Voxel-based morphometry in single subjects without a scanner-specific normal database using a convolutional neural network.

OBJECTIVES: Reliable detection of disease-specific atrophy in individual T1w-MRI by voxel-based morphometry (VBM) requires scanner-specific normal databases (NDB), which often are not available. The aim of this retrospective study was to design, train, and test a deep convolutional neural network (CNN) for single-subject VBM without the need for a NDB (CNN-VBM). MATERIALS AND METHODS: The training dataset comprised 8945 T1w scans from 65 different scanners. The gold standard VBM maps were obtained by conventional VBM with a scanner-specific NDB for each of the 65 scanners. CNN-VBM was tested in an independent dataset comprising healthy controls (n = 37) and subjects with Alzheimer's disease (AD, n = 51) or frontotemporal lobar degeneration (FTLD, n = 30). A scanner-specific NDB for the generation of the gold standard VBM maps was available also for the test set. The technical performance of CNN-VBM was characterized by the Dice coefficient of CNN-VBM maps relative to VBM maps from scanner-specific VBM. For clinical testing, VBM maps were categorized visually according to the clinical diagnoses in the test set by two independent readers, separately for both VBM methods. RESULTS: The VBM maps from CNN-VBM were similar to the scanner-specific VBM maps (median Dice coefficient 0.85, interquartile range [0.81, 0.90]). Overall accuracy of the visual categorization of the VBM maps for the detection of AD or FTLD was 89.8% for CNN-VBM and 89.0% for scanner-specific VBM. CONCLUSION: CNN-VBM without NDB provides a similar performance in the detection of AD- and FTLD-specific atrophy as conventional VBM. CLINICAL RELEVANCE STATEMENT: A deep convolutional neural network for voxel-based morphometry eliminates the need of scanner-specific normal databases without relevant performance loss and, therefore, could pave the way for the widespread clinical use of voxel-based morphometry to support the diagnosis of neurodegenerative diseases. KEY POINTS: • The need of normal databases is a barrier for widespread use of voxel-based brain morphometry. • A convolutional neural network achieved a similar performance for detection of atrophy than conventional voxel-based morphometry. • Convolutional neural networks can pave the way for widespread clinical use of voxel-based morphometry.

Automatic segmentation of the thalamus using a massively trained 3D convolutional neural network: higher sensitivity for the detection of reduced thalamus volume by improved inter-scanner stability.

OBJECTIVES: To develop an automatic method for accurate and robust thalamus segmentation in T1w-MRI for widespread clinical use without the need for strict harmonization of acquisition protocols and/or scanner-specific normal databases. METHODS: A three-dimensional convolutional neural network (3D-CNN) was trained on 1975 T1w volumes from 170 MRI scanners using thalamus masks generated with FSL-FIRST as ground truth. Accuracy was evaluated with 18 manually labeled expert masks. Intra- and inter-scanner test-retest stability were assessed with 477 T1w volumes of a single healthy subject scanned on 123 MRI scanners. The sensitivity of 3D-CNN-based volume estimates for the detection of thalamus atrophy was tested with 127 multiple sclerosis (MS) patients and a normal database comprising 4872 T1w volumes from 160 scanners. The 3D-CNN was compared with a publicly available 2D-CNN (FastSurfer) and FSL. RESULTS: The Dice similarity coefficient of the automatic thalamus segmentation with manual expert delineation was similar for all tested methods (3D-CNN and FastSurfer 0.86 ± 0.02, FSL 0.87 ± 0.02). The standard deviation of the single healthy subject's thalamus volume estimates was lowest with 3D-CNN for repeat scans on the same MRI scanner (0.08 mL, FastSurfer 0.09 mL, FSL 0.15 mL) and for repeat scans on different scanners (0.28 mL, FastSurfer 0.62 mL, FSL 0.63 mL). The proportion of MS patients with significantly reduced thalamus volume was highest for 3D-CNN (24%, FastSurfer 16%, FSL 11%). CONCLUSION: The novel 3D-CNN allows accurate thalamus segmentation, similar to state-of-the-art methods, with considerably improved robustness with respect to scanner-related variability of image characteristics. This might result in higher sensitivity for the detection of disease-related thalamus atrophy. KEY POINTS: • A three-dimensional convolutional neural network was trained for automatic segmentation of the thalamus with a heterogeneous sample of T1w-MRI from 1975 patients scanned on 170 different scanners. • The network provided high accuracy for thalamus segmentation with manual segmentation by experts as ground truth. • Inter-scanner variability of thalamus volume estimates across different MRI scanners was reduced by more than 50%, resulting in increased sensitivity for the detection of thalamus atrophy.

Single-subject analysis of regional brain volumetric measures can be strongly influenced by the method for head size adjustment.

PURPOSE: Total intracranial volume (TIV) is often a nuisance covariate in MRI-based brain volumetry. This study compared two TIV adjustment methods with respect to their impact on z-scores in single subject analyses of regional brain volume estimates. METHODS: Brain parenchyma, hippocampus, thalamus, and TIV were segmented in a normal database comprising 5059 T1w images. Regional volume estimates were adjusted for TIV using the residual method or the proportion method. Age was taken into account by regression with both methods. TIV- and age-adjusted regional volumes were transformed to z-scores and then compared between the two adjustment methods. Their impact on the detection of thalamus atrophy was tested in 127 patients with multiple sclerosis. RESULTS: The residual method removed the association with TIV in all regions. The proportion method resulted in a switch of the direction without relevant change of the strength of the association. The reduction of physiological between-subject variability was larger with the residual method than with the proportion method. The difference between z-scores obtained with the residual method versus the proportion method was strongly correlated with TIV. It was larger than one z-score point in 5% of the subjects. The area under the ROC curve of the TIV- and age-adjusted thalamus volume for identification of multiple sclerosis patients was larger with the residual method than with the proportion method (0.84 versus 0.79). CONCLUSION: The residual method should be preferred for TIV and age adjustments of T1w-MRI-based brain volume estimates in single subject analyses.

Infratentorial lesions in multiple sclerosis patients: intra- and inter-rater variability in comparison to a fully automated segmentation using 3D convolutional neural networks.

OBJECTIVE: Automated quantification of infratentorial multiple sclerosis lesions on magnetic resonance imaging is clinically relevant but challenging. To overcome some of these problems, we propose a fully automated lesion segmentation algorithm using 3D convolutional neural networks (CNNs). METHODS: The CNN was trained on a FLAIR image alone or on FLAIR and T1-weighted images from 1809 patients acquired on 156 different scanners. An additional training using an extra class for infratentorial lesions was implemented. Three experienced raters manually annotated three datasets from 123 MS patients from different scanners. RESULTS: The inter-rater sensitivity (SEN) was 80% for supratentorial lesions but only 62% for infratentorial lesions. There was no statistically significant difference between the inter-rater SEN and the SEN of the CNN with respect to the raters. For supratentorial lesions, the CNN featured an intra-rater intra-scanner SEN of 0.97 (R1 = 0.90, R2 = 0.84) and for infratentorial lesion a SEN of 0.93 (R1 = 0.61, R2 = 0.73). CONCLUSION: The performance of the CNN improved significantly for infratentorial lesions when specifically trained on infratentorial lesions using a T1 image as an additional input and matches the detection performance of experienced raters. Furthermore, for infratentorial lesions the CNN was more robust against repeated scans than experienced raters. KEY POINTS: • A 3D convolutional neural network was trained on MRI data from 1809 patients (156 different scanners) for the quantification of supratentorial and infratentorial multiple sclerosis lesions. • Inter-rater variability was higher for infratentorial lesions than for supratentorial lesions. The performance of the 3D convolutional neural network (CNN) improved significantly for infratentorial lesions when specifically trained on infratentorial lesions using a T1 image as an additional input. • The detection performance of the CNN matches the detection performance of experienced raters.

Age-dependent cut-offs for pathological deep gray matter and thalamic volume loss using Jacobian integration.

INTRODUCTION: Several recent studies indicate that deep gray matter or thalamic volume loss (VL) might be promising surrogate markers of disease activity in multiple sclerosis (MS) patients. To allow applying these markers to individual MS patients in clinical routine, age-dependent cut-offs distinguishing physiological from pathological VL and an estimation of the measurement error, which provides the confidence of the result, are to be defined. METHODS: Longitudinal MRI scans of the following cohorts were analyzed in this study: 189 healthy controls (HC) (mean age 54 years, 22% female), 98 MS patients from Zurich university hospital (mean age 34 years, 62% female), 33 MS patients from Dresden university hospital (mean age 38 years, 60% female), and publicly available reliability data sets consisting of 162 short-term MRI scan-rescan pairs with scan intervals of days or few weeks. Percentage annualized whole brain volume loss (BVL), gray matter (GM) volume loss (GMVL), deep gray matter volume loss (deep GMVL), and thalamic volume loss (ThalaVL) were computed deploying the Jacobian integration (JI) method. BVL was additionally computed using Siena, an established method used in many Phase III drug trials. A linear mixed effect model was used to estimate the measurement error as the standard deviation (SD) of model residuals of all 162 scan-rescan pairs For estimation of age-dependent cut-offs, a quadratic regression function between age and the corresponding annualized VL values of the HC was computed. The 5th percentile was defined as the threshold for pathological VL per year since 95% of HC subjects exhibit a less pronounced VL for a given age. For the MS patients BVL, GMVL, deep GMVL, and ThalaVL were mutually compared and a paired t-test was used to test whether there are systematic differences in VL between these brain regions. RESULTS: Siena and JI showed a high agreement for BVL measures, with a median absolute difference of 0.1% and a correlation coefficient of r = 0.78. Siena and GMVL showed a similar standard deviation (SD) of the scan-rescan error of 0.28% and 0.29%, respectively. For deep GMVL, ThalaVL the SD of the scan-rescan error was slightly higher (0.43% and 0.5%, respectively). Among the HC the thalamus showed the highest mean VL (-0.16%, -0.39%, and -0.59% at ages 35, 55, and 75, respectively). Corresponding cut-offs for a pathological VL/year were -0.68%, -0.91%, and -1.11%. The MS cohorts did not differ in BVL and GMVL. However, both MS cohorts showed a significantly (p = 0.05) stronger deep GMVL than BVL per year. CONCLUSION: It might be methodologically feasible to assess deep GMVL using JI in individual MS patients. However, age and the measurement error need to be taken into account. Furthermore, deep GMVL may be used as a complementary marker to BVL since MS patients exhibit a significantly stronger deep GMVL than BVL.

MRI-Based Brain Volumetry at a Single Time Point Complements Clinical Evaluation of Patients With Multiple Sclerosis in an Outpatient Setting.

Purpose: Thalamic atrophy and whole brain atrophy in multiple sclerosis (MS) are associated with disease progression. The motivation of this study was to propose and evaluate a new grouping scheme which is based on MS patients' whole brain and thalamus volumes measured on MRI at a single time point. Methods: In total, 185 MS patients (128 relapsing-remitting (RRMS) and 57 secondary-progressive MS (SPMS) patients) were included from an outpatient facility. Whole brain parenchyma (BP) and regional brain volumes were derived from single time point MRI T1 images. Standard scores (z-scores) were computed by comparing individual brain volumes against corresponding volumes from healthy controls. A z-score cut-off of -1.96 was applied to separate pathologically atrophic from normal brain volumes for thalamus and whole BP (accepting a 2.5% error probability). Subgroup differences with respect to the Symbol Digit Modalities Test (SDMT) and the Expanded Disability Status Scale (EDSS) were assessed. Results: Except for two, all MS patients showed either no atrophy (group 0: 61 RRMS patients, 10 SPMS patients); thalamic but no BP atrophy (group 1: 37 RRMS patients; 18 SPMS patients) or thalamic and BP atrophy (group 2: 28 RRMS patients; 29 SPMS patients). RRMS patients without atrophy and RRMS patients with thalamic atrophy did not differ in EDSS, however, patients with thalamus and BP atrophy showed significantly higher EDSS scores than patients in the other groups. Conclusion: MRI-based brain volumetry at a single time point is able to reliably distinguish MS patients with isolated thalamus atrophy (group 1) from those without brain atrophy (group 0). MS patients with isolated thalamus atrophy might be at risk for the development of widespread atrophy and disease progression. Since RRMS patients in group 0 and 1 are clinically not distinguishable, the proposed grouping may aid identification of RRMS patients at risk of disease progression and thus complement clinical evaluation in the routine patient care.

Impact of plasma glucose level on the pattern of brain FDG uptake and the predictive power of FDG PET in mild cognitive impairment.

PURPOSE: Increased blood glucose level (BGL) has been reported to cause alterations of FDG uptake in the brain that mimic Alzheimer's disease (AD), even within the "acceptable" range ≤ 160 mg/dl. The aim of this study was (i) to confirm this in a large sample of well-characterized normal control (NC) subjects, and (ii) to analyze its impact on the prediction of AD dementia (ADD) in mild cognitive impairment (MCI). METHODS: The study included NCs from the Alzheimer's Disease Neuroimaging Initiative (ADNI) that were cognitively stable for ≥36 months after PET (n = 87, 74.2 ± 5.3 y), and ADNI MCIs with ≥36 months follow-up if not progressed to ADD earlier (n = 323, 71.1 ± 7.1 y). Seventy-three of the MCIs had progressed to ADD within 36 months. In the NCs, parenchyma-scaled FDG uptake was tested for clusters of correlation with BGL on the family-wise, error-corrected 5% level. In the MCIs, ROC analysis was used to assess the power of FDG uptake in a predefined AD-typical region for prediction of ADD. ROC analysis was repeated after correcting mean FDG uptake in the AD-typical region for BGL based on linear regression in the NCs. RESULTS: In the NCs, BGL (59-149 mg/dl) was negatively correlated with FDG uptake in a cluster comprising the occipital cortex and precuneus but sparing the posterior cingulate, independent of amyloid-ß and ApoE4 status. In the MCIs, FDG uptake in the AD-typical region provided an area of 0.804 under the ROC curve for prediction of ADD. Correcting FDG uptake in the AD-typical region for BGL (55-189 mg/dl) did not change predictive performance (area = 0.808, p = 0.311). CONCLUSIONS: Increasing BGL is associated with relative reduction of FDG uptake in the posterior cortex even in the "acceptable" range ≤ 160 mg/dl. The BGL-associated pattern is similar to the typical AD pattern, but not identical. BGL-associated variability of regional FDG uptake has no relevant impact on the power of FDG PET for prediction of MCI-to-ADD progression.

Hypermetabolism in the hippocampal formation of cognitively impaired patients indicates detrimental maladaptation.

Structural deterioration and volume loss of the hippocampal formation is observed in many diseases associated with memory decline. Paradoxically, glucose metabolism of the hippocampal formation can be increased at the same time. This might be a consequence of compensatory (beneficial) or maladaptive (detrimental) mechanisms. Aim of this study was to differentiate between compensation and maladaptation by analyzing the association between glucose metabolism in the hippocampal formation measured by positron emission tomography with the glucose analogue 18F-fluorodeoxyglucose and cognitive performance as characterized by the extended Consortium to Establish a Registry for Alzheimer's Disease test battery in a sample of 87 patients (81.8 ± 5.4 years) with mild cognitive impairment or mild dementia and varying etiological diagnoses. Glucose metabolism in the hippocampal formation was negatively correlated with the performance in several cognitive subdomains, most pronounced for verbal semantic fluency, independent of overall neuronal dysfunction, presence of clinical Alzheimer's disease, and overall cognitive performance. This finding provides evidence that increased glucose metabolism in the hippocampal formation of cognitively impaired patients indicates detrimental maladaptation rather than a beneficial compensatory reaction. Excess glucose metabolism in the hippocampal formation might be a useful therapeutic target in these patients.

Prediction of Alzheimer's Dementia in Patients with Amnestic Mild Cognitive Impairment in Clinical Routine: Incremental Value of Biomarkers of Neurodegeneration and Brain Amyloidosis Added Stepwise to Cognitive Status.

The aim of this study was to evaluate the incremental benefit of biomarkers for prediction of Alzheimer's disease dementia (ADD) in patients with mild cognitive impairment (MCI) when added stepwise in the order of their collection in clinical routine. The model started with cognitive status characterized by the ADAS-13 score. Hippocampus volume (HV), cerebrospinal fluid (CSF) phospho-tau (pTau), and the FDG t-sum score in an AD meta-region-of-interest were compared as neurodegeneration markers. CSF-Aß1-42 was used as amyloidosis marker. The incremental prognostic benefit from these markers was assessed by stepwise Kaplan-Meier survival analysis in 402 ADNI MCI subjects. Predefined cutoffs were used to dichotomize patients as 'negative' or 'positive' for AD characteristic alteration with respect to each marker. Among the neurodegeneration markers, CSF-pTau provided the best incremental risk stratification when added to ADAS-13. FDG PET outperformed HV only in MCI subjects with relatively preserved cognition. Adding CSF-Aß provided further risk stratification in pTau-positive subjects, independent of their cognitive status. Stepwise integration of biomarkers allows stepwise refinement of risk estimates for MCI-to-ADD progression. Incremental benefit strongly depends on the patient's status according to the preceding diagnostic steps. The stepwise Kaplan-Meier curves might be useful to optimize diagnostic workflow in individual patients.

Alzheimer's Disease Diagnosis Relies on a Twofold Clinical-Biological Algorithm: Three Memory Clinic Case Reports.

The International Working Group recently provided revised criteria of Alzheimer's disease (AD) proposing that the diagnosis of typical amnesic AD should be established by a clinical-biological signature, defined by the phenotype of an "amnesic syndrome of the hippocampal type" (ASHT) combined with positive in vivo evidence of AD pathophysiology in the cerebrospinal fluid (CSF) or on amyloid PET imaging. The application and clinical value of this refined diagnostic algorithm, initially intended for research purposes, is explored in three memory clinic cases presenting with different cognitive profiles including an ASHT, hippocampal atrophy, and CSF AD-biomarker data. The case reports highlight that the isolated occurrence of one of the two proposed AD criteria, ASHT or positive pathophysiological markers, does not provide a reliable diagnosis of typical AD. It is proposed that the twofold diagnostic IWG algorithm can be applied and operationalized in memory clinic settings to improve the diagnostic accuracy of typical amnesic AD in clinical practice.

Fully Automatic MRI-Based Hippocampus Volumetry Using FSL-FIRST: Intra-Scanner Test-Retest Stability, Inter-Field Strength Variability, and Performance as Enrichment Biomarker for Clinical Trials Using Prodromal Target Populations at Risk for Alzheimer's Disease.

BACKGROUND: MRI-based hippocampus volume is a core clinical biomarker for identification of Alzheimer's disease (AD). OBJECTIVE: To assess robustness of automatic hippocampus volumetry with the freely available FSL-FIRST software with respect to short-term repeat and across field strength imaging. FSL-FIRST hippocampus volume (FIRST-HV) was also evaluated as enrichment biomarker for mild cognitive impairment (MCI) trials. METHODS: Robustness of FIRST-HV was assessed in 51 healthy controls (HC), 74 MCI subjects, and 28 patients with AD dementia from ADNI1, each with two pairs of back-to-back scans, one at 1.5T one at 3T. Enrichment performance was tested in a second sample of 287 ADNI MCI subjects. RESULTS: FSL-FIRST worked properly in all four scans in 147 out of 153 subjects of the first sample (49 HC, 72 MCI, 26 AD). In these subjects, FIRST-HV did not differ between the first and the second scan within an imaging session, neither at 1.5T nor at 3T (p≥0.302). FIRST-HV was on average 0.78% larger at 3T compared to 1.5T (p = 0.012). The variance of the FIRST-HV difference was larger in the inter-field strength setting than in the intra-scanner settings (p < 0.0005). Computer simulations suggested that the additional variability encountered in the inter-field strength scenario does not cause a relevant degradation of FIRST-HV's prognostic performance in MCI. FIRST-HV based enrichment resulted in considerably increased effect size of the 2-years change of cognitive measures. CONCLUSION: The impact of intra-scanner test-retest and inter-field strength variability of FIRST-HV on clinical tasks is negligible. In addition, FIRST-HV is useful for enrichment in clinical MCI trials.

Global and regional annual brain volume loss rates in physiological aging.

The objective is to estimate average global and regional percentage brain volume loss per year (BVL/year) of the physiologically ageing brain. Two independent, cross-sectional single scanner cohorts of healthy subjects were included. The first cohort (n = 248) was acquired at the Medical Prevention Center (MPCH) in Hamburg, Germany. The second cohort (n = 316) was taken from the Open Access Series of Imaging Studies (OASIS). Brain parenchyma (BP), grey matter (GM), white matter (WM), corpus callosum (CC), and thalamus volumes were calculated. A non-parametric technique was applied to fit the resulting age-volume data. For each age, the BVL/year was derived from the age-volume curves. The resulting BVL/year curves were compared between the two cohorts. For the MPCH cohort, the BVL/year curve of the BP was an increasing function starting from 0.20% at the age of 35 years increasing to 0.52% at 70 years (corresponding values for GM ranged from 0.32 to 0.55%, WM from 0.02 to 0.47%, CC from 0.07 to 0.48%, and thalamus from 0.25 to 0.54%). Mean absolute difference between BVL/year trajectories across the age range of 35-70 years was 0.02% for BP, 0.04% for GM, 0.04% for WM, 0.11% for CC, and 0.02% for the thalamus. Physiological BVL/year rates were remarkably consistent between the two cohorts and independent from the scanner applied. Average BVL/year was clearly age and compartment dependent. These results need to be taken into account when defining cut-off values for pathological annual brain volume loss in disease models, such as multiple sclerosis.

Mental speed is associated with the shape irregularity of white matter MRI hyperintensity load.

Brain MRI white matter hyperintensities (WMHs) are common in elderly subjects. Their impact on cognition, however, appears highly variable. Complementing conventional scoring of WMH load (volume and location) by quantitative characterization of the shape irregularity of WMHs might improve the understanding of the relationship between WMH load and cognitive performance. Here we propose the "confluency sum score" (COSU) as a marker of the total shape irregularity of WMHs in the brain. The study included two independent patient samples: 87 cognitively impaired geriatric inpatients from a prospective neuroimaging study (iDSS) and 198 subjects from the National Alzheimer's Coordinating Center (NACC) database (132 with, 66 w/o cognitive impairment). After automatic segmentation and clustering of the WMHs on FLAIR (LST toolbox, SPM8), the confluency of the i-th contiguous WMH cluster was computed as confluencyi = [1/(36π)∙surfacei3/volumei2]1/3-1. The COSU was obtained by summing the confluency over all WMH clusters. COSU was tested for correlation with CERAD-plus subscores. Correlation analysis was restricted to subjects with at least moderate WMH load (≥ 13.5 ml; iDSS / NACC: n = 52 / 80). In the iDSS sample, among the 12 CERAD-plus subtests the trail making test A (TMT-A) was most strongly correlated with the COSU (Spearman rho = -0.345, p = 0.027). TMT-A performance was not associated with total WMH volume (rho = 0.147, p = 0.358). This finding was confirmed in the NACC sample (rho = -0.261, p = 0.023 versus rho = -0.040, p = 0.732). Cognitive performance in specific domains including mental speed and fluid abilities seems to be more strongly associated with the shape irregularity of white matter MRI hyperintensities than with their volume.

MRI FLAIR lesion segmentation in multiple sclerosis: Does automated segmentation hold up with manual annotation?

INTRODUCTION: Magnetic resonance imaging (MRI) has become key in the diagnosis and disease monitoring of patients with multiple sclerosis (MS). Both, T2 lesion load and Gadolinium (Gd) enhancing T1 lesions represent important endpoints in MS clinical trials by serving as a surrogate of clinical disease activity. T2- and fluid-attenuated inversion recovery (FLAIR) lesion quantification - largely due to methodological constraints - is still being performed manually or in a semi-automated fashion, although strong efforts have been made to allow automated quantitative lesion segmentation. In 2012, Schmidt and co-workers published an algorithm to be applied on FLAIR sequences. The aim of this study was to apply the Schmidt algorithm on an independent data set and compare automated segmentation to inter-rater variability of three independent, experienced raters. METHODS: MRI data of 50 patients with RRMS were randomly selected from a larger pool of MS patients attending the MS Clinic at the Brain and Mind Centre, University of Sydney, Australia. MRIs were acquired on a 3.0T GE scanner (Discovery MR750, GE Medical Systems, Milwaukee, WI) using an 8 channel head coil. We determined T2-lesion load (total lesion volume and total lesion number) using three versions of an automated segmentation algorithm (Lesion growth algorithm (LGA) based on SPM8 or SPM12 and lesion prediction algorithm (LPA) based on SPM12) as first described by Schmidt et al. (2012). Additionally, manual segmentation was performed by three independent raters. We calculated inter-rater correlation coefficients (ICC) and dice coefficients (DC) for all possible pairwise comparisons. RESULTS: We found a strong correlation between manual and automated lesion segmentation based on LGA SPM8, regarding lesion volume (ICC = 0.958 and DC = 0.60) that was not statistically different from the inter-rater correlation (ICC = 0.97 and DC = 0.66). Correlation between the two other algorithms (LGA SPM12 and LPA SPM12) and manual raters was weaker but still adequate (ICC = 0.927 and DC = 0.53 for LGA SPM12 and ICC = 0.949 and DC = 0.57 for LPA SPM12). Variability of both manual and automated segmentation was significantly higher regarding lesion numbers. CONCLUSION: Automated lesion volume quantification can be applied reliably on FLAIR data sets using the SPM based algorithm of Schmidt et al. and shows good agreement with manual segmentation.

Combination of Structural MRI and FDG-PET of the Brain Improves Diagnostic Accuracy in Newly Manifested Cognitive Impairment in Geriatric Inpatients.

BACKGROUND: The cause of cognitive impairment in acutely hospitalized geriatric patients is often unclear. The diagnostic process is challenging but important in order to treat potentially life-threatening etiologies or identify underlying neurodegenerative disease. OBJECTIVE: To evaluate the add-on diagnostic value of structural and metabolic neuroimaging in newly manifested cognitive impairment in elderly geriatric inpatients. METHODS: Eighty-one inpatients (55 females, 81.6±5.5 y) without history of cognitive complaints prior to hospitalization were recruited in 10 acute geriatrics clinics. Primary inclusion criterion was a clinical hypothesis of Alzheimer's disease (AD), cerebrovascular disease (CVD), or mixed AD+CVD etiology (MD), which remained uncertain after standard diagnostic workup. Additional procedures performed after enrollment included detailed neuropsychological testing and structural MRI and FDG-PET of the brain. An interdisciplinary expert team established the most probable etiologic diagnosis (non-neurodegenerative, AD, CVD, or MD) integrating all available data. Automatic multimodal classification based on Random Undersampling Boosting was used for rater-independent assessment of the complementary contribution of the additional diagnostic procedures to the etiologic diagnosis. RESULTS: Automatic 4-class classification based on all diagnostic routine standard procedures combined reproduced the etiologic expert diagnosis in 31% of the patients (p = 0.100, chance level 25%). Highest accuracy by a single modality was achieved by MRI or FDG-PET (both 45%, p≤0.001). Integration of all modalities resulted in 76% accuracy (p≤0.001). CONCLUSION: These results indicate substantial improvement of diagnostic accuracy in uncertain de novo cognitive impairment in acutely hospitalized geriatric patients with the integration of structural MRI and brain FDG-PET into the diagnostic process.

Preserved brain metabolic activity at the age of 96 years.

Loss of brain tissue becomes notable to cerebral magnetic resonance imaging (MRI) at age 30 years, and progresses more rapidly from mid 60s. The incidence of dementia increases exponentially with age, and is all too frequent in the oldest old (≥ 90 years of age), the fastest growing age group in many countries. However, brain pathology and cognitive decline are not inevitable, even at extremely old age (den Dunnen et al., 2008).

Performance of Hippocampus Volumetry with FSL-FIRST for Prediction of Alzheimer's Disease Dementia in at Risk Subjects with Amnestic Mild Cognitive Impairment.

MRI-based hippocampus volume, a core feasible biomarker of Alzheimer's disease (AD), is not yet widely used in clinical patient care, partly due to lack of validation of software tools for hippocampal volumetry that are compatible with routine workflow. Here, we evaluate fully-automated and computationally efficient hippocampal volumetry with FSL-FIRST for prediction of AD dementia (ADD) in subjects with amnestic mild cognitive impairment (aMCI) from phase 1 of the Alzheimer's Disease Neuroimaging Initiative. Receiver operating characteristic analysis of FSL-FIRST hippocampal volume (corrected for head size and age) revealed an area under the curve of 0.79, 0.70, and 0.70 for prediction of aMCI-to-ADD conversion within 12, 24, or 36 months, respectively. Thus, FSL-FIRST provides about the same power for prediction of progression to ADD in aMCI as other volumetry methods.

Atlas based brain volumetry: How to distinguish regional volume changes due to biological or physiological effects from inherent noise of the methodology.

Fully-automated regional brain volumetry based on structural magnetic resonance imaging (MRI) plays an important role in quantitative neuroimaging. In clinical trials as well as in clinical routine multiple MRIs of individual patients at different time points need to be assessed longitudinally. Measures of inter- and intrascanner variability are crucial to understand the intrinsic variability of the method and to distinguish volume changes due to biological or physiological effects from inherent noise of the methodology. To measure regional brain volumes an atlas based volumetry (ABV) approach was deployed using a highly elastic registration framework and an anatomical atlas in a well-defined template space. We assessed inter- and intrascanner variability of the method in 51 cognitively normal subjects and 27 Alzheimer dementia (AD) patients from the Alzheimer's Disease Neuroimaging Initiative by studying volumetric results of repeated scans for 17 compartments and brain regions. Median percentage volume differences of scan-rescans from the same scanner ranged from 0.24% (whole brain parenchyma in healthy subjects) to 1.73% (occipital lobe white matter in AD), with generally higher differences in AD patients as compared to normal subjects (e.g., 1.01% vs. 0.78% for the hippocampus). Minimum percentage volume differences detectable with an error probability of 5% were in the one-digit percentage range for almost all structures investigated, with most of them being below 5%. Intrascanner variability was independent of magnetic field strength. The median interscanner variability was up to ten times higher than the intrascanner variability.

Optimization of Statistical Single Subject Analysis of Brain FDG PET for the Prognosis of Mild Cognitive Impairment-to-Alzheimer's Disease Conversion.

BACKGROUND: Positron emission tomography (PET) with the glucose analog F-18-fluorodeoxyglucose (FDG) is widely used in the diagnosis of neurodegenerative diseases. Guidelines recommend voxel-based statistical testing to support visual evaluation of the PET images. However, the performance of voxel-based testing strongly depends on each single preprocessing step involved. OBJECTIVE: To optimize the processing pipeline of voxel-based testing for the prognosis of dementia in subjects with amnestic mild cognitive impairment (MCI). METHODS: The study included 108 ADNI MCI subjects grouped as 'stable MCI' (n = 77) or 'MCI-to-AD converter' according to their diagnostic trajectory over 3 years. Thirty-two ADNI normals served as controls. Voxel-based testing was performed with the statistical parametric mapping software (SPM8) starting with default settings. The following modifications were added step-by-step: (i) motion correction, (ii) custom-made FDG template, (iii) different reference regions for intensity scaling, and (iv) smoothing was varied between 8 and 18 mm. The t-sum score for hypometabolism within a predefined AD mask was compared between the different settings using receiver operating characteristic (ROC) analysis with respect to differentiation between 'stable MCI' and 'MCI-to-AD converter'. The area (AUC) under the ROC curve was used as performance measure. RESULTS: The default setting provided an AUC of 0.728. The modifications of the processing pipeline improved the AUC up to 0.832 (p = 0.046). Improvement of the AUC was confirmed in an independent validation sample of 241 ADNI MCI subjects (p = 0.048). CONCLUSION: The prognostic value of voxel-based single subject analysis of brain FDG PET in MCI subjects can be improved considerably by optimizing the processing pipeline.