AV-1451 Positron Emission Tomography Research Articles

Generative AI unlocks PET insights: brain amyloid dynamics and quantification.

Studying the spatiotemporal patterns of amyloid accumulation in the brain over time is crucial in understanding Alzheimer's disease (AD). Positron Emission Tomography (PET) imaging plays a pivotal role because it allows for the visualization and quantification of abnormal amyloid beta (Aβ) load in the living brain, providing a powerful tool for tracking disease progression and evaluating the efficacy of anti-amyloid therapies. Generative artificial intelligence (AI) can learn complex data distributions and generate realistic synthetic images. In this study, we demonstrate for the first time the potential of Generative Adversarial Networks (GANs) to build a low-dimensional representation space that effectively describes brain amyloid load and its dynamics. Using a cohort of 1,259 subjects with AV45 PET images from the Alzheimer's Disease Neuroimaging Initiative (ADNI), we develop a 3D GAN model to project images into a latent representation space and generate back synthetic images. Then, we build a progression model on the representation space based on non-parametric ordinary differential equations to study brain amyloid evolution. We found that global SUVR can be accurately predicted with a linear regression model only from the latent representation space (RMSE = 0.08 ± 0.01). We generated synthetic PET trajectories and illustrated predicted Aβ change in four years compared with actual progression. Generative AI can generate rich representations for statistical prediction and progression modeling and simulate evolution in synthetic patients, providing an invaluable tool for understanding AD, assisting in diagnosis, and designing clinical trials. The aim of this study was to illustrate the huge potential that generative AI has in brain amyloid imaging and to encourage its advancement by providing use cases and ideas for future research tracks.

Prediction of Cognitive Progression Due to Alzheimer's Disease in Normal Participants Based on Individual Default Mode Network Metabolic Connectivity Strength

BackgroundPredicting cognitive decline among individuals in the aging population who are already amyloid-β (Aβ) positive or tau positive poses clinical challenges. In Alzheimer's disease research, intra–default mode network (DMN) connections play a pivotal role in diagnosis. In this article, we propose metabolic connectivity within the DMN as a supplementary biomarker to the Aβ, pathological tau, and neurodegeneration framework. MethodsExtracting data from 1292 participants in the Alzheimer’s Disease Neuroimaging Initiative, we collected paired T1-weighted structural magnetic resonance imaging and 18F-labeled-fluorodeoxyglucose positron emission computed tomography scans. Individual metabolic DMN networks were constructed, and metabolic connectivity (MC) strength in the DMN was assessed. In the cognitively unimpaired group, the Cox model identified cognitively unimpaired (MC+), high-risk participants, with Kaplan-Meier survival analyses and hazard ratios revealing the strength of MC’s predictive performance. Spearman correlation analyses explored relationships between MC strength, and Aβ, pathological tau, neurodegeneration biomarkers, and clinical scales. DMN standard uptake value ratio (SUVR) provided comparative insights in the analyses. ResultsBoth MC strength and SUVR exhibited gradual declines with cognitive deterioration, displaying significant intergroup differences. Survival analyses indicated enhanced Aβ and tau prediction with both metrics, with MC strength outperforming SUVR. Combined MC strength and Aβ yielded optimal predictive performance (hazard ratio = 9.29), followed by MC strength and tau (hazard ratio = 8.92). Generally, the strength of MC’s correlations with Aβ, pathological tau, and neurodegeneration biomarkers exceeded SUVR. ConclusionsIndividuals with normal cognition and disrupted DMN metabolic connectivity face an elevated risk of cognitive decline linked to Aβ that precedes metabolic issues.

NODDI in gray matter is a sensitive marker of aging and early AD changes.

Age-related and Alzheimer's disease (AD) dementia-related neurodegeneration impact brain health. While morphometric measures from T1-weighted scans are established biomarkers, they may be less sensitive to earlier changes. Neurite orientation dispersion and density imaging (NODDI), offering biologically meaningful interpretation of tissue microstructure, may be an advanced brain health biomarker. We contrasted regional gray matter NODDI and morphometric evaluations concerning their correlation with (1) age, (2) clinical diagnosis stage, and (3) tau pathology as assessed by AV1451 positron emission tomography. Our study hypothesizes that NODDI measures are more sensitive to aging and early AD changes than morphometric measures. One NODDI output, free water fraction (FWF), showed higher sensitivity to age-related changes, generally better effect sizes in separating mild cognitively impaired from cognitively unimpaired participants, and stronger associations with regional tau deposition than morphometric measures. These findings underscore NODDI's utility in capturing early neurodegenerative changes and enhancing our understanding of aging and AD. Neurite orientation dispersion and density imaging can serve as an effective brain health biomarker for aging and early Alzheimer's disease (AD).Free water fraction has higher sensitivity to normal brain aging.Free water fraction has stronger associations with early AD and regional tau deposition.

Sex and family history differences in Aβ and tau vulnerability in preclinical Alzheimer’s disease

AbstractBackgroundFemales and individuals with a family history (FH) of Alzheimer’s disease (AD) are considered at higher risk of sporadic AD. However, how sex and maternal/paternal heredity affects in vivo AD biomarkers is not well understood. Our objectives were to 1) assess if females or individuals with a first‐degree maternal FH of AD accumulate amyloid‐beta (Aβ) and/or tau faster than males or individuals with a first‐degree paternal FH of AD and 2) assess if both could influence the rate of Aβ driving tau in preclinical AD.MethodTwo hundred and thirty‐five older adults (age 68.3 ± 5.1 years, 69.8% female) from the PREVENT‐AD cohort, cognitively unimpaired at baseline, underwent [18F]‐NAV4694 and [18F]‐AV1451 positron emission tomography (PET) scans. Longitudinal PET scans were available for 106 individuals (4.3 ± 0.4 years follow‐up). We extracted and averaged the standard uptake value ratio (SUVr) in fronto‐parietal regions for Aβ and in temporal regions for tau. We performed t‐tests and ANOVA models to assess sex or maternal/paternal FH (FHsex) differences in Aβ and tau burden or annual change. We then performed linear regression models with an interaction term between Aβ and sex (or Aβ and FHsex) on tau burden and annual change, plus additional models to adjust for age and education.ResultSex and FHsex differences on Aβ and tau burden or annual rate of change did not reach significance although females tended to have higher tau SUVr at baseline (p = 0.053) (Figure 1 & 2). We found an interaction between Aβ and sex (𝛽 = ‐0.13, p = 0.008), and between Aβ and FHsex (𝛽 = 0.11, p = 0.03), on tau at baseline (Figure 3) suggesting that, for the same level of Aβ burden, females and individuals with paternal FH of AD had higher tau burden than males and individuals with maternal FH of AD. Results were similar when adjusted for age and education.ConclusionFemales and individuals with a paternal FH of AD might need less Aβ before developing AD‐related tau, but did not accumulate tau faster. Identifying individuals more vulnerable to AD pathology, by disentangling sex‐specific effects, would help to design personalized interventions for AD.

Sex and family history differences in Aβ and tau vulnerability in preclinical Alzheimer’s disease

AbstractBackgroundFemales and individuals with a family history (FH) of Alzheimer’s disease (AD) are considered at higher risk of sporadic AD. However, how sex and maternal/paternal heredity affects in vivo AD biomarkers is not well understood. Our objectives were to 1) assess if females or individuals with a first‐degree maternal FH of AD accumulate amyloid‐beta (Aβ) and/or tau faster than males or individuals with a first‐degree paternal FH of AD and 2) assess if both could influence the rate of Aβ driving tau in preclinical AD.MethodTwo hundred and thirty‐five older adults (age 68.3 ± 5.1 years, 69.8% female) from the PREVENT‐AD cohort, cognitively unimpaired at baseline, underwent [18F]‐NAV4694 and [18F]‐AV1451 positron emission tomography (PET) scans. Longitudinal PET scans were available for 106 individuals (4.3 ± 0.4 years follow‐up). We extracted and averaged the standard uptake value ratio (SUVr) in fronto‐parietal regions for Aβ and in temporal regions for tau. We performed t‐tests and ANOVA models to assess sex or maternal/paternal FH (FHsex) differences in Aβ and tau burden or annual change. We then performed linear regression models with an interaction term between Aβ and sex (or Aβ and FHsex) on tau burden and annual change, plus additional models to adjust for age and education.ResultSex and FHsex differences on Aβ and tau burden or annual rate of change did not reach significance although females tended to have higher tau SUVr at baseline (p = 0.053) (Figure 1 & 2). We found an interaction between Aβ and sex (𝛽 = ‐0.13, p = 0.008), and between Aβ and FHsex (𝛽 = 0.11, p = 0.03), on tau at baseline (Figure 3) suggesting that, for the same level of Aβ burden, females and individuals with paternal FH of AD had higher tau burden than males and individuals with maternal FH of AD. Results were similar when adjusted for age and education.ConclusionFemales and individuals with a paternal FH of AD might need less Aβ before developing AD‐related tau, but did not accumulate tau faster. Identifying individuals more vulnerable to AD pathology, by disentangling sex‐specific effects, would help to design personalized interventions for AD.

Prediction of Conversion from Mild Cognitive Impairment to Alzheimer's Disease Using Amyloid PET and Brain MR Imaging Data: A 48-Month Follow-Up Analysis of the Alzheimer's Disease Neuroimaging Initiative Cohort.

We developed a novel quantification method named "shape feature" by combining the features of amyloid positron emission tomography (PET) and brain magnetic resonance imaging (MRI) and evaluated its significance in predicting the conversion from mild cognitive impairment (MCI) to Alzheimer's disease (AD) in the Alzheimer's Disease Neuroimaging Initiative (ADNI) cohort. From the ADNI database, 334 patients with MCI were included. The brain amyloid smoothing score (AV45_BASS) and brain atrophy index (MR_BAI) were calculated using the surface area and volume of the region of interest in AV45 PET and MRI. During the 48-month follow-up period, 108 (32.3%) patients converted from MCI to AD. Age, Mini-Mental State Examination (MMSE), cognitive subscale of the Alzheimer's Disease Assessment Scale (ADAS-cog), apolipoprotein E (APOE), standardized uptake value ratio (SUVR), AV45_BASS, MR_BAI, and shape feature were significantly different between converters and non-converters. Univariate analysis showed that age, MMSE, ADAS-cog, APOE, SUVR, AV45_BASS, MR_BAI, and shape feature were correlated with the conversion to AD. In multivariate analyses, high shape feature, SUVR, and ADAS-cog values were associated with an increased risk of conversion to AD. In patients with MCI in the ADNI cohort, our quantification method was the strongest prognostic factor for predicting their conversion to AD.

5 Rejuvenating Blood Factor TIMP2 Relates to Physical Activity and Cognitive Functioning in Older Adults on The Alzheimer’s Disease Continuum

Objective:Tissue inhibitor of metalloproteinases 2 (TIMP2) is produced peripherally, crosses the blood-brain barrier, and improves synaptic plasticity and hippocampal-dependent cognition in aged mice; however, the role of TIMP2 in human cognitive aging is unclear. We examined associations of circulating TIMP2 levels in blood with a known plasticity-inducing behavior, physical activity, and cognitive functioning among older adults along the Alzheimer’s disease continuum.Participants and Methods:Participants included 84 community-dwelling older adults (meanage = 78.8; 57% female; 82% cognitively normal; 14% MCI; 4% mild dementia; 35% PET Aß+) enrolled in the UC San Francisco Memory and Aging Center. All participants completed 30 days of observational FitbitTM monitoring to quantify physical activity (average daily steps), as well as a comprehensive in-person visit including blood draw (proteins assayed on SOMAscan platform), [18F]AV-45 positron emission tomography (PET) to quantify brain beta-amyloid (centiloids), and neuropsychological assessment. Composite cognitive z-scores were calculated for memory (California Verbal Learning Test-II [CVLT-II] and Benson Figure Recall), semantic processing (animal fluency and Boston Naming Test), and executive functioning (digits backwards span, Stroop inhibition, modified trail making test, lexical fluency, and design fluency). Multiple linear regression examined TIMP2 as a function of physical activity, covarying for age and PET centiloids. Additional regression models separately examined cognitive z-scores as a function of TIMP2, covarying for age, sex, education, PET centiloids, and body mass index (BMI).Results:TIMP2 was not significantly correlated with age, sex, education, or PET centiloids (ps > 0.05); however, TIMP2 was negatively correlated with BMI (r = -0.23, p = 0.036). Greater average daily steps related to higher levels of TIMP2 (b = 0.30, 95%CI = 0.04-0.55, p = 0.022). TIMP2 also related to better semantic processing (b = 0.28, 95%CI = 0.04-0.51, p = 0.021) and executive functioning (b = 0.26, 95%CI = 0.03-0.49, p = 0.028). TIMP2 did not significantly relate to memory (p > 0.05).Conclusions:Greater physical activity was associated with higher concentrations of blood factor TIMP2, which in turn related to better cognitive functioning independent of Alzheimer’s disease pathology burden. These results support previous mouse models by broadly replicating relationships between TIMP2 and cognition in humans, while also uniquely demonstrating an association between TIMP2 and physical activity, a modifiable protective factor in both typical and diseased cognitive aging. Our domain-specific results, however, suggest that benefits of TIMP2 in humans may involve a broader neuroanatomical network than the hippocampal-specific effects previously shown in mice. Although exact mechanisms of TIMP2 need further examination, TIMP2 is known to be enriched in human umbilical cord plasma, has been shown to be involved in cell-growth promoting activities, and may relate to increased neural plasticity in older age. Further examination of TIMP2 and other novel blood-based proteins as potential therapeutic targets for improved cognitive aging, including in the presence of Alzheimer’s disease, is warranted.

Synergistic interaction of high blood pressure and cerebral beta-amyloid on tau pathology

BackgroundHypertension has been associated with Alzheimer’s disease (AD) dementia as well as vascular dementia. However, the underlying neuropathological changes that link hypertension to AD remain poorly understood. In our study, we examined the relationships of a history of hypertension and high current blood pressure (BP) with in vivo AD pathologies including β-amyloid (Aβ) and tau and also investigated whether a history of hypertension and current BP respectively affect the association between Aβ and tau deposition.MethodsThis cross-sectional study was conducted as part of the Korean Brain Aging Study for Early Diagnosis and Prediction of Alzheimer’s Disease, a prospective cohort study. Cognitively normal older adults who underwent both Aβ and tau positron emission tomography (PET) (i.e., [11C]-Pittsburgh compound B and [18F] AV-1451 PET) were selected. History of hypertension and current BP were evaluated and cerebral Aβ and tau deposition measured by PET were used as main outcomes. Generalized linear regression models were used to estimate associations.ResultsA total of 68 cognitively normal older adults (mean [SD] age, 71.5 [7.4] years; 40 women [59%]) were included in the study. Neither a history of hypertension nor the current BP exhibited a direct association with Aβ or tau deposition. However, the synergistic interaction effects of high current systolic (β, 0.359; SE, 0.141; p = 0.014) and diastolic (β, 0.696; SE, 0.158; p < 0.001) BP state with Aβ deposition on tau deposition were significant, whereas there was no such effect for a history of hypertension (β, 0.186; SE, 0.152; p = 0.224).ConclusionsThe findings suggest that high current BP, but not a history of hypertension, synergistically modulate the relationship between cerebral Aβ and tau deposition in late-life. In terms of AD prevention, the results support the importance of strict BP control in cognitively normal older adults with hypertension.

Genome-wide association study of brain tau deposition as measured by 18F-flortaucipir positron emission tomography imaging

The related genetic variants of tau deposition, a seminal pathological hallmark of Alzheimer's disease, remain poorly understood. We sought to perform a genome-wide association study of brain tau load as measured by AV1451 positron emission tomography (PET). Among 543 non-demented European individuals, novel associations with higher tau were identified for rs56298435 (p=8.35×10-10, β=0.31) within ZBTB20, and for rs150532 (p=1.90×10-8, β=0.26) in the protein phosphorylation regulatory gene EYA4. The APOE association additionally reached genome-wide significant when APOE ε4 was not adjusted. Minor allele carriers of rs56298435 or rs150532 showed higher levels of tau PET load. As expected, phosphorylated-tau analyses in both plasma and cerebrospinal fluid also revealed the same direction of effect. Functionally, the effects of novel loci on cognitive decline could be mediated by tau pathology. In addition, we observed that the expression of VNN2 as regulated by rs150532, together with EYA4, displayed significant correlations with the tau-related gene MAPT in numerous brain regions. Our novel finding lends additional credence to heritable underpinnings of tau deposition.

Escalation of Tau Accumulation after a Traumatic Brain Injury: Findings from Positron Emission Tomography.

Traumatic brain injury (TBI) has come to be recognized as a risk factor for Alzheimer’s disease (AD), with poorly understood underlying mechanisms. We hypothesized that a history of TBI would be associated with greater tau deposition in elders with high-risk for dementia. A Groups of 20 participants with self-reported history of TBI and 100 without any such history were scanned using [18F]-AV1451 positron emission tomography as part of the Alzheimer’s Disease Neuroimaging Initiative (ADNI). Scans were stratified into four groups according to TBI history, and by clinical dementia rating scores into cognitively normal (CDR = 0) and those showing cognitive decline (CDR ≥ 0.5). We pursued voxel-based group comparison of [18F]-AV1451 uptake to identify the effect of TBI history on brain tau deposition, and for voxel-wise correlation analyses between [18F]-AV1451 uptake and different neuropsychological measures and cerebrospinal fluid (CSF) biomarkers. Compared to the TBI-/CDR ≥ 0.5 group, the TBI+/CDR ≥ 0.5 group showed increased tau deposition in the temporal pole, hippocampus, fusiform gyrus, and inferior and middle temporal gyri. Furthermore, the extent of tau deposition in the brain of those with TBI history positively correlated with the extent of cognitive decline, CSF-tau, and CSF-amyloid. This might suggest TBI to increase the risk for tauopathies and Alzheimer’s disease later in life.

Serum Adiponectin and In Vivo Brain Amyloid Deposition in Cognitively Normal Older Adults: A Cohort Study.

High blood adiponectin has been associated with Alzheimer's disease (AD) dementia and related cognitive decline. We aimed to investigate the association between serum adiponectin level and in vivo AD pathologies. Cross-sectional and longitudinal study designs for the data of the Korean Brain Aging Study for Early Diagnosis and Prediction of Alzheimer's Disease, an ongoing prospective cohort study that began in 2014. A total of 283 cognitively normal older adults between 55 and 90 years of age were included in community and memory clinic setting. Participants underwent comprehensive clinical assessments, measurement of serum adiponectin level, and multimodal brain imaging, including Pittsburgh compound-B positron emission tomography (PET), AV-1451 PET, fluorodeoxyglucose (FDG)-PET, and MRI at baseline and 2-year follow-up. Serum adiponectin level was positively associated with global beta-amyloid protein (Aβ) retention and change therein over 2 years, but not with other AD neuroimaging markers including tau deposition, AD-related neurodegeneration, and white matter hyperintensities. Blood adiponectin level is associated with increased brain amyloid deposition, which suggests that adiponectin may be a potential target for therapeutic and preventive strategies against AD.

Differences in temporal AD biomarker trajectories according to sex and APOE genotype: Implication of importance of striatal amyloid

AbstractBackgroundAccumulation of β‐amyloid (Aβ) plaques and neurofibrillary tangles are core components of Alzheimer's disease (AD) pathogenesis. Longitudinal in vivo observations of AD pathologic changes using amyloid and tau positron emission tomography (PET) enable us to obtain AD biomarkers' hypothetical trajectory curves. However, the difference in disease progression by striatal Aβ deposition, sex, and apolipoprotein E (APOE) genotype has not been explained with trajectory curves. The aim of this study is to develop the trajectory in accumulation of cortical and striatal Aβ and tau deposits. We also tried to investigate the differences in sex and APOE genotype on trajectory curves.MethodWe obtained 817 subjects from the Alzheimer’s Disease Neuroimaging Initiative database, who showed either 18F‐florbetapir (AV45) PET positivity at least once or AV45 PET negativity with normal cognition. We Z‐transformed each value based on Aβ‐negative, cognitively normal subjects. Instead of obtaining a single rate value (∆Z/∆t) per subject, we calculated the slope for every interval of PET scans. For each biomarker, we fitted a penalized spline to model the slope of Z value as a nonlinear function of baseline Z value. Using the fitted splines, we obtained the predicted Z curves as a function of time and developed trajectory curves.ResultAmong the subjects, 534 subjects were available for AV45 PET analysis and 163 subjects underwent 18F‐flortaucipir PET. While cortical Aβ accumulation rate increased until Z value reached 4.33 and decreased subsequently, ∆Z/∆t for the striatal Aβ and tau stayed more constant. Time from Z=0 to Z=2 was the longest for tau PET (22.6 years) and shortest for cortical Aβ (14.9 years). For cortical Aβ, Z values of males reached 1.7 years earlier than females. However, for striatal Aβ, males took 2.8 more years than females to reach Z=2. Also, APOE ɛ4 carriers showed faster progression for all biomarkers.ConclusionThis study shows that Aβ accumulates in the striatum after cortex and then tau protein, which is consistent with the amyloid cascade hypothesis. The trajectory curves differ according to sex and APOE genotype. Therefore, prognosis and treatment should be approached differently in clinical practice with respect to striatal involvement, sex, and APOE genotype.

Characterization of Alzheimer\u2019s tau biomarker discordance using plasma, CSF, and PET

BackgroundWe aimed to investigate the tau biomarker discrepancies of Alzheimer’s disease (AD) using plasma tau phosphorylated at threonine 181 (p-tau181), cerebrospinal fluid (CSF) p-tau181, and AV1451 positron emission tomography (PET).MethodsIn the Alzheimer’s Disease Neuroimaging Initiative, 724 non-demented participants were categorized into plasma/CSF and plasma/PET groups. Demographic and clinical variables, amyloid-β (Aβ) burden, flortaucipir-PET binding in Braak regions of interest (ROIs), longitudinal changes in clinical outcomes, and conversion risk were compared.ResultsAcross different tau biomarker groups, the proportion of participants with a discordant profile varied (plasma+/CSF− 15.6%, plasma−/CSF+ 15.3%, plasma+/PET− 22.4%, and plasma−/PET+ 6.1%). Within the plasma/CSF categories, we found an increase from concordant-negative to discordant to concordant-positive in the frequency of Aβ pathology or cognitive impairment, rates of cognitive decline, and risk of cognitive conversion. However, the two discordant categories (plasma+/CSF− and plasma−/CSF+) showed comparable performances, resulting in similarly reduced cognitive capacities. Regarding plasma/PET categories, as expected, PET-positive individuals had increased Aβ burden, elevated flortaucipir retention in Braak ROIs, and accelerated cognitive deterioration than concordant-negative persons. Noteworthy, discordant participants with normal PET exhibited reduced flortaucipir uptake in Braak stage ROIs and slower rates of cognitive decline, relative to those PET-positive. Therefore, individuals with PET abnormality appeared to have advanced tau pathological changes and poorer cognitive function, regardless of the plasma status. Furthermore, these results were found only in individuals with Aβ pathology.ConclusionsOur results indicate that plasma and CSF p-tau181 abnormalities associated with amyloidosis occur simultaneously in the progression of AD pathogenesis and related cognitive decline, before tau-PET turns positive.

Significant effects of cholinesterase inhibitors on tau pathology in the Alzheimer's disease continuum: An in vivo positron emission tomography study.

No prior study has assessed the effects of cholinesterase inhibitors (ChEIs) on tau pathology in the brains of patients with Alzheimer's disease (AD). Using positron emission tomography, this study aimed to investigate whether ChEIs reduce tau aggregation in amyloid-positive participants. We analyzed datasets from the Alzheimer's Disease Neuroimaging Initiative and included amyloid-positive participants who had undergone baseline and 1- or 2-year follow-up AV-1451 positron emission tomography scans. We included participants treated with and without ChEIs (ChEIs group: n=15, No-ChEIs group, n=45). The annual change in tau aggregation was calculated as the difference in AV-1451- standardized uptake value ratio (SUVR) between the two scans divided by the time between scans. Group differences in annual AV-1451-SUVR change were examined. We found a significantly lower annual change in AV-1451-SUVR in the Braak 1/2 regions (entorhinal cortex and hippocampus) of participants taking ChEIs. Increased AV-1451-SUVR between the first and second examinations were observed in 22 of 45 participants not taking ChEIs and 2 of 15 participants taking ChEIs. Fisher's exact test showed a significant difference in the ratio of participants with increased AV-1451-SUVR between the groups. The findings of this positron emission tomography study suggest that the administration of ChEIs has some neuroprotective effects in patients of the AD continuum, at least in the early stage of the disease progression. This in vivo effect may be mediated via tau, preventing amyloid β-induced neurotoxicity.

Machine Learning for Diagnosis of AD and Prediction of MCI Progression From Brain MRI Using Brain Anatomical Analysis Using Diffeomorphic Deformation.

Background: With the growing momentum for the adoption of machine learning (ML) in medical field, it is likely that reliance on ML for imaging will become routine over the next few years. We have developed a software named BAAD, which uses ML algorithms for the diagnosis of Alzheimer's disease (AD) and prediction of mild cognitive impairment (MCI) progression.Methods: We constructed an algorithm by combining a support vector machine (SVM) to classify and a voxel-based morphometry (VBM) to reduce concerned variables. We grouped progressive MCI and AD as an AD spectrum and trained SVM according to this classification. We randomly selected half from the total 1,314 subjects of AD neuroimaging Initiative (ADNI) from North America for SVM training, and the remaining half were used for validation to fine-tune the model hyperparameters. We created two types of SVMs, one based solely on the brain structure (SVMst), and the other based on both the brain structure and Mini-Mental State Examination score (SVMcog). We compared the model performance with two expert neuroradiologists, and further evaluated it in test datasets involving 519, 592, 69, and 128 subjects from the Australian Imaging, Biomarker & Lifestyle Flagship Study of Aging (AIBL), Japanese ADNI, the Minimal Interval Resonance Imaging in AD (MIDIAD) and the Open Access Series of Imaging Studies (OASIS), respectively.Results: BAAD's SVMs outperformed radiologists for AD diagnosis in a structural magnetic resonance imaging review. The accuracy of the two radiologists was 57.5 and 70.0%, respectively, whereas, that of the SVMst was 90.5%. The diagnostic accuracy of the SVMst and SVMcog in the test datasets ranged from 88.0 to 97.1% and 92.5 to 100%, respectively. The prediction accuracy for MCI progression was 83.0% in SVMst and 85.0% in SVMcog. In the AD spectrum classified by SVMst, 87.1% of the subjects were Aβ positive according to an AV-45 positron emission tomography. Similarly, among MCI patients classified for the AD spectrum, 89.5% of the subjects progressed to AD.Conclusion: Our ML has shown high performance in AD diagnosis and prediction of MCI progression. It outperformed expert radiologists, and is expected to provide support in clinical practice.

Sleep and Tau Pathology in Vietnam War Veterans with Preclinical and Prodromal Alzheimer's Disease.

Background:The increasing prevalence of Alzheimer’s disease (AD) and lack of effective medications has led to a need to identify modifiable risk factors as targets for interventions.Objective:In this cross-sectional study, we sought to determine whether worse sleep quality is associated with increased pathological tau, and whether this relationship is affected by amyloid pathology.Methods:66 male participants underwent Florbetapir (AV45) positron emission tomography (PET) and Flortaucipir (FTP) PET and completed the Pittsburgh Sleep Quality Index questionnaire (PSQI) as part of the Department of Defense Alzheimer’s Disease Neuroimaging Initiative, a multicenter study collecting data from Vietnam War veterans, some of whom have a history of post-traumatic stress disorder, or non-penetrating traumatic brain injury. AV45 PET was used to determine the presence of significant amyloid pathology. We used regression models to determine the effects of amyloid pathology and PSQI on tau deposition in brain regions associated with Braak stages.Results:Among the 66 participants, 14 individuals were amyloid positive (21%) and 52 were amyloid negative (79%). In regions associated with Braak stages III-IV, there was a significant interaction of amyloid status on PSQI (β= 0.04, p = 0.003) with higher PSQI correlating with higher FTP SUVr in amyloid-positive individuals only (β= 0.031, p = 0.005).Conclusion:Our study found that an AD profile of tau deposition was associated with an interaction between self-reported sleep quality and amyloid pathology such that worse self-reported sleep was related to higher tau in regions usually associated with AD progression, but only in individuals with high cerebral amyloid deposition.

Evaluation of the early-phase [18F]AV45 PET as an optimal surrogate of [18F]FDG PET in ageing and Alzheimer’s clinical syndrome

Dual-phase [18F]AV45 positron emission tomography (PET) is highly promising in the assessment of neurodegenerative diseases, allowing to obtain information on both neurodegeneration (early-phase; eAV45) and amyloid deposition (late-phase; lAV45) which are highly complementary; yet eAV45 needs further evaluation. This study aims at validating eAV45 as an optimal proxy of [18F]FDG PET in a large mixed-population of healthy ageing and Alzheimer’s clinical syndrome participants (n = 191) who had [18F]FDG PET, eAV45 and lAV45 scans. We found early time frame 0–4 min to give maximal correlation with [18F]FDG PET and minimal correlation with lAV45. Moreover, maximal overlap of [18F]FDG PET versus eAV45 associations with clinical diagnosis and cognition was obtained with pons scaling. Across reference regions, classification performance between clinical subgroups was similar for both eAV45 and [18F]FDG PET. These findings highlight the optimal use of eAV45 to assess neurodegeneration as a validated proxy of [18F]FDG PET. On top of this purpose, this study showed that combined [18F]AV45 PET dual-biomarker even outperformed [18F]FDG PET or lAV45 alone.

Deep learning improves utility of tau PET in the study of Alzheimer's disease.

IntroductionPositron emission tomography (PET) imaging targeting neurofibrillary tau tangles is increasingly used in the study of Alzheimer's disease (AD), but its utility may be limited by conventional quantitative or qualitative evaluation techniques in earlier disease states. Convolutional neural networks (CNNs) are effective in learning spatial patterns for image classification.Methods18F‐MK6240 (n = 320) and AV‐1451 (n = 446) PET images were pooled from multiple studies. We performed iterations with differing permutations of radioligands, heuristics, and architectures. Performance was compared to a standard region of interest (ROI)‐based approach on prediction of memory impairment. We visualized attention of the network to illustrate decision making.ResultsOverall, models had high accuracy (> 80%) with good average sensitivity and specificity (75% and 82%, respectively), and had comparable or higher accuracy to the ROI standard. Visualizations of model attention highlight known characteristics of tau radioligand binding.DiscussionCNNs could improve tau PET's role in early disease and extend the utility of tau PET across generations of radioligands.

Imaging tau burden in dementia with Lewy bodies using [18F]-AV1451 positron emission tomography

Alzheimer's disease (AD) pathology is frequently observed as a comorbidity in people with dementia with Lewy bodies (DLB). Here, we evaluated the in vivo distribution of tau burden and its influence on the clinical phenotype of DLB. Tau deposition was quantified using [18F]-AV1451 positron emission tomography in people with DLB (n = 10), AD (n = 27), and healthy controls (n = 14). A subset of patients with Lewy body diseases (n = 4) also underwent [11C]-PK11195 positron emission tomography to estimate microglial activation. [18F]-AV1451 BPND was lower in DLB than AD across widespread regions. The medial temporal lobe [18F]-AV1451 BPND distinguished people with DLB from AD (AUC = 0.87), and negatively correlated with Addenbrooke's Cognitive Examination-Revised and Mini-Mental State Examination. There was a high degree of colocalization between [18F]-AV1451 and [11C]-PK11195 binding (p < 0.001). Our findings of minimal tau burden in DLB confirm previous studies. Nevertheless, the associations of [18F]-AV1451 binding with cognitive impairment suggest that tau may interact synergistically with other pathologic processes to aggravate disease severity in DLB.

Beta-amyloid (Aβ) uptake by PET imaging in older HIV+ and HIV- individuals.

The causes of cognitive impairment among older HIV+ individuals may overlap with causes among elderly HIV seronegative (HIV-) individuals. The objective of this study was to determine if beta-amyloid (Aβ) deposition measured by [18F] AV-45 (florbetapir) positron emission tomography (PET) is increased in older HIV+ individuals compared to HIV- individuals. Forty-eight HIV+ and 25 HIV- individuals underwent [18F] AV-45 PET imaging. [18F] AV-45 binding to Aβ was measured by standardized uptake value ratios (SUVR) relative to the cerebellum in 16 cortical and subcortical regions of interest. Global and regional cortical SUVRs were compared by (1) serostatus, (2) HAND stage, and (3) age decade, comparing individuals in their 50s and >60s. There were no differences in median global cortical SUVR stratified by HIV serostatus or HAND stage. The proportion of HIV+ participants in their 50s with elevated global amyloid uptake (SUVR > 1.40) was significantly higher than the proportion in HIV- participants (67% versus 25%, p = 0.04), and selected regional SUVR values were also higher (p < 0.05) in HIV+ compared to HIV- participants in their 50s. However, these group differences were not seen in participants in their 60s. In conclusion, PET imaging found no differences in overall global Aβ deposition stratified by HIV serostatus or HAND stage. Although there was some evidence of increased Aβ deposition in HIV+ individuals in their 50s compared to HIV- individuals which might indicate premature aging, the most parsimonious explanation for this is the relatively small sample size in this cross-sectional cohort study.