Kantarci, Kejal

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.

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.

AbstractBackgroundData heterogeneity due to cross‐scanner variations is a major challenge in multi‐center aging and dementia studies. Brain structural measures for the same participant can vary due to scanner differences (manufacturer, scanner age/technology, signal‐to‐noise ratio, pulse sequence design, contrast, resolution) and result in biomarker variability. In this work, we applied basic image processing and deep learning methods (style transfer (ST) and generative adversarial networks (GANs)) for harmonizing T1‐weighted MRI scans across change in vendors (GE to Siemens) and resolution (1x1x1.2mm to 0.8x0.8x0.8mm) and test whether this harmonization improved compatibility of AD biomarker measures.MethodWe utilized training (n=814) and test (n=113 same participants scanned on two scanners close‐in‐time, typically on the same day, with different resolution) data from cognitively impaired and unimpaired participants scanned on GE and Siemens scanners from Mayo Clinic Study of Aging and Mayo ADRC. The harmonization was conducted to translate GE to Siemens. All scans were affine transformed to the same template space, resampled to 1.5 mm3, and bias corrected. Histogram matching was performed using cumulative density functions. A ResNet18 was trained for the ST’s content and style layers. Two types of GANs, conditional GANs (cGAN) and cycle‐consistent GANs (cycleGAN), were constructed. We then measured regional cortical thickness from each image using FreeSurfer‐7.1.1 and compared the thickness measurements from the original and translated scans using intraclass‐correlation (ICC) and Deming regression.ResultIn the test dataset, ST and cycleGAN showed the best performances when comparing the translated GE to Siemens. With ST, the ICC increased (vs. the original scans) slightly for the temporal meta‐ROI (0.956 from 0.954) and more substantially for the frontal pole ROI (0.706 from 0.594). The cycleGAN showed an increase in ICC for the frontal pole ROI (0.610 from 0.594) but not the meta‐ROI (Fig. 1).ConclusionEach method leveraged a different strength. Histogram matching captures contrast, ST extracts textural information, and GANs learn combination of contrast, edge and texture properties. We found that deep learning is a promising approach to cross‐scanner variability. Our comparisons revealed anatomical differences across methods; thus, disease specific measure should be considered for selection of the scanner harmonization method.

AbstractBackgroundSeveral hypotheses exist regarding the neurologic substrate underlying visual hallucinations (VH) in Dementia with Lewy Bodies (DLB). Studies have suggested an association with regional cerebral hypometabolism in the primary visual or visual association cortices on FDG‐PET. We compared regional cerebral glucose metabolism and posterior cingulate island sign (CIS) ratios in DLB and in Mild Cognitive Impairment with Lewy Bodies (MCI‐LB) participants with (VH+) and without (VH‐) VH.MethodParticipants with clinically probable DLB or MCI‐LB and an FDG‐PET scan were identified from the Mayo ADRC database. Responses on the Visual Hallucinations and Delusions Questionnaire and Neuropsychiatric Inventory were used to assess presence or absence of VH. Standardized uptake value ratios (SUVr) were used to calculate regional cerebral glucose hypometabolism in the primary visual cortex (PVC), lateral occipital cortex (LOC), and whole occipital cortex (WOC). The CIS ratio was defined as posterior cingulate divided by the sum of the precuneus plus cuneus FDG‐PET uptake ratio.ResultTwo cohorts were identified (27 DLB and 18 MCI‐LB, 87% male). Eighteen DLB participants were VH+ and 9 were VH‐, whereas 5 MCI‐LB were VH+ and 13 were VH‐. There were no statistically significant differences in demographic (age, sex, education) and clinical features (MoCA, CDR, presence of other core DLB features, and UPDRS) between VH+ vs VH‐ in those with DLB, and between VH+ vs VH‐ in those with MCI‐LB. Similarly, there were no statistically significant differences in DLB between VH+ vs VH‐ in PVC (1.55±0.14 vs 1.58±0.15), LOC (1.22±0.16 vs 1.28±0.12), WOC (1.29±0.15 vs 1.34±0.11), or CIS ratio (1.16±0.08 vs 1.14±0.10), nor in MCI‐LB between VH+ vs VH‐ in PVC (1.68±0.19 vs 1.58±0.14), LOC (1.40±0.21 vs 1.32±0.14), WOC (1.45±0.20 vs 1.37±0.14), or CIS ratio (1.17±0.08 vs 1.19±0.10) (P>0.05 for all comparisons).ConclusionThese findings do not support a direct correlation between regional cerebral glucose metabolism and VH in DLB or MCI‐LB. Further work in DLB and MCI‐LB with larger numbers is warranted. Other neurologic substrates and mechanisms, such as REM sleep intrusions during wakefulness, neurotransmitter dysfunction, and disruption of functional connectivity across brain regions should be explored as contributors to VH in DLB.

AbstractBackgroundInter‐cellular communication within the gliovascular unit (GVU) is critical for cerebral blood flow regulation, maintenance of the blood‐brain‐barrier (BBB) properties, and brain energy metabolism. Although numerous cell biology studies demonstrate the role of the GVU for BBB breakdown in Alzheimer’s disease (AD), the precise molecular changes contributing to its pathophysiology are unclear.MethodWe performed single nucleus RNA sequencing (snRNAseq) of temporal cortex tissue in 24 AD and control brains to understand the transcriptional changes in the cells of GVU. We acquired the snRNAseq profile of 79,751 total brain cells that comprise 6,541 astrocytes and 2,210 vascular cells. The latter formed three distinct vascular clusters characterized as activated pericytes, endothelia and resting pericytes. We identified differentially expressed genes (DEGs) and their enriched pathways in these clusters and detected the most transcriptional changes within activated pericytes. Using our data and a knowledge‐based predictive algorithm, we discovered and prioritized molecular interactions between vascular and astrocyte clusters, the main cell types of the GVU of the BBB.ResultsVascular targets predicted to interact with astrocytic ligands have biological functions in signalling, angiogenesis, amyloid ß metabolism and cytoskeletal structure. Top astrocytic and vascular interacting molecules include both novel and known AD risk genes such as APOE, APP and ECE1. We validated gene expression changes using qPCR. We are in the process of evaluating these gene expression changes in antemortem blood from AD and control participants.ConclusionOur findings provide valuable information into the transcriptional changes in predicted vascular‐astrocytic partners at the GVU, highlighting insights into the molecular mechanisms of BBB breakdown in AD.

AbstractBackgroundWhite matter signal abnormalities (WMSA) are frequently observed on magnetic resonance imaging (MRI) scans of people with frontotemporal dementia (FTD). We hypothesized that carriers of mutations in progranulin (GRN+), chromosome 9 open reading frame 72 (C9orf72+) and microtubule associated protein tau (MAPT+) have increased rates of progression of WMSA compared to non‐carrier individuals prior to onset of dementia, and that different mutations may have different rates of WMSA accumulation.MethodParticipants were recruited through the ARTFL‐LEFFTDS Longitudinal Frontotemporal Lobar Degeneration (ALLFTD) Study. We selected participants with Clinical Dementia Rating scale (CDR) scores of 0 and 0.5. If a participant developed FTD during the follow‐up, we only analyzed observations collected before the conversion. WMSA were defined as hyperintensities on FLAIR MRI. Total WMSA volumes were normalized to the respective intracranial volumes. We used a linear mixed effects model, with random intercepts and slopes, to compare the baseline burden and the longitudinal progression of total WMSA volumes between mutation carriers and controls. The model was adjusted for baseline age, sex, education, baseline Montreal Cognitive Assessment (MoCA) scores, and MRI acquisition sites.ResultWe analyzed MRI data from 199 participants who had at least two MRI visits (46 C9orf72+, 17 GRN+, 35 MAPT+, 101 non‐carrier controls; up to five years of follow‐up). We did not find significant group differences in baseline demographic features, except that MAPT+ was younger than non‐carrier controls (average age: C9orf72+=47, GRN+=56, MAPT+=40, controls=47). Baseline WMSA volumes were not significantly different between mutation carriers and controls. Longitudinally, the rates of WMSA volume increase in C9orf72+ and MAPT+ were comparable to controls; whereas, GRN+ had higher rates of WMSA volume increases compared to controls (p=0.01).ConclusionWMSA may accumulate at higher rates in GRN+ prior to the onset of FTD, which is consistent with the frequent presence of white matter diseases observed in symptomatic FTD patients with GRN mutations. Future work is warranted to investigate the association between white matter structural changes and cognitive/psychiatric changes in FTD mutation carriers.

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.

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.