Robin Wolz

Fast and robust multi-atlas segmentation of brain magnetic resonance images.

We introduce an optimised pipeline for multi-atlas brain MRI segmentation. Both accuracy and speed of segmentation are considered. We study different similarity measures used in non-rigid registration. We show that intensity differences for intensity normalised images can be used instead of standard normalised mutual information in registration without compromising the accuracy but leading to threefold decrease in the computation time. We study and validate also different methods for atlas selection. Finally, we propose two new approaches for combining multi-atlas segmentation and intensity modelling based on segmentation using expectation maximisation (EM) and optimisation via graph cuts. The segmentation pipeline is evaluated with two data cohorts: IBSR data (N=18, six subcortial structures: thalamus, caudate, putamen, pallidum, hippocampus, amygdala) and ADNI data (N=60, hippocampus). The average similarity index between automatically and manually generated volumes was 0.849 (IBSR, six subcortical structures) and 0.880 (ADNI, hippocampus). The correlation coefficient for hippocampal volumes was 0.95 with the ADNI data. The computation time using a standard multicore PC computer was about 3-4 min. Our results compare favourably with other recently published results.

Multi-Method Analysis of MRI Images in Early Diagnostics of Alzheimer's Disease

The role of structural brain magnetic resonance imaging (MRI) is becoming more and more emphasized in the early diagnostics of Alzheimers disease (AD). This study aimed to assess the improvement in classification accuracy that can be achieved by combining features from different structural MRI analysis techniques. Automatically estimated MR features used are hippocampal volume, tensor-based morphometry, cortical thickness and a novel technique based on manifold learning. Baseline MRIs acquired from all 834 subjects (231 healthy controls (HC), 238 stable mild cognitive impairment (S-MCI), 167 MCI to AD progressors (P-MCI), 198 AD) from the Alzheimers Disease Neuroimaging Initiative (ADNI) database were used for evaluation. We compared the classification accuracy achieved with linear discriminant analysis (LDA) and support vector machines (SVM). The best results achieved with individual features are 90% sensitivity and 84% specificity (HC/AD classification), 64%/66% (S-MCI/P-MCI) and 82%/76% (HC/P-MCI) with the LDA classifier. The combination of all features improved these results to 93% sensitivity and 85% specificity (HC/AD), 67%/69% (S-MCI/P-MCI) and 86%/82% (HC/P-MCI). Compared with previously published results in the ADNI database using individual MR-based features, the presented results show that a comprehensive analysis of MRI images combining multiple features improves classification accuracy and predictive power in detecting early AD. The most stable and reliable classification was achieved when combining all available features.

Segmentation of MR images via discriminative dictionary learning and sparse coding: Application to hippocampus labeling

We propose a novel method for the automatic segmentation of brain MRI images by using discriminative dictionary learning and sparse coding techniques. In the proposed method, dictionaries and classifiers are learned simultaneously from a set of brain atlases, which can then be used for the reconstruction and segmentation of an unseen target image. The proposed segmentation strategy is based on image reconstruction, which is in contrast to most existing atlas-based labeling approaches that rely on comparing image similarities between atlases and target images. In addition, we propose a Fixed Discriminative Dictionary Learning for Segmentation (F-DDLS) strategy, which can learn dictionaries offline and perform segmentations online, enabling a significant speed-up in the segmentation stage. The proposed method has been evaluated for the hippocampus segmentation of 80 healthy ICBM subjects and 202 ADNI images. The robustness of the proposed method, especially of our F-DDLS strategy, was validated by training and testing on different subject groups in the ADNI database. The influence of different parameters was studied and the performance of the proposed method was also compared with that of the nonlocal patch-based approach. The proposed method achieved a median Dice coefficient of 0.879 on 202 ADNI images and 0.890 on 80 ICBM subjects, which is competitive compared with state-of-the-art methods.

Automated Abdominal Multi-Organ Segmentation With Subject-Specific Atlas Generation

A robust automated segmentation of abdominal organs can be crucial for computer aided diagnosis and laparoscopic surgery assistance. Many existing methods are specialized to the segmentation of individual organs and struggle to deal with the variability of the shape and position of abdominal organs. We present a general, fully-automated method for multi-organ segmentation of abdominal computed tomography (CT) scans. The method is based on a hierarchical atlas registration and weighting scheme that generates target specific priors from an atlas database by combining aspects from multi-atlas registration and patch-based segmentation, two widely used methods in brain segmentation. The final segmentation is obtained by applying an automatically learned intensity model in a graph-cuts optimization step, incorporating high-level spatial knowledge. The proposed approach allows to deal with high inter-subject variation while being flexible enough to be applied to different organs. We have evaluated the segmentation on a database of 150 manually segmented CT images. The achieved results compare well to state-of-the-art methods, that are usually tailored to more specific questions, with Dice overlap values of 94%, 93%, 70%, and 92% for liver, kidneys, pancreas, and spleen, respectively.

Injury markers predict time to dementia in subjects with MCI and amyloid pathology

Objectives: Alzheimer disease (AD) can now be diagnosed in subjects with mild cognitive impairment (MCI) using biomarkers. However, little is known about the rate of decline in those subjects. In this cohort study, we aimed to assess the conversion rate to dementia and identify prognostic markers in subjects with MCI and evidence of amyloid pathology. Methods: We pooled subjects from the VU University Medical Center Alzheimer Center and the Development of Screening Guidelines and Criteria for Predementia Alzheimers Disease (DESCRIPA) study. We included subjects with MCI, an abnormal level of β-amyloid1−42 (Aβ1–42) in the CSF, and at least one diagnostic follow-up visit. We assessed the effect of APOE genotype, CSF total tau (t-tau) and tau phosphorylated at threonine 181 (p-tau) and hippocampal volume on time to AD-type dementia using Cox proportional hazards models and on decline on the Mini-Mental State Examination (MMSE) using linear mixed models. Results: We included 110 subjects with MCI with abnormal CSF Aβ1–42 and a mean MMSE score of 26.3 ± 2.8. During a mean follow-up of 2.2 ± 1.0 (range 0.4–5.0) years, 63 subjects (57%) progressed to AD-type dementia. Abnormal CSF t-tau (hazard ratio [HR] 2.3, 95% confidence interval [CI] 1.1–4.6, p = 0.03) and CSF p-tau (HR 3.5, 95% CI 1.3–9.2, p = 0.01) concentration and hippocampal atrophy (HR 2.5, 95% CI 1.1–5.6, p = 0.02) predicted time to dementia. For subjects with both abnormal t-tau concentration and hippocampal atrophy, HR was 7.3 (95% CI 1.0–55.9, p = 0.06). Furthermore, abnormal CSF t-tau and p-tau concentrations and hippocampal atrophy predicted decline in MMSE score. Conclusions: In subjects with MCI and evidence of amyloid pathology, the injury markers CSF t-tau and p-tau and hippocampal atrophy can predict further cognitive decline.

Sparse reduced-rank regression detects genetic associations with voxel-wise longitudinal phenotypes in Alzheimer's disease.

Scanning the entire genome in search of variants related to imaging phenotypes holds great promise in elucidating the genetic etiology of neurodegenerative disorders. Here we discuss the application of a penalized multivariate model, sparse reduced-rank regression (sRRR), for the genome-wide detection of markers associated with voxel-wise longitudinal changes in the brain caused by Alzheimers disease (AD). Using a sample from the Alzheimers Disease Neuroimaging Initiative database, we performed three separate studies that each compared two groups of individuals to identify genes associated with disease development and progression. For each comparison we took a two-step approach: initially, using penalized linear discriminant analysis, we identified voxels that provide an imaging signature of the disease with high classification accuracy; then we used this multivariate biomarker as a phenotype in a genome-wide association study, carried out using sRRR. The genetic markers were ranked in order of importance of association to the phenotypes using a data re-sampling approach. Our findings confirmed the key role of the APOE and TOMM40 genes but also highlighted some novel potential associations with AD.

Prediction of Alzheimer disease in subjects with amnestic and nonamnestic MCI

Objective: To compare the predictive accuracy of β-amyloid (Aβ)1–42 and total tau in CSF, hippocampal volume (HCV), and APOE genotype for Alzheimer disease (AD)-type dementia in subjects with amnestic mild cognitive impairment (aMCI) and nonamnestic mild cognitive impairment (naMCI). Methods: We selected 399 subjects with aMCI and 226 subjects with naMCI from a multicenter memory clinic–based cohort. We measured CSF Aβ1–42 and tau by ELISA (n = 231), HCV on MRI (n = 388), and APOE ε4 (n = 523). Follow-up was performed annually up to 5 years. Outcome measures were progression to AD-type dementia and cognitive decline. Results: At least 1 follow-up was available for 538 subjects (86%). One hundred thirty-two subjects with aMCI (38%) and 39 subjects with naMCI (20%) progressed to AD-type dementia after an average follow-up of 2.5 years. CSF Aβ1–42, tau, Aβ1–42/tau ratio, HCV, and APOE ε4 predicted AD-type dementia in each MCI subgroup with the same overall diagnostic accuracy. However, CSF Aβ1–42 concentration was higher and hippocampal atrophy less severe in subjects with naMCI compared with aMCI. This reduced the sensitivity but increased the specificity of these markers for AD-type dementia in subjects with naMCI. Conclusions: AD biomarkers are useful to predict AD-type dementia in subjects with aMCI and naMCI. However, biomarkers might not be as sensitive for early diagnosis of AD in naMCI compared with aMCI. This may have implications for clinical implementation of the National Institute on Aging and Alzheimers Association criteria.

Test sequence of CSF and MRI biomarkers for prediction of AD in subjects with MCI

Our aim was to identify the best diagnostic test sequence for predicting Alzheimers disease (AD)-type dementia in subjects with mild cognitive impairment (MCI) using cerebrospinal fluid (CSF) and magnetic resonance imaging (MRI) biomarkers. We selected 153 subjects with mild cognitive impairment from a multicenter memory clinic-based cohort. We tested the CSF beta amyloid (Aβ)1-42/tau ratio using enzyme-linked immunosorbent assay (ELISA) and hippocampal volumes (HCVs) using the atlas-based learning embeddings for atlas propagation (LEAP) method. Outcome measure was progression to AD-type dementia in 2 years. At follow-up, 48 (31%) subjects converted to AD-type dementia. In multivariable analyses, CSF Aβ1-42/tau and HCV predicted AD-type dementia regardless of apolipoprotein E (APOE) genotype and cognitive scores. Test sequence analyses showed that CSF Aβ1-42/tau increased predictive accuracy in subjects with normal HCV (p < 0.001) and abnormal HCV (p = 0.025). HCV increased predictive accuracy only in subjects with normal CSF Aβ1-42/tau (p = 0.014). Slope analyses for annual cognitive decline yielded similar results. For selection of subjects for a prodromal AD trial, the best balance between sample size and number of subjects needed to screen was obtained with CSF markers. These results provide further support for the use of CSF and magnetic resonance imaging biomarkers to identify prodromal AD.

Fast and robust extraction of hippocampus from MR images for diagnostics of Alzheimer's disease

Assessment of temporal lobe atrophy from magnetic resonance images is a part of clinical guidelines for the diagnosis of prodromal Alzheimers disease. As hippocampus is known to be among the first areas affected by the disease, fast and robust definition of hippocampus volume would be of great importance in the clinical decision making. We propose a method for computing automatically the volume of hippocampus using a modified multi-atlas segmentation framework, including an improved initialization of the framework and the correction of partial volume effect. The method produced a high similarity index, 0.87, and correlation coefficient, 0.94, with semi-automatically generated segmentations. When comparing hippocampus volumes extracted from 1.5T and 3T images, the absolute value of the difference was low: 3.2% of the volume. The correct classification rate for Alzheimers disease and cognitively normal cases was about 80% while the accuracy 65% was obtained for classifying stable and progressive mild cognitive impairment cases. The method was evaluated in three cohorts consisting altogether about 1000 cases, the main emphasis being in the analysis of the ADNI cohort. The computation time of the method is about 2 minutes on a standard laptop computer. The results show a clear potential for applying the method in clinical practice.

Multi-region analysis of longitudinal FDG-PET for the classification of Alzheimer's disease.

Imaging biomarkers for Alzheimers disease are desirable for improved diagnosis and monitoring, as well as drug discovery. Automated image-based classification of individual patients could provide valuable diagnostic support for clinicians, when considered alongside cognitive assessment scores. We investigate the value of combining cross-sectional and longitudinal multi-region FDG-PET information for classification, using clinical and imaging data from the Alzheimers Disease Neuroimaging Initiative. Whole-brain segmentations into 83 anatomically defined regions were automatically generated for baseline and 12-month FDG-PET images. Regional signal intensities were extracted at each timepoint, as well as changes in signal intensity over the follow-up period. Features were provided to a support vector machine classifier. By combining 12-month signal intensities and changes over 12 months, we achieve significantly increased classification performance compared with using any of the three feature sets independently. Based on this combined feature set, we report classification accuracies of 88% between patients with Alzheimers disease and elderly healthy controls, and 65% between patients with stable mild cognitive impairment and those who subsequently progressed to Alzheimers disease. We demonstrate that information extracted from serial FDG-PET through regional analysis can be used to achieve state-of-the-art classification of diagnostic groups in a realistic multi-centre setting. This finding may be usefully applied in the diagnosis of Alzheimers disease, predicting disease course in individuals with mild cognitive impairment, and in the selection of participants for clinical trials.