Wiste, Heather J.

Abstract INTRODUCTION The timing of plasma biomarker changes is not well understood. The goal of this study was to evaluate the temporal co‐evolution of plasma and positron emission tomography (PET) Alzheimer's disease (AD) biomarkers. METHODS We included 1408 Mayo Clinic Study of Aging and Alzheimer's Disease Research Center participants. An accelerated failure time (AFT) model was fit with amyloid beta (Aβ) PET, tau PET, plasma p‐tau217, p‐tau181, and glial fibrillary acidic protein (GFAP) as endpoints. RESULTS Individual timing of plasma p‐tau progression was strongly associated with Aβ PET and GFAP progression. In the population, GFAP became abnormal first, then Aβ PET, plasma p‐tau, and tau PET temporal meta‐regions of interest when applying cut points based on young, cognitively unimpaired participants. DISCUSSION Plasma p‐tau is a stronger indicator of a temporally linked response to elevated brain Aβ than of tau pathology. While Aβ deposition and a rise in GFAP are upstream events associated with tau phosphorylation, the temporal link between p‐tau and Aβ PET was the strongest. Highlights Plasma p‐tau progression was more strongly associated with Aβ than tau PET. Progression on plasma p‐tau was associated with Aβ PET and GFAP progression. P‐tau181 and p‐tau217 become abnormal after Aβ PET and before tau PET. GFAP became abnormal first, before plasma p‐tau and Aβ PET.

Abstract Alzheimer's disease (AD) exhibits spatially heterogeneous 3R/4R tau pathology distributions across participants, making it a challenge to quantify extent of tau deposition. Utilizing Tau-PET from three independent cohorts, we trained and validated a machine learning model to identify visually positive Tau-PET scans from regional SUVR values and developed a novel summary measure, THETA, that accounts for heterogeneity in tau deposition. The model for identification of tau positivity achieved a balanced test accuracy of 95% and accuracy of ≥87% on the validation datasets. THETA captured heterogeneity of tau deposition, had better association with clinical measures, and corresponded better with visual assessments in comparison with the temporal meta-region-of-interest Tau-PET quantification methods. Our novel approach aids in identification of positive Tau-PET scans and provides a quantitative summary measure, THETA, that effectively captures the heterogeneous tau deposition seen in AD. The application of THETA for quantifying Tau-PET in AD exhibits great potential.

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.

Abstract Staging the severity of Alzheimer’s disease pathology using biomarkers is useful for therapeutic trials and clinical prognosis. Disease staging with amyloid and tau PET has face validity; however, this would be more practical with plasma biomarkers. Our objectives were, first, to examine approaches for staging amyloid and tau PET and, second, to examine prediction of amyloid and tau PET stages using plasma biomarkers. Participants (n = 1136) were enrolled in either the Mayo Clinic Study of Aging or the Alzheimer’s Disease Research Center; had a concurrent amyloid PET, tau PET and blood draw; and met clinical criteria for cognitively unimpaired (n = 864), mild cognitive impairment (n = 148) or Alzheimer’s clinical syndrome with dementia (n = 124). The latter two groups were combined into a cognitively impaired group (n = 272). We used multinomial regression models to estimate discrimination [concordance (C) statistics] among three amyloid PET stages (low, intermediate, high), four tau PET stages (Braak 0, 1–2, 3–4, 5–6) and a combined amyloid and tau PET stage (none/low versus intermediate/high severity) using plasma biomarkers as predictors separately within unimpaired and impaired individuals. Plasma analytes, p-tau181, Aβ1–42 and Aβ1–40 (analysed as the Aβ42/Aβ40 ratio), glial fibrillary acidic protein and neurofilament light chain were measured on the HD-X Simoa Quanterix platform. Plasma p-tau217 was also measured in a subset (n = 355) of cognitively unimpaired participants using the Lilly Meso Scale Discovery assay. Models with all Quanterix plasma analytes along with risk factors (age, sex and APOE) most often provided the best discrimination among amyloid PET stages (C = 0.78–0.82). Models with p-tau181 provided similar discrimination of tau PET stages to models with all four plasma analytes (C = 0.72–0.85 versus C = 0.73–0.86). Discriminating a PET proxy of intermediate/high from none/low Alzheimer’s disease neuropathological change with all four Quanterix plasma analytes was excellent but not better than p-tau181 only (C = 0.88 versus 0.87 for unimpaired and C = 0.91 versus 0.90 for impaired). Lilly p-tau217 outperformed the Quanterix p-tau181 assay for discriminating high versus intermediate amyloid (C = 0.85 versus 0.74) but did not improve over a model with all Quanterix plasma analytes and risk factors (C = 0.85 versus 0.83). Plasma analytes along with risk factors can discriminate between amyloid and tau PET stages and between a PET surrogate for intermediate/high versus none/low neuropathological change with accuracy in the acceptable to excellent range. Combinations of plasma analytes are better than single analytes for many staging predictions with the exception that Quanterix p-tau181 alone usually performed equivalently to combinations of Quanterix analytes for tau PET discrimination.

AbstractBackgroundCerebral Microbleeds (CMBs) are tracked in anti‐amyloid drug safety monitoring. T2*GRE or SWI MRI images are visually assessed for the presence of CMBs. Automated methods tuned for sensitivity often have unacceptably high false positive rates requiring extensive human cleanup.MethodAssume contemporaneous T2*GRE and T1‐weighted images. CMB detection (Figures 1,2) has three steps: 1) Segmentation outputs from the T1‐weighted image are resampled into the T2*GRE image voxel raster; 2) Normalized cross‐correlation of the T2*GRE with a CMB template identifies “candidate CMBs”; 3) a neural network using voxel patches centered on each candidate CMB rejects false positives. Patches presented to the network are 4D and include five contrasts drawn from the T2*GRE, correlation, T1‐weighted, WM probability and CSF probability images. The simple network architecture consists of convolutional blocks followed by dense blocks. The system is trained using images from ADNI, ARIC, MCSA, and the Mayo Clinic ADRC that have been previously visually graded for CMBs (Table in Figure 3). Importantly, we include participants with and without CMBs in our data reflecting the fact that the majority of people (even the elderly) have no CMBs. Data is split 70:10:20 by subject for training, validation, and testing. Various network configurations were evaluated.ResultHigh candidate detection sensitivity can be achieved at the expense of presenting hundreds to thousands of false positive candidates per input image to the rejection network. Our best performing network configuration to date has AUC 0.982 (95% bootstrap CI 0.971 to 0.990 based on the 10% validation subset). Choosing an operating point with 95% sensitivity in the validation set and admits, on average, 0.6 false positive CMB candidates per input T2*GRE image. Sensitivity is hindered by a small number of obvious errors in the ground truth visual assessment. Validation loss tracks training loss with no indication of over‐fitting. Example patches are shown in Figure 4.ConclusionExcessive false positive detection requires significant human correction and effort, preventing automated CMB detection from being widely adopted. We have an automated detection system that is sensitive (95%) and provides excellent false positive rejection (<1 false positive CMB/input image) reducing needed human effort.

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.

AbstractBackgroundCerebral Microbleeds (CMBs) are tracked in anti‐amyloid drug safety monitoring. T2*GRE or SWI MRI images are visually assessed for the presence of CMBs. Automated methods tuned for sensitivity often have unacceptably high false positive rates requiring extensive human cleanup.MethodAssume contemporaneous T2*GRE and T1‐weighted images. CMB detection (Figures 1,2) has three steps: 1) Segmentation outputs from the T1‐weighted image are resampled into the T2*GRE image voxel raster; 2) Normalized cross‐correlation of the T2*GRE with a CMB template identifies “candidate CMBs”; 3) a neural network using voxel patches centered on each candidate CMB rejects false positives. Patches presented to the network are 4D and include five contrasts drawn from the T2*GRE, correlation, T1‐weighted, WM probability and CSF probability images. The simple network architecture consists of convolutional blocks followed by dense blocks. The system is trained using images from ADNI, ARIC, MCSA, and the Mayo Clinic ADRC that have been previously visually graded for CMBs (Table in Figure 3). Importantly, we include participants with and without CMBs in our data reflecting the fact that the majority of people (even the elderly) have no CMBs. Data is split 70:10:20 by subject for training, validation, and testing. Various network configurations were evaluated.ResultHigh candidate detection sensitivity can be achieved at the expense of presenting hundreds to thousands of false positive candidates per input image to the rejection network. Our best performing network configuration to date has AUC 0.982 (95% bootstrap CI 0.971 to 0.990 based on the 10% validation subset). Choosing an operating point with 95% sensitivity in the validation set and admits, on average, 0.6 false positive CMB candidates per input T2*GRE image. Sensitivity is hindered by a small number of obvious errors in the ground truth visual assessment. Validation loss tracks training loss with no indication of over‐fitting. Example patches are shown in Figure 4.ConclusionExcessive false positive detection requires significant human correction and effort, preventing automated CMB detection from being widely adopted. We have an automated detection system that is sensitive (95%) and provides excellent false positive rejection (<1 false positive CMB/input image) reducing needed human effort.

AbstractIntroductionThis study established the psychometric properties and preliminary validity of the Stricker Learning Span (SLS), a novel computer adaptive word list memory test designed for remote assessment and optimized for smartphone use.MethodsWomen enrolled in the Mayo Clinic Specialized Center of Research Excellence (SCORE) were recruited via e‐mail or phone to complete two remote cognitive testing sessions. Convergent validity was assessed through correlation with previously administered in‐person neuropsychological tests (n = 96, ages 55–79) and criterion validity through associations with magnetic resonance imaging measures of neurodegeneration sensitive to Alzheimer's disease (n = 47).ResultsSLS performance significantly correlated with the Auditory Verbal Learning Test and measures of neurodegeneration (temporal meta‐regions of interest and entorhinal cortical thickness, adjusting for age and education). Test–retest reliabilities across two sessions were 0.71–0.76 (two‐way mixed intraclass correlation coefficients).DiscussionThe SLS is a valid and reliable self‐administered memory test that shows promise for remote assessment of aging and neurodegenerative disorders.

BackgroundLocalized regions of left–right image intensity asymmetry (LRIA) were incidentally observed on T2‐weighted (T2‐w) and T1‐weighted (T1‐w) diagnostic magnetic resonance imaging (MRI) images. Suspicion of herpes encephalitis resulted in unnecessary follow‐up imaging. A nonbiological imaging artifact that can lead to diagnostic uncertainty was identified.PurposeTo investigate whether systematic LRIA exist for a range of scanner models and to determine if LRIA can introduce diagnostic uncertainty.Study TypeA retrospective study using the Alzheimer's Disease Neuroimaging Initiative (ADNI) data base.SubjectsOne thousand seven hundred fifty‐three (median age: 72, males/females: 878/875) unique participants with longitudinal data were included.Field Strength3T.SequencesT1‐w three‐dimensional inversion‐recovery spoiled gradient‐echo (IR‐SPGR) or magnetization‐prepared rapid gradient‐echo (MP‐RAGE) and T2‐w fluid‐attenuated inversion recovery (FLAIR) long tau fast spin echo inversion recovery (LT‐FSE‐IR). Only General Electric, Philips, and Siemens' product sequences were used.AssessmentLRIA was calculated as the left–right percent difference with respect to the mean intensity from automated anatomical atlas segmented regions. Three neuroradiologists with 37 (**), 32 (**), and 3 (**) years of experience rated the clinical impact of 30 T2‐w three‐dimensional FLAIR exams with LRIA to determine the diagnostic uncertainty. Statistical comparisons between retrospective intensity normalized T1m and original T1‐w images were made.Statistical TestsFor each image type, a linear mixed effects model was fit using LRIA scores from all scanners, regions, and participants as the outcome and age and sex as predictors. Statistical significance was defined as having a P‐value <0.05.ResultsLRIA scores were significantly different from zero on most scanners. All clinicians were uncertain or recommended definite diagnostic follow‐up in 62.5% of cases with LRIA >10%. Individuals with acute brain pathology or focal neurologic deficits are not enrolled in ADNI; therefore, focal signal abnormalities were considered false positives.Data ConclusionLRIA is system specific, systematic, creates diagnostic uncertainty, and impacts IR‐SPGR, MP‐RAGE, and LT‐FSE‐IR product sequences.Level of Evidence: 2Technical Efficacy Stage: 3