Gunter, Jeffrey L.

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.

AbstractBackgroundStudies of aging and dementia often acquire brain MRI and PET images, then de‐identify and share these widely with other researchers. It is known that research participants can potentially be re‐identified from brain MRI and CT using face recognition, but this has not been tested with PET imaging.MethodWe generated face reconstruction images of 182 volunteers using their existing amyloid (PiB), tau (FTP), and FDG PET scans from clinical GE PET/CT scanners, and we measured how often commercial automatic face recognition (Microsoft Azure) correctly matched these reconstructions with photographs of their faces. We additionally compared these match rates with face reconstructions from CT (from PET/CT) and MRI. When testing face recognition from PET scans, CT was used only during PET reconstruction, not for face recognition. We also validated our updated mri_reface software, originally developed to de‐identify (“de‐face”) faces in MRI, with new support for PET images. We measured face recognition rates before and after applying mri_reface to PET, CT, and MRI. In addition, we measured effects of de‐facing on biomarker measurements (global and regional SUVR) using 244 ADNI Florbetapir (FBP) amyloid PET scans with two automated pipelines: FreeSurfer 6.0 (PETSurfer) and an in‐house SPM12‐based pipeline.ResultRates of successful face recognition with PET ranged from 32‐41% (Table 1) across tracers. These were lower than MRI (98%) and CT (78%) but still concerning for participant privacy. Using mri_reface reduced face recognition to 0‐3.5% for PET, 5% for CT, and 8% for MRI. mri_reface had little effect on global amyloid SUVR measurements from ADNI PET images (Figure 1). ICC values between original and de‐faced images were 1.00 with biases and median absolute differences < 0.5%, across both pipelines. Effects on individual regions all had ICC values > 0.98 with biases and median absolute differences < 2%.ConclusionFace reconstructions from PET images have sufficient quality for potential re‐identification using publicly available face recognition technology. Research studies should consider using face de‐identification (de‐facing) software on PET images in addition to CT and structural MRI. Our free, automatic mri_reface software greatly reduced the potential for face recognition without substantially affecting SUVR measurements.

AbstractBackgroundResting state functional connectivity (rsfMRI) studies have shown functional network disruptions in logopenic progressive aphasia (LPA) (reduced connectivity within the left temporal language network) and posterior cortical atrophy (PCA) (reduced connectivity within ventral visual network). However, little is known about how these networks compare and how connectivity differs within and between networks in these atypical Alzheimer’s Disease (AD) phenotypes.MethodFifty‐nine amyloid‐positive PCA patients and eighty‐five amyloid‐positive LPA patients were recruited by the Neurodegenerative Research Group at Mayo Clinic, Rochester, MN, and underwent structural and resting state functional MRI. Spatially preprocessed data was analyzed using the CONN functional connectivity toolbox to explore the default mode network (DMN), salience, sensorimotor, left language, visual and memory networks, which were generated by averaging multiple regions‐of‐interest (ROI) within each network. The data was analyzed at both the voxel‐level and network‐level (ROI‐ROI).ResultVoxel‐level differences in functional connectivity between PCA and LPA were observed in all networks (p<0.05; cluster size, FWE=0.05). PCA showed reduced connectivity in the occipital lobe in visual and memory networks, parietal lobe in language and DMN, and sensorimotor strip in sensorimotor network, particularly on the right, compared to LPA. Conversely, LPA showed reduced connectivity in the frontal cortex in salience, memory, visual and sensorimotor networks, inferior parietal lobe in visual network, and anterior temporal pole and sensorimotor cortex in the language network, compared to PCA. Between network differences (p<0.05; cluster size, FDR=0.05) were observed between groups, with PCA showing reduced connectivity between the visual and sensorimotor networks, while LPA showed reduced connectivity between the language and sensorimotor networks. The DMN was anti‐correlated to the language network in PCA, while it was positively correlated to the language network in LPA. In both phenotypes, the DMN was anticorrelated with the salience network. The visual network in PCA showed connections to all networks, while in LPA, it was only connected to the salience, language and DMN.ConclusionThe atypical AD phenotypes were associated with multiple disruptions in connectivity, both within and between brain networks. Phenotype specific differences in connectivity patterns were noted in visual network for PCA and language network for LPA.

BackgroundFocally enlarged sulci (FES) are areas of proposed extraventricular fluid entrapment that may occur within idiopathic normal pressure hydrocephalus (iNPH) with radiographic evidence of disproportionately enlarged subarachnoid‐space hydrocephalus (DESH), and should be differentiated from atrophy.PurposeTo evaluate for change in FES size and pituitary height after shunt placement in iNPH.Study typeRetrospective.SubjectsA total of 125 iNPH patients who underwent shunt surgery and 40 age‐matched controls.Field Strength/Sequence1.5 T and 3 T. Axial T2w FLAIR, 3D T1w MPRAGE, 2D sagittal T1w.AssessmentFES were measured in three dimensions and volume was estimated by assuming an ellipsoid shape. Pituitary gland height was measured in the mid third of the gland in iNPH patients and controls.Statistical testsWilcoxon signed‐rank test for comparisons between MRI measurements; Wilcoxon rank sum test for comparison of cases/controls. Significance level was P < 0.05.ResultsFifty percent of the patients had FES. FES volume significantly decreased between the pre and first postshunt MRI by a median of 303 mm3 or 30.0%. Pituitary gland size significantly increased by 0.48 mm or 14.4%. FES decreased significantly by 190 mm3 or 23.1% and pituitary gland size increased significantly by 0.25 mm or 6% between the first and last postshunt MRI.Data ConclusionDecrease in size of FES after shunt placement provides further evidence that these regions are due to disordered cerebrospinal fluid (CSF) dynamics and should not be misinterpreted as atrophy. A relatively smaller pituitary gland in iNPH patients that normalizes after shunt is a less‐well recognized feature of altered CSF dynamics.Evidence Level3Technical EfficacyStage 2

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

Abstract Mild cognitive impairment with the core clinical features of dementia with Lewy bodies is recognized as a prodromal stage of dementia with Lewy bodies. Although grey matter atrophy has been demonstrated in prodromal dementia with Lewy bodies, longitudinal rates of atrophy during progression to probable dementia with Lewy bodies are unknown. We investigated the regional patterns of cross-sectional and longitudinal rates of grey matter atrophy in prodromal dementia with Lewy bodies, including those who progressed to probable dementia with Lewy bodies. Patients with mild cognitive impairment with at least one core clinical feature of dementia with Lewy bodies (mean age = 70.5; 95% male), who were enrolled in the Mayo Clinic Alzheimer’s Disease Research Center and followed for at least two clinical evaluations and MRI examinations, were included (n = 56). A cognitively unimpaired control group (n = 112) was matched 2:1 to the patients with mild cognitive impairment by age and sex. Patients either remained stable (n = 28) or progressed to probable dementia with Lewy bodies (n = 28) during a similar follow-up period and pathologic confirmation was available in a subset of cases (n = 18). Cross-sectional and longitudinal rates of grey matter atrophy were assessed using voxel-based and atlas-based region of interest analyses. At baseline, prodromal dementia with Lewy bodies was characterized by atrophy in the nucleus basalis of Meynert both in those who remained stable and those who progressed to probable dementia with Lewy bodies (P &lt; 0.05 false discovery rate corrected). Increase in longitudinal grey matter atrophy rates were widespread, with greatest rates of atrophy observed in the enthorhinal and parahippocampal cortices, temporoparietal association cortices, thalamus and the basal ganglia, in mild cognitive impairment patients who progressed to probable dementia with Lewy bodies at follow-up (P &lt; 0.05 false discovery rate corrected). Rates of inferior temporal atrophy were associated with greater rates of worsening on the clinical dementia rating–sum of boxes. Seventeen of the 18 (94%) autopsied cases had Lewy body disease. Results show that atrophy in the nucleus basalis of Meynert is a feature of prodromal dementia with Lewy bodies regardless of proximity to progression to probable dementia with Lewy bodies. Longitudinally, grey matter atrophy progresses in regions with significant cholinergic innervation, in alignment with clinical disease progression, with widespread and accelerated rates of atrophy in patients who progress to probable dementia with Lewy bodies. Given the prominent neurodegeneration in the cholinergic system, patients with prodromal dementia with Lewy bodies may be candidates for cholinesterase inhibitor treatment.

AbstractBackgroundIn animal models of Alzheimer’s disease (AD), aerobic exercise favorably modified the accumulation, degradation, and removal of Aβ and tau. However, human mechanistic randomized controlled trials (RCTs) are limited with mixed findings on hippocampal volume and biofluid Aβ and tau. Hence, an objective of the FIT‐AD Trial was to examine the effects of 6‐month aerobic exercise on magnetic resonance imaging (MRI) biomarkers in community‐dwelling older adults with AD dementia.MethodThe FIT‐AD Trial was a pilot RCT that first qualified participants for the main exercise study eligibility and then for MRI. Participants were randomized to moderate intensity cycling or low intensity stretching for 20‐50 minutes, 3 times a week for six months on a 2:1 ratio with three age strata (66‐75, 76‐85, and 85+ years of age) and followed up for another six months. MRI biomarkers included hippocampal volume, temporal meta‐regions of interest cortical thickness, white matter hyperintensity (WMH) volume, and network failure quotient (NFQ) measured at baseline, six months, and 12 months.ResultSixty participants met MRI eligibility, but one was excluded when this participant’s baseline MRI failed quality control. Among the 59 remaining participants, 38 were randomized to cycling and 21 to stretching. The sample characteristics (n=59) were 77.3±6.3 years old with 15.6±2.9 years of education and 53% men. Both groups experienced significant declines in hippocampal volume (2.64% in cycling vs. 2.89% in stretching) and cortical thickness (0.94% vs. 1.54%) over six months and over 12 months (hippocampal volume: 4.47% vs. 3.84%; cortical thickness: 2.27% vs. 1.79%). These declines didn’t differ between groups. WMH volume increased significantly, but the cycling group increased >50% less than stretching (10.9% vs. 24.5% over six months [f=4.47, p=.04]; 12.1% vs. 27.6% over 12 months [f=5.88, p=.02]). NFQ didn’t change significantly over time nor differed between group.ConclusionAerobic exercise may reduce hippocampal volume and cortical thickness declines during the intervention period; however, its effects are likely to be small and dose‐dependent and reverse after the intervention stops. Aerobic exercise is effective on reducing WMH progression but has no effect on NFQ.

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.

AbstractBackgroundAlzheimer’s disease biomarkers of tau pathology may be assessed by both CSF and PET. Cross‐sectional associations between CSF phosphorylated tau (p‐tau) and tau PET have been studied and regional tau PET SUVR has been shown to have similar diagnostic performance as CSF p‐tau. The association between CSF p‐tau and longitudinal tau PET has not been studied. CSF measures may be thought of as a result of the imbalance of influx vs efflux of soluble tau, whereas, tau PET reflects total tau accumulation into insoluble aggregates to date. We therefore hypothesize that baseline CSF p‐tau may be a leading indicator of future tau PET accumulation.MethodWe identified Mayo Clinic Study of Aging (MCSA) and Mayo Alzheimer’s Disease Research Center (ADRC) participants with diagnoses of cognitively unimpaired, mild cognitive impairment, and amnestic dementia who had CSF p‐tau (Elecsys p‐tau [181P]) and subsequent serial tau PET (flortaucipir) exams. The first tau PET scan was within 3 years of the CSF p‐tau collection. A longitudinal pipeline with two‐compartment partial volume correction was used to measure change in tau PET in a temporal‐lobe meta‐ROI (amygdala, fusiform, middle/inferior temporal, entorhinal, and parahippocampal regions) with a composite reference region (eroded supratentorial white matter, pons, and whole cerebellum). Spearman correlation was used to assess the association between CSF p‐tau and annual percent change in tau PET. A linear mixed effects model was fit to assess the association adjusting for age and sex.ResultThe study included 143 participants (76% cognitively unimpaired) (). CSF p‐tau was significantly associated with annual percent change in tau PET overall (Spearman R=0.19, p=0.023) () and after adjusting for age and sex (p<0.001) (). There was nonlinearity in the CSF p‐tau effect, with higher values (>20 pg/mL) having a greater association with annual change in tau PET than lower values.ConclusionIn a group of cognitively unimpaired and impaired participants, CSF p‐tau predicted subsequent tau PET accumulation rate. A threshold effect is suggested with subsequent tau PET accumulation primarily in participants with elevated CSF p‐tau levels near the Mayo threshold of 22 pg/mL.

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.