Adaptive fuzzy segmentation of magnetic resonance images

Rough sets for bias field correction in MR images using contraharmonic mean and quantitative index

One of the challenging tasks for magnetic resonance (MR) image analysis is to remove the intensity inhomogeneity artifact present in MR images, which often degrades the performance of an automatic image analysis technique. In this regard, the paper presents a novel approach for bias field correction in MR images. It judiciously integrates the merits of rough sets and contraharmonic mean. While the contraharmonic mean is used in low-pass averaging filter to estimate the bias field in multiplicative model, the concept of lower approximation and boundary region of rough sets deals with vagueness and incompleteness in filter structure definition. A theoretical analysis is presented to justify the use of both rough sets and contraharmonic mean for bias field estimation. The integration enables the algorithm to estimate optimum or near optimum bias field. Some new quantitative indexes are introduced to measure intensity inhomogeneity artifact present in a MR image. The performance of the proposed approach, along with a comparison with other approaches, is demonstrated on both simulated and real MR images for different bias fields and noise levels.

Automated measurement of cerebral cortical thickness based on fuzzy membership map derived from MR images for evaluation of Alzheimer's disease

We have proposed an automated method for three-dimensional (3D) measurement of cerebral cortical thicknesses based on fuzzy membership maps derived from magnetic resonance (MR) images for evaluation of Alzheimer's disease (AD). The cerebral cortical thickness was three-dimensionally measured on each cortical surface voxel by using a localized gradient vector trajectory in a fuzzy membership map. The proposed method could be useful for the 3D measurement of the cerebral cortical thickness on individual cortical surface voxels as an atrophy feature in AD.

Deformable templates guided discriminative models for robust 3D brain MRI segmentation

Automatically segmenting anatomical structures from 3D brain MRI images is an important task in neuroimaging. One major challenge is to design and learn effective image models accounting for the large variability in anatomy and data acquisition protocols. A deformable template is a type of generative model that attempts to explicitly match an input image with a template (atlas), and thus, they are robust against global intensity changes. On the other hand, discriminative models combine local image features to capture complex image patterns. In this paper, we propose a robust brain image segmentation algorithm that fuses together deformable templates and informative features. It takes advantage of the adaptation capability of the generative model and the classification power of the discriminative models. The proposed algorithm achieves both robustness and efficiency, and can be used to segment brain MRI images with large anatomical variations. We perform an extensive experimental study on four datasets of T1-weighted brain MRI data from different sources (1,082 MRI scans in total) and observe consistent improvement over the state-of-the-art systems.

Analytic estimation of statistical significance maps for support vector machine based multi-variate image analysis and classification

Multivariate pattern analysis (MVPA) methods such as support vector machines (SVMs) have been increasingly applied to fMRI and sMRI analyses, enabling the detection of distinctive imaging patterns. However, identifying brain regions that significantly contribute to the classification/group separation requires computationally expensive permutation testing. In this paper we show that the results of SVM-permutation testing can be analytically approximated. This approximation leads to more than a thousandfold speedup of the permutation testing procedure, thereby rendering it feasible to perform such tests on standard computers. The speedup achieved makes SVM based group difference analysis competitive with standard univariate group difference analysis methods.

Longitudinal progression of cognitive decline correlates with changes in the spatial pattern of brain 18F-FDG PET

Evaluating the symptomatic progression of mild cognitive impairment (MCI) caused by Alzheimer disease (AD) is practically accomplished by tracking performance on cognitive tasks, such as the Alzheimer Disease Assessment Scale's cognitive subscale (ADAS_cog), the Mini-Mental Status Examination (MMSE), and the Functional Activities Questionnaire (FAQ). The longitudinal relationships between cognitive decline and metabolic function as assessed using (18)F-FDG PET are needed to address both the cognitive and the biologic progression of disease state in individual subjects. We conducted an exploratory investigation to evaluate longitudinal changes in brain glucose metabolism of individual subjects and their relationship to the subject's changes of cognitive status.

METHODS

We describe a method to determine correlations in (18)F-FDG spatial distribution over time. This parameter is termed the regional (18)F-FDG time correlation coefficient (rFTC). By using linear mixed-effects models, we determined the difference in the rFTC decline rate between controls and subjects at high risk of developing AD, such as individuals with MCI or the presence of apolipoprotein E (APOE)-ε4 allele. The association between each subject's rFTC and performance on cognitive tests (ADAS_cog, MMSE, and FAQ) was determined with 2 different correlation methods. All subject data were downloaded from the Alzheimer Disease Neuroimaging Initiative.

RESULTS

The rFTC values of controls remained fairly constant over time (-0.003 annual change; 95% confidence interval, -0.010-0.004). In MCI patients, the rFTC declined faster than in controls by an additional annual change of -0.02 (95% confidence interval, -0.030 to -0.010). In MCI patients, the decline in rFTC was associated with cognitive decline (ADAS_cog, P = 0.011; FAQ, P = 0.0016; MMSE, P = 0.004). After a linear effect of time was accounted for, visit-to-visit changes in rFTC correlated with visit-to-visit changes in all 3 cognitive tests.

CONCLUSION

Longitudinal changes in rFTC detect subtle metabolic changes in individuals associated with variations in their cognition. This analytic tool may be useful for a patient-based monitoring of cognitive decline.

Localized FCM Clustering with Spatial Information for Medical Image Segmentation and Bias Field Estimation

This paper presents a novel fuzzy energy minimization method for simultaneous segmentation and bias field estimation of medical images. We first define an objective function based on a localized fuzzy c-means (FCM) clustering for the image intensities in a neighborhood around each point. Then, this objective function is integrated with respect to the neighborhood center over the entire image domain to formulate a global fuzzy energy, which depends on membership functions, a bias field that accounts for the intensity inhomogeneity, and the constants that approximate the true intensities of the corresponding tissues. Therefore, segmentation and bias field estimation are simultaneously achieved by minimizing the global fuzzy energy. Besides, to reduce the impact of noise, the proposed algorithm incorporates spatial information into the membership function using the spatial function which is the summation of the membership functions in the neighborhood of each pixel under consideration. Experimental results on synthetic and real images are given to demonstrate the desirable performance of the proposed algorithm.

Bayesian Parameter Estimation and Segmentation in the Multi-Atlas Random Orbit Model

This paper examines the multiple atlas random diffeomorphic orbit model in Computational Anatomy (CA) for parameter estimation and segmentation of subcortical and ventricular neuroanatomy in magnetic resonance imagery. We assume that there exist multiple magnetic resonance image (MRI) atlases, each atlas containing a collection of locally-defined charts in the brain generated via manual delineation of the structures of interest. We focus on maximum a posteriori estimation of high dimensional segmentations of MR within the class of generative models representing the observed MRI as a conditionally Gaussian random field, conditioned on the atlas charts and the diffeomorphic change of coordinates of each chart that generates it. The charts and their diffeomorphic correspondences are unknown and viewed as latent or hidden variables. We demonstrate that the expectation-maximization (EM) algorithm arises naturally, yielding the likelihood-fusion equation which the a posteriori estimator of the segmentation labels maximizes. The likelihoods being fused are modeled as conditionally Gaussian random fields with mean fields a function of each atlas chart under its diffeomorphic change of coordinates onto the target. The conditional-mean in the EM algorithm specifies the convex weights with which the chart-specific likelihoods are fused. The multiple atlases with the associated convex weights imply that the posterior distribution is a multi-modal representation of the measured MRI. Segmentation results for subcortical and ventricular structures of subjects, within populations of demented subjects, are demonstrated, including the use of multiple atlases across multiple diseased groups.

Increasing the contrast of the brain MR FLAIR images using fuzzy membership functions and structural similarity indices in order to segment MS lesions

Segmentation is an important step for the diagnosis of multiple sclerosis (MS). This paper presents a new approach to the fully automatic segmentation of MS lesions in Fluid Attenuated Inversion Recovery (FLAIR) Magnetic Resonance (MR) images. With the aim of increasing the contrast of the FLAIR MR images with respect to the MS lesions, the proposed method first estimates the fuzzy memberships of brain tissues (i.e., the cerebrospinal fluid (CSF), the normal-appearing brain tissue (NABT), and the lesion). The procedure for determining the fuzzy regions of their member functions is performed by maximizing fuzzy entropy through Genetic Algorithm. Research shows that the intersection points of the obtained membership functions are not accurate enough to segment brain tissues. Then, by extracting the structural similarity (SSIM) indices between the FLAIR MR image and its lesions membership image, a new contrast-enhanced image is created in which MS lesions have high contrast against other tissues. Finally, the new contrast-enhanced image is used to segment MS lesions. To evaluate the result of the proposed method, similarity criteria from all slices from 20 MS patients are calculated and compared with other methods, which include manual segmentation. The volume of segmented lesions is also computed and compared with Gold standard using the Intraclass Correlation Coefficient (ICC) and paired samples t test. Similarity index for the patients with small lesion load, moderate lesion load and large lesion load was 0.7261, 0.7745 and 0.8231, respectively. The average overall similarity index for all patients is 0.7649. The t test result indicates that there is no statistically significant difference between the automatic and manual segmentation. The validated results show that this approach is very promising.

A fast and robust level set method for image segmentation using fuzzy clustering and lattice Boltzmann method

In the last decades, due to the development of the parallel programming, the lattice Boltzmann method (LBM) has attracted much attention as a fast alternative approach for solving partial differential equations. In this paper, we first designed an energy functional based on the fuzzy c-means objective function which incorporates the bias field that accounts for the intensity inhomogeneity of the real-world image. Using the gradient descent method, we obtained the corresponding level set equation from which we deduce a fuzzy external force for the LBM solver based on the model by Zhao. The method is fast, robust against noise, independent to the position of the initial contour, effective in the presence of intensity inhomogeneity, highly parallelizable and can detect objects with or without edges. Experiments on medical and real-world images demonstrate the performance of the proposed method in terms of speed and efficiency.

Segmentation of brain MRI using SOM-FCM-based method and 3D statistical descriptors

Current medical imaging systems provide excellent spatial resolution, high tissue contrast, and up to 65535 intensity levels. Thus, image processing techniques which aim to exploit the information contained in the images are necessary for using these images in computer-aided diagnosis (CAD) systems. Image segmentation may be defined as the process of parcelling the image to delimit different neuroanatomical tissues present on the brain. In this paper we propose a segmentation technique using 3D statistical features extracted from the volume image. In addition, the presented method is based on unsupervised vector quantization and fuzzy clustering techniques and does not use any a priori information. The resulting fuzzy segmentation method addresses the problem of partial volume effect (PVE) and has been assessed using real brain images from the Internet Brain Image Repository (IBSR).

Atlas-based neuroinformatics via MRI: harnessing information from past clinical cases and quantitative image analysis for patient care

With the ever-increasing amount of anatomical information radiologists have to evaluate for routine diagnoses, computational support that facilitates more efficient education and clinical decision making is highly desired. Despite the rapid progress of image analysis technologies for magnetic resonance imaging of the human brain, these methods have not been widely adopted for clinical diagnoses. To bring computational support into the clinical arena, we need to understand the decision-making process employed by well-trained clinicians and develop tools to simulate that process. In this review, we discuss the potential of atlas-based clinical neuroinformatics, which consists of annotated databases of anatomical measurements grouped according to their morphometric phenotypes and coupled with the clinical informatics upon which their diagnostic groupings are based. As these are indexed via parametric representations, we can use image retrieval tools to search for phenotypes along with their clinical metadata. The review covers the current technology, preliminary data, and future directions of this field.

Patient-specific computational biomechanics of the brain without segmentation and meshing

Motivated by patient-specific computational modelling in the context of image-guided brain surgery, we propose a new fuzzy mesh-free modelling framework. The method works directly on an unstructured cloud of points that do not form elements so that mesh generation is not required. Mechanical properties are assigned directly to each integration point based on fuzzy tissue classification membership functions without the need for image segmentation. Geometric integration is performed over an underlying uniform background grid. The verification example shows that, while requiring no hard segmentation and meshing, the proposed model gives, for all practical purposes, equivalent results to a finite element model.

System for integrated neuroimaging analysis and processing of structure

Mapping brain structure in relation to neurological development, function, plasticity, and disease is widely considered to be one of the most essential challenges for opening new lines of neuro-scientific inquiry. Recent developments with MRI analysis of structural connectivity, anatomical brain segmentation, cortical surface parcellation, and functional imaging have yielded fantastic advances in our ability to probe the neurological structure-function relationship in vivo. To date, the image analysis efforts in each of these areas have typically focused on a single modality. Here, we extend the cortical reconstruction using implicit surface evolution (CRUISE) methodology to perform efficient, consistent, and topologically correct analyses in a natively multi-parametric manner. This effort combines and extends state-of-the-art techniques to simultaneously consider and analyze structural and diffusion information alongside quantitative and functional imaging data. Robust and consistent estimates of the cortical surface extraction, cortical labeling, diffusion-inferred contrasts, diffusion tractography, and subcortical parcellation are demonstrated in a scan-rescan paradigm. Accompanying this demonstration, we present a fully automated software system complete with validation data.

An improved variational level set method for MR image segmentation and bias field correction

In this paper, we propose an improved variational level set approach to correct the bias and to segment the magnetic resonance (MR) images with inhomogeneous intensity. First, we use a Gaussian distribution with bias field as a local region descriptor in two-phase level set formulation for segmentation and bias field correction of the images with inhomogeneous intensities. By using the information of the local variance in this descriptor, our method is able to obtain accurate segmentation results. Furthermore, we extend this method to three-phase level set formulation for brain MR image segmentation and bias field correction. By using this three-phase level set function to replace the four-phase level set function, we can reduce the number of convolution operations in each iteration and improve the efficiency. Compared with other approaches, this algorithm demonstrates a superior performance.

Cognitive and functional resilience despite molecular evidence of Alzheimer's disease pathology

BACKGROUND

The correlation between neuropathological lesions and cognition is modest. Some individuals remain cognitively intact despite the presence of significant Alzheimer's disease (AD) pathology, whereas others manifest cognitive symptoms and dementia in the same context. The aim of the present study was to examine cognitive and cerebral reserve factors associated with resilient functioning in the setting of AD pathology.

METHODS

University of Pennsylvania Alzheimer's Disease Center research participants with biochemical biomarker evidence of AD pathology (cerebrospinal fluid amyloid-β1-42 <192 pg/mL) and comparable medial temporal lobe atrophy were categorized by Clinical Dementia Rating Scale-Sum of Boxes (CDR-SOB) score as AD dementia (CDR-SOB >1) or AD resilient (CDR-SOB ≤0.5). Groups were compared for a variety of demographic, clinical, and neuroimaging variables to identify factors that are associated with resilience to AD pathology.

RESULTS

A univariate model identified education and intracranial volume (ICV) as significant covariates. In a multivariate model with backward selection procedure, ICV was retained as a factor most significantly associated with resilience. The interaction term between ICV and education was not significant, suggesting that larger cranial vault size is associated with resilience even in the absence of more education.

CONCLUSIONS

Premorbid brain volume, as measured through ICV, provided protection against clinical manifestations of dementia despite evidence of significant accumulations of AD pathology. This finding provides support for the brain reserve hypothesis of resilience to AD.

Generalized rough fuzzy c-means algorithm for brain MR image segmentation

Fuzzy sets and rough sets have been widely used in many clustering algorithms for medical image segmentation, and have recently been combined together to better deal with the uncertainty implied in observed image data. Despite of their wide spread applications, traditional hybrid approaches are sensitive to the empirical weighting parameters and random initialization, and hence may produce less accurate results. In this paper, a novel hybrid clustering approach, namely the generalized rough fuzzy c-means (GRFCM) algorithm is proposed for brain MR image segmentation. In this algorithm, each cluster is characterized by three automatically determined rough-fuzzy regions, and accordingly the membership of each pixel is estimated with respect to the region it locates. The importance of each region is balanced by a weighting parameter, and the bias field in MR images is modeled by a linear combination of orthogonal polynomials. The weighting parameter estimation and bias field correction have been incorporated into the iterative clustering process. Our algorithm has been compared to the existing rough c-means and hybrid clustering algorithms in both synthetic and clinical brain MR images. Experimental results demonstrate that the proposed algorithm is more robust to the initialization, noise, and bias field, and can produce more accurate and reliable segmentations.

Low degree of cortical pathology is associated with benign course of multiple sclerosis

BACKGROUND

Although a more favorable course of multiple sclerosis is associated with a low degree of cortical pathology, only longitudinal studies could definitely confirm this association.

MATERIALS AND METHODS

We followed 95 early relapsing-remitting MS (RRMS; median Expanded Disability Status Scale (EDSS) = 1.5, mean disease duration = 3.1 ± 1.3 years) and 45 benign MS patients (EDSS ≤ 3.0, disease duration ≥ 15 years, normal cognition) for 6 years, with EDSS evaluations every 6 months and brain magnetic resonance imaging (MRI) at baseline and then yearly.

RESULTS

At baseline, we detected 406 cortical lesions (CLs) in 67/95 (70.5%) early RRMS and in 24/45 (53.3%) benign MS patients (p = 0.046). After 6 years, the appearance of new CLs was observed in 80/95 (84.2%; 518 CLs) of our early RRMS and in 25/45 (55.5%; 63 CLs; p < 0.001) benign MS patients. At baseline, after corrections for age and disease duration, we observed a cortical thinning of several frontal and temporal regions in our RRMS study patients, compared to the benign MS patients (p ranging between 0.001-0.05). After 6 years, the cortical thinning had increased significantly in several cortices of RRMS patients, but only in the occipital-temporal (p = 0.036) and superior parietal gyrus (p = 0.035) of those with benign MS. Stepwise regression analysis revealed the CL volume (p = 0.006) and the cortical thickness of the temporal middle (p < 0.001), insular long (p < 0.001), superior frontal (p < 0.001) and middle frontal gyri (p < 0.001) as the most sensitive independent predictors of a favorable disease course.

CONCLUSIONS

Our data confirmed that a significantly milder cortical pathology characterizes the most favorable clinical course of MS. Measures of focal and diffuse grey matter should be combined to increase the accuracy in the identification of a benign MS course.

Alcohol consumption and premotor corpus callosum in older adults

Heavy alcohol consumption is toxic to the brain, especially to the frontal white matter (WM), but whether lesser amounts of alcohol negatively impact the brain WM is unclear. In this study, we examined the relationship between self-reported alcohol consumption and regional WM and grey matter (GM) volume in fifty-six men and thirty-seven women (70+- 7years) cognitively intact participants of the Baltimore Longitudinal Study of Aging (BLSA) with no history of alcohol abuse. We used regional analysis of volumes examined in normalized space (RAVENS) maps methodology for WM and GM segmentation and normalization followed by voxel based morphometry (VBM) implemented in SPM8 to examine the cross-sectional association between alcohol consumption and regional WM (and, separately, GM) volume controlling for age, sex, smoking, blood pressure and dietary thiamine intake. WM VBM revealed that in men, but not in women, higher alcohol consumption was associated with lower volume in premotor frontal corpus callosum. This finding suggests that even moderate amounts of alcohol may be detrimental to corpus callosum and white matter integrity.

Efficient inhomogeneity compensation using fuzzy c-means clustering models

Intensity inhomogeneity or intensity non-uniformity (INU) is an undesired phenomenon that represents the main obstacle for magnetic resonance (MR) image segmentation and registration methods. Various techniques have been proposed to eliminate or compensate the INU, most of which are embedded into classification or clustering algorithms, they generally have difficulties when INU reaches high amplitudes and usually suffer from high computational load. This study reformulates the design of c-means clustering based INU compensation techniques by identifying and separating those globally working computationally costly operations that can be applied to gray intensity levels instead of individual pixels. The theoretical assumptions are demonstrated using the fuzzy c-means algorithm, but the proposed modification is compatible with a various range of c-means clustering based INU compensation and MR image segmentation algorithms. Experiments carried out using synthetic phantoms and real MR images indicate that the proposed approach produces practically the same segmentation accuracy as the conventional formulation, but 20-30 times faster.

Classification of multicolor fluorescence in situ hybridization (M-FISH) images with sparse representation

There has been a considerable interest in sparse representation and compressive sensing in applied mathematics and signal processing in recent years but with limited success to medical image processing. In this paper we developed a sparse representation-based classification (SRC) algorithm based on L1-norm minimization for classifying chromosomes from multicolor fluorescence in situ hybridization (M-FISH) images. The algorithm has been tested on a comprehensive M-FISH database that we established, demonstrating improved performance in classification. When compared with other pixel-wise M-FISH image classifiers such as fuzzy c-means (FCM) clustering algorithms and adaptive fuzzy c-means (AFCM) clustering algorithms that we proposed earlier the current method gave the lowest classification error. In order to evaluate the performance of different SRC for M-FISH imaging analysis, three different sparse representation methods, namely, Homotopy method, Orthogonal Matching Pursuit (OMP), and Least Angle Regression (LARS), were tested and compared. Results from our statistical analysis have shown that Homotopy based method is significantly better than the other two methods. Our work indicates that sparse representations based classifiers with proper models can outperform many existing classifiers for M-FISH classification including those that we proposed before, which can significantly improve the multicolor imaging system for chromosome analysis in cancer and genetic disease diagnosis.

Investigating axonal damage in multiple sclerosis by diffusion tensor spectroscopy

Sensitive and specific in vivo measures of axonal damage, an important determinant of clinical status in multiple sclerosis (MS), might greatly benefit prognostication and therapy assessment. Diffusion tensor spectroscopy (DTS) combines features of diffusion tensor imaging and magnetic resonance spectroscopy, allowing measurement of the diffusion properties of intracellular, cell-type-specific metabolites. As such, it may be sensitive to disruption of tissue microstructure within neurons. In this cross-sectional pilot study, diffusion of the neuronal metabolite N-acetylaspartate (NAA) was measured in the human normal-appearing corpus callosum on a 7 tesla MRI scanner, comparing 15 MS patients and 14 healthy controls. We found that NAA parallel diffusivity is lower in MS (p = 0.030) and inversely correlated with both water parallel diffusivity (p = 0.020) and clinical severity (p = 0.015). Interpreted in the context of previous experiments, our findings provide preliminary evidence that DTS can distinguish axonopathy from other processes such as inflammation, edema, demyelination, and gliosis. By detecting reduced diffusion of NAA parallel to axons in white matter, DTS may thus be capable of distinguishing axonal disruption in MS in the setting of increased parallel diffusion of water, which is commonly observed in MS but pathologically nonspecific.

Topology-based nonlocal fuzzy segmentation of brain MR image with inhomogeneous and partial volume intensity

PURPOSE

The aim was to automatically segment brain magnetic resonance (MR) image with inhomogeneous and partial volume (PV) intensity for brain and neurophysiology analysis.

METHODS

Rather than assuming the presence of a single bias field over the image data, we first apply a local model to MR image analysis. With the brain topology knowledge, several specific local regions are selected, and typical brain tissues are then extracted for the prior estimation of fuzzy clustering center and member function. A new nonlocal fuzzy labeling scheme is applied to global optimization segmentation based on the block comparison and distance weight, which is robust to noise and inhomogeneous intensity. The nonlocal labeling provides optimized fuzzy member value and local intensity estimation of brain tissues such as cerebrospinal fluid (CSF), white matter (WM), and gray matter (GM). In addition to inhomogeneous intensity, PV may lead to error segmentation. To correct error segmentation because of PV, this article also provides two correction schemes. The first one is to extract CSF in deep sulci, which captures more CSF candidate by intensity comparison and topology shape comparison. The local pure CSF, WM, and GM is then estimated to correct the interfaces of CSF/GM and WM/GM.

RESULTS

The segmentation experiments are performed on both brainweb-simulated images and Internet brain segmentation repository database (IBSR) real images. The experimental results demonstrate the robust and efficient performance of our approach.

CONCLUSIONS

Our approach can be applied to automatic segmentation of the brain MR image.

The five factors of personality and regional cortical variability in the Baltimore longitudinal study of aging

Although personality changes have been associated with brain lesions and atrophy caused by neurodegenerative diseases and aging, neuroanatomical correlates of personality in healthy individuals and their stability over time have received relatively little investigation. In this study, we explored regional gray matter (GM) volumetric associations of the five-factor model of personality. Eighty-seven healthy older adults took the NEO Personality Inventory and had brain MRI at two time points 2 years apart. We performed GM segmentation followed by regional analysis of volumes examined in normalized space map creation and voxel based morphometry-type statistical inference in SPM8. We created a regression model including all five factors and important covariates. Next, a conjunction analysis identified associations between personality scores and GM volumes that were replicable across time, also using cluster-level Family-Wise-Error correction. Larger right orbitofrontal and dorsolateral prefrontal cortices and rolandic operculum were associated with lower Neuroticism; larger left temporal, dorsolateral prefrontal, and anterior cingulate cortices with higher Extraversion; larger right frontopolar and smaller orbitofrontal and insular cortices with higher Openness; larger right orbitofrontal cortex with higher Agreeableness; larger dorsolateral prefrontal and smaller frontopolar cortices with higher Conscientiousness. In summary, distinct personality traits were associated with stable individual differences in GM volumes. As expected for higher-order traits, regions performing a large number of cognitive and affective functions were implicated. Our findings highlight personality-related variation that may be related to individual differences in brain structure that merit additional attention in neuroimaging research.

JointMMCC: joint maximum-margin classification and clustering of imaging data

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 nonconvex optimization problem associated with JointMMCC. We apply our proposed approach to an medical resonance imaging study of aging, and identify coherent subpopulations (i.e., clusters) of cognitively less stable adults.

Pure-tone auditory thresholds are not chronically elevated in multiple sclerosis

Despite the fact that acute cases of multiple sclerosis (MS)-related pure-tone hearing loss have been reported in the literature, consensus is lacking as to the chronic influences of MS on pure-tone thresholds. Most studies examining such influences have been limited by small sample sizes, lack of statistical comparisons between patients and controls, and confounding of the hearing measure with influences from sex and age. To date, associations between pure-tone thresholds and central MS-related brain lesions have not been assessed. In this study, pure-tone thresholds ranging from 0.5 to 8 kHz were measured in 73 MS patients and 73 individually age- and gender-matched normal controls. In 63 MS patients, correlations were computed between the threshold values and MRI-determined lesion activity in 26 central brain regions. Although thresholds were strongly influenced by sex, age, and tonal frequency, no meaningful influences of MS were discerned. Moreover, no significant association between the threshold values and central MS-related lesion activity was evident in any brain region evaluated. This study, the largest on this topic to use carefully matched control subjects and the sole study to assess relationships between auditory thresholds and central MS-related lesions, strongly suggests that (a) MS is not chronically associated with pure-tone hearing loss and (b) pure-tone thresholds are unrelated to MS lesion activity in higher brain regions. These findings, along with general reports from the literature, support the concept that when MS-related hearing threshold deficits are found, they are episodic and primarily dependent on lesions within the eighth nerve or brainstem.

Longitudinal imaging pattern analysis (SPARE-CD index) detects early structural and functional changes before cognitive decline in healthy older adults

This article investigates longitudinal imaging characteristics of early cognitive decline during normal aging, leveraging on high-dimensional imaging pattern classification methods for the development of early biomarkers of cognitive decline. By combining magnetic resonance imaging (MRI) and resting positron emission tomography (PET) cerebral blood flow (CBF) images, an individualized score is generated using high-dimensional pattern classification, which predicts subsequent cognitive decline in cognitively normal older adults of the Baltimore Longitudinal Study of Aging. The resulting score, termed SPARE-CD (Spatial Pattern of Abnormality for Recognition of Early Cognitive Decline), analyzed longitudinally for 143 cognitively normal subjects over 8 years, shows functional and structural changes well before (2.3-2.9 years) changes in neurocognitive testing (California Verbal Learning Test [CVLT] scores) can be measured. Additionally, this score is found to be correlated to the [(11)C] Pittsburgh compound B (PiB) PET mean distribution volume ratio at a later time. This work indicates that MRI and PET images, combined with advanced pattern recognition methods, may be useful for very early detection of cognitive decline.

Consistent segmentation using a Rician classifier

Several popular classification algorithms used to segment magnetic resonance brain images assume that the image intensities, or log-transformed intensities, satisfy a finite Gaussian mixture model. In these methods, the parameters of the mixture model are estimated and the posterior probabilities for each tissue class are used directly as soft segmentations or combined to form a hard segmentation. It is suggested and shown in this paper that a Rician mixture model fits the observed data better than a Gaussian model. Accordingly, a Rician mixture model is formulated and used within an expectation maximization (EM) framework to yield a new tissue classification algorithm called Rician Classifier using EM (RiCE). It is shown using both simulated and real data that RiCE yields comparable or better performance to that of algorithms based on the finite Gaussian mixture model. As well, we show that RiCE yields more consistent segmentation results when used on images of the same individual acquired with different T1-weighted pulse sequences. Therefore, RiCE has the potential to stabilize segmentation results in brain studies involving heterogeneous acquisition sources as is typically found in both multi-center and longitudinal studies.

Cortical Surface Reconstruction from High-Resolution MR Brain Images

Reconstruction of the cerebral cortex from magnetic resonance (MR) images is an important step in quantitative analysis of the human brain structure, for example, in sulcal morphometry and in studies of cortical thickness. Existing cortical reconstruction approaches are typically optimized for standard resolution (~1 mm) data and are not directly applicable to higher resolution images. A new PDE-based method is presented for the automated cortical reconstruction that is computationally efficient and scales well with grid resolution, and thus is particularly suitable for high-resolution MR images with submillimeter voxel size. The method uses a mathematical model of a field in an inhomogeneous dielectric. This field mapping, similarly to a Laplacian mapping, has nice laminar properties in the cortical layer, and helps to identify the unresolved boundaries between cortical banks in narrow sulci. The pial cortical surface is reconstructed by advection along the field gradient as a geometric deformable model constrained by topology-preserving level set approach. The method's performance is illustrated on exvivo images with 0.25–0.35 mm isotropic voxels. The method is further evaluated by cross-comparison with results of the FreeSurfer software on standard resolution data sets from the OASIS database featuring pairs of repeated scans for 20 healthy young subjects.

ADAPTIVE SEGMENTATION OF MEDICAL MR IMAGES BASED ON BIAS CORRECTION

A two-phase model is introduced to extract clinically useful information from medical MR images. In the preprocessing phase, a refined bias correction method is adopted to reduce the influence of intensity inhomogeneity by removing the bias field, which paves the way for improving the subsequent segmentation accuracy. During image segmentation process, a novel adaptive level set technique is designed to capture the boundary of desired region. By virtue of adaptive driving term, the external force automatically changes its propagating direction when evolving curve goes through object boundary, which effectively prevents the final results deviating from correct position. Moreover, insensitivity to initial contour also enables its automatic applications. Experiments on synthetic and real MR images demonstrate the feasibility and robustness of the proposed method.

Fuzzy local Gaussian mixture model for brain MR image segmentation

Accurate brain tissue segmentation from magnetic resonance (MR) images is an essential step in quantitative brain image analysis. However, due to the existence of noise and intensity inhomogeneity in brain MR images, many segmentation algorithms suffer from limited accuracy. In this paper, we assume that the local image data within each voxel's neighborhood satisfy the Gaussian mixture model (GMM), and thus propose the fuzzy local GMM (FLGMM) algorithm for automated brain MR image segmentation. This algorithm estimates the segmentation result that maximizes the posterior probability by minimizing an objective energy function, in which a truncated Gaussian kernel function is used to impose the spatial constraint and fuzzy memberships are employed to balance the contribution of each GMM. We compared our algorithm to state-of-the-art segmentation approaches in both synthetic and clinical data. Our results show that the proposed algorithm can largely overcome the difficulties raised by noise, low contrast, and bias field, and substantially improve the accuracy of brain MR image segmentation.

Magnetic Resonance Image Analysis for Brain CAD Systems with Machine Learning

This chapter describes the image analysis for brain Computer-Aided Diagnosis (CAD) systems with machine learning techniques, which could assist radiologists in the detection of such brain diseases as asymptomatic unruptured aneurysms, Alzheimer’s Disease (AD), vascular dementia, and Multiple Sclerosis (MS) by magnetic resonance imaging. Image analysis in CAD systems consists of image enhancement, initial detection, and image feature extraction, including segmentation. In addition, the authors review the classification of true and false positives using machine learning techniques, as well as the evaluation methods and development cycle for CAD systems.

A composite multivariate polygenic and neuroimaging score for prediction of conversion to Alzheimer's disease

Alzheimer's disease (AD) and Mild Cognitive Impairment (MCI) are characterized by widespread pathological changes in the brain. At the same time, Alzheimer's disease is heritable with complex genetic underpinnings that may influence the timing of the related pathological changes in the brain and can affect the progression from MCI to AD. In this paper, we present a multivariate imaging genetics approach for prediction of conversion to Alzheimer's disease in patients with mild cognitive impairment. We employ multivariate pattern recognition approaches to obtain neuroimaging and polygenic discriminators between the healthy individuals and AD patients. We then design, in a linear manner, a composite imaging-genetic score for prediction of conversion to Alzheimer's disease in patients with mild cognitive impairment. We apply our approach within the Alzheimer's Disease Neuroimaging Initiative and show that the integration of polygenic and neuroimaging information improves prediction of conversion to AD.

Generative-discriminative basis learning for medical imaging

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.

Longitudinally guided level sets for consistent tissue segmentation of neonates

Quantification of brain development as well as disease-induced pathologies in neonates often requires precise delineation of white matter, grey matter and cerebrospinal fluid. Unlike adults, tissue segmentation in neonates is significantly more challenging due to the inherently lower tissue contrast. Most existing methods take a voxel-based approach and are limited to working with images from a single time-point, even though longitudinal scans are available. We take a different approach by taking advantage of the fact that the pattern of the major sulci and gyri are already present in the neonates and generally preserved but fine-tuned during brain development. That is, the segmentation of late-time-point image can be used to guide the segmentation of neonatal image. Accordingly, we propose a novel longitudinally guided level-sets method for consistent neonatal image segmentation by combining local intensity information, atlas spatial prior, cortical thickness constraint, and longitudinal information into a variational framework. The minimization of the proposed energy functional is strictly derived from a variational principle. Validation performed on both simulated and in vivo neonatal brain images shows promising results.

A NOVEL FUZZY C-MEANS ALGORITHM AND ITS APPLICATION

The accurate and effective algorithm for segmenting image is very useful in many fields, especially in medical images. In this paper we introduced a novel method that focuses on segmenting the brain MR Image that is important for neural diseases. Because of many noises embedded in the acquiring procedure, such as eddy currents, susceptibility artifacts, rigid body motion and intensity inhomogeneity, segmenting the brain MR image is a difficult work. In this algorithm, we overcame the inhomogeneity shortage, by modifying the objective function by compensating its immediate neighborhood effect using Gaussian smooth method for decreasing the influence of the inhomogeneity and increasing the segmenting accuracy. Using simulate image and clinical MRI data, experiments show that our proposed algorithm is effective.

Cortical diffusion-tensor imaging abnormalities in multiple sclerosis: a 3-year longitudinal study

PURPOSE

To evaluate whether diffusion-tensor imaging can be combined with double inversion recovery to improve the detection of structural changes occurring in the cortex of patients with multiple sclerosis (MS).

MATERIALS AND METHODS

Once local ethics committee approval and informed consent were obtained, 168 patients with relapsing-remitting MS and 45 sex- and age-matched control subjects were included in a 3-year longitudinal study. Expanded Disability Status Scale (EDSS) and magnetic resonance (MR) imaging examinations were performed at study entry and after 3 years. Number and volume of cortical lesions, T2 white matter lesion volume (WMLV), and fractional anisotropy (FA) and mean diffusivity (MD) of normal-appearing gray matter (NAGM) and cortical lesions were analyzed. Between-group differences in terms of NAGM-FA and NAGM-MD were assessed with analysis of variance followed by Tukey test correction.

RESULTS

At baseline, NAGM-FA was higher in patients (mean ± standard deviation, 0.149 ± 0.011) than in control subjects (0.125 ± 0.008; P < .001) and higher in patients with cortical lesions (0.154 ± 0.011) than in those without (0.138 ± 0.010; P < .001). Moreover, FA was higher in cortical lesions than in NAGM (P < .001). After 3 years, NAGM-FA was unchanged in control subjects and increased in patients (0.154 ± 0.012; P < .001), especially in patients with worsened EDSS score (0.170 ± 0.011; P < .001). The same behavior was observed for NAGM-MD. At baseline, NAGM-FA significantly correlated with EDSS score (r = 0.75; P < .001) and cortical lesion volume (r = 0.850; P < .001). Multivariate analysis identified NAGM-FA (B = 0.654; P < .001) and T2 WMLV (B = 0.310; P < .001) as independent predictors of EDSS score, while NAGM-FA change (B = 0.523; P < .001) and disease duration (B = 0.342; P < .001) were independent predictors of EDSS change.

CONCLUSION

Compared with control subjects, patients with RRMS had an increase in FA of NAGM that strongly correlated with cortical lesion volume and clinical disability.