Citations

Showing 10 of 108083 citations.

The Learning of Memory Support System in Individuals with Mild Cognitive Impairment
Koay, Jun Min , Shandera‐Ochsner, Anne L., Chandler, Melanie , Locke, Dona E.C.

Mayo Clinic

Alzheimer's & Dementia | December 20, 2022 | Volume: 18 | Issue: S8 | Pages: No page available

10.1002/alz.063432 Get It

AbstractBackgroundThe syndrome of mild cognitive impairment (MCI) is classified into different subtypes– amnestic MCI (aMCI) and non‐amnestic MCI based on cognitive domains impacted, while different underlying disease etiologies cause the impairments. The Memory Support System (MSS), a memory‐support tool which utilizes a calendar/planner, has been shown to have positive impact on daily functioning in MCI (Chandler et al., 2017). We have previously shown that cognitive impairment severity and personality traits are associated with MSS learning (De Wit et al., 2021; Khayoun et al., 2021). In this study, we hypothesized that 1) participants with single domain aMCI (SD‐aMCI) will have higher MSS learning scores than multi‐domain aMCI (MD‐aMCI), and 2) participants with suspected Alzheimer’s disease (AD) etiology will have lower MSS learning scores than other etiologies.MethodParticipants (mean age = 75.2) underwent daily MSS training between 2017 and 2021 as part of the 10‐day Mayo Clinic HABIT program. The MSS learning success score (LSS) was determined by how far participants progressed in three learning phases of increasing difficulty: Acquisition (0‐2 points), Application (3‐4 points), and Adaptation (5‐6 points; Greenway et al., 2008). Ordinal logistic regression analysis was used to predict MSS learning scores between SD‐aMCI (n = 142) versus MD‐aMCI (n = 119), and AD etiology (n = 213) versus other neurodegenerative etiologies (n = 57). Dementia Rating Scale‐2 scores (Jurica, 2001) were included to control for cognitive severity.ResultCompared to participants with SD‐aMCI, those with MD‐aMCI had 54.1% lower odds of having higher LSS at training end (p = .004), after controlling for cognitive impairment severity. AD versus other etiology’s impact on LSS was nonsignificant.ConclusionParticipants with MD‐aMCI showed poorer MSS learning efficiency than participants with SD‐aMCI. Etiology did not impact MSS learning. Results suggest having more than just memory impairment (e.g., additional language or executive dysfunction) reduces MSS learning, regardless of overall impairment level. Additional MSS training may be needed to facilitate learning for these individuals.
Patient and Care Partner Ratings of Communication Participation in Frontotemporal Dementia
Martin, Peter R. , Stierwalt, Julie A. G., Ali, Farwa , Josephs, Keith A. , Utianski, Rene L. , Clark, Heather M. , Duffy, Joseph R. , Botha, Hugo

Mayo Clinic

Alzheimer's & Dementia | December 20, 2022 | Volume: 18 | Issue: S9 | Pages: No page available

10.1002/alz.060715 Get It

AbstractPrior studies have shown communication‐related participation restrictions in patients with degenerative disease do not always match clinician judgment of symptom severity. Relatedly, there is a growing body of literature documenting discrepancies between patients with dementia and care partner perception of participation restrictions. However, it is not known how care partner perceptions of communication participation restrictions match or diverge from the patient's experience, which was the topic of this study.Toward that end, 28 patients with apraxia of speech and/or dysarthria associated with primary progressive apraxia of speech, nonfluent/agrammatic primary progressive aphasia, or progressive supranuclear palsy, all types of frontotemporal dementia, were seen for speech‐language examinations. The patients and their care partners were asked to independently complete the Communication Participation Item Bank (CPIB), short form, which is a 10‐question survey about communication in different contexts; higher scores reflect less interference from their condition on communication. Care partners were instructed to complete the form with their perception of the patient's restrictions. The total CPIB score (maximum 30) and difference scores were calculated and visualized.The data (Figure) suggest mismatches exist in care partner and patient ratings of communication participation restrictions. Of 28 patients, only 1 pair had identical scores, each rating severe interference in all communication contexts. 57% of patients rated communication as less impacted (higher scores) compared to their family member, leaving 39% of family members rating communication as less impacted than their loved one's perception. This study lays the foundation for future research to include patient and care partner ratings when examining the benefit of impairment‐based therapy, utilization of compensatory speech strategies, effectiveness of such strategies, and impact of other augmentative or alternative means of communication. The CPIB may be useful to document reduced psychosocial impact of disease and diminished burden and burnout on care partners with different intervention options. Future studies will explore possible differences between FTD phenotypes and, more specifically, whether 1) the motor speech disorder (MSD) disorder is primary or secondary to other motor impairment, 2) the nature or severity of the MSD, or 3) concomitant cognitive‐communication impairment predict the existence of and/or direction of a discrepancy.
AD‐causing variants that affect PSEN1 transmembrane domains are associated with faster neurodegeneration and cognitive decline compared to those affecting cytoplasmic domains.
Schultz, Stephanie A. , Fagan, Anne M. , Hanseeuw, Bernard , Gordon, Brian A. , Chen, Charles D., Xiong, Chengjie , Fitzpatrick, Colleen , Chui, Helena C., Mori, Hiroshi , Morris, John C. , Johnson, Keith A., Liu, Lei , Farlow, Martin R. , Farrell, Michelle E. , Graff‐Radford, Neill R. , Perrin, Richard J. , Berman, Sarah , Salloway, Stephen , Shirzadi, Zahra , Bateman, Randall J. , Chhatwal, Jasmeer P. , Gordon, Brian A , Bateman, Randall J , Xiong, Chengjie , Morris, John C , Berman, Sarah , Allegri, Ricardo , Schultz, Aaron P. , Goate, Alison , Levey, Allan I. , Koeppe, Robert A. , Cruchaga, Carlos , Karch, Celeste M. , Xiong, Chengjie , Jack, Clifford R. , McDade, Eric , Chui, Helena C. , Lee, Jae‐Hong , Noble, James M. , Hassenstab, Jason , Johnson, Keith A. , Jucker, Mathias , Joseph‐Mathurin, Nelly , Fox, Nick C. , Schofield, Peter R. , Martins, Ralph N. , Sánchez‐Valle, Raquel , Rosa-Neto, Pedro , Benzinger, Tammie L.S. , Sperling, Reisa Anne

Mayo Clinic

Alzheimer's & Dementia | December 20, 2022 | Volume: 18 | Issue: S1 | Pages: No page available

10.1002/alz.068221 Get It

AbstractBackgroundRates of cognitive and biomarker change in Autosomal Dominant Alzheimer disease (ADAD) vary substantially across individuals. Prior cross‐sectional work suggests that the location of the pathogenic variant within PSEN1, specifically whether the underlying variant affects transmembrane (TM) or cytoplasmic (CY) domains in PSEN1, may be a key determinant in these differential rates of progression. Here we use longitudinal data from the Dominantly Inherited Alzheimer Network observational study (DIAN‐Obs) to examine whether variants affecting TM versus CY domains in PSEN1 have differential rates of change in key cognitive and neurodegenerative markers, and whether these differences are relevant to ADAD clinical trials.MethodsUsing longitudinal clinical, cognitive, and MRI data from PSEN1 pathogenic variant carriers [TM group N=76 and CY group N=44; Table 1], we assessed rates of change in Mini‐Mental State Exam (MMSE), Clinical Dementia Rating® Sum of Boxes (CDR®‐SOB), and hippocampal volume (HV) using linear mixed effects models accounting for disease stage (estimated years to symptom onset [EYO]). We further assessed how PSEN1 mutation location (TM versus CY) impacts sample size and detectable effect size in a potential ADAD clinical trial (modeled as a 4‐year trial with annual assessments; 80% power; α = 0.05).Results PSEN1 TM and PSEN1 CY groups did not differ on baseline age, EYO, or CDR®. The PSEN1 TM group had significantly greater rates of change on MMSE (B[SE] = ‐0.42[0.1], p=0.002), CDR®‐SOB (B[SE] = 0.23[0.1], p=0.001), and HV atrophy (B[SE] = ‐58.93[14.3], p=0.0006 compared to the PSEN1 CY group (Fig.1). Consistent with these differential rates of change, power analyses indicated the required sample size to detect a 30% treatment effect on MMSE or HV would be reduced by 59.6% for MMSE and 91.0% for HV for a trial population comprised of PSEN1 TM versus CY carriers (Fig.2).ConclusionsIndividuals who had a variant affecting the transmembrane domains of PSEN1 had greater rates of cognitive decline and neurodegeneration compared to those with variants affecting cytoplasmic domains. In addition to having implications for ADAD pathophysiology, these results suggest that incorporating information regarding the location of PSEN1 variants may be beneficial in analyzing and designing stratification approaches for ADAD trials.
Progression of white matter signal abnormalities in predementia frontotemporal dementia mutation carriers
Lee, Hyunwoo , Chatterjee, Atri , Popuri, Karteek , Mackenzie, Ian R. , Rosen, Howard J. , Boxer, Adam L. , Gibson, Erin, Beg, Mirza Faisal , Kantarci, Kejal , Boeve, Bradley F. , Tartaglia, Maria Carmela , Hsiung, Ging‐Yuek Robin

Mayo Clinic

Alzheimer's & Dementia | December 20, 2022 | Volume: 18 | Issue: S1 | Pages: No page available

10.1002/alz.068066 Get It

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.
Improved automated cerebral microbleed (CMB) detection
Gunter, Jeffrey L. , Mead, Aaron K, Bermudez, Camilo L, Wiste, Heather J. , Gebre, Robel K , Vemuri, Prashanthi , Petersen, Ronald C. , Graff‐Radford, Jonathan , Vemuri, Prashanthi , Bermudez, Camilo , Knopman, David S. , Jack, Clifford R. , Cogswell, Petrice M.

Mayo Clinic

Alzheimer's & Dementia | December 20, 2022 | Volume: 18 | Issue: S1 | Pages: No page available

10.1002/alz.067992 Get It

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.
Harmonizing machine learning imaging biomarkers – CDESH and the case for harmonization in both MR image and low‐dimensional (scalar) output space
Gunter, Jeffrey L. , Petersen, Ronald C. , Graff‐Radford, Neill R. , Graff‐Radford, Jonathan , Cogswell, Petrice M. , Senjem, Matthew L. , Kantarci, Kejal , Knopman, David S. , Jack, Clifford R.

Mayo Clinic

Alzheimer's & Dementia | December 20, 2022 | Volume: 18 | Issue: S1 | Pages: No page available

10.1002/alz.067965 Get It

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.
Genetic contribution to grey matter network disruptions and Alzheimer disease cerebrospinal fluid markers
Dicks, Ellen , Tomassen, Jori , Kate, Mara ten , Braber, Anouk den , Teunissen, Charlotte E. , Scheltens, Philip , Barkhof, Frederik , Visser, Pieter Jelle , Tijms, Betty M.

Mayo Clinic

Alzheimer's & Dementia | December 20, 2022 | Volume: 18 | Issue: S1 | Pages: No page available

10.1002/alz.067822 Get It

AbstractBackgroundGrey matter covariance networks become disrupted early in Alzheimer’s disease (AD), when amyloid starts aggregating, and before the onset of irreversible atrophy. However, the precise relationship of grey matter network breakdown and the AD pathophysiological process remains unclear. Here, we studied to what extent shared familial (genes and family environment) or environmental factors unique to a twin contribute to these relationships in a sample of older monozygotic twins with intact cognition.MethodFrom the EMIF‐AD PreclinAD study we included monozygotic twins who had at least an MRI scan (n=197) and CSF available (n=124). We assessed the upper limit of genetic contribution to grey matter network measures (size, degree, connectivity density, clustering, path length, small‐world measures) with within‐twin pair correlations. Associations between CSF AD markers (Aβ42/40, t‐tau, p‐tau) and other markers related to AD pathophysiology (neurogranin, Aβ38, Aβ40, BACE1) with grey matter network disruptions were assessed with linear mixed models. Twin analyses (cross‐twin cross‐trait, twin difference analyses) were used to assess the contribution of shared familial and/or unique environmental factors to these associations.ResultTwenty individuals (16%) had abnormal CSF Aβ42/40 levels. Grey matter network measures were highly correlated within twin pairs (r=0.54‐0.97; all p<0.001, Fig.1), suggesting a moderate to strong genetic background. Across the whole sample, more abnormal Aβ42/40 ratios were moderately related to lower connectivity density (β±SE = 0.176±0.09, p=0.055, Fig.2). The strongest associations with grey matter network measures were observed for t‐tau and p‐tau levels (range β=‐0.344‐0.182), followed by Aβ production markers (Aβ38, Aβ40, BACE1) (range β=‐0.202‐0.165). We observed no relationships between neurogranin and grey matter network measures. Cross‐twin cross‐trait analyses showed that levels for t‐tau, p‐tau and Aβ38 in one twin were associated with grey matter network measures in their co‐twin (r=‐0.27 to ‐0.21; p range=0.02 to 0.07, Fig.3). Within‐pair differences in BACE1 were related to within‐pair differences in normalized path length values (r=0.35; p=0.01; Fig.4).ConclusionOur results suggest a shared familial background for the relationship of grey matter network disruptions and AD‐related processes as measured in CSF. In addition, unique environmental factors influencing BACE1 may also affect grey matter network disruptions.
Choice of Inversion Time for Arterial Spin Labeling MRI in the U.S. POINTER Lifestyle Intervention Trial
Hong, Sarah Y., Kim, Dong‐Hoon , Borowski, Bret, Gordineer, Leslie, Woolard, Nancy , Lovato, Laura, Masdeu, Joseph C. , Oh, Hwamee , Aggarwal, Neelum T. , Carrillo, Marı́a C., Snyder, Heather M. , Whitmer, Rachel A. , Landau, Susan, Jung, Youngkyoo , Vemuri, Prashanthi , Jack, Clifford R. , Koeppe, Robert A. , Lockhart, Samuel N. , Harrison, Theresa M. , Espeland, Mark Andrew , Harvey, Danielle , Toga, Arthur W. , Masdeu, Joseph C , Gitelman, Darren R. , Baker, Laura D. , DeCarli, Charles

Mayo Clinic

Alzheimer's & Dementia | December 20, 2022 | Volume: 18 | Issue: S1 | Pages: No page available

10.1002/alz.067351 Get It

AbstractBackgroundThe U.S. Study to Protect Brain Health Through Lifestyle Intervention to Reduce Risk (U.S. POINTER) is a 2‐year randomized controlled trial to evaluate the effect of lifestyle interventions in older adults (60‐79 years). The POINTER Imaging ancillary study is collecting Arterial Spin Labeling (ASL) MRI data to map cerebral blood flow (CBF) and evaluate the effect of interventions in the perfusion imaging biomarker. The optimization of timing parameters is essential for robust and efficient acquisition of ASL MRI.MethodA subset (n=83; F/M=51/32; age=69.0±5.5) of POINTER Imaging participants at two imaging sites underwent two ASL MRI scans during the same baseline session. Two 3D Pulsed ASL were obtained with TI1 of 790ms and TI2 values of 2000ms or 2750ms, which provide the delay times (between labeling and imaging) of 1210ms or 1960ms. ASL images were quantified into a physiological unit of CBF, ml/100g/min, using a single compartment kinetic model. CBF maps from two scans were normalized into a standard space and a voxel‐wise paired t‐test was performed after site variations were harmonized and covariates (age and sex) were adjusted. The age and sex effects in the difference of CBF values between two scans were also examined using linear regression. To control false positives, clusters smaller than 41ml were removed based on a simulation with α=0.05.ResultThe CBF values in ASL MRI rely on the timing of image acquisition: only a fraction of label bolus arrives in the tissue with a short delay while images suffer from low signal due to the magnetization decay with a long delay. Figure 1 shows the regions that require a long delay time (red) or a short delay (blue). The difference in CBF is proportional to arterial transit time (ATT) and the analysis shows females have shorter ATT mainly in the peri‐Sylvian region (Figure 2). No cluster survived correction in the analysis of the aging effect.ConclusionThe acquisition of two CBF maps not only offers optimization of acquisition timing but provides an additional perfusion parameter, arterial transit time, which may be a potential biomarker of cerebrovascular pathophysiology.
Latent space projection of brain FDG‐PET creates a powerful classifier for neurodegenerative diseases
Barnard, Leland R , Dicks, Ellen , Lee, Jeyeon , Gunter, Jeffrey L. , Lowe, Val J. , Petersen, Ronald C. , Graff‐Radford, Jonathan , Botha, Hugo , Corriveau‐Lecavalier, Nick , Min, Hoon-Ki Paul , Senjem, Matthew L. , Schwarz, Christopher G. , Boeve, Bradley F. , Knopman, David S. , Jack, Clifford R. , Jones, David T.

Mayo Clinic

Alzheimer's & Dementia | December 20, 2022 | Volume: 18 | Issue: S1 | Pages: No page available

10.1002/alz.066614 Get It

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.
A standardized protocol for detection of Amyloid Related Imaging Abnormality (ARIA) on 3T Philips Magnetic Resonance Imaging (MRI)
Pintér, Nándor , Johnson, B. Connor, Ajtai, Bela, Dorn, Ryu, Alnaji, Baraa, Harlock, Sarah, Westphal, Erica, Friel, Harry T. , Mechtler, Laszlo , Ganji, Sandeep K , Johnson, Brian, Huijbers, Willem

Mayo Clinic

Alzheimer's & Dementia | December 20, 2022 | Volume: 18 | Issue: S1 | Pages: No page available

10.1002/alz.065618 Get It

AbstractBackgroundARIA is a common side effect of aducanumab, the first anti‐amyloid pharmacotherapy approved by the US Food and Drug Administration (FDA) to treat Alzheimer’s disease. Regular MRI is required by FDA to detect and monitor different forms of ARIA during initiation of therapy. MRI protocols must be a) high resolution to detect abnormalities with high sensitivity, b) fast to accommodate workflow and ensure patient compliance and c) standardized to maximize data acquisition consistency across sites. Based on a vendor agnostic protocol recommendation by Benzinger et al (CTAD 2021), we propose specific parameters for 3T Philips systems, for an accelerated and enhanced protocol.MethodThe protocol was developed on a 3T Philips Elition X scanner, using 32‐channel head coil, and included 3D T1, 3D FLAIR, 2D DWI, 2D T2* and multi echo 3D Susceptibility Weighted Imaging (SWI) sequences.ResultAcquisition voxel resolution of 3D T1, 3D FLAIR, T2* and DWI matches current recommendations. 3D SWI resolution is 0.7x0.7x2mm. Compressed‐SENSE (C‐SENSE) acceleration is applied on 3D T1, 3D FLAIR, T2* and 3D SWI. SENSE is applied on DWI (Figure 1). Total acquisition time including the additional 3D SWI scan is 11 minutes, 6 minutes faster than the original recommendation. Qualitative assessment of images showed high signal‐to‐noise and contrast‐to‐noise. Images were free of acceleration related artifacts. Automated slice prescription localizer ensures better reproducibility for longitudinal assessment.ConclusionImaging protocol standardization is necessary to ensure consistent accuracy for diagnosing ARIA. Broad recommendations leave room for variability, therefore specific parameters are needed to achieve cross‐platform standardization. Our protocol is applicable for 3T Philips systems with compressed‐SENSE capability and 32‐channel head coil. The recommended C‐SENSE values maintain image quality with shorter exam time. This is more comfortable for patients and easier to fit into the workflow. The higher sensitivity of SWI can improve thresholds for therapy monitoring and provide additional quantitative measurements.