accessible to patients compared to other neuroimaging methods. In this study, we present a convolutional neural network (CNN) model that imputes tau-PET images from more widely available cross-modality imaging inputs. Participants (n = 1192) with brain T1-weighted MRI (T1w), fluorodeoxyglucose (FDG)-PET, amyloid-PET and tau-PET were included. We found that a CNN model can impute tau-PET images with high accuracy, the highest being for the FDG-based model followed by amyloid-PET and T1w. In testing implications of artificial intelligence-imputed tau-PET, only the FDG-based model showed a significant improvement of performance in classifying tau positivity and diagnostic groups compared to the original input data, suggesting that application of the model could enhance the utility of the metabolic images. The interpretability experiment revealed that the FDG- and T1w-based models utilized the non-local input from physically remote regions of interest to estimate the tau-PET, but this was not the case for the Pittsburgh compound B-based model. This implies that the model can learn the distinct biological relationship between FDG-PET, T1w and tau-PET from the relationship between amyloid-PET and tau-PET. Our study suggests that extending neuroimaging’s use with artificial intelligence to predict protein specific pathologies has great potential to inform emerging care models.

AbstractBackgroundAlzheimer’s disease (AD) pathologic changes (e.g. amyloid and tau aggregation), and cerebrovascular disease often coexist, and it remains unclear whether these are mechanistically linked processes (Graff‐Radford, Brain 2019; Provenzano, JAMA Neurol 2013). Most studies evaluating these associations are cross‐sectional; however, establishing temporal relationships may provide additional insight into potential mechanistic associations. One method to assess the temporal evolution of a biomarker is the Accelerated Failure Time (AFT) model, which assumes a common pattern of progression for a given biomarker that is shifted earlier or later in time for each individual (Therneau, Neuroimage 2021). In this work we investigate the relationship of disease trajectories of cerebrovascular disease (via white matter hyperintensity, WMH, volume) and AD biomarkers (via amyloid and tau PET).MethodsWe included Mayo Clinic Study of Aging (MCSA) and Mayo Alzheimer’s Disease Research Center (ADRC) participants with amyloid PET, tau PET, and MRI, age > 50 years, and a clinical diagnosis of cognitively unimpaired (CU), mild cognitive impairment (MCI) or Alzheimer’s disease dementia. The AFT model was fit with amyloid PET (PiB) global meta‐ROI SUVR, tau PET (flortaucipir) temporal meta‐ROI SUVR, and WMH volume as the tri‐variate endpoints, with APOE genotype, sex, education, total intracranial volume, and referral/population subject as covariates. A per subject/endpoint random effect represents individual adjustments for each biomarker to indicate if the subject's biomarker became abnormal earlier or later relative to their demographic peers, accounting for the covariates.ResultsThe study included 1144 participants (Table 1). There was a strong correlation between earlier onset of amyloid and earlier onset of tau (r=0.64, CI=0.60‐0.67) (Figure 1, Table 2); early/late amyloid timing explained nearly half (0.642 = 41%) of the variation in tau onset. There were only weak associations between an individual’s WMH and amyloid PET onset adjustments (r=0.10, 1.0%) and WMH and tau PET onset adjustments (r=‐0.07, 0.5%).ConclusionThis analysis supports a strong mechanistic relationship between amyloid and tau aggregation, as reported by others. However, our findings do not support a mechanistic association between WMH and amyloid or tau PET.

AbstractBackgroundIn vivo tau‐positron emission tomography (PET) is an attractive biomarker for Alzheimer’s disease (AD) diagnosis and treatment. However, tau‐PET is less widely available than other modalities. In this study, we tested cross‐modality synthesis of tau‐PET brain images from fluorodeoxyglucose F‐18 (FDG)‐PET using a deep convolutional neural network (CNN).MethodParticipants (n=1,192) who had brain FDG‐PET with 18F‐FDG and tau‐PET with Flortaucipir (F‐18‐AV‐1451) were included for training and testing. This cohort spanned normal aging (ages 26‐98), pre‐clinical, and clinical AD and related disorders including the FTD and DLB spectrum. External validation was done using ADNI (n=288). The PET scans were co‐registered to the corresponding MRI and subsequently warped to Mayo Clinic Adult Lifespan Template (MCALT) space. Tau‐PET images were SUVR‐normalized to the cerebellar crus, and FDG to the pons. A 3D dense‐U‐net model was utilized as an architecture. Cross‐validation experiments were conducted using 5‐fold validations (60% training set, 20% validation set, and 20% test set) with mean squared error as the loss function.ResultOur dense‐U‐net model successfully synthesized tau‐PET from metabolic images with good correlation and low prediction error for regional SUVRs (Figure 1A‐C). The model showed a robust prediction ability, performing accurately in an independent, external ADNI cohort (Figure 1D‐F). The model‐imputed tau‐PET significantly improved performance in classifying tau positivity (mean AUROC(±SD)=0.78±0.04 and 0.85±0.03 for FDG‐PET and synthesized tau‐PET, respectively) and diagnostic groups (cognitively unimpaired with abnormal amyloid‐PET vs. cognitively impaired with abnormal amyloid‐PET) compared to the original input FDG data (mean AUROC(±SD)=0.89±0.04, 0.85±0.05 0.91±0.04 for actual tau‐PET, FDG‐PET and synthesized tau‐PET, respectively) (Figure 2), suggesting enhanced clinical utility for metabolic images. The ADNI cohort also showed similar results (for tau positivity: AUROC=0.66 and 0.78 for FDG‐PET and synthesized tau‐PET, respectively; for CU A+ vs. CI A+: AUROC=0.86, 0.62, and 0.73 for actual tau‐PET, FDG‐PET, and synthesized tau‐PET; Figure 3).ConclusionWe showed that using a CNN model to predict tau‐PET from FDG‐PET is feasible. The synthesized tau‐PET can augment the value of FDG‐PET, facilitating the multi‐modal diagnosis of AD.

Abstract Introduction The aim of this study was to develop a conditional normative model for Rey's Auditory Verbal Learning Test (AVLT) that accounts for practice effects. Methods In our normative sample, robust conditional norms were derived from 1001 cognitively unimpaired (CU) adults ages 50 to 89 who completed the AVLT up to eight times. Linear mixed‐effects models adjusted for baseline performance, prior test exposures, time, demographics, and interaction terms. In our preliminary validation, mean performance on conditional and typical normative scores across two to four completed follow‐up tests in preclinical Alzheimer's disease participants at baseline with positive amyloid and tau positron emission ( n = 27 CU amyloid [A]+tau[T]+) was compared to biomarker negative individuals ( n = 269 CU A–T–). Results AVLT performance using typical norms did not differ across A+T+ and A–T– groups. Conditional norms z‐scores were lower in the A+T+ relative to the A–T– group for 30‐minute recall ( P = .033) and sum of trials ( P = .030). Discussion Conditional normative methods that account for practice effects show promise for identifying longitudinal cognitive decline.

AbstractBackgroundIn longitudinal tau (flortaucipir) positron emission tomography (PET), a reliable method to detect a tau accumulation while minimizing a random variability is crucial. Variability can be a problem especially in the early stages of tau pathology in which only small regions and low levels of accumulation may exist relative to the range of random noise fluctuation.MethodWe recruited 76 participants who had serial scans for a total of 234 tau PET scans. In this cohort we tested a PET signal measurement method we developed called the “overlap index” (OI). The OI was calculated by identifying voxels that have elevated tau PET signal that overlap on two successive tau PET scans in the same participant (Figure 1). This analysis procedure tests the hypothesis that voxel‐wise, elevated‐uptake consistency might be more sensitive for early detection of tau tangles than standard ROI based measures. We compared OI to ROI based measures for early detection of increasing tau PET signal and detection clinical progression. A meta ROI used in this analysis included the amygdala, entorhinal cortex, fusiform, parahippocampal, and inferior temporal and middle temporal gyri.ResultOI showed regional progression of tau in the temporal lobe followed by increases throughout the brain at relatively low standardized uptake value ratio (SUVr) levels (Figure 2A and B). The topographical pattern of OI was in agreement in some respects with the sequential appearance of tau aggregation (Figure 2B and C). The high‐OI group (OI>0.5) had a significantly higher ΔSUVr compared to the low‐OI group (OI<0.5) (Figure 3A and B). OI identified subjects that did or didn’t have tau accumulation within meta SUVr subgroups even when below the meta ROI SUVr threshold. OI was associated with early clinical disease stage progression vs meta‐ROI SUVr measures (Figure 3C‐E).ConclusionIn this study, we found that OI tau PET measurement was able to quantify voxel‐wise consistency using a set of serial scans. OI may detect earlier tau tangle accumulation and earlier disease progression than standard SUVr measurements in tau PET.

Abstract Dementia and mortality rates rise inexorably with age and consequently interact. However, because of the major logistical difficulties in accounting for both outcomes in a defined population, very little work has examined how risk factors and biomarkers for incident dementia are influenced by competing mortality. The objective of this study was to examine long-term associations between amyloid PET, APOE ɛ4, sex, education and cardiovascular/metabolic conditions, and hazard and absolute risk of dementia and mortality in individuals without dementia at enrolment. Participants were enrolled in the Mayo Clinic Study of Aging, a population-based study of cognitive ageing in Olmsted County, MN, USA. All were without dementia and were age 55–92 years at enrolment and were followed longitudinally. Predictor variables were amyloid PET, APOE ɛ4 status, sex, education, cardiovascular/metabolic conditions and age. The main outcomes were incident dementia and mortality. Multivariable, multi-state models were used to estimate mortality and incident dementia rates and absolute risk of dementia and mortality by predictor variable group. Of the 4984 participants in the study, 4336 (87%) were cognitively unimpaired and 648 (13%) had mild cognitive impairment at enrolment. The median age at enrolment was 75 years; 2463 (49%) were women. The median follow-up time was 9.4 years (7.5 years after PET). High versus normal amyloid (hazard ratio 2.11, 95% confidence interval 1.43–2.79), APOE ɛ4 (women: hazard ratio 2.24, 95% confidence interval 1.80–2.77; men: hazard ratio 1.37, 95% confidence interval 1.09–1.71), older age and two additional cardiovascular/metabolic conditions (hazard ratio 1.37, 95% confidence interval 1.22–1.53) were associated with the increased hazard of dementia (all P &lt; 0.001). Among APOE ɛ4 carriers with elevated amyloid, remaining lifetime risk of dementia at age 65 years was greater in women [74% (95% confidence interval 65–84%) high and 58% (95% confidence interval 52–65%) moderate amyloid], than men [62% (95% confidence interval 52–73%) high and 44% (95% confidence interval 35–53%) moderate amyloid]. Overall, the hazard and absolute risk of dementia varied considerably by predictor group. The absolute risk of dementia associated with predictors characteristic of Alzheimer’s disease was greater in women than men while at the same time the combination of APOE ɛ4 non-carrier with normal amyloid was more protective in women than men. This set of findings may be attributed in part to different biological effects and in part to lower mortality rates in women.

Abstract Introduction The aim of this study was to examine white matter hyperintensities (WMH) and fractional anisotropy (FA) in empirically derived incident mild cognitive impairment (MCI) subtypes. Methods We evaluated 188 participants with incident MCI in the Mayo Clinic Study of Aging (MCSA) identified as having one of four cluster‐derived subtypes: subtle cognitive impairment, amnestic, dysnomic, and dysexecutive. We used linear regression models to evaluate whole brain and regional WMH volumes. We examined fractional anisotropy (FA) on a subset of 63 participants with diffusion tensor imaging. Results Amnestic and dysexecutive subtypes had higher WMH volumes in differing patterns than cognitively unimpaired; the dysexecutive subtype had higher WMH than subtle cognitive impairment. There was widespread WM degeneration in long association and commissural fibers in the amnestic, dysnomic, and dysexecutive subtypes, and corpus callosum FA accounted for significant variability in global cognition. Discussion White matter changes likely contribute to cognitive symptoms in incident MCI.

AbstractBackgroundEarly changes in white matter (WM) measured using diffusion tensor imaging (DTI) are sensitive markers of WM degeneration and predict future cognitive decline in mild cognitive impairment (MCI). We sought to examine whether changes in WM integrity differed among empirically derived subtypes of incident MCI.MethodParticipants included 66 individuals with incident MCI enrolled in the population‐based Mayo Clinic Study of Aging (MCSA) previously identified via cluster analysis as having one of four MCI subtypes: subtle cognitive impairment (SCI; n = 13, mean age 78; 15% women), amnestic (n = 24; mean age 79; 54% women), dysnomic (n = 8; mean age 79; 38% women), and dysexecutive (n = 21; mean age 82; 33% women). All participants completed 3T MRI at the time of the MCI diagnosis. We compared the MCI subtypes to 100 cognitively unimpaired (CU) participants (mean age 77; 49% women). We used tract‐based spatial statistics to examine voxel‐level differences in fractional anisotropy (FA). We also fit a linear regression model to regional FA data from the corpus callosum (CC), the major interhemispheric WM connection, to quantify the relative differences in WM damage.ResultAll MCI subtypes except the subtle cognitive impairment group had widespread decreased FA. Relative to CU, the amnestic cluster showed decreased FA in the CC (genu), cingulum, fornix and uncinate fasciculus (UF); the dysnomic cluster showed decreased FA in the CC (genu, splenium), fornix, UF, anterior thalamic radiation (ATR), and corticospinal tract (CST); and the dysexecutive group showed decreased FA in the CC (genu, body, splenium), cingulum, UF, ATR, CST, and superior longitudinal fasciculus. The dysexecutive cluster had the most severe bilateral involvement among all MCI subtypes. The regional analysis showed that the amnestic, dysnomic, and dysexecutive groups (but not the subtle cognitive impairment group) had significantly lower FA of the CC compared to CU (p<0.001; Figure 1).ConclusionWe found widespread WM degeneration in the commissural and long association fibers in amnestic, dysnomic, and dysexecutive incident MCI subtypes. The extent of CC damage seen in Figure 1. confirmed the voxel‐level results and suggests that interhemispheric WM disconnection is relevant to the development of MCI.

Abstract Normal brain aging is accompanied by patterns of functional and structural change. Alzheimer's disease (AD), a representative neurodegenerative disease, has been linked to accelerated brain aging at respective age ranges. Here, we developed a deep learning-based brain age prediction model using fluorodeoxyglucose (FDG) PET and structural MRI and tested how the brain age gap relates to degenerative cognitive syndromes including mild cognitive impairment, AD, frontotemporal dementia, and Lewy body dementia. Occlusion analysis, performed to facilitate interpretation of the model, revealed that the model learns an age- and modality-specific pattern of brain aging. The elevated brain age gap in dementia cohorts was highly correlated with the cognitive impairment and AD biomarker. However, regions generating brain age gaps were different for each diagnosis group of which the AD continuum showed similar patterns to normal aging in the CU.

Background: Longitudinal, but not cross-sectional, cognitive testing is one option proposed to define transitional cognitive decline for individuals on the Alzheimer’s disease continuum. Objective: Compare diagnostic accuracy of cross-sectional subtle objective cognitive impairment (sOBJ) and longitudinal objective decline (ΔOBJ) over 30 months for identifying 1) cognitively unimpaired participants with preclinical Alzheimer’s disease defined by elevated brain amyloid and tau (A+T+) and 2) incident mild cognitive impairment (MCI) based on Cogstate One Card Learning (OCL) accuracy performance. Methods: Mayo Clinic Study of Aging cognitively unimpaired participants aged 50 + with amyloid and tau PET scans (n = 311) comprised the biomarker-defined sample. A case-control sample of participants aged 65 + remaining cognitively unimpaired for at least 30 months included 64 who subsequently developed MCI (incident MCI cases) and 184 controls, risk-set matched by age, sex, education, and visit number. sOBJ was assessed by OCL z-scores. ΔOBJ was assessed using within subjects’ standard deviation and annualized change from linear regression or linear mixed effects (LME) models. Concordance measures Area Under the ROC Curve (AUC) or C-statistic and odds ratios (OR) from conditional logistic regression models were derived. sOBJ and ΔOBJ were modeled jointly to compare methods. Results: sOBJ and ΔOBJ-LME methods differentiated A+T+ from A-T- (AUC = 0.64, 0.69) and controls from incident MCI (C-statistic = 0.59, 0.69) better than chance; other ΔOBJ methods did not. ΔOBJ-LME improved prediction of future MCI over baseline sOBJ (p = 0.003) but not over 30-month sOBJ (p = 0.09). Conclusion: Longitudinal decline did not offer substantial benefit over cross-sectional assessment in detecting preclinical Alzheimer’s disease or incident MCI.