Citations

Clear

4093 citation(s) found for "Yu, Jonathan".

Unique brain iron profiles associated with logopenic progressive aphasia and posterior cortical atrophy
Graff‐Radford, Jonathan, Martin, Peter , Shu, Yunhong , Petersen, Ronald C. , Lowe, Val J. , Josephs, Keith A. , Whitwell, Jennifer , Singh, Neha Atulkumar , Arani, Arvin , Graff‐Radford, Jonathan , Senjem, Matthew L. , Schwarz, Christopher G. , Cogswell, Petrice M. , Knopman, David S. , Jack, Clifford R.

Mayo Clinic

Alzheimer's & Dementia | December 20, 2022 | Volume: 18 | Issue: S6 | Pages: No page available

10.1002/alz.063235 Get It

AbstractBackgroundQuantitative susceptibility mapping (QSM) can detect iron distribution in the brain by estimating the local tissue magnetic susceptibility of every voxel. Dysregulation of neuronal iron has been correlated with typical Alzheimer’s disease (tAD), but little is known about iron distribution in atypical clinical presentations of AD such as logopenic progressive aphasia (LPA) and posterior cortical atrophy (PCA).MethodEleven PCA patients and eight LPA patients were recruited by the Neurodegenerative Research Group at Mayo Clinic, Rochester, MN, and underwent MRI that included a five‐echo gradient echo sequence for calculation of QSM. Mean QSM signal was extracted from gray and white matter for regions‐of‐interest across the brain using the Mayo Clinic Adult Lifespan Template. Hierarchical models were fit per‐region and per‐hemisphere to compare PCA and LPA to each other, to 20 healthy controls, and to 20 patients with tAD recruited by the Alzheimer’s Disease Research Center.ResultStrong evidence (posterior probability>0.99) was observed for greater susceptibility in the left middle occipital gyrus and amygdala in both LPA and PCA, and in the right precuneus and inferior temporal gyrus in PCA compared to controls. Moderate evidence for greater susceptibility (posterior probability>0.90) was also observed in the left insula, inferior occipital gyrus, entorhinal cortex, and right inferior parietal gyrus and amygdala in both LPA and PCA, along with right angular gyrus and middle occipital gyrus in PCA and right insula and caudate in LPA, when compared to controls. Comparing between phenotypes, LPA showed moderate evidence for greater susceptibility in the caudate, hippocampus, substantia nigra, left supramarginal gyrus and posterior cingulate compared to PCA, while PCA showed greater susceptibility in the right precuneus compared to LPA. Both LPA and PCA showed moderate‐strong evidence for greater susceptibility than tAD, particularly in medial and lateral parietal regions.ConclusionUnique iron profiles were identified in LPA and PCA within cortical and subcortical structures. These changes are in line with disease‐related neurodegenerative changes in the clinical phenotypes, suggesting that QSM could be an informative marker to study iron deposition in these patients.
Medial temporal atrophy in posterior cortical atrophy and its relationship to the cingulate island sign
Josephs, Kennedy A., Pham, Nha Trang Thu, Graff‐Radford, Jonathan, Lowe, Val J. , Whitwell, Jennifer L. , Graff‐Radford, Jonathan , Machulda, Mary M. , Whitwell, Jennifer L.

Mayo Clinic

Alzheimer's & Dementia | December 20, 2022 | Volume: 18 | Issue: S6 | Pages: No page available

10.1002/alz.062612 Get It

AbstractBackgroundPosterior cortical atrophy (PCA) is associated with hypometabolism on FDG‐PET and atrophy on MRI in the parietal and occipital lobes, and patients often show the cingulate island sign (CIS) whereby posterior cingulate metabolism is relatively spared compared to the precuneus and cuneus. It has been hypothesized that medial temporal sparing may be related to CIS in PCA. We aimed to assess the severity of medial temporal atrophy in PCA and determine whether the presence of a CIS is related to medial temporal sparing.MethodFifty‐five PCA patients underwent a 3T volumetric MRI and FDG‐PET. The degree and symmetry of medial temporal atrophy on MRI was visually assessed in both hemispheres using the five‐point Scheltens scale (0=normal; 1=mild; 2=moderate; 3=marked; 4=severe). Visual assessments of FDG‐PET coded the presence/absence of a CIS and whether the CIS was symmetric or asymmetric. Hippocampal volumes and a quantitative CIS were also measured. Associations between medial temporal atrophy scores and clinical measures were assessed using linear regression correcting for age.ResultMedial temporal atrophy was most commonly mild (38% on the right, 40% on the left), followed by moderate (35% on the right, 29% on the left), and then no atrophy (18% on right, 25% on left). Marked or severe atrophy was only observed in 9% of patients on the right and 5% of patients on the left. Atrophy was asymmetric in 55%, and when asymmetric was most commonly worse on the right (76%). Greater medial temporal atrophy was associated with older age (p<0.001) and worse verbal episodic memory (p=0.008). The CIS was observed in 44% of the PCA patients and was asymmetric in 50% of these. The patients with a CIS showed greater medial temporal asymmetry (p=0.016), but did not show lower medial temporal atrophy scores, compared to those without a CIS. Hippocampal volumes were not associated with quantitative CIS.ConclusionMild to moderate medial temporal atrophy is a common finding in PCA and is associated with worse memory impairment and older age. However, medial temporal sparing was not related to the presence of a CIS in PCA.
Biomarkers and clinical presentations in Creutzfeldt‐Jakob Disease
Lazar, Evelyn, Graff‐Radford, Jonathan , Aksamit, Allen J. , Cutsforth‐Gregory, Jeremy K. , Prusinski, Christian , Porter, Amanda , Shir, Dror , Jones, David T. , Botha, Hugo , Ramanan, Vijay K. , Day, Gregory S.

Mayo Clinic

Alzheimer's & Dementia | December 20, 2022 | Volume: 18 | Issue: S6 | Pages: No page available

10.1002/alz.062598 Get It

AbstractBackgroundThe ability to detect malformed prion proteins using real‐time quaking‐induced conversion (RT‐QuIC) assays has transformed the diagnostic approach to sporadic Creutzfeldt‐Jakob disease (CJD), facilitating earlier recognition of affected patients. Recognizing this, we evaluated the frequency of clinical features and biomarker results at initial evaluation in patients with CJD and determined the relationship between these early features and CJD diagnosis and prognosis.MethodClinical data were extracted from the electronic medical records of patients with probable or definite (pathologically confirmed) CJD assessed at Mayo Clinic from 2014‐2021. Diagnoses of probable CJD were established by clinical consensus, referencing the Centers for Disease Control and Prevention diagnostic criteria. Clinical features and biomarkers results were evaluated at presentation, and associations with CJD diagnosis and symptomatic disease duration determined.ResultOne‐hundred fifteen patients were included (40, [35%] with definite CJD). Mean age‐at‐symptom onset was 64.8±9.4 years; 68 patients were female (59%). The sensitivity of clinical markers (myoclonus) and tests historically considered in patients with suspected CJD (e.g., stereotyped EEG abnormalities (16%), CSF 14‐3‐3 (60%)) was poor. Biomarkers with good diagnostic sensitivity included RT‐QuIC (93%), t‐tau levels >1149 pg/mL (88%), and characteristic signal abnormalities on MRI (77%). Multivariable linear regression confirmed shorter survival for patients with myoclonus (125.9 days, 95%CI 23.3‐15.5, p=0.026), visual/cerebellar signs (180.19 days, 95%CI 282.2‐78.2, p<0.001), positive 14‐3‐3 (193 days, 95%CI 304.9‐82.9; p<0.001), and elevated t‐tau levels (each 1000 pg/ml increase was associated with a nine‐day shorter time‐to‐death, 95%CI 1‐18; p=0.041).ConclusionCSF RT‐QuIC and elevated t‐tau levels, and stereotyped MRI abnormalities continue to be strongly associated with the diagnosis in the modern era, while other clinical findings (myoclonus) and biomarkers results traditionally ascribed to CJD (e.g., PSWC on EEG, 14‐3‐3) offered less value in the diagnostic evaluation. Detection of visual or cerebellar features, myoclonus, CSF 14‐3‐3, and t‐tau levels may predict disease duration, justifying inclusion in the evaluation of CJD‐suspected patients.
White Matter Degeneration Pathways Associated with Tau Deposition in Alzheimer’s Disease
Tian, Jianqiao , Przybelski, Scott A. , Raghavan, Sheelakumari , Gebre, Robel K , Graff‐Radford, Jonathan, Lowe, Val J. , Petersen, Ronald C. , Reid, Robert I. , Graff‐Radford, Jonathan , Kantarci, Kejal , Knopman, David S. , Jack, Clifford R. , Vemuri, Prashanthi

Mayo Clinic

Alzheimer's & Dementia | December 20, 2022 | Volume: 18 | Issue: S6 | Pages: No page available

10.1002/alz.062596 Get It

AbstractBackgroundThe dynamics of white matter (WM) changes are understudied in Alzheimer’s disease (AD). Leveraging tau deposition measured from Tau‐PET, our goal was to study the association between tau and white matter health using NODDI from multi‐shell diffusion MRI (dMRI). Specifically, we focused on the Neurite Density Index (NDI) from NODDI, which in WM captures the signal from axons.MethodWe identified 251 participants (126 cognitively normal, 58 MCI, 67 dementia) from the Mayo ADRC and Mayo Clinic Study of Aging with Aβ‐PET, Tau‐PET, and multi‐shell dMRI who were Aβ‐positive (mean age of 77 years and 55% male). We limited to Aβ‐positive participants because Aβ deposition accelerates tau deposition. For Tau‐PET, we estimated SUVRs from three regions corresponding to Braak I/II, III/IV, and V/VI (Figure 1.a). To understand the associations between Tau‐PET SUVRs at three Braak regions and NDIs at 30 candidate WM tracts, we implemented three analyses methods ‐ Pearson correlation, linear regression, and multilayer perceptron machine learning regression.ResultHigher tau burden in all three Braak regions was associated with lower neurite density in 10 significant WM tracts (Table 1). Interestingly, uncinate fasciculus (UNC) was found significantly associated with all three Braak regions. All three analysis methods consistently showed differential involvement of WM pathways for Braak staging such as ‐ Cingulum adjoining Hippocampus (CGH) for Braak I/II regions, Medial Temporal WM (MTWM) for Braak III/IV regions, and Inferior Occipital WM (IOWM) for Braak V/VI regions (Figure 1.b). The linear regression and machine learning regression models also suggested that WM measurements reflected 18‐35% of variance due to tau depositionConclusionWe found that CGH and UNC WM were the most impacted ROIs associated with Braak I/II regions as expected. UNC, directly connecting anterior temporal lobes to the orbitofrontal cortex, was a key WM tract identified as important for all Braak I‐VI regions and warrants further investigation in the study of AD progression. This study highlights the significant impact tau deposition may have on WM. This work also demonstrates the feasibility of using NODDI as an informative supplementary imaging modality for monitoring AD progression.
Plasma Biomarkers of Amyloid and Neurodegeneration predictive of Neuropathologic Scales of Cerebrovascular Disease
Graff‐Radford, Jonathan , Hofrenning, Ekaterina I. , Lesnick, Timothy G. , Cabrera‐Rodriguez, Janisse N, Rothberg, Darren M., Przybelski, Scott A. , Petersen, Ronald C. , Mielke, Michelle M. , Kouri, Naomi , Moloney, Christina M. , Rabinstein, Alejandro A. , Knopman, David S. , Dickson, Dennis W. , Nguyen, Aivi T. , Murray, Melissa E. , Vemuri, Prashanthi

Mayo Clinic

Alzheimer's & Dementia | December 20, 2022 | Volume: 18 | Issue: S5 | Pages: No page available

10.1002/alz.067350 Get It

AbstractBackgroundBlood‐based biomarkers of amyloid and neurodegeneration are increasingly used in clinical trials and entering clinical use. Differentially mapping the plasma markers to post‐mortem neuropathology in a community‐based sample is critical for interpretation.MethodWe identified 64 Mayo Clinic Study of Aging (MCSA) participants with antemortem plasma markers (Aβ42, Aβ40, NfL, T‐tau, Aβ42/40 ratio) measured on the Quanterix Simoa HD‐1 analyzer and with postmortem neuropathologic assessments of Alzheimer’s pathology (Braak tangle stage, Thal phase, neuritic plaque burden) and cerebrovascular pathology (Strozyk scale focused on macrovascular brain changes and Kalaria scale focused on detailed micro‐ and macro‐ vascular brain changes). Weighted linear regression models with adjustment for time between plasma markers and death were conducted with exact permutation tests to evaluate the relationships between antemortem plasma and postmortem neuropathology markers.ResultHigher plasma NfL levels and Aβ42/40 ratio were associated with both cerebrovascular neuropathologic scales (p<0.05) but were not associated with Braak neurofibrillary tangle stage, neuritic plaque score, or Thal stage (p>0.5). Plasma T‐tau was not associated with any pathological assessment. Plasma Aβ42/40 and NfL explained up to 18% of the variability in cerebrovascular neuropathologic scales.ConclusionIn this community sample of participants predominantly without dementia, plasma markers for amyloid (Aβ42/40) and neurodegeneration (NfL) were associated with cerebrovascular neuropathology at autopsy. NfL is a non‐specific marker of brain injury, therefore, its association with cerebrovascular neuropathology was in the expected direction. The association between greater cerebrovascular neuropathology and elevated Aβ42/40 requires further investigation. These findings provide evidence that cerebrovascular disease may significantly influence levels of plasma biomarkers proposed for Alzheimer’s disease. This information will be important to consider for accurate clinical interpretation of the proposed biomarkers.
Baseline and Longitudinal Ioflupane SPECT Findings in DLB and MCI‐LB
Miyagawa, Toji , Przybelski, Scott A. , Jordan, Lennon, Lesnick, Tim, Savica, Rodolfo , Graff‐Radford, Jonathan , Petersen, Ronald C. , Graff‐Radford, Neill R. , Fields, Julie A. , Forsberg, Leah K. , Christine, Cliatt Brown J, Jain, Manoj , Lowe, Val J. , Boeve, Bradley F. , Min, Hoon-Ki Paul , Lesnick, Timothy G. , Jones, David T. , Botha, Hugo , Ramanan, Vijay K. , Knopman, David S. , Day, Gregory S. , Machulda, Mary M. , Ferman, Tanis J. , Diaz‐Galvan, Patricia , Li, Wentao , Jack, Clifford R. , Kantarci, Kejal

Mayo Clinic

Alzheimer's & Dementia | December 20, 2022 | Volume: 18 | Issue: S5 | Pages: No page available

10.1002/alz.067066 Get It

AbstractBackgroundReduced striatal uptake on ioflupane SPECT is considered an indicative biomarker for Dementia with Lewy Bodies (DLB), and has been proposed as an indicative biomarker for Mild Cognitive Impairment with Lewy Bodies (MCI‐LB). Little data exists on the profile of uptake on key striatal regions of interest (ROIs) in DLB or MCI‐LB.MethodParticipants with DLB or MCI‐LB at baseline based on the presence of ≥2 core clinical DLB features, and ≥2 ioflupane SPECT scans performed approximately annually, were identified from the Mayo ADRC database. Minimum brain laterality z‐score values for the putamen (whole, anterior and posterior), caudate and striatum were determined using DaTQUANT 2 software. Baseline clinical and scan data was used for all analyses, and the annualized minimum putamen z‐change was determined on serial scans. The scan was considered abnormal if the minimum putamen z‐score was <‐0.98 based on clinicopathologic data.Result27 participants were included (21 DLB and 6 MCI‐LB, 96% male). Compared to MCI‐LB, DLB had a lower mean MoCA score and a trend toward a higher UPDRS score compared to MCI‐LB; there were no statistically significant differences in age, sex, onset age or duration of cognitive decline, or presence of other core DLB features. The majority (89%) had an abnormal scan at baseline. All ROI z‐scores showed the expected general trend of DLB<MCI‐LB, and the annualized z‐change was more negative in DLB, but none of the findings reached statistical significance.ConclusionThese findings suggest in MCI‐LB and DLB that 1) an abnormal ioflupane SPECT scan is frequently present at diagnosis, 2) z‐scores become more negative over time, and 3) the annualized z‐change is similar. Similar findings in larger cohorts would support the use of ioflupane SPECT as a biomarker in both MCI‐LB and DLB clinical trials.
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: S5 | Pages: No page available

10.1002/alz.066652 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.
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. , Radford, Jonathan Graff, 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: S5 | Pages: No page available

10.1002/alz.064607 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.
Comparing cerebrovascular disease diffusion MRI markers using post‐mortem and longitudinal imaging data
Raghavan, Sheelakumari , Przybelski, Scott A. , Kamykowski, Michael G. , Lesnick, Timothy G. , Reichard, Ross R., Graff‐Radford, Jonathan , Petersen, Ronald C. , Reid, Robert I. , Murray, Melissa E. , Nguyen, Aivi T. , Knopman, David S. , Mielke, Michelle M. , Jack, Clifford R. , Vemuri, Prashanthi

Mayo Clinic

Alzheimer's & Dementia | December 20, 2022 | Volume: 18 | Issue: S5 | Pages: No page available

10.1002/alz.063705 Get It

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

Mayo Clinic

Alzheimer's & Dementia | December 20, 2022 | Volume: 18 | Issue: S5 | Pages: No page available

10.1002/alz.063351 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.