Different inflammatory and metabolic pathways have been associated with Alzheimeŕs disease (AD). However, only recently multi-analyte panels to study a large number of molecules in well characterized cohorts have been made available. These panels could help identify molecules that point to the affected pathways. We studied the relationship between a panel of plasma biomarkers (Human DiscoveryMAP®) and presence of AD-like brain atrophy patterns defined by a previously published index (SPARE-AD) at baseline in subjects of the ADNI cohort. 818 subjects had MRI-derived SPARE-AD scores, of these subjects 69% had plasma biomarkers and 51% had CSF tau and Aβ measurements. Significant analyte-SPARE-AD and analytes correlations were studied in adjusted models. Plasma cortisol and chromogranin A showed a significant association that did not remain significant in the CSF signature adjusted model. Plasma macrophage inhibitory protein-1α and insulin-like growth factor binding protein 2 showed a significant association with brain atrophy in the adjusted model. Cortisol levels showed an inverse association with tests measuring processing speed. Our results indicate that stress and insulin responses and cytokines associated with recruitment of inflammatory cells in MCI-AD are associated with its characteristic AD-like brain atrophy pattern and correlate with clinical changes or CSF biomarkers.

Identifying interactions among brain regions from structural magnetic-resonance images presents one of the major challenges in computational neuroanatomy. We propose a Bayesian data-mining approach to the detection of longitudinal morphological changes in the human brain. Our method uses a dynamic Bayesian network to represent evolving inter-regional dependencies. The major advantage of dynamic Bayesian network modeling is that it can represent complicated interactions among temporal processes. We validated our approach by analyzing a simulated atrophy study, and found that this approach requires only a small number of samples to detect the ground-truth temporal model. We further applied dynamic Bayesian network modeling to a longitudinal study of normal aging and mild cognitive impairment — the Baltimore Longitudinal Study of Aging. We found that interactions among regional volume-change rates for the mild cognitive impairment group are different from those for the normal-aging group.

Recent genetic and proteomic studies demonstrate that clusterin/apolipoprotein-J is associated with risk, pathology, and progression of Alzheimer’s disease (AD). Our main aim was to examine associations between plasma clusterin concentration and longitudinal changes in brain volume in normal aging and mild cognitive impairment (MCI). A secondary objective was to examine associations between peripheral concentration of clusterin and its concentration in the brain within regions that undergo neuropathological changes in AD. Non-demented individuals (N = 139; mean baseline age 70.5 years) received annual volumetric MRI (912 MRI scans in total) over a mean six-year interval. Sixteen participants (92 MRI scans in total) were diagnosed during the course of the study with amnestic MCI. Clusterin concentration was assayed by ELISA in plasma samples collected within a year of the baseline MRI. Mixed effects regression models investigated whether plasma clusterin concentration was associated with rates of brain atrophy for control and MCI groups and whether these associations differed between groups. In a separate autopsy sample of individuals with AD (N=17) and healthy controls (N=4), we examined the association between antemortem clusterin concentration in plasma and postmortem levels in the superior temporal gyrus, hippocampus and cerebellum. The associations of plasma clusterin concentration with rates of change in brain volume were significantly different between MCI and control groups in several volumes including whole brain, ventricular CSF, temporal gray matter as well as parahippocampal, superior temporal and cingulate gyri. Within the MCI but not control group, higher baseline concentration of plasma clusterin was associated with slower rates of brain atrophy in these regions. In the combined autopsy sample of AD and control cases, representing a range of severity in AD pathology, we observed a significant association between clusterin concentration in the plasma and that in the superior temporal gyrus. Our findings suggest that clusterin, a plasma protein with roles in amyloid clearance, complement inhibition and apoptosis, is associated with rate of brain atrophy in MCI. Furthermore, peripheral concentration of clusterin also appears to reflect its concentration within brain regions vulnerable to AD pathology. These findings in combination suggest an influence of this multi-functional protein on early stages of progression in AD pathology.

Research suggests overlap in brain regions undergoing neurodegeneration in Parkinson's and Alzheimer's disease. To assess the clinical significance of this, we applied a validated Alzheimer's disease-spatial pattern of brain atrophy to patients with Parkinson's disease with a range of cognitive abilities to determine its association with cognitive performance and decline. At baseline, 84 subjects received structural magnetic resonance imaging brain scans and completed the Dementia Rating Scale-2, and new robust and expanded Dementia Rating Scale-2 norms were applied to cognitively classify participants. Fifty-nine non-demented subjects were assessed annually with the Dementia Rating Scale-2 for two additional years. Magnetic resonance imaging scans were quantified using both a region of interest approach and voxel-based morphometry analysis, and a method for quantifying the presence of an Alzheimer's disease spatial pattern of brain atrophy was applied to each scan. In multivariate models, higher Alzheimer's disease pattern of atrophy score was associated with worse global cognitive performance (β = −0.31, P = 0.007), including in non-demented patients (β = −0.28, P = 0.05). In linear mixed model analyses, higher baseline Alzheimer's disease pattern of atrophy score predicted long-term global cognitive decline in non-demented patients [F(1, 110) = 9.72, P = 0.002], remarkably even in those with normal cognition at baseline [F(1, 80) = 4.71, P = 0.03]. In contrast, in cross-sectional and longitudinal analyses there was no association between region of interest brain volumes and cognitive performance in patients with Parkinson's disease with normal cognition. These findings support involvement of the hippocampus and parietal–temporal cortex with cognitive impairment and long-term decline in Parkinson's disease. In addition, an Alzheimer's disease pattern of brain atrophy may be a preclinical biomarker of cognitive decline in Parkinson's disease.

We propose an automated method to segment cortical necrosis from brain FLAIR-MR Images. Cortical necrosis are regions of dead brain tissue in the cortex caused by cerebrovascular disease (CVD). The accurate segmentation of these regions is difficult as their intensity patterns are similar to the adjoining cerebrospinal fluid (CSF). We generate a model of normal variation using MR scans of healthy controls. The model is based on the Jacobians of warps obtained by registering scans of normal subjects to a common coordinate system. For each patient scan a Jacobian is obtained by warping it to the same coordinate system. Large deviations between the model and subject-specific Jacobians are flagged as `abnormalities'. Abnormalities are segmented as cortical necrosis if they are in the cortex and have the intensity profile of CSF. We evaluate our method by using a set of 72 healthy subjects to model cortical variation.We use this model to successfully detect and segment cortical necrosis in a set of 37 patients with CVD. A comparison of the results with segmentations from two independent human experts shows that the overlap between our approach and either of the human experts is in the range of the overlap between the two human experts themselves.

Amyloid-β plaques (Aβ) are a hallmark of Alzheimer's disease (AD), begin deposition decades before the incipient disease, and are thought to be associated with neuronal loss, brain atrophy and cognitive impairment. We examine associations between 11C-PiB-PET measurement of Aβ burden and brain volume changes in the preceding years in 57 non-demented individuals (age 64-86; M = 78.7). Participants were prospectively followed through the Baltimore Longitudinal Study of Aging, with up to 10 consecutive MRI scans (M = 8.1) and an 11C-PiB scan approximately 10 years after the initial MRI. Linear mixed effects models were used to determine whether mean cortical 11C-PiB distribution volume ratios, estimated by fitting a reference tissue model to the measured time activity curves, were associated with longitudinal regional brain volume changes of the whole brain, ventricular CSF, frontal, temporal, parietal, and occipital white and gray matter, the hippocampus, orbito-frontal cortex, and the precuneus. Despite significant longitudinal declines in the volumes of all investigated regions (p < 0.05), no associations were detected between current Aβ burden and regional brain volume decline trajectories in the preceding years, nor did the regional volume trajectories differ between those with highest and lowest Aβ burden. Consistent with a threshold model of disease, our findings suggest that Aβ load does not seem to affect brain volume changes in individuals without dementia.

Objective

To assess regions and patterns of brain atrophy in patients with Parkinson disease (PD) with normal cognition (PD-NC), mild cognitive impairment (PD-MCI), and dementia-level cognitive deficits (PDD).

Design

Images were quantified using a region-of-interest approach and voxel-based morphometry analysis. We used a high-dimensional pattern classification approach to delineate brain regions that collectively formed the Spatial Pattern of Abnormalities for Recognition of PDD.

Setting

The Parkinson’s Disease and Movement Disorders Center at the University of Pennsylvania.

Subjects

Eighty-four PD patients (61 PD-NC, 12 PD-MCI, and 11 PDD) and 23 healthy control subjects (HCs) underwent magnetic resonance imaging of the brain.

Results

The PD-NC patients did not demonstrate significant brain atrophy compared with HCs. Compared with PD-NC patients, PD-MCI patients had hippocampal atrophy (β=−0.37; P=.001), and PDD patients demonstrated hippocampal (β=−0.32; P=.004) and additional medial temporal lobe atrophy (β=−0.36; P=.003). The PD-MCI patients had a different pattern of atrophy compared with PD-NC patients (P=.04) and a similar pattern to that of PDD patients (P=.81), characterized by hippocampal, prefrontal cortex gray and white matter, occipital lobe gray and white matter, and parietal lobe white matter atrophy. In nondemented PD patients, there was a correlation between memory-encoding performance and hippocampal volume.

Conclusions

Hippocampal atrophy is a biomarker of initial cognitive decline in PD, including impaired memory encoding and storage, suggesting heterogeneity in the neural substrate of memory impairment. Use of a pattern classification approach may allow identification of diffuse regions of cortical gray and white matter atrophy early in the course of cognitive decline.

MRI patterns were examined together with cerebrospinal fluid (CSF) biomarkers in serial scans of ADNI participants with mild cognitive impairment (MCI). The SPARE-AD score, summarizing brain atrophy patterns, was tested as predictor of short-term conversion to AD. MCI individuals that converted to AD (MCI-C) had mostly positive baseline SPARE-AD and atrophy in temporal lobe grey (GM) and white (WM) matter, posterior cingulate/precuneous, insula. MCI-C had mostly AD-like baseline CSF biomarkers. MCI non-converters (MCI-NC) had mixed baseline SPARE-AD and CSF values, suggesting that some MCI-NC subjects may later convert. Those MCI-NC with most negative baseline SPARE-AD scores (normal brain structure) had significantly higher baseline MMSE scores (28.67) than others, and relatively low annual rate of MMSE decrease (−0.25). MCI-NC with mid-level baseline SPARE-AD displayed faster annual rates of SPARE-AD increase (indicating progressing atrophy). SPARE-AD and CSF combination improved prediction over individual values. In summary, both SPARE-AD and CSF biomarkers showed high baseline sensitivity, however, many MCI-NC had abnormal baseline SPARE-AD and CSF biomarkers. Longer follow-up will elucidate the specificity of baseline measurements.

Background

Persons with type 2 diabetes (T2D) are at risk for cognitive impairment and brain atrophy. The ACCORD Memory in Diabetes (MIND) Study investigated whether persons randomized to an intensive glycaemic therapeutic strategy targeting HbA1c to <6% had better cognitive function and a larger brain volume at 40 months than persons randomized to a standard strategy targeting HbA1c to 7%–7.9%.

Methods

ACCORD MIND was a double 2×2 factorial parallel group randomised trial conducted in 52 clinical sites in North America. Participants [age 55 – <80 years] with T2D, high HbA1c concentrations (>7.5%), and at high risk for cardiovascular events were randomised to treatment groups using a centralized web-based system. Clinic staff and participants were not blinded to treatment arm. The cognitive primary outcome, the Digit Symbol Substitution Test (DSST) score, was assessed at baseline, 20 and 40 months. Total brain volume (TBV), the primary brain structure outcome, was assessed with MRI at baseline and 40 months in a sub-set of 632 participants. All participants with follow-up data were included in the primary analyses. In February, 2008, increased mortality risk led to the termination of the intensive therapy and transition of those participants to standard glycaemic treatment.

Results

Randomised patients (n=2977; mean age 62.3 years) were consecutively enrolled; the final analysis included 1358 intensive and 1416 standard arm participants with a 20 or 40 month DSST score. Of the 614 with a baseline MRI, 230 intensive and 273 standard therapy participants were included in the analysis. There was no treatment difference in the DSST score. The intensive group had a greater TBV than the standard group (difference, 4.62; 95% CI 2.0 to7.3 cm3; p=0.0007).

Interpretation

Although significant differences in TBV favored the intensive therapy, cognitive outcomes were not different. Combined with the unfavorable effects on other ACCORD outcomes, MIND findings do not support using intensive therapy to reduce the adverse effects of diabetes on the brain in patients similar to MIND participants. (ClinicalTrials.gov number, NCT00182910).

A number of conditions are characterized by pathologies that form continuous or nearly-continuous spectra spanning from the absence of pathology to very pronounced pathological changes (e.g., normal aging, Mild Cognitive Impairment, Alzheimer's). Moreover, diseases are often highly heterogeneous with a number of diagnostic subcategories or subconditions lying within the spectra (e.g., Autism Spectrum Disorder, schizophrenia). Discovering coherent subpopulations of subjects within the spectrum of pathological changes may further our understanding of diseases, and potentially identify subconditions that require alternative or modified treatment options. In this paper, we propose an approach that aims at identifying coherent subpopulations with respect to the underlying MRI in the scenario where the condition is heterogeneous and pathological changes form a continuous spectrum. We describe a Joint Maximum-Margin Classification and Clustering (JointMMCC) approach that jointly detects the pathologic population via semi-supervised classification, as well as disentangles heterogeneity of the pathological cohort by solving a clustering subproblem. We propose an efficient solution to the non-convex optimization problem associated with JointMMCC. We apply our proposed approach to an MRI study of aging, and identify coherent subpopulations (i.e., clusters) of cognitively less stable adults.

We explore a connection between the singular value decomposition (SVD) and functional principal component analysis (FPCA) models in high-dimensional brain imaging applications. We formally link right singular vectors to principal scores of FPCA. This, combined with the fact that left singular vectors estimate principal components, allows us to deploy the numerical efficiency of SVD to fully estimate the components of FPCA, even for extremely high-dimensional functional objects, such as brain images. As an example, a FPCA model is fit to high-resolution morphometric (RAVENS) images. The main directions of morphometric variation in brain volumes are identified and discussed.

We tested the hypothesis that social engagement is associated with larger brain volumes in a cohort study of 348 older male former lead manufacturing workers (n = 305) and population-based controls (n = 43), age 48 to 82. Social engagement was measured using a summary scale derived from confirmatory factor analysis. The volumes of 20 regions of interest (ROIs), including total brain, total gray matter (GM), total white matter (WM), each of the four lobar GM and WM, and 9 smaller structures were derived from T1-weighted structural magnetic resonance images. Linear regression models adjusted for age, education, race/ethnicity, intracranial volume, hypertension, diabetes, and control (versus lead worker) status. Higher social engagement was associated with larger total brain and GM volumes, specifically temporal and occipital GM, but was not associated with WM volumes except for corpus callosum. A voxel-wise analysis supported an association in temporal lobe GM. Using longitudinal data to discern temporal relations, change in ROI volumes over five years showed null associations with current social engagement. Findings are consistent with the hypothesis that social engagement preserves brain tissue, and not consistent with the alternate hypothesis that persons with smaller or shrinking volumes become less socially engaged, though this scenario cannot be ruled out.

A general-purpose deformable registration algorithm referred to as “DRAMMS” is presented in this paper. DRAMMS bridges the gap between the traditional voxel-wise methods and landmark/feature-based methods with primarily two contributions. First, DRAMMS renders each voxel relatively distinctively identifiable by a rich set of attributes, therefore largely reducing matching ambiguities. In particular, a set of multi-scale and multi-orientation Gabor attributes are extracted and the optimal components are selected, so that they form a highly distinctive morphological signature reflecting the anatomical and geometric context around each voxel. Moreover, the way in which the optimal Gabor attributes are constructed is independent from the underlying image modalities or contents, which renders DRAMMS generally applicable to diverse registration tasks. A second contribution of DRAMMS is that it modulates the registration by assigning higher weights to those voxels having higher ability to establish unique (hence reliable) correspondences across images, therefore reducing the negative impact of those regions that are less capable of finding correspondences. A continuously-valued weighting function named “mutual-saliency” is developed to reflect the matching reliability between a pair of voxels implied by the tentative transformation. As a result, voxels do not contribute equally as in most voxel-wise methods, nor in isolation as in landmark/feature-based methods. Instead, they contribute according to the continuously-valued mutual-saliency map, which dynamically evolves during the registration process. Experiments in simulated images, inter-subject images, single-/multi-modality images, from brain, heart, and prostate have demonstrated the general applicability and the accuracy of DRAMMS.

One of the many advantages of multivariate pattern recognition approaches over conventional mass-univariate group analysis using voxel-wise statistical tests is their potential to provide highly sensitive and specific markers of diseases on an individual basis. However, a vast majority of imaging problems addressed by pattern recognition are viewed from the perspective of a two-class classification. In this article, we provide a summary of selected works that propose solutions to biomedical problems where the widely-accepted classification paradigm is not appropriate. These pattern recognition approaches address common challenges in many imaging studies: high heterogeneity of populations and continuous progression of diseases. We focus on diseases associated with aging and propose that clustering-based approaches may be more suitable for disentanglement of the underlying heterogeneity, while high-dimensional pattern regression methodology is appropriate for prediction of continuous and gradual clinical progression from magnetic resonance brain images.

Objective

Image-guided prostate biopsy has become routine in medical diagnosis. Although it improves biopsy outcome, it mostly operates in 2 dimensions, therefore lacking presentation of information in the complete 3-dimensional (3D) space. Because prostatic carcinomas are nonuniformly distributed within the prostate gland, it is crucial to accurately guide the needles toward clinically important locations within the 3D volume for both diagnosis and treatment.

Methods

We reviewed the uses of 3D image-guided needle procedures in prostate cancer diagnosis and cancer therapy as well as their advantages, work flow, and future directions.

Results

Guided procedures for the prostate rely on accurate 3D target identification and needle navigation. This 3D approach has potential for better disease diagnosis and therapy. Additionally, when fusing together different imaging modalities and cancer probability maps obtained from a population of interest, physicians can potentially place biopsy needles and other interventional devices more accurately and efficiently by better targeting regions that are likely to host cancerous tissue.

Conclusions

With the information from anatomic, metabolic, functional, biochemical, and biomechanical statuses of different regions of the entire gland, prostate cancers will be better diagnosed and treated with improved work flow.

Populations of healthy older individuals are often highly heterogeneous, as prevalence of various underlying pathologies increases with age. Finding coherent groups of normal older adults may allow to identify subpopulations that are at risk of developing Alzheimer’s disease (AD). In this paper, we propose an approach that utilizes longitudinal magnetic resonance imaging (MRI) data to obtain natural groupings of older adult subjects via an unsupervised (i.e., clustering) technique. We develop a k-medoids-like clustering algorithm that simultaneously finds clusters of longitudinal images, as well as weights brain regions in such a way that the obtained clusters are maximally coherent. We propose a cluster-based measure that reflects the individual subject’s cognitive decline. The proposed method is unsupervised and is suitable for analyzing AD at its very early stages.

Gaussian smoothing of images prior to applying voxel-based statistics is an important step in Voxel-Based Analysis and Statistical Parametric Mapping (VBA-SPM), and is used to account for registration errors, to Gaussianize the data, and to integrate imaging signals from a region around each voxel. However, it has also become a limitation of VBA-SPM based methods, since it is often chosen empirically and lacks spatial adaptivity to the shape and spatial extent of the region of interest, such as a region of atrophy or functional activity. In this paper, we propose a new framework, named Optimally-Discriminative Voxel-Based Analysis (ODVBA), for determining the optimal spatially adaptive smoothing of images, followed by applying voxel-based group analysis. In ODVBA, Nonnegative Discriminative Projection is applied regionally to get the direction that best discriminates between two groups, e.g., patients and controls; this direction is equivalent to local filtering by an optimal kernel whose coefficients define the optimally discriminative direction. By considering all the neighborhoods that contain a given voxel, we then compose this information to produce the statistic for each voxel. Finally, permutation tests are used to obtain a statistical parametric map of group differences. ODVBA has been evaluated using simulated data in which the ground truth is known and with data from an Alzheimer’s disease (AD) study. The experimental results have shown that the proposed ODVBA can precisely describe the shape and location of structural abnormality.

This paper presents a novel dimensionality reduction method for classification in medical imaging. The goal is to transform very high-dimensional input (typically, millions of voxels) to a low-dimensional representation (small number of constructed features) that preserves discriminative signal and is clinically interpretable. We formulate the task as a constrained optimization problem that combines generative and discriminative objectives and show how to extend it to the semi-supervised learning (SSL) setting. We propose a novel large-scale algorithm to solve the resulting optimization problem. In the fully supervised case, we demonstrate accuracy rates that are better than or comparable to state-of-the-art algorithms on several datasets while producing a representation of the group difference that is consistent with prior clinical reports. Effectiveness of the proposed algorithm for SSL is evaluated with both benchmark and medical imaging datasets. In the benchmark datasets, the results are better than or comparable to the state-of-the-art methods for SSL. For evaluation of the SSL setting in medical datasets, we use images of subjects with Mild Cognitive Impairment (MCI), which is believed to be a precursor to Alzheimer's disease (AD), as unlabeled data. AD subjects and Normal Control (NC) subjects are used as labeled data, and we try to predict conversion from MCI to AD on follow-up. The semi-supervised extension of this method not only improves the generalization accuracy for the labeled data (AD/NC) slightly but is also able to predict subjects which are likely to converge to AD.

The authors used cross-sectional data (2001–2003) to consider the pathway through which past occupational lead exposure impacts cognitive function. They were motivated by studies linking cumulative lead dose with brain volumes, volumes with cognitive function, and lead dose with cognitive function. It was hypothesized that the brain regions associated with lead mediate a portion of the relation between lead dose and cognitive function. Data were derived from an ongoing US study of 513 former organolead manufacturing workers. Magnetic resonance imaging was used to perform a novel analysis to investigate mediation. Volumes associated with cognitive function and lead dose were derived by using registered images and were used in a subsequent mediation analysis. Cumulative lead dose was associated with adverse function in the visuo-construction, executive function, and eye-hand coordination domains. Regarding these domains, there was strong evidence of volumetric mediation of lead’s effect on cognition in the visuo-construction domain and a moderate amount for executive function and eye-hand coordination. A second path-analysis-based approach was also used. To address the possibility that chance associations explained these findings, a permuted analysis was conducted, the results of which supported the mediation inferences. The approach to evaluating volumetric mediation may have general applicability in epidemiologic neuroimaging settings.

Many progressive disorders are characterized by unclear or transient diagnoses for specific subgroups of patients. Commonly used supervised pattern recognition methodology may not be the most suitable approach to deriving image-based biomarkers in such cases, as it relies on the availability of categorically labeled data (e.g., patients and controls). In this paper, we explore the potential of semi-supervised pattern classification to provide image-based biomarkers in the absence of precise diagnostic information for some individuals. We employ semi-supervised support vector machines (SVM) and apply them to the problem of classifying MR brain images of patients with uncertain diagnoses. We examine patterns in serial scans of ADNI participants with mild cognitive impairment (MCI), and propose that in the absence of sufficient follow-up evaluations of individuals with MCI, semi-supervised strategy is potentially more appropriate than the fully-supervised paradigm employed up to date.

In this paper, we present a semi-supervised clustering-based framework for discovering coherent subpopulations in heterogeneous image sets. Our approach involves limited supervision in the form of labeled instances from two distributions that reflect a rough guess about subspace of features that are relevant for cluster analysis. By assuming that images are defined in a common space via registration to a common template, we propose a segmentation-based method for detecting locations that signify local regional differences in the two labeled sets. A PCA model of local image appearance is then estimated at each location of interest, and ranked with respect to its relevance for clustering. We develop an incremental k-means-like algorithm that discovers novel meaningful categories in a test image set. The application of our approach in this paper is in analysis of populations of healthy older adults. We validate our approach on a synthetic dataset, as well as on a dataset of brain images of older adults. We assess our method’s performance on the problem of discovering clusters of MR images of human brain, and present a cluster-based measure of pathology that reflects the deviation of a subject’s MR image from normal (i.e. cognitively stable) state. We analyze the clusters’ structure, and show that clustering results obtained using our approach correlate well with clinical data.

This paper investigates the problem of atlas registration of brain images with gliomas. Multi-parametric imaging modalities (T1, T1-CE, T2, and FLAIR) are first utilized for segmentations of different tissues, and to compute the posterior probability map (PBM) of membership to each tissue class, using supervised learning. Similar maps are generated in the initially normal atlas, by modeling the tumor growth, using reaction-diffusion equation. Deformable registration using a demons-like algorithm is used to register the patient images with the tumor bearing atlas. Joint estimation of the simulated tumor parameters (e.g. location, mass effect and degree of infiltration), and the spatial transformation is achieved by maximization of the log-likelihood of observation. An Expectation-Maximization algorithm is used in registration process to estimate the spatial transformation and other parameters related to tumor simulation are optimized through Asynchronous Parallel Pattern Search (APPSPACK). The proposed method has been evaluated on five simulated data sets created by Statistically Simulated Deformations (SSD), and fifteen real multichannel glioma data sets. The performance has been evaluated both quantitatively and qualitatively, and the results have been compared to ORBIT, an alternative method solving a similar problem. The results show that our method outperforms ORBIT, and the warped templates have better similarity to patient images.

This paper presents an approach for joint segmentation and deformable registration of brain scans of glioma patients to a normal atlas. The proposed method is based on the Expectation Maximization (EM) algorithm that incorporates a glioma growth model for atlas seeding, a process which modifies the normal atlas into one with a tumor and edema. The modified atlas is registered into the patient space and utilized for the posterior probability estimation of various tissue labels. EM iteratively refines the estimates of the registration parameters, the posterior probabilities of tissue labels and the tumor growth model parameters. We have applied this approach to 10 glioma scans acquired with four Magnetic Resonance (MR) modalities (T1, T1-CE, T2 and FLAIR ) and validated the result by comparing them to manual segmentations by clinical experts. The resulting segmentations look promising and quantitatively match well with the expert provided ground truth.

This study examined associations between polymorphisms in three genes, apolipoprotein E (APOE), angiotensin converting enzyme (ACE), and vitamin D receptor (VDR), and longitudinal change in brain volumes and white matter lesions (WML) as well as effect modification by cardiovascular factors and tibia lead concentrations. Two MRIs, an average of 5 years apart, were obtained for 317 former organolead workers and 45 population-based controls. Both regions-of-interest and voxel-wise analyses were conducted. APOE ε3/ε4 and ε4/ε4 genotypes were associated with less decline in white matter volumes. There was some evidence of interaction between genetic polymorphisms and cardiovascular risk factors (ACE and high-density lipoprotein; VDR and diabetes) on brain volume decline. The VDR FokI ff genotype was associated with an increase in WML (no association for APOE or ACE). This study expands our understanding of how genetic precursors of dementia and cardiovascular diseases are related to changes in brain structure.

Medical image registration is a challenging problem, especially when there is large anatomical variation in the anatomies. Geodesic registration methods have been proposed to solve the large deformation registration problem. However, analytically defined geodesic paths may not coincide with biologically plausible paths of registration, since the manifold of diffeomorphisms is immensely broader than the manifold spanned by diffeomorphisms between real anatomies. In this paper, we propose a novel framework for large deformation registration using the learned manifold of anatomical variation in the data. In this framework, a large deformation between two images is decomposed into a series of small deformations along the shortest path on an empirical manifold that represents anatomical variation. Using a manifold learning technique, the major variation of the data can be visualized by a low dimensional embedding, and the optimal group template is chosen as the geodesic mean on the manifold. We demonstrate the advantages of the proposed framework over direct registration with both simulated and real databases of brain images.