Author name cluster

Prashanthi Vemuri

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

24 papers

1 author row

YNIMG Journal 2025 Journal Article

Measuring the potential risk of re-identification of imaging research participants from open-source automated face recognition software

Carl M. Prakaashana
Marios Savvides
Jeffrey L. Gunter
Matthew L. Senjem
Prashanthi Vemuri
Kejal Kantarci
Johnanthan Graff-Radford
Ronald C. Petersen

In recent years facial recognition software has gone from an area of research to widespread adoption and broad public availability. Open-source face recognition packages are freely available on the internet for anyone to download, and several public websites allow users to run facial recognition on photos without needing any technical knowledge or equipment beyond internet access, making facial recognition accessible for anyone to use for any purpose. Previous research has demonstrated the ability of commercial software to identify a person based on facial content in brain imaging. In this study we tested two commercial facial recognition programs and a variety of popular open-source computer vision and facial recognition software packages to measure how accurately they could be used for reidentification of research participants in brain imaging studies. We tested a "population to sample" threat model, measuring the rates of success for which face recognition software selected the correct MRI-based face reconstruction from a set of 182 participants as its top-scoring match for input facial photographs. We found that the freely available open-source software packages we tested can reidentify a research participant with up to 59 % accuracy. This was less than the commercial packages, which were able to achieve much higher accuracies in the ranges of 92 % and 98 % in identical testing scenarios, but it demonstrates the feasibility of re-identifying faces in research MRI even by individuals with access to only freely available software. As the trust and confidence of potential participants is essential to brain imaging research, especially with widespread and mandated data-sharing of brain scans, this further supports the need to replace identifiable face imagery in brain images to protect the privacy of research participants.

YNICL Journal 2024 Journal Article

Complex relationships of socioeconomic status with vascular and Alzheimer’s pathways on cognition

Dror Shir
Jonathan Graff-Radford
Angela J. Fought
Timothy G. Lesnick
Scott A. Przybelski
Maria Vassilaki
Val J. Lowe
David S. Knopman

INTRODUCTION: AD and CVD, which frequently co-occur, are leading causes of age-related cognitive decline. We assessed how demographic factors, socioeconomic status (SES) as indicated by education and occupation, vascular risk factors, and a range of biomarkers associated with both CVD (including white matter hyperintensities [WMH], diffusion MRI abnormalities, infarctions, and microbleeds) and AD (comprising amyloid-PET and tau-PET) collectively influence cognitive function. METHODS: In this cross-sectional population study, structural equation models were utilized to understand these associations in 449 participants (mean age (SD) = 74.5 (8.4) years; 56% male; 7.5% cognitively impaired). RESULTS: (1) Higher SES had a protective effect on cognition with mediation through the vascular pathway. (2) The effect of amyloid directly on cognition and through tau was 11-fold larger than the indirect effect of amyloid on cognition through WMH. (3) There is a significant effect of vascular risk on tau deposition. DISCUSSION: The utilized biomarkers captured the impact of CVD and AD on cognition. The overall effect of vascular risk and SES on these biomarkers are complex and need further investigation.

YNIMG Journal 2023 Journal Article

A face-off of MRI research sequences by their need for de-facing

Christopher G. Schwarz
Walter K. Kremers
Arvin Arani
Marios Savvides
Robert I. Reid
Jeffrey L. Gunter
Matthew L. Senjem
Petrice M. Cogswell

It is now widely known that research brain MRI, CT, and PET images may potentially be re-identified using face recognition, and this potential can be reduced by applying face-deidentification ("de-facing") software. However, for research MRI sequences beyond T1-weighted (T1-w) and T2-FLAIR structural images, the potential for re-identification and quantitative effects of de-facing are both unknown, and the effects of de-facing T2-FLAIR are also unknown. In this work we examine these questions (where applicable) for T1-w, T2-w, T2*-w, T2-FLAIR, diffusion MRI (dMRI), functional MRI (fMRI), and arterial spin labelling (ASL) sequences. Among current-generation, vendor-product research-grade sequences, we found that 3D T1-w, T2-w, and T2-FLAIR were highly re-identifiable (96-98%). 2D T2-FLAIR and 3D multi-echo GRE (ME-GRE) were also moderately re-identifiable (44-45%), and our derived T2* from ME-GRE (comparable to a typical 2D T2*) matched at only 10%. Finally, diffusion, functional and ASL images were each minimally re-identifiable (0-8%). Applying de-facing with mri_reface version 0.3 reduced successful re-identification to ≤8%, while differential effects on popular quantitative pipelines for cortical volumes and thickness, white matter hyperintensities (WMH), and quantitative susceptibility mapping (QSM) measurements were all either comparable with or smaller than scan-rescan estimates. Consequently, high-quality de-facing software can greatly reduce the risk of re-identification for identifiable MRI sequences with only negligible effects on automated intracranial measurements. The current-generation echo-planar and spiral sequences (dMRI, fMRI, and ASL) each had minimal match rates, suggesting that they have a low risk of re-identification and can be shared without de-facing, but this conclusion should be re-evaluated if they are acquired without fat suppression, with a full-face scan coverage, or if newer developments reduce the current levels of artifacts and distortion around the face.

YNIMG Journal 2023 Journal Article

Cross–scanner harmonization methods for structural MRI may need further work: A comparison study

Robel K. Gebre
Matthew L. Senjem
Sheelakumari Raghavan
Christopher G. Schwarz
Jeffery L. Gunter
Ekaterina I. Hofrenning
Robert I. Reid
Kejal Kantarci

The clinical usefulness MRI biomarkers for aging and dementia studies relies on precise brain morphological measurements; however, scanner and/or protocol variations may introduce noise or bias. One approach to address this is post-acquisition scan harmonization. In this work, we evaluate deep learning (neural style transfer, CycleGAN and CGAN), histogram matching, and statistical (ComBat and LongComBat) methods. Participants who had been scanned on both GE and Siemens scanners (cross-sectional participants, known as Crossover (n = 113), and longitudinally scanned participants on both scanners (n = 454)) were used. The goal was to match GE MPRAGE (T1-weighted) scans to Siemens improved resolution MPRAGE scans. Harmonization was performed on raw native and preprocessed (resampled, affine transformed to template space) scans. Cortical thicknesses were measured using FreeSurfer (v.7.1.1). Distributions were checked using Kolmogorov-Smirnov tests. Intra-class correlation (ICC) was used to assess the degree of agreement in the Crossover datasets and annualized percent change in cortical thickness was calculated to evaluate the Longitudinal datasets. Prior to harmonization, the least agreement was found at the frontal pole (ICC = 0.72) for the raw native scans, and at caudal anterior cingulate (0.76) and frontal pole (0.54) for the preprocessed scans. Harmonization with NST, CycleGAN, and HM improved the ICCs of the preprocessed scans at the caudal anterior cingulate (>0.81) and frontal poles (>0.67). In the Longitudinal raw native scans, over- and under-estimations of cortical thickness were observed due to the changing of the scanners. ComBat matched the cortical thickness distributions throughout but was not able to increase the ICCs or remove the effects of scanner changeover in the Longitudinal datasets. CycleGAN and NST performed slightly better to address the cortical thickness variations between scanner change. However, none of the methods succeeded in harmonizing the Longitudinal dataset. CGAN was the worst performer for both datasets. In conclusion, the performance of the methods was overall similar and region dependent. Future research is needed to improve the existing approaches since none of them outperformed each other in terms of harmonizing the datasets at all ROIs. The findings of this study establish framework for future research into the scan harmonization problem.

YNICL Journal 2023 Journal Article

Effects of de-facing software mri_reface on utility of imaging biomarkers used in Alzheimer’s disease research

Christopher G. Schwarz
Walter K. Kremers
Stephen D. Weigand
Carl M. Prakaashana
Matthew L. Senjem
Scott A. Przybelski
Val J. Lowe
Jeffrey L. Gunter

Brain imaging research studies increasingly use "de-facing" software to remove or replace facial imagery before public data sharing. Several works have studied the effects of de-facing software on brain imaging biomarkers by directly comparing automated measurements from unmodified vs de-faced images, but most research brain images are used in analyses of correlations with cognitive measurements or clinical statuses, and the effects of de-facing on these types of imaging-to-cognition correlations has not been measured. In this work, we focused on brain imaging measures of amyloid (A), tau (T), neurodegeneration (N), and vascular (V) measures used in Alzheimer's Disease (AD) research. We created a retrospective sample of participants from three age- and sex-matched clinical groups (cognitively unimpaired, mild cognitive impairment, and AD dementia, and we performed region- and voxel-wise analyses of: hippocampal volume (N), white matter hyperintensity volume (V), amyloid PET (A), and tau PET (T) measures, each from multiple software pipelines, on their ability to separate cognitively defined groups and their degrees of correlation with age and Clinical Dementia Rating (CDR)-Sum of Boxes (CDR-SB). We performed each of these analyses twice: once with unmodified images and once with images de-faced with leading de-facing software mri_reface, and we directly compared the findings and their statistical strengths between the original vs. the de-faced images. Analyses with original and with de-faced images had very high agreement. There were no significant differences between any voxel-wise comparisons. Among region-wise comparisons, only three out of 55 correlations were significantly different between original and de-faced images, and these were not significant after correction for multiple comparisons. Overall, the statistical power of the imaging data for AD biomarkers was almost identical between unmodified and de-faced images, and their analyses results were extremely consistent.

YNIMG Journal 2023 Journal Article

Optimizing quantification of MK6240 tau PET in unimpaired older adults

Theresa M. Harrison
Tyler J. Ward
Alice Murphy
Suzanne L. Baker
Pablo A. Dominguez
Robert Koeppe
Prashanthi Vemuri
Samuel N. Lockhart

F]florbetaben [FBB]) and MRI data to evaluate neuroimaging biomarkers of AD and cerebrovascular pathophysiology in this at-risk sample. Here 481 participants (70.0±5.0; 66% F) with baseline MK6240, FBB and structural MRI scans were included. PET scans were coregistered to the structural MRI which was used to create FreeSurfer-defined reference regions and target regions of interest (ROIs). We also created off-target signal (OTS) ROIs to examine the magnitude and distribution of MK6240 OTS across the brain as well as relationships between OTS and age, sex, and race. OTS was unimodally distributed, highly correlated across OTS ROIs and related to younger age and sex but not race. Aiming to identify an optimal processing approach for MK6240 that would reduce the influence of OTS, we compared our previously validated MRI-guided standard PET processing and 6 alternative approaches. The alternate approaches included combinations of reference region erosion and meningeal OTS masking before spatial smoothing as well as partial volume correction. To compare processing approaches we examined relationships between target ROIs (entorhinal cortex (ERC), hippocampus or a temporal meta-ROI (MetaROI)) SUVR and age, sex, race, Aβ and a general cognitive status measure, the Modified Telephone Interview for Cognitive Status (TICSm). Overall, the processing approaches performed similarly, and none showed a meaningful improvement over standard processing. Across processing approaches we observed previously reported relationships with MK6240 target ROIs including positive associations with age, an Aβ+> Aβ- effect and negative associations with cognition. In sum, we demonstrated that different methods for minimizing effects of OTS, which is highly correlated across the brain within subject, produced no substantive change in our performance metrics. This is likely because OTS contaminates both reference and target regions and this contamination largely cancels out in SUVR data. Caution should be used when efforts to reduce OTS focus on target or reference regions in isolation as this may exacerbate OTS contamination in SUVR data.

YNICL Journal 2022 Journal Article

Causal structure discovery identifies risk factors and early brain markers related to evolution of white matter hyperintensities

Xinpeng Shen
Sheelakumari Raghavan
Scott A. Przybelski
Timothy G. Lesnick
Sisi Ma
Robert I. Reid
Jonathan Graff-Radford
Michelle M. Mielke

Our goal was to understand the complex relationship between age, sex, midlife risk factors, and early white matter changes measured by diffusion tensor imaging (DTI) and their role in the evolution of longitudinal white matter hyperintensities (WMH). We identified 1564 participants (1396 cognitively unimpaired, 151 mild cognitive impairment and 17 dementia participants) with age ranges of 30-90 years from the population-based sample of Mayo Clinic Study of Aging. We used computational causal structure discovery and regression analyses to evaluate the predictors of WMH and DTI, and to ascertain the mediating effect of DTI on WMH. We further derived causal graphs to understand the complex interrelationships between midlife protective factors, vascular risk factors, diffusion changes, and WMH. Older age, female sex, and hypertension were associated with higher baseline and progression of WMH as well as DTI measures (P ≤ 0.003). The effects of hypertension and sex on WMH were partially mediated by microstructural changes measured on DTI. Higher midlife physical activity was predictive of lower WMH through a direct impact on better white matter tract integrity as well as an indirect effect through reducing the risk of hypertension by lowering BMI. This study identified key risks factors, early brain changes, and pathways that may lead to the evolution of WMH.

YNIMG Journal 2022 Journal Article

Deep learning identifies brain structures that predict cognition and explain heterogeneity in cognitive aging

Krishnakant V. Saboo
Chang Hu
Yogatheesan Varatharajah
Scott A. Przybelski
Robert I. Reid
Christopher G. Schwarz
Jonathan Graff-Radford
David S. Knopman

Specific brain structures (gray matter regions and white matter tracts) play a dominant role in determining cognitive decline and explain the heterogeneity in cognitive aging. Identification of these structures is crucial for screening of older adults at risk of cognitive decline. Using deep learning models augmented with a model-interpretation technique on data from 1432 Mayo Clinic Study of Aging participants, we identified a subset of brain structures that were most predictive of individualized cognitive trajectories and indicative of cognitively resilient vs. vulnerable individuals. Specifically, these structures explained why some participants were resilient to the deleterious effects of elevated brain amyloid and poor vascular health. Of these, medial temporal lobe and fornix, reflective of age and pathology-related degeneration, and corpus callosum, reflective of inter-hemispheric disconnection, accounted for 60% of the heterogeneity explained by the most predictive structures. Our results are valuable for identifying cognitively vulnerable individuals and for developing interventions for cognitive decline.

YNIMG Journal 2022 Journal Article

Face recognition from research brain PET: An unexpected PET problem

Christopher G. Schwarz
Walter K. Kremers
Val J. Lowe
Marios Savvides
Jeffrey L. Gunter
Matthew L. Senjem
Prashanthi Vemuri
Kejal Kantarci

It is well known that de-identified research brain images from MRI and CT can potentially be re-identified using face recognition; however, this has not been examined for PET images. We generated face reconstruction images of 182 volunteers using amyloid, tau, and FDG PET scans, and we measured how accurately commercial face recognition software (Microsoft Azure's Face API) automatically matched them with the individual participants' face photographs. We then compared this accuracy with the same experiments using participants' CT and MRI. Face reconstructions from PET images from PET/CT scanners were correctly matched at rates of 42% (FDG), 35% (tau), and 32% (amyloid), while CT were matched at 78% and MRI at 97-98%. We propose that these recognition rates are high enough that research studies should consider using face de-identification ("de-facing") software on PET images, in addition to CT and structural MRI, before data sharing. We also updated our mri_reface de-identification software with extended functionality to replace face imagery in PET and CT images. Rates of face recognition on de-faced images were reduced to 0-4% for PET, 5% for CT, and 8% for MRI. We measured the effects of de-facing on regional amyloid PET measurements from two different measurement pipelines (PETSurfer/FreeSurfer 6.0, and one in-house method based on SPM12 and ANTs), and these effects were small: ICC values between de-faced and original images were > 0.98, biases were <2%, and median relative errors were < 2%. Effects on global amyloid PET SUVR measurements were even smaller: ICC values were 1.00, biases were <0.5%, and median relative errors were also <0.5%.

YNIMG Journal 2021 Journal Article

Associations of quantitative susceptibility mapping with Alzheimer's disease clinical and imaging markers

Petrice M. Cogswell
Heather J. Wiste
Matthew L. Senjem
Jeffrey L. Gunter
Stephen D. Weigand
Christopher G. Schwarz
Arvin Arani
Terry M. Therneau

Altered iron metabolism has been hypothesized to be associated with Alzheimer's disease pathology, and prior work has shown associations between iron load and beta amyloid plaques. Quantitative susceptibility mapping (QSM) is a recently popularized MR technique to infer local tissue susceptibility secondary to the presence of iron as well as other minerals. Greater QSM values imply greater iron concentration in tissue. QSM has been used to study relationships between cerebral iron load and established markers of Alzheimer's disease, however relationships remain unclear. In this work we study QSM signal characteristics and associations between susceptibility measured on QSM and established clinical and imaging markers of Alzheimer's disease. The study included 421 participants (234 male, median age 70 years, range 34-97 years) from the Mayo Clinic Study of Aging and Alzheimer's Disease Research Center; 296 (70%) had a diagnosis of cognitively unimpaired, 69 (16%) mild cognitive impairment, and 56 (13%) amnestic dementia. All participants had multi-echo gradient recalled echo imaging, PiB amyloid PET, and Tauvid tau PET. Variance components analysis showed that variation in cortical susceptibility across participants was low. Linear regression models were fit to assess associations with regional susceptibility. Expected increases in susceptibility were found with older age and cognitive impairment in the deep and inferior gray nuclei (pallidum, putamen, substantia nigra, subthalamic nucleus) (betas: 0.0017 to 0.0053 ppm for a 10 year increase in age, p = 0.03 to <0.001; betas: 0.0021 to 0.0058 ppm for a 5 point decrease in Short Test of Mental Status, p = 0.003 to p<0.001). Effect sizes in cortical regions were smaller, and the age associations were generally negative. Higher susceptibility was significantly associated with higher amyloid PET SUVR in the pallidum and putamen (betas: 0.0029 and 0.0012 ppm for a 20% increase in amyloid PET, p = 0.05 and 0.02, respectively), higher tau PET in the basal ganglia with the largest effect size in the pallidum (0.0082 ppm for a 20% increase in tau PET, p<0.001), and with lower cortical gray matter volume in the medial temporal lobe (0.0006 ppm for a 20% decrease in volume, p = 0.03). Overall, these findings suggest that susceptibility in the deep and inferior gray nuclei, particularly the pallidum and putamen, may be a marker of cognitive decline, amyloid deposition, and off-target binding of the tau ligand. Although iron has been demonstrated in amyloid plaques and in association with neurodegeneration, it is of insufficient quantity to be reliably detected in the cortex using this implementation of QSM.

YNIMG Journal 2021 Journal Article

Changing the face of neuroimaging research: Comparing a new MRI de-facing technique with popular alternatives

Christopher G. Schwarz
Walter K. Kremers
Heather J. Wiste
Jeffrey L. Gunter
Prashanthi Vemuri
Anthony J. Spychalla
Kejal Kantarci
Aaron P. Schultz

Recent advances in automated face recognition algorithms have increased the risk that de-identified research MRI scans may be re-identifiable by matching them to identified photographs using face recognition. A variety of software exist to de-face (remove faces from) MRI, but their ability to prevent face recognition has never been measured and their image modifications can alter automated brain measurements. In this study, we compared three popular de-facing techniques and introduce our mri_reface technique designed to minimize effects on brain measurements by replacing the face with a population average, rather than removing it. For each technique, we measured 1) how well it prevented automated face recognition (i.e. effects on exceptionally-motivated individuals) and 2) how it altered brain measurements from SPM12, FreeSurfer, and FSL (i.e. effects on the average user of de-identified data). Before de-facing, 97% of scans from a sample of 157 volunteers were correctly matched to photographs using automated face recognition. After de-facing with popular software, 28-38% of scans still retained enough data for successful automated face matching. Our proposed mri_reface had similar performance with the best existing method (fsl_deface) at preventing face recognition (28-30%) and it had the smallest effects on brain measurements in more pipelines than any other, but these differences were modest.

YNIMG Journal 2021 Journal Article

Relationships between β-amyloid and tau in an elderly population: An accelerated failure time model

Terry M. Therneau
David S. Knopman
Val J. Lowe
Hugo Botha
Jonathan Graff-Radford
David T. Jones
Prashanthi Vemuri
Michelle M. Mielke

Using positron emission tomography (PET)-derived amyloid and tau measurements from 1,495 participants, we explore the evolution of these values over time via an accelerated failure time (AFT) model. The AFT model assumes a shared pattern of progression, but one which is shifted earlier or later in time for each individual; an individual's time shift for amyloid and for tau are assumed to be linked. The resulting pattern for each outcome consists of an earlier indolent phase followed by sharp progression of the accumulation rate. APOE ε4 shifts the amyloid curve leftward (earlier) by 6.1 years, and the tau curve leftward by 2.6 years. Female sex shifts the amyloid curve leftward by 2.4 years and the tau curve leftward by 2.6 years. Per-person shifts (i.e., the individual's deviation from the population mean) for the onset of amyloid accumulation ranged from 13 years earlier to 13 years later (10th to 90th percentile) than average and 11 years earlier to 14 years later for tau, with an estimated correlation of 0.49. The average delay between amyloid increase and tau increase was 13.3 years.

YNIMG Journal 2021 Journal Article

Selecting software pipelines for change in flortaucipir SUVR: Balancing repeatability and group separation

Christopher G. Schwarz
Terry M. Therneau
Stephen D. Weigand
Jeffrey L. Gunter
Val J. Lowe
Scott A. Przybelski
Matthew L. Senjem
Hugo Botha

Since tau PET tracers were introduced, investigators have quantified them using a wide variety of automated methods. As longitudinal cohort studies acquire second and third time points of serial within-person tau PET data, determining the best pipeline to measure change has become crucial. We compared a total of 415 different quantification methods (each a combination of multiple options) according to their effects on a) differences in annual SUVR change between clinical groups, and b) longitudinal measurement repeatability as measured by the error term from a linear mixed-effects model. Our comparisons used MRI and Flortaucipir scans of 97 Mayo Clinic study participants who clinically either: a) were cognitively unimpaired, or b) had cognitive impairments that were consistent with Alzheimer's disease pathology. Tested methods included cross-sectional and longitudinal variants of two overarching pipelines (FreeSurfer 6.0, and an in-house pipeline based on SPM12), three choices of target region (entorhinal, inferior temporal, and a temporal lobe meta-ROI), five types of partial volume correction (PVC) (none, two-compartment, three-compartment, geometric transfer matrix (GTM), and a tau-specific GTM variant), seven choices of reference region (cerebellar crus, cerebellar gray matter, whole cerebellum, pons, supratentorial white matter, eroded supratentorial WM, and a composite of eroded supratentorial WM, pons, and whole cerebellum), two choices of region masking (GM or GM and WM), and two choices of statistic (voxel-wise mean vs. median). Our strongest findings were: 1) larger temporal-lobe target regions greatly outperformed entorhinal cortex (median sample size estimates based on a hypothetical clinical trial were 520-526 vs. 1740); 2) longitudinal processing pipelines outperformed cross-sectional pipelines (median sample size estimates were 483 vs. 572); and 3) reference regions including supratentorial WM outperformed traditional cerebellar and pontine options (median sample size estimates were 370 vs. 559). Altogether, our results favored longitudinally SUVR methods and a temporal-lobe meta-ROI that includes adjacent (juxtacortical) WM, a composite reference region (eroded supratentorial WM + pons + whole cerebellum), 2-class voxel-based PVC, and median statistics.

YNICL Journal 2018 Journal Article

Regional cortical perfusion on arterial spin labeling MRI in dementia with Lewy bodies: Associations with clinical severity, glucose metabolism and tau PET

Zuzana Nedelska
Matthew L. Senjem
Scott A. Przybelski
Timothy G. Lesnick
Val J. Lowe
Bradley F. Boeve
Arvin Arani
Prashanthi Vemuri

Visually preserved metabolism in posterior cingulate cortex relative to hypometabolism in precuneus and cuneus, the cingulate island sign, is a feature of dementia with Lewy bodies (DLB) on FDG-PET. Lower cingulate island sign ratio (posterior cingulate cortex/cuneus+precuneus; FDG-CISr) values have been associated with a higher Braak neurofibrillary tangle stage in autopsied DLB. Using voxel-wise analysis, we assessed the patterns of regional cortical perfusion and metabolism, and using an atlas-based approach, we measured perfusion cingulate island sign ratio on arterial spin labeling MRI (ASL-CISr), and its associations with FDG-CISr, uptake on tau-PET and clinical severity in DLB. Our study sample (n = 114) included clinically probable DLB patients (n = 19), age-matched patients with probable Alzheimer's disease dementia (AD; n = 19) and matched controls (n = 76) who underwent MRI with 3-dimensional pseudo-continuous arterial spin labeling, 18F-FDG-PET and 18F-AV-1451 tau PET. Patterns of cortical perfusion and metabolism were derived from quantitative maps using Statistical Parametric Mapping. DLB patients showed hypoperfusion on ASL-MRI in precuneus, cuneus and posterior parieto-occipital cortices, compared to controls, and relatively spared posterior cingulate gyrus, similar to pattern of hypometabolism on FDG-PET. DLB patients had higher ASL-CISr and FDG-CISr than AD patients (p <0. 001). ASL-CISr correlated with FDG-CISr in DLB patients (r = 0. 67; p =0. 002). Accuracy of distinguishing DLB from AD patients was 0. 80 for ASL-CISr and 0. 91 for FDG-CISr. Lower ASL-CISr was moderately associated with a higher composite medial temporal AV-1451 uptake (r = −0. 50; p =0. 03) in DLB. Lower perfusion in precuneus and cuneus was associated with worse global clinical scores. In summary, the pattern of cortical hypoperfusion on ASL-MRI is similar to hypometabolism on FDG-PET, and respective cingulate island sign ratios correlate with each other in DLB. Non-invasive and radiotracer-free ASL-MRI may be further developed as a tool for the screening and diagnostic evaluation of DLB patients in a variety of clinical settings where FDG-PET is not accessible.

YNIMG Journal 2017 Journal Article

Optimizing PiB-PET SUVR change-over-time measurement by a large-scale analysis of longitudinal reliability, plausibility, separability, and correlation with MMSE

Christopher G. Schwarz
Matthew L. Senjem
Jeffrey L. Gunter
Nirubol Tosakulwong
Stephen D. Weigand
Bradley J. Kemp
Anthony J. Spychalla
Prashanthi Vemuri

Quantitative measurements of change in β-amyloid load from Positron Emission Tomography (PET) images play a critical role in clinical trials and longitudinal observational studies of Alzheimer's disease. These measurements are strongly affected by methodological differences between implementations, including choice of reference region and use of partial volume correction, but there is a lack of consensus for an optimal method. Previous works have examined some relevant variables under varying criteria, but interactions between them prevent choosing a method via combined meta-analysis. In this work, we present a thorough comparison of methods to measure change in β-amyloid over time using Pittsburgh Compound B (PiB) PET imaging. Methods We compare 1, 024 different automated software pipeline implementations with varying methodological choices according to four quality metrics calculated over three-timepoint longitudinal trajectories of 129 subjects: reliability (straightness/variance); plausibility (lack of negative slopes); ability to predict accumulator/non-accumulator status from baseline value; and correlation between change in β-amyloid and change in Mini Mental State Exam (MMSE) scores. Results and conclusion From this analysis, we show that an optimal longitudinal measure of β-amyloid from PiB should use a reference region that includes a combination of voxels in the supratentorial white matter and those in the whole cerebellum, measured using two-class partial volume correction in the voxel space of each subject's corresponding anatomical MR image.

YNICL Journal 2016 Journal Article

A large-scale comparison of cortical thickness and volume methods for measuring Alzheimer's disease severity

Christopher G. Schwarz
Jeffrey L. Gunter
Heather J. Wiste
Scott A. Przybelski
Stephen D. Weigand
Chadwick P. Ward
Matthew L. Senjem
Prashanthi Vemuri

Alzheimer's disease (AD) researchers commonly use MRI as a quantitative measure of disease severity. Historically, hippocampal volume has been favored. Recently, “AD signature” measurements of gray matter (GM) volumes or cortical thicknesses have gained attention. Here, we systematically evaluate multiple thickness- and volume-based candidate-methods side-by-side, built using the popular FreeSurfer, SPM, and ANTs packages, according to the following criteria: (a) ability to separate clinically normal individuals from those with AD; (b) (extent of) correlation with head size, a nuisance covariatel (c) reliability on repeated scans; and (d) correlation with Braak neurofibrillary tangle stage in a group with autopsy. We show that volume- and thickness-based measures generally perform similarly for separating clinically normal from AD populations, and in correlation with Braak neurofibrillary tangle stage at autopsy. Volume-based measures are generally more reliable than thickness measures. As expected, volume measures are highly correlated with head size, while thickness measures are generally not. Because approaches to statistically correcting volumes for head size vary and may be inadequate to deal with this underlying confound, and because our goal is to determine a measure which can be used to examine age and sex effects in a cohort across a large age range, we thus recommend thickness-based measures. Ultimately, based on these criteria and additional practical considerations of run-time and failure rates, we recommend an AD signature measure formed from a composite of thickness measurements in the entorhinal, fusiform, parahippocampal, mid-temporal, inferior-temporal, and angular gyrus ROIs using ANTs with input segmentations from SPM12.

YNIMG Journal 2015 Journal Article

Accelerated vs. unaccelerated serial MRI based TBM-SyN measurements for clinical trials in Alzheimer's disease

Prashanthi Vemuri
Matthew L. Senjem
Jeffrey L. Gunter
Emily S. Lundt
Nirubol Tosakulwong
Stephen D. Weigand
Bret J. Borowski
Matt A. Bernstein

Objective Our primary objective was to compare the performance of unaccelerated vs. accelerated structural MRI for measuring disease progression using serial scans in Alzheimer's disease (AD). Methods We identified cognitively normal (CN), early mild cognitive impairment (EMCI), late mild cognitive impairment (LMCI) and AD subjects from all available Alzheimer's Disease Neuroimaging Initiative (ADNI) subjects with usable pairs of accelerated and unaccelerated scans. There were a total of 696 subjects with baseline and 3month scans, 628 subjects with baseline and 6month scans and 464 subjects with baseline and 12month scans available. We employed the Symmetric Diffeomorphic Image Normalization method (SyN) for normalization of the serial scans to obtain tensor based morphometry (TBM) maps which indicate the structural changes between pairs of scans. We computed a TBM-SyN summary score of annualized structural changes over 31 regions of interest (ROIs) that are characteristically affected in AD. TBM-SyN scores were computed using accelerated and unaccelerated scan pairs and compared in terms of agreement, group-wise discrimination, and sample size estimates for a hypothetical therapeutic trial. Results We observed a number of systematic differences between TBM-SyN scores computed from accelerated and unaccelerated pairs of scans. TBM-SyN scores computed from accelerated scans tended to have overall higher estimated values than those from unaccelerated scans. However, the performance of accelerated scans was comparable to unaccelerated scans in terms of discrimination between clinical groups and sample sizes required in each clinical group for a therapeutic trial. We also found that the quality of both accelerated vs. unaccelerated scans were similar. Conclusions Accelerated scanning protocols reduce scan time considerably. Their group-wise discrimination and sample size estimates were comparable to those obtained with unaccelerated scans. The two protocols did not produce interchangeable TBM-SyN estimates, so it is arguably important to use either accelerated pairs of scans or unaccelerated pairs of scans throughout the study duration.

YNIMG Journal 2014 Journal Article

Improved DTI registration allows voxel-based analysis that outperforms Tract-Based Spatial Statistics

Christopher G. Schwarz
Robert I. Reid
Jeffrey L. Gunter
Matthew L. Senjem
Scott A. Przybelski
Samantha M. Zuk
Jennifer L. Whitwell
Prashanthi Vemuri

Tract-Based Spatial Statistics (TBSS) is a popular software pipeline to coregister sets of diffusion tensor Fractional Anisotropy (FA) images for performing voxel-wise comparisons. It is primarily defined by its skeleton projection step intended to reduce effects of local misregistration. A white matter “skeleton” is computed by morphological thinning of the inter-subject mean FA, and then all voxels are projected to the nearest location on this skeleton. Here we investigate several enhancements to the TBSS pipeline based on recent advances in registration for other modalities, principally based on groupwise registration with the ANTS-SyN algorithm. We validate these enhancements using simulation experiments with synthetically-modified images. When used with these enhancements, we discover that TBSS's skeleton projection step actually reduces algorithm accuracy, as the improved registration leaves fewer errors to warrant correction, and the effects of this projection's compromises become stronger than those of its benefits. In our experiments, our proposed pipeline without skeleton projection is more sensitive for detecting true changes and has greater specificity in resisting false positives from misregistration. We also present comparative results of the proposed and traditional methods, both with and without the skeleton projection step, on three real-life datasets: two comparing differing populations of Alzheimer's disease patients to matched controls, and one comparing progressive supranuclear palsy patients to matched controls. The proposed pipeline produces more plausible results according to each disease's pathophysiology.

YNIMG Journal 2012 Journal Article

Diagnostic neuroimaging across diseases

Stefan Klöppel
Ahmed Abdulkadir
Clifford R. Jack
Nikolaos Koutsouleris
Janaina Mourão-Miranda
Prashanthi Vemuri

Fully automated classification algorithms have been successfully applied to diagnose a wide range of neurological and psychiatric diseases. They are sufficiently robust to handle data from different scanners for many applications and in specific cases outperform radiologists. This article provides an overview of current applications taking structural imaging in Alzheimer's disease and schizophrenia as well as functional imaging to diagnose depression as examples. In this context, we also report studies aiming to predict the future course of the disease and the response to treatment for the individual. This has obvious clinical relevance but is also important for the design of treatment studies that may aim to include a cohort with a predicted fast disease progression to be more sensitive to detect treatment effects. In the second part, we present our own opinions on i) the role these classification methods can play in the clinical setting; ii) where their limitations are at the moment and iii) how those can be overcome. Specifically, we discuss strategies to deal with disease heterogeneity, diagnostic uncertainties, a probabilistic framework for classification and multi-class classification approaches.

YNIMG Journal 2011 Journal Article

Antemortem differential diagnosis of dementia pathology using structural MRI: Differential-STAND

Prashanthi Vemuri
Gyorgy Simon
Kejal Kantarci
Jennifer L. Whitwell
Matthew L. Senjem
Scott A. Przybelski
Jeffrey L. Gunter
Keith A. Josephs

The common neurodegenerative pathologies underlying dementia are Alzheimer's disease (AD), Lewy body disease (LBD) and frontotemporal lobar degeneration (FTLD). Our aim was to identify patterns of atrophy unique to each of these diseases using antemortem structural MRI scans of pathologically confirmed dementia cases and build an MRI-based differential diagnosis system. Our approach of creating atrophy maps using structural MRI and applying them for classification of new incoming patients is labeled Differential-STAND (Differential Diagnosis Based on Structural Abnormality in Neurodegeneration). Pathologically confirmed subjects with a single dementing pathologic diagnosis who had an MRI at the time of clinical diagnosis of dementia were identified: 48 AD, 20 LBD, 47 FTLD-TDP (pathology-confirmed FTLD with TDP-43). Gray matter density in 91 regions-of-interest was measured in each subject and adjusted for head size and age using a database of 120 cognitively normal elderly. The atrophy patterns in each dementia type when compared to pathologically confirmed controls mirrored known disease-specific anatomic patterns: AD-temporoparietal association cortices and medial temporal lobe; FTLD-TDP-frontal and temporal lobes and LBD-bilateral amygdalae, dorsal midbrain and inferior temporal lobes. Differential-STAND based classification of each case was done based on a mixture model generated using bisecting k-means clustering of the information from the MRI scans. Leave-one-out classification showed reasonable performance compared to the autopsy gold standard and clinical diagnosis: AD (sensitivity: 90. 7%; specificity: 84%), LBD (sensitivity: 78. 6%; specificity: 98. 8%) and FTLD-TDP (sensitivity: 84. 4%; specificity: 93. 8%). The proposed approach establishes a direct a priori relationship between specific topographic patterns on MRI and “gold standard” of pathology which can then be used to predict underlying dementia pathology in new incoming patients.

YNIMG Journal 2011 Journal Article

Effects of hardware heterogeneity on the performance of SVM Alzheimer's disease classifier

Ahmed Abdulkadir
Bénédicte Mortamet
Prashanthi Vemuri
Clifford R. Jack
Gunnar Krueger
Stefan Klöppel

Fully automated machine learning methods based on structural magnetic resonance imaging (MRI) data can assist radiologists in the diagnosis of Alzheimer's disease (AD). These algorithms require large data sets to learn the separation of subjects with and without AD. Training and test data may come from heterogeneous hardware settings, which can potentially affect the performance of disease classification. A total of 518 MRI sessions from 226 healthy controls and 191 individuals with probable AD from the multicenter Alzheimer's Disease Neuroimaging Initiative (ADNI) were used to investigate whether grouping data by acquisition hardware (i. e. vendor, field strength, coil system) is beneficial for the performance of a support vector machine (SVM) classifier, compared to the case where data from different hardware is mixed. We compared the change of the SVM decision value resulting from (a) changes in hardware against the effect of disease and (b) changes resulting simply from rescanning the same subject on the same machine. Maximum accuracy of 87% was obtained with a training set of all 417 subjects. Classifiers trained with 95 subjects in each diagnostic group and acquired with heterogeneous scanner settings had an empirical detection accuracy of 84. 2±2. 4% when tested on an independent set of the same size. These results mirror the accuracy reported in recent studies. Encouragingly, classifiers trained on images acquired with homogenous and heterogeneous hardware settings had equivalent cross-validation performances. Two scans of the same subject acquired on the same machine had very similar decision values and were generally classified into the same group. Higher variation was introduced when two acquisitions of the same subject were performed on two scanners with different field strengths. The variation was unbiased and similar for both diagnostic groups. The findings of the study encourage the pooling of data from different sites to increase the number of training samples and thereby improving performance of disease classifiers. Although small, a change in hardware could lead to a change of the decision value and thus diagnostic grouping. The findings of this study provide estimators for diagnostic accuracy of an automated disease diagnosis method involving scans acquired with different sets of hardware. Furthermore, we show that the level of confidence in the performance estimation significantly depends on the size of the training sample, and hence should be taken into account in a clinical setting.

YNIMG Journal 2011 Journal Article

Time-to-event voxel-based techniques to assess regional atrophy associated with MCI risk of progression to AD

Prashanthi Vemuri
Stephen D. Weigand
David S. Knopman
Kejal Kantarci
Bradley F. Boeve
Ronald C. Petersen
Clifford R. Jack

Objective When using imaging to predict time to progression from mild cognitive impairment (MCI) to Alzheimer's disease (AD), time-to-event statistical methods account for varying lengths of follow-up times among subjects whereas two-sample t-tests in voxel-based morphometry (VBM) do not. Our objectives were to apply a time-to-event voxel-based analytic method to identify regions on MRI where atrophy is associated with significantly increased risk of future progression to AD in subjects with MCI and to compare it to traditional voxel-level patterns obtained by applying two-sample methods. We also compared the power required to detect an association using time-to-event methods versus two-sample approaches. Methods Subjects with MCI at baseline were followed prospectively. The event of interest was clinical diagnosis of AD. Cox proportional hazards models adjusted for age, sex, and education were used to estimate the relative hazard of progression from MCI to AD based on rank-transformed voxel-level gray matter density (GMD) estimates. Results The greatest risk of progression to AD was associated with atrophy of the medial temporal lobes. Patients ranked at the 25th percentile of GMD in these regions had more than a doubling of risk of progression to AD at a given time point compared to patients at the 75th percentile. Power calculations showed the time-to-event approach to be more efficient than the traditional two-sample approach. Conclusions We present a new voxel-based analytic method that incorporates time-to-event statistical methods. In the context of a progressive disease like AD, time-to-event VBM seems more appropriate and powerful than traditional two-sample methods.

YNIMG Journal 2008 Journal Article

Alzheimer's disease diagnosis in individual subjects using structural MR images: Validation studies

Prashanthi Vemuri
Jeffrey L. Gunter
Matthew L. Senjem
Jennifer L. Whitwell
Kejal Kantarci
David S. Knopman
Bradley F. Boeve
Ronald C. Petersen

Objective To develop and validate a tool for Alzheimer's disease (AD) diagnosis in individual subjects using support vector machine (SVM)-based classification of structural MR (sMR) images. Background Libraries of sMR scans of clinically well characterized subjects can be harnessed for the purpose of diagnosing new incoming subjects. Methods One hundred ninety patients with probable AD were age- and gender-matched with 190 cognitively normal (CN) subjects. Three different classification models were implemented: Model I uses tissue densities obtained from sMR scans to give STructural Abnormality iNDex (STAND)-score; and Models II and III use tissue densities as well as covariates (demographics and Apolipoprotein E genotype) to give adjusted-STAND (aSTAND)-score. Data from 140 AD and 140 CN were used for training. The SVM parameter optimization and training were done by four-fold cross validation (CV). The remaining independent sample of 50 AD and 50 CN was used to obtain a minimally biased estimate of the generalization error of the algorithm. Results The CV accuracy of Model II and Model III aSTAND-scores was 88. 5% and 89. 3%, respectively, and the developed models generalized well on the independent test data sets. Anatomic patterns best differentiating the groups were consistent with the known distribution of neurofibrillary AD pathology. Conclusions This paper presents preliminary evidence that application of SVM-based classification of an individual sMR scan relative to a library of scans can provide useful information in individual subjects for diagnosis of AD. Including demographic and genetic information in the classification algorithm slightly improves diagnostic accuracy.

YNIMG Journal 2008 Journal Article

Antemortem MRI based STructural Abnormality iNDex (STAND)-scores correlate with postmortem Braak neurofibrillary tangle stage

Prashanthi Vemuri
Jennifer L. Whitwell
Kejal Kantarci
Keith A. Josephs
Joseph E. Parisi
Maria S. Shiung
David S. Knopman
Bradley F. Boeve

The clinical diagnosis of Alzheimer's disease (AD) does not exactly match the pathological findings at autopsy in every subject. Therefore, in-vivo imaging measures, such as Magnetic Resonance Imaging (MRI) that reflect underlying pathology, would be clinically useful independent supplementary measures of disease stage. We have developed an algorithm that extracts atrophy information from individual patient's 3D MRI scans and assigns a STructural Abnormality iNDex (STAND)-score to the scan based on the degree of atrophy in comparison to patterns extracted from a large library of clinically well characterized AD and CN (cognitively normal) subject's MRI scans. STAND-scores can be adjusted for demographics to give adjusted-STAND (aSTAND)-scores which are >0 for subjects with brains identified as abnormal by the algorithm. Since histopathological findings are considered to represent the “ground truth”, our objective was to assess the sensitivity of aSTAND-scores to pathological AD staging. This was done by comparing antemortem MRI based aSTAND-scores with postmortem grading of disease severity in 101 subjects who had both antemortem MRI and postmortem Braak neurofibrillary tangle (NFT) staging. We found a rank correlation of 0. 62 (p <0. 0001) between Braak NFT stage and aSTAND-scores. The results show that optimally extracted information from MRI scans such as STAND-scores accurately capture the severity of neuronal pathology and can be used as an independent approximate surrogate marker for in-vivo pathological staging as well as for early identification of AD in individual subjects.