Citations

AbstractBackgroundThe NIA‐AA research framework group and the IWG both agree that abnormal AD biomarkers are necessary for the diagnosis of AD; however, the groups disagree on the appropriate definition of Alzheimer’s disease. The NIA‐AA framework argues that a CU A+T+ individual has AD pathology and therefore has the disease. The IWG argues that such an individual should be labeled “at risk for AD” because both abnormal biomarkers and clinically significant impairment are required for an AD diagnosis.MethodThe major IWG argument against a biological‐only definition of AD is that some CU A+T+ individuals will die of other causes without experiencing overt symptoms (MCI or dementia) in their lifetime. However, the same statement can be made about any other disease in medicine. The question therefore must be how often will CU A+T+ individuals die without experiencing dementia.ResultMany studies have examined rates of cognitive decline in CU A+ relative to CU A‐ (fewer studies in CU A+T+ vs CU A‐T‐). Studies have examined the risk of incident MCI/dementia in CU A+ relative to CU A‐ (fewer in CU A+T+ vs CU A‐T‐). Relative risk indicates likelihood of an outcome in a particular risk group relative to a reference group; it does not indicate the likelihood in percentage terms that an individual will experience an outcome in their lifetime. It is lifetime risk (i.e., absolute risk) that is needed to address the current controversy and to our knowledge only 2 published studies have estimated lifetime risk associated with AD biomarkers. A recent Mayo Clinic Study of Aging analysis examined lifetime risk of dementia associated with varying levels of amyloid PET, APOE and sex. Among APOE ε4 carriers with high amyloid PET SUVR, remaining lifetime risk of dementia at age 75 years was 76% for women and 64% for men. Lifetime risk of CU A+T+ remains to be determined, however.ConclusionThe major discordance between the NIA‐AA framework and the IWG (the definition of AD) points to the question, how risky is the CU A+T+ state? Accurate estimates of lifetime risk from population‐based studies are needed to address this question.

AbstractBackgroundReduced striatal uptake on ioflupane SPECT is considered an indicative biomarker for Dementia with Lewy Bodies (DLB), and has been proposed as an indicative biomarker for Mild Cognitive Impairment with Lewy Bodies (MCI‐LB). Little data exists on the profile of uptake on key striatal regions of interest (ROIs) in DLB or MCI‐LB.MethodParticipants with DLB or MCI‐LB at baseline based on the presence of ≥2 core clinical DLB features, and ≥2 ioflupane SPECT scans performed approximately annually, were identified from the Mayo ADRC database. Minimum brain laterality z‐score values for the putamen (whole, anterior and posterior), caudate and striatum were determined using DaTQUANT 2 software. Baseline clinical and scan data was used for all analyses, and the annualized minimum putamen z‐change was determined on serial scans. The scan was considered abnormal if the minimum putamen z‐score was <‐0.98 based on clinicopathologic data.Result27 participants were included (21 DLB and 6 MCI‐LB, 96% male). Compared to MCI‐LB, DLB had a lower mean MoCA score and a trend toward a higher UPDRS score compared to MCI‐LB; there were no statistically significant differences in age, sex, onset age or duration of cognitive decline, or presence of other core DLB features. The majority (89%) had an abnormal scan at baseline. All ROI z‐scores showed the expected general trend of DLB<MCI‐LB, and the annualized z‐change was more negative in DLB, but none of the findings reached statistical significance.ConclusionThese findings suggest in MCI‐LB and DLB that 1) an abnormal ioflupane SPECT scan is frequently present at diagnosis, 2) z‐scores become more negative over time, and 3) the annualized z‐change is similar. Similar findings in larger cohorts would support the use of ioflupane SPECT as a biomarker in both MCI‐LB and DLB clinical trials.

AbstractBackgroundFluorodeoxyglucose positron emission tomography (FDG‐PET) is an established modality for differential diagnosis of dementia. Deriving phenotypic signatures from FDG‐PET via machine learning is challenging due to the high dimensional nature of brain images relative to the generally small number of labeled examples available for training, the class imbalance among those labels, and the cooccurrence of multiple pathologies. In this study, we developed a multi‐class, multi‐label framework to address these challenges.MethodA database of clinically acquired PET/CT images from 3,000 unique patients was used to develop a latent space model using matrix decomposition. This model was then applied to images from a separate cohort of Mayo Clinic Alzheimer’s Disease Research Center participants (n=1,745) labeled as cognitively unimpaired (CU) (n=1,436) or with the following potentially co‐occurring phenotypes: Alzheimer’s disease (AD) (n=165), Lewy body dementia (DLB) (n=92), behavioral variant frontotemporal dementia (bvFTD) (n=43), semantic (svPPA) (n=10) and logopenic (lvPPA) (n=13) variant PPA, and posterior cortical atrophy (PCA) (n=17). A k‐nearest neighbors classifier that is robust to these imbalanced and overlapping labels was then trained on these examples. The resulting classifier was evaluated by area under receiver‐operator characteristic curve (ROC‐AUC) via leave one out cross validation, using clinical diagnosis as the gold standard.ResultROC curves and AUC scores for each phenotype are illustrated in Fig. 1a. Because the classifier is based on a k‐nearest neighbors connectivity matrix, it has a convenient graphical representation, where images are nodes and edges are drawn between an image and its set of nearest neighbors in latent space. A self‐organizing force directed graph constructed in this way is illustrated in Fig 1b, highlighting the strong separation of CU and degenerative images, as well as the segregation of each phenotype within the neurodegenerative region of the graph.ConclusionIn this study, we developed a machine learning framework for classification of neurodegenerative disease based on k‐nearest neighbor analysis in a low dimensional latent space projection of FDG‐PET images. By leveraging low‐dimensional representations and k‐nearest neighbors analysis, this framework is robust in multi‐class, multi‐label tasks with strong class imbalance and provides a highly interpretable graphical representation.

AbstractBackgroundNeurite Orientation Dispersion and Density Imaging (NODDI) is becoming increasingly common as multiband acceleration becomes available for clinical scanning, but fitting the model can be extremely slow. Since the release of the original MATLAB implementation in 2012, three alternatives have become popular: Accelerated Microstructure Imaging via Convex Optimization (AMICO), the Microstructure Diffusion Toolbox (MDT), and the CUDA Diffusion Modelling Toolbox (cuDIMOT). They accelerate fitting through reformulation and/or using GPUs, but the implementation differences raise the question of which approach is best. To our knowledge all previous comparisons lacked knowledge of the true values and used the original implementation as the nominally correct one, with in vivo data. We remedy that using simulations with known NODDI values, in addition to in vivo scans.MethodWe created a software phantom with Neurite Density Index (NDI) values linearly increasing from 0.1 to 1.0 in x, Orientation Dispersion (ODI) from 0 to 1 in y, and Isotropic water Volume Fraction (ISOVF) from 0 to 0.9 in z. We simulated five scans using the ADNI3 advanced diffusion MRI protocol. The phantom had 20 voxels in each direction, and the fiber bundle principal direction randomly varied between the simulations. The simulations were fit by the original, AMICO, MDT, and cuDIMOT implementations, and root mean square errors were calculated as shown in Table 1. A discrepancy measure was also calculated using the brain voxels of three in vivo human scans acquired using the same protocol on a Siemens Prisma, substituting the original implementation’s values for the truth since the latter is unknown for in vivo scans.ResultcuDIMOT had the least error (for ODI < 0.8) and was fastest. The original implementation was a close second in accuracy but much slower. cuDIMOT’s ODI underestimation can be corrected with a transfer function in the noise‐free case, but that approach fails with actual scans.ConclusionThe original or cuDIMOT implementations should be used, with cuDIMOT the favorite when at least one CUDA‐capable GPU is available and the number of scans are large. Correcting cuDIMOT’s ODI underestimation using a different initialization or form of Dawson’s integral should be investigated.

AbstractBackgroundIn 2018 we presented the Computational DESH (CDESH) metric (DOI:10.1016/j.nicl.2018.11.015), a machine learning measure of abnormal CSF space patterns commonly observed on MRI in Disproportionately Enlarged Subarachnoid‐space Hydrocephalus (DESH‐type) NPH. We have shown that CDESH positive individuals often have discordant CSF and PET amyloid measures (DOI:10.1016/j.jalz.2019.06.4921). Positive CDESH scores are predictive of cognitive decline (DOI:10.1016/j.neuroimage.2021.117899, DOI: 10.1212/WNL.0000000000008616). The score is calculated from regional CSF volumes in a sulcal atlas and within the ventricles using a support vector machine (SVM). The Mayo Clinic Study of Aging (MCSA) changed scanner platforms (GE to Siemens) and T1‐weighted image resolution (1.2mm x 1.05mm x 1.05mm to 0.8mm isotropic) in 2017. We refer to these as “isotropic” or “anisotropic” scans. Our objective was to assess the dependence of a machine learning method (specifically CDESH) to image input variation and, if necessary, determine what needed corrections.MethodAll data considered is from the MCSA or Mayo Clinic ADRC. The SVM was trained on anisotropic images with laboriously labelled ground truth. We resampled the isotropic data from a crossover study (N=112, typically scanned same‐day with both platforms/resolutions) to match the anisotropic resolution. Two approaches to correction were evaluated (Figure 1). In Figure 2 we compare of the score with and without correction cross‐sectionally in 998 MCSA participants. In Figure 3 we present longitudinal series from 23 participants with multiple scans using the isotropic resolution protocol and at least one prior anisotropic image.ResultsComparisons of data from the crossover study are presented in Figure 1. Matching voxel resolution to the data used to train the SVM is critical and a subsequent mild linear score adjustment may be warranted. Cross‐sectional comparisons (Figure 2) confirm improvement matching voxel resolution with a possible mild linear score adjustment. After matching voxel resolution CDESH score trajectories (Figure 3) are markedly more stable across this scanner/protocol change.ConclusionThe SVM‐based CDESH score is sensitive to voxel resolution. Corrections are needed in image processing and possibly in the scalar output score to achieve stability across protocol and scanner changes. The resulting correction supports coherent long timeseries data and longitudinal extension of previous work.

AbstractBackgroundDiffusion MRI (dMRI) based quantification of microstructural changes in white matter (WM) are increasingly proposed to measure cerebrovascular disease (CVD) related changes. Our objective was to compare the proposed dMRI markers using postmortem neuropathologic CVD data and then evaluate the predictors of longitudinal dMRI markers using serial scans.MethodWe identified n=51 participants (mean age: 83.8 years, 63% males) with ante‐mortem dMRI and postmortem CVD evaluation and n=718 participants (mean age: 71.1 years, 56% males) with at least two dMRI scans from the population‐based sample of Mayo Clinic Study of Aging. We computed dMRI measures proposed for measuring CVD: Free Water (FW), Fractional Anisotropy (FA) adjusted for FW (FAadj), Peak width Skeletonized Mean Diffusivity (PSMD), and FA of the genu of corpus callosum (Genu‐FA). We used the FW and PSMD (PSMD release 1.8.1) kits from the MarkVCID consortium.Using weighted linear regression models with adjustments for MRI scan time to death, we evaluated associations between the baseline dMRI and two pathology CVD scores: Strozyk (represents the presence and number of macroscopic lesions) and Kalaria (represents the summary score of vessel wall modifications) scales. We ran linear mixed effect models with all available serial dMRI measures as outcomes and vascular risk (measured by the number of cardiovascular and metabolic conditions‐CMC), baseline imaging measures (amyloid and white matter hyperintensities (WMH)) and their interaction with time as key predictors.ResultMost dMRI markers were predictors of postmortem CVD pathology (Table 1). In longitudinal dMRI models, terms associated with amyloid explained little variability in dMRI (<1%) (Table 2). WMH was a significant predictor of baseline and decline in dMRI measures with WMH explaining a considerable percentage of variability in FW (34%) and PSMD (28%). Vascular risk measures were significant predictors of three out of the four dMRI measures.ConclusionThe diffusion measures proposed as surrogate markers of CVD map reasonably well to CVD pathological scales and do not change substantially as a function of baseline amyloidosis. Our findings shed light on variability in the proposed diffusion markers using postmortem data and longitudinal imaging data. Further work is needed to evaluate their clinical utility.

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.

AbstractBackgroundMulti‐compartment modelling of white matter (WM) microstructure using Neurite Orientation Dispersion and Density Imaging (NODDI) can provide information on WM health through the neurite (axons and dendrites) density index and free water measures. We hypothesized that cerebrovascular disease (CVD), Alzheimer’s disease (AD), and an FDG pattern suggestive of TDP‐43 proteinopathy would be associated with distinct NODDI readouts of WM damage which would be informative for identifying the substrate for cognitive impairment.MethodWe identified two independent cohorts with multi‐shell diffusion MRI, amyloid and tau PET, and cognitive assessments. One, were participants from the Mayo Clinic Study of Aging, a population‐based cohort of 347 elderly randomly sampled from the Olmsted county, Minnesota. The second were 61 amyloid positive AD participants from the Mayo AD Research Center.ResultWe observed an increase in free water and decrease in neurite density in the genu of the corpus callosum associated with vascular risk factors, which we refer to as vascular WM component (Figure 1). Tau PET signal reflective of 3R/4R tau deposition was associated with worsening neurite density index in the temporal WM where we measured parahippocampal cingulum and inferior temporal WM bundles. Worsening temporal neurite density was associated with (antemortem confirmed) FDG TDP‐43 signature. Post‐mortem neuropathologic data on a small subset (n=9) of this sample lend support to our findings. In the population‐based cohort where vascular disease was more prevalent, the vascular WM component explained variability in global cognition (partial R2 of free water and neurite density = 8.3%) and MMSE performance (8.2%) which was comparable to amyloid PET (7.4% for global cognition and 6.6% for memory) (Table 1). In the AD dementia clinic‐based cohort, tau deposition was the greatest contributor to cognitive performance (9.6%), but there was also a non‐trivial contribution of the temporal WM component (8.5%) to cognitive performance. The differences observed between the two cohorts were reflective of their distinct clinical composition.ConclusionWhite matter microstructural damage assessed using advanced diffusion models may add significant value for distinguishing the underlying substrate (whether CVD versus neurodegenerative disease caused by tau deposition or TDP‐43 pathology) for cognitive impairment in older individuals.

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.