Adaptive fuzzy segmentation of magnetic resonance images

Encoding probabilistic brain atlases using Bayesian inference

This paper addresses the problem of creating probabilistic brain atlases from manually labeled training data. Probabilistic atlases are typically constructed by counting the relative frequency of occurrence of labels in corresponding locations across the training images. However, such an "averaging" approach generalizes poorly to unseen cases when the number of training images is limited, and provides no principled way of aligning the training datasets using deformable registration. In this paper, we generalize the generative image model implicitly underlying standard "average" atlases, using mesh-based representations endowed with an explicit deformation model. Bayesian inference is used to infer the optimal model parameters from the training data, leading to a simultaneous group-wise registration and atlas estimation scheme that encompasses standard averaging as a special case. We also use Bayesian inference to compare alternative atlas models in light of the training data, and show how this leads to a data compression problem that is intuitive to interpret and computationally feasible. Using this technique, we automatically determine the optimal amount of spatial blurring, the best deformation field flexibility, and the most compact mesh representation. We demonstrate, using 2-D training datasets, that the resulting models are better at capturing the structure in the training data than conventional probabilistic atlases. We also present experiments of the proposed atlas construction technique in 3-D, and show the resulting atlases' potential in fully-automated, pulse sequence-adaptive segmentation of 36 neuroanatomical structures in brain MRI scans.

Prostate cancer segmentation with simultaneous estimation of Markov random field parameters and class

Prostate cancer is one of the leading causes of death from cancer among men in the United States. Currently, high-resolution magnetic resonance imaging (MRI) has been shown to have higher accuracy than trans-rectal ultrasound (TRUS) when used to ascertain the presence of prostate cancer. As MRI can provide both morphological and functional images for a tissue of interest, some researchers are exploring the uses of multispectral MRI to guide prostate biopsies and radiation therapy. However, success with prostate cancer localization based on current imaging methods has been limited due to overlap in feature space of benign and malignant tissues using any one MRI method and the interobserver variability. In this paper, we present a new unsupervised segmentation method for prostate cancer detection, using fuzzy Markov random fields (fuzzy MRFs) for the segmentation of multispectral MR prostate images. Typically, both hard and fuzzy MRF models have two groups of parameters to be estimated: the MRF parameters and class parameters for each pixel in the image. To date, these two parameters have been treated separately, and estimated in an alternating fashion. In this paper, we develop a new method to estimate the parameters defining the Markovian distribution of the measured data, while performing the data clustering simultaneously. We perform computer simulations on synthetic test images and multispectral MR prostate datasets to demonstrate the efficacy and efficiency of the proposed method and also provide a comparison with some of the commonly used methods.

MR image segmentation using a power transformation approach

This study proposes a segmentation method for brain MR images using a distribution transformation approach. The method extends traditional Gaussian mixtures expectation-maximization segmentation to a power transformed version of mixed intensity distributions, which includes Gaussian mixtures as a special case. As MR intensities tend to exhibit non-Gaussianity due to partial volume effects, the proposed method is designed to fit non-Gaussian tissue intensity distributions. One advantage of the method is that it is intuitively appealing and computationally simple. To avoid performance degradation caused by intensity inhomogeneity, different methods for correcting bias fields were applied prior to image segmentation, and their correction effects on the segmentation results were examined in the empirical study. The partitions of brain tissues (i.e., gray and white matter) resulting from the method were validated and evaluated against manual segmentation results based on 38 real T1-weighted image volumes from the internet brain segmentation repository, and 18 simulated image volumes from BrainWeb. The Jaccard and Dice similarity indexes were computed to evaluate the performance of the proposed approach relative to the expert segmentations. Empirical results suggested that the proposed segmentation method yielded higher similarity measures for both gray matter and white matter as compared with those based on the traditional segmentation using the Gaussian mixtures approach.

Improved cerebellar tissue classification on magnetic resonance images of brain

PURPOSE

To develop and implement a method for improved cerebellar tissue classification on the MRI of brain by automatically isolating the cerebellum prior to segmentation.

MATERIALS AND METHODS

Dual fast spin echo (FSE) and fluid attenuation inversion recovery (FLAIR) images were acquired on 18 normal volunteers on a 3 T Philips scanner. The cerebellum was isolated from the rest of the brain using a symmetric inverse consistent nonlinear registration of individual brain with the parcellated template. The cerebellum was then separated by masking the anatomical image with individual FLAIR images. Tissues in both the cerebellum and rest of the brain were separately classified using hidden Markov random field (HMRF), a parametric method, and then combined to obtain tissue classification of the whole brain. The proposed method for tissue classification on real MR brain images was evaluated subjectively by two experts. The segmentation results on Brainweb images with varying noise and intensity nonuniformity levels were quantitatively compared with the ground truth by computing the Dice similarity indices.

RESULTS

The proposed method significantly improved the cerebellar tissue classification on all normal volunteers included in this study without compromising the classification in remaining part of the brain. The average similarity indices for gray matter (GM) and white matter (WM) in the cerebellum are 89.81 (+/-2.34) and 93.04 (+/-2.41), demonstrating excellent performance of the proposed methodology.

CONCLUSION

The proposed method significantly improved tissue classification in the cerebellum. The GM was overestimated when segmentation was performed on the whole brain as a single object.

An improved level set method for brain MR images segmentation and bias correction

Intensity inhomogeneities cause considerable difficulty in the quantitative analysis of magnetic resonance (MR) images. Thus, bias field estimation is a necessary step before quantitative analysis of MR data can be undertaken. This paper presents a variational level set approach to bias correction and segmentation for images with intensity inhomogeneities. Our method is based on an observation that intensities in a relatively small local region are separable, despite of the inseparability of the intensities in the whole image caused by the overall intensity inhomogeneity. We first define a localized K-means-type clustering objective function for image intensities in a neighborhood around each point. The cluster centers in this objective function have a multiplicative factor that estimates the bias within the neighborhood. The objective function is then integrated over the entire domain to define the data term into the level set framework. Our method is able to capture bias of quite general profiles. Moreover, it is robust to initialization, and thereby allows fully automated applications. The proposed method has been used for images of various modalities with promising results.

Longitudinal progression of Alzheimer's-like patterns of atrophy in normal older adults: the SPARE-AD index

A challenge in developing informative neuroimaging biomarkers for early diagnosis of Alzheimer's disease is the need to identify biomarkers that are evident before the onset of clinical symptoms, and which have sufficient sensitivity and specificity on an individual patient basis. Recent literature suggests that spatial patterns of brain atrophy discriminate amongst Alzheimer's disease, mild cognitive impairment (MCI) and cognitively normal (CN) older adults with high accuracy on an individual basis, thereby offering promise that subtle brain changes can be detected during prodromal Alzheimer's disease stages. Here, we investigate whether these spatial patterns of brain atrophy can be detected in CN and MCI individuals and whether they are associated with cognitive decline. Images from the Alzheimer's Disease Neuroimaging Initiative (ADNI) were used to construct a pattern classifier that recognizes spatial patterns of brain atrophy which best distinguish Alzheimer's disease patients from CN on an individual person basis. This classifier was subsequently applied to longitudinal magnetic resonance imaging scans of CN and MCI participants in the Baltimore Longitudinal Study of Aging (BLSA) neuroimaging study. The degree to which Alzheimer's disease-like patterns were present in CN and MCI subjects was evaluated longitudinally in relation to cognitive performance. The oldest BLSA CN individuals showed progressively increasing Alzheimer's disease-like patterns of atrophy, and individuals with these patterns had reduced cognitive performance. MCI was associated with steeper longitudinal increases of Alzheimer's disease-like patterns of atrophy, which separated them from CN (receiver operating characteristic area under the curve equal to 0.89). Our results suggest that imaging-based spatial patterns of brain atrophy of Alzheimer's disease, evaluated with sophisticated pattern analysis and recognition methods, may be useful in discriminating among CN individuals who are likely to be stable versus those who will show cognitive decline. Future prospective studies will elucidate the temporal dynamics of spatial atrophy patterns and the emergence of clinical symptoms.

Fast Image Registration by Hierarchical Soft Correspondence Detection

A new approach, based on the hierarchical soft correspondence detection, has been presented for significantly improving the speed of our previous HAMMER image registration algorithm. Currently, HAMMER takes a relative long time, e.g., up to 80 minutes, to register two regular sized images using Linux machine (with 2.40GHz CPU and 2-Gbyte memory). This is because the results of correspondence detection, used to guide the image warping, can be ambiguous in complex structures and thus the image warping has to be conservative and accordingly takes long time to complete. In this paper, a hierarchical soft correspondence detection technique has been employed to detect correspondences more robustly, thereby allowing the image warping to be completed straightforwardly and fast. By incorporating this hierarchical soft correspondence detection technique into the HAMMER registration framework, the robustness and the accuracy of registration (in terms of low average registration error) can be both achieved. Experimental results on real and simulated data show that the new registration algorithm, based the hierarchical soft correspondence detection, can run nine times faster than HAMMER while keeping the similar registration accuracy.

Online resource for validation of brain segmentation methods

One key issue that must be addressed during the development of image segmentation algorithms is the accuracy of the results they produce. Algorithm developers require this so they can see where methods need to be improved and see how new developments compare with existing ones. Users of algorithms also need to understand the characteristics of algorithms when they select and apply them to their neuroimaging analysis applications. Many metrics have been proposed to characterize error and success rates in segmentation, and several datasets have also been made public for evaluation. Still, the methodologies used in analyzing and reporting these results vary from study to study, so even when studies use the same metrics their numerical results may not necessarily be directly comparable. To address this problem, we developed a web-based resource for evaluating the performance of skull-stripping in T1-weighted MRI. The resource provides both the data to be segmented and an online application that performs a validation study on the data. Users may download the test dataset, segment it using whichever method they wish to assess, and upload their segmentation results to the server. The server computes a series of metrics, displays a detailed report of the validation results, and archives these for future browsing and analysis. We applied this framework to the evaluation of 3 popular skull-stripping algorithms--the Brain Extraction Tool [Smith, S.M., 2002. Fast robust automated brain extraction. Hum. Brain Mapp. 17 (3),143-155 (Nov)], the Hybrid Watershed Algorithm [Ségonne, F., Dale, A.M., Busa, E., Glessner, M., Salat, D., Hahn, H.K., Fischl, B., 2004. A hybrid approach to the skull stripping problem in MRI. NeuroImage 22 (3), 1060-1075 (Jul)], and the Brain Surface Extractor [Shattuck, D.W., Sandor-Leahy, S.R., Schaper, K.A., Rottenberg, D.A., Leahy, R.M., 2001. Magnetic resonance image tissue classification using a partial volume model. NeuroImage 13 (5), 856-876 (May) under several different program settings. Our results show that with proper parameter selection, all 3 algorithms can achieve satisfactory skull-stripping on the test data.

A hybrid geometric-statistical deformable model for automated 3-D segmentation in brain MRI

We present a novel 3-D deformable model-based approach for accurate, robust, and automated tissue segmentation of brain MRI data of single as well as multiple magnetic resonance sequences. The main contribution of this study is that we employ an edge-based geodesic active contour for the segmentation task by integrating both image edge geometry and voxel statistical homogeneity into a novel hybrid geometric-statistical feature to regularize contour convergence and extract complex anatomical structures. We validate the accuracy of the segmentation results on simulated brain MRI scans of both single T1-weighted and multiple T1/T2/PD-weighted sequences. We also demonstrate the robustness of the proposed method when applied to clinical brain MRI scans. When compared to a current state-of-the-art region-based level-set segmentation formulation, our white matter and gray matter segmentation resulted in significantly higher accuracy levels with a mean improvement in Dice similarity indexes of 8.55% ( p < 0.0001) and 10.18% ( p < 0.0001), respectively.

Network Administrator Assistance System Based on Fuzzy C-means Analysis

In this research we design a network administrator assistance system based on traffic measurement and fuzzy c-means (FCM) clustering analysis method. Network traffic measurement is an essential tool for monitoring and controlling communication network. It can provide valuable information about network traffic-load patterns and performances. The proposed system utilizes the FCM method to analyze users' network behaviors and traffic-load patterns based on traffic measurement data of IP network. Analysis results can be used as assistance for administrator to determine efficient controlling and configuring parameters of network management systems. The system is applied in Dali University campus network, and it is effective in practice.

Investigation of the neural correlates underlying action observation in multiple sclerosis patients

Recent fMRI evidence indicates that both the execution and the observation of hand actions in multiple sclerosis (MS) patients increase recruitment of a portion of the so-called mirror neuron system. However, it remains unclear whether this is the expression of a compensatory mechanism for the coding of observed action or whether such a mechanism represents a rather unspecific functional adaptation process. Here we used fMRI on early relapsing remitting MS (RRMS) patients to clarify this issue. Functional images of 15 right-handed early RRMS patients and of 15 sex- and age-matched right-handed healthy controls were acquired using a 1.5 T scanner. During scanning, participants simply observed images depicting a human hand either grasping an object or resting alongside an object. As shown by a between-group analysis, when compared to controls, RRMS patients revealed a robust increase of activation in an extensive network of brain regions including frontal, parietal, temporal and visual areas usually activated during action observation. However, this pattern of hemodynamic activity was completely independent of the type of observed hand-object interaction as revealed by the lack of any significant between-group interaction. Our findings are in line with previous fMRI evidence demonstrating cortical reorganization in MS patients during action observation. However, based on our findings we go one step further and suggest that such functional cortical changes may be the expression of a generalized and unspecific compensatory mechanism, that is not necessarily involved in action understanding.

K-Bayes reconstruction for perfusion MRI. I: concepts and application

Despite the continued spread of magnetic resonance imaging (MRI) methods in scientific studies and clinical diagnosis, MRI applications are mostly restricted to high-resolution modalities, such as structural MRI. While perfusion MRI gives complementary information on blood flow in the brain, its reduced resolution limits its power for detecting specific disease effects on perfusion patterns. This reduced resolution is compounded by artifacts such as partial volume effects, Gibbs ringing, and aliasing, which are caused by necessarily limited k-space sampling and the subsequent use of discrete Fourier transform (DFT) reconstruction. In this study, a Bayesian modeling procedure (K-Bayes) is developed for the reconstruction of perfusion MRI. The K-Bayes approach (described in detail in Part II: Modeling and Technical Development) combines a process model for the MRI signal in k-space with a Markov random field prior distribution that incorporates high-resolution segmented structural MRI information. A simulation study was performed to determine qualitative and quantitative improvements in K-Bayes reconstructed images compared with those obtained via DFT. The improvements were validated using in vivo perfusion MRI data of the human brain. The K-Bayes reconstructed images were demonstrated to provide reduced bias, increased precision, greater effect sizes, and higher resolution than those obtained using DFT.

An EM approach to MAP solution of segmenting tissue mixtures: a numerical analysis

This work presents an iterative expectation-maximization (EM) approach to the maximum a posteriori (MAP) solution of segmenting tissue mixtures inside each image voxel. Each tissue type is assumed to follow a normal distribution across the field-of-view (FOV). Furthermore, all tissue types are assumed to be independent from each other. Under these assumptions, the summation of all tissue mixtures inside each voxel leads to the image density mean value at that voxel. The summation of all the tissue mixtures' unobservable random processes leads to the observed image density at that voxel, and the observed image density value also follows a normal distribution (image data are observed to follow a normal distribution in many applications). By modeling the underlying tissue distributions as a Markov random field across the FOV, the conditional expectation of the posteriori distribution of the tissue mixtures inside each voxel is determined, given the observed image data and the current-iteration estimation of the tissue mixtures. Estimation of the tissue mixtures at next iteration is computed by maximizing the conditional expectation. The iterative EM approach to a MAP solution is achieved by a finite number of iterations and reasonable initial estimate. This MAP-EM framework provides a theoretical solution to the partial volume effect, which has been a major cause of quantitative imprecision in medical image processing. Numerical analysis demonstrated its potential to estimate tissue mixtures accurately and efficiently.

Inhomogeneity compensation for MR brain image segmentation using a multi-stage FCM-based approach

Intensity inhomogeneity or intensity non-uniformity (INU) is an undesired phenomenon that represents the main obstacle for MR image segmentation and registration methods. Various techniques have been proposed to eliminate or compensate the INU, most of which are embedded into clustering algorithms. This paper proposes a multiple stage fuzzy c-means (FCM) based algorithm for the estimation and compensation of the slowly varying additive or multiplicative noise, supported by a pre-filtering technique for Gaussian and impulse noise elimination. The slowly varying behavior of the bias or gain field is assured by a smoothening filter that performs a context dependent averaging, based on a morphological criterion. The experiments using 2-D synthetic phantoms and real MR images show, that the proposed method provides accurate segmentation. The produced segmentation and fuzzy membership values can serve as excellent support for 3-D registration and segmentation techniques.

A Scalable Framework For Segmenting Magnetic Resonance Images

A fast, accurate and fully automatic method of segmenting magnetic resonance images of the human brain is introduced. The approach scales well allowing fast segmentations of fine resolution images. The approach is based on modifications of the soft clustering algorithm, fuzzy c-means, that enable it to scale to large data sets. Two types of modifications to create incremental versions of fuzzy c-means are discussed. They are much faster when compared to fuzzy c-means for medium to extremely large data sets because they work on successive subsets of the data. They are comparable in quality to application of fuzzy c-means to all of the data. The clustering algorithms coupled with inhomogeneity correction and smoothing are used to create a framework for automatically segmenting magnetic resonance images of the human brain. The framework is applied to a set of normal human brain volumes acquired from different magnetic resonance scanners using different head coils, acquisition parameters and field strengths. Results are compared to those from two widely used magnetic resonance image segmentation programs, Statistical Parametric Mapping and the FMRIB Software Library (FSL). The results are comparable to FSL while providing significant speed-up and better scalability to larger volumes of data.

Automatic correction of intensity nonuniformity from sparseness of gradient distribution in medical images

We propose to use the sparseness property of the gradient probability distribution to estimate the intensity nonuniformity in medical images, resulting in two novel automatic methods: a non-parametric method and a parametric method. Our methods are easy to implement because they both solve an iteratively re-weighted least squares problem. They are remarkably accurate as shown by our experiments on images of different imaged objects and from different imaging modalities.

Development of a realistic head model for EEG event-detection and source localization in newborn infants

In this work we present an integrated method for electroencephalography (EEG) source localization in newborn infants, based on a realistic head model. To build a realistic head model we propose an interactive hybrid segmentation method for T1 magnetic resonance images (MRI), consisting of active contours, fuzzy c-means (FCM) clustering and mathematical morphology. Subsequently, we solve the localization problem using a spike train detection algorithm and an algorithm that deals with the forward and inverse problem. The performance of this fused method indicates that our realistic head model is suitable for the accurate localization of the EEG activity. We will present both initial qualitative and quantitative results.

MRI tissue classification and bias field estimation based on coherent local intensity clustering: a unified energy minimization framework

This paper presents a new energy minimization method for simultaneous tissue classification and bias field estimation of magnetic resonance (MR) images. We first derive an important characteristic of local image intensities--the intensities of different tissues within a neighborhood form separable clusters, and the center of each cluster can be well approximated by the product of the bias within the neighborhood and a tissue-dependent constant. We then introduce a coherent local intensity clustering (CLIC) criterion function as a metric to evaluate tissue classification and bias field estimation. An integration of this metric defines an energy on a bias field, membership functions of the tissues, and the parameters that approximate the true signal from the corresponding tissues. Thus, tissue classification and bias field estimation are simultaneously achieved by minimizing this energy. The smoothness of the derived optimal bias field is ensured by the spatially coherent nature of the CLIC criterion function. As a result, no extra effort is needed to smooth the bias field in our method. Moreover, the proposed algorithm is robust to the choice of initial conditions, thereby allowing fully automatic applications. Our algorithm has been applied to high field and ultra high field MR images with promising results.

A geometry-driven optical flow warping for spatial normalization of cortical surfaces

Spatial normalization is frequently used to map data to a standard coordinate system by removing intersubject morphological differences, thereby allowing for group analysis to be carried out. The work presented in this paper is motivated by the need for an automated cortical surface normalization technique that will automatically identify homologous cortical landmarks and map them to the same coordinates on a standard manifold. The geometry of a cortical surface is analyzed using two shape measures that distinguish the sulcal and gyral regions in a multiscale framework. A multichannel optical flow warping procedure aligns these shape measures between a reference brain and a subject brain, creating the desired normalization. The partial differential equation that carries out the warping is implemented in a Euclidean framework in order to facilitate a multiresolution strategy, thereby permitting large deformations between the two surfaces. The technique is demonstrated by aligning 33 normal cortical surfaces and showing both improved structural alignment in manually labeled sulci and improved functional alignment in positron emission tomography data mapped to the surfaces. A quantitative comparison between our proposed surface-based spatial normalization method and a leading volumetric spatial normalization method is included to show that the surface-based spatial normalization performs better in matching homologous cortical anatomies.

Baseline and longitudinal patterns of brain atrophy in MCI patients, and their use in prediction of short-term conversion to AD: results from ADNI

High-dimensional pattern classification was applied to baseline and multiple follow-up MRI scans of the Alzheimer's Disease Neuroimaging Initiative (ADNI) participants with mild cognitive impairment (MCI), in order to investigate the potential of predicting short-term conversion to Alzheimer's Disease (AD) on an individual basis. MCI participants that converted to AD (average follow-up 15 months) displayed significantly lower volumes in a number of grey matter (GM) regions, as well as in the white matter (WM). They also displayed more pronounced periventricular small-vessel pathology, as well as an increased rate of increase of such pathology. Individual person analysis was performed using a pattern classifier previously constructed from AD patients and cognitively normal (CN) individuals to yield an abnormality score that is positive for AD-like brains and negative otherwise. The abnormality scores measured from MCI non-converters (MCI-NC) followed a bimodal distribution, reflecting the heterogeneity of this group, whereas they were positive in almost all MCI converters (MCI-C), indicating extensive patterns of AD-like brain atrophy in almost all MCI-C. Both MCI subgroups had similar MMSE scores at baseline. A more specialized classifier constructed to differentiate converters from non-converters based on their baseline scans provided good classification accuracy reaching 81.5%, evaluated via cross-validation. These pattern classification schemes, which distill spatial patterns of atrophy to a single abnormality score, offer promise as biomarkers of AD and as predictors of subsequent clinical progression, on an individual patient basis.

Segmentation of brain magnetic resonance images for measurement of gray matter atrophy in multiple sclerosis patients

Multiple sclerosis (MS) affects both white matter and gray matter (GM). Measurement of GM volumes is a particularly useful method to estimate the total extent of GM tissue damage because it can be done with conventional magnetic resonance images (MRI). Many algorithms exist for segmentation of GM, but none were specifically designed to handle issues associated with MS, such as atrophy and the effects that MS lesions may have on the classification of GM. A new GM segmentation algorithm has been developed specifically for calculation of GM volumes in MS patients. The new algorithm uses a combination of intensity, anatomical, and morphological probability maps. Several validation tests were performed to evaluate the algorithm in terms of accuracy, reproducibility, and sensitivity to MS lesions. The accuracy tests resulted in error rates of 1.2% and 3.1% for comparisons to BrainWeb and manual tracings, respectively. Similarity indices indicated excellent agreement with the BrainWeb segmentation (0.858-0.975, for various levels of noise and rf inhomogeneity). The scan-rescan reproducibility test resulted in a mean coefficient of variation of 1.1% for GM fraction. Tests of the effects of varying the size of MS lesions revealed a moderate and consistent dependence of GM volumes on T2 lesion volume, which suggests that GM volumes should be corrected for T2 lesion volumes using a simple scale factor in order to eliminate this technical artifact. The new segmentation algorithm can be used for improved measurement of GM volumes in MS patients, and is particularly applicable to retrospective datasets.

Bias artifact suppression on MR volumes

RF-inhomogeneity correction is a relevant research topic in the field of magnetic resonance imaging (MRI). A volume corrupted by this artifact exhibits nonuniform illumination both inside a single slice and between adjacent ones. In this work a bias correction technique is presented, which suppresses this artifact on MR volumes scanned from different body parts without any a priori hypothesis on the artifact model. Theoretical foundations of the method are reported together with experimental results and a comparison is presented with both the 2D version of the algorithm and other techniques that are widely used in MRI literature.

Is total brain volume correlated to cognitive function and education in patients with Alzheimer disease?

This study aimed to correlate whole brain volume measurements with MRI in patients with Alzheimer disease and the same Mini Mental State Examination (MMSE) but different levels of education. We describe the procedure we used to create 3D models of the brain from MRI images in patients with Alzheimer disease and then took volumetric measurements of the whole brain parenchyma. After this procedure we correlated the total brain volume measurements in patients with six or fewer years of education with those who had at least 12 years of education. Twenty patients with Alzheimer disease were examined with MRI. All of them had an MMSE score between 21 and 24 and were classified as mild Alzheimer disease. Ten of the patients had at least six years of education and the remaining ten had more than 12 years of education. The examinations were done by using a Siemens Expert Plus system of 1T and the MR images were studied using an automatic algorithm. The MRI images were segmented into grey, white matter and CSF. We then measured the volume of each component and classified those in each patient in relation to years of education. The whole procedure was completed successfully in 20 patients. After the volumetric study of the total brain volume by calculating separately grey matter, white matter and CSF, we classified the patients and made the correlation between those with six or fewer years of education and those with twelve or more years of study. Correlating the whole brain volume measurements of patients with Alzheimer disease and the same MMSE but different levels of education showed that there is no significant difference between the total brain volume of the two groups of our study.

Robust MRI brain tissue parameter estimation by multistage outlier rejection

This article addresses the problem of the tissue type parameter estimation in brain MRI in the presence of partial volume effects. Automatic MRI brain tissue classification is hampered by partial volume effects that are caused by the finite resolution of the acquisition process. Due to this effect intensity distributions in brain MRI cannot be well modeled by a simple mixture of Gaussians and therefore more complex models have been developed. Unfortunately, these models do not seem to be robust enough for clinical conditions, as the quality of the tissue classification decreases rapidly with the image quality. Also, the application of these methods for pathological images with unmodeled intensities (e.g. MS plaques, tumors, etc.) remains uncertain. In the present work a new robust method for brain tissue characterization is presented, treating the partial volume affected voxels as outliers of the pure tissue distributions. The proposed method estimates the tissue characteristics from a reduced set of intensities belonging to a particular pure tissue class. This reduced set is selected by using a trimming procedure based on local gradient information and distributional data. This feature makes the method highly tolerant of a large amount of unexpected intensities without degrading its performance. The proposed method has been evaluated using both synthetic and real MR data and compared with state-of-the-art methods showing the best results in the comparative.

A modified fuzzy C-means classification method using a multiscale diffusion filtering scheme

A fully automatic, multiscale fuzzy C-means (MsFCM) classification method for MR images is presented in this paper. We use a diffusion filter to process MR images and to construct a multiscale image series. A multiscale fuzzy C-means classification method is applied along the scales from the coarse to fine levels. The objective function of the conventional fuzzy C-means (FCM) method is modified to allow multiscale classification processing where the result from a coarse scale supervises the classification in the next fine scale. The method is robust for noise and low-contrast MR images because of its multiscale diffusion filtering scheme. The new method was compared with the conventional FCM method and a modified FCM (MFCM) method. Validation studies were performed on synthesized images with various contrasts and on the McGill brain MR image database. Our MsFCM method consistently performed better than the conventional FCM and MFCM methods. The MsFCM method achieved an overlap ratio of greater than 90% as validated by the ground truth. Experiments results on real MR images were given to demonstrate the effectiveness of the proposed method. Our multiscale fuzzy C-means classification method is accurate and robust for various MR images. It can provide a quantitative tool for neuroimaging and other applications.

Volume and shape in feature space on adaptive FCM in MRI segmentation

Intensity non-uniformity (bias field) correction, contextual constraints over spatial intensity distribution and non-spherical cluster's shape in the feature space are incorporated into the fuzzy c-means (FCM) for segmentation of three-dimensional multi-spectral MR images. The bias field is modeled by a linear combination of smooth polynomial basis functions for fast computation in the clustering iterations. Regularization terms for the neighborhood continuity of either intensity or membership are added into the FCM cost functions. Since the feature space is not isotropic, distance measures, other than the Euclidean distance, are used to account for the shape and volumetric effects of clusters in the feature space. The performance of segmentation is improved by combining the adaptive FCM scheme with the criteria used in Gustafson-Kessel (G-K) and Gath-Geva (G-G) algorithms through the inclusion of the cluster scatter measure. The performance of this integrated approach is quantitatively evaluated on normal MR brain images using the similarity measures. The improvement in the quality of segmentation obtained with our method is also demonstrated by comparing our results with those produced by FSL (FMRIB Software Library), a software package that is commonly used for tissue classification.

Design and implementation of an automated partial volume correction in PET: application to dopamine receptor quantification in the normal human striatum

The considerable effort and potential lack of reproducibility of human-driven PET quantification and partial volume correction (PVC) can be alleviated by use of atlas-based automatic analysis. The present study examined the application of a new algorithm designed to automatically define 3-dimensional regions of interest (ROIs) and their effect on dopamine receptor quantification in the normal human brain striatum, both without and with PVC.

METHODS

A total of 90 healthy volunteers (age range, 18-46 y) received a single injection of (11)C-raclopride, and automatic segmentation of concomitant structural MR images was performed using a maximum-probability atlas in combination with a trained neural network. For each identified tissue segment considered homogeneous for the tracer (or volumes of interest [VOIs]), an a priori criterion based on minimum axial recovery coefficient (RC(zmin) = 50%, 75%, and 90%) was used to constrain the extent of each ROI.

RESULTS

With ROIs essentially overlapping the entire VOI volume (obtained with RC(zmin) = 50%), the binding potential (BP(ND)) of (11)C-raclopride was found to be around 2.2 for caudate and 2.9 for putamen, an underestimation by 35% and 28%, respectively, according to PVC values. At increased RC(zmin), BP(ND) estimates of (11)C-raclopride were increased by 12% and 21% for caudate and 8% and 15% for putamen when the associated ROIs decreased to around 65% and 43% of total tissue volume (VOI) for caudate and 67% and 31% for putamen. After PVC, we observed relative increases in BP(ND) variance of 12% for caudate and 20% for putamen, whereas estimated BP(ND) values all increased to 3.4 for caudate and 4.0 for putamen, regardless of ROI size. Dopamine receptor concentrations appeared less heterogeneous in the normal human striatum after PVC than they did without PVC: the 25%-30% difference in BP(ND) estimates observed between caudate and putamen remained significant after PVC but was reduced to slightly less than 20%. Furthermore, the results were comparable with those obtained with a manual method currently in use in our laboratory.

CONCLUSION

The new algorithm allows for traditional PET data extraction and PVC in an entirely automatic fashion, thus avoiding labor-intensive analyses and potential intra- or interobserver variability. This study also offers the first, to our knowledge, large-scale application of PVC to dopamine D(2)/D(3) receptor imaging with (11)C-raclopride in humans.

Reduction of disease activity and disability with high-dose cyclophosphamide in patients with aggressive multiple sclerosis

OBJECTIVE

To explore the safety and effectiveness of high-dose cyclophosphamide (HiCy) without bone marrow transplantation in patients with aggressive multiple sclerosis (MS).

DESIGN

A 2-year open-label trial of patients with aggressive relapsing-remitting multiple sclerosis (RRMS) given an immunoablative regimen of HiCy (50 mg/kg/d for 4 consecutive days) with no subsequent immunomodulatory therapy unless disease activity reappeared that required rescue therapy.

SETTING

The Johns Hopkins University Multiple Sclerosis Center, Baltimore, Maryland. Patients A total of 21 patients with RRMS were screened for eligibility and 9 patients were enrolled in the trial. Patients were required to have 2 or more gadolinium-enhancing lesions on each of 2 pretreatment magnetic resonance imaging scans, at least 1 clinical exacerbation in the 12 months prior to HiCy treatment, or a sustained increase of 1.0 point or higher on the Expanded Disability Status Scale (EDSS) in the preceding year. Intervention Patients received 50 mg/kg/d of cyclophosphamide intravenously for 4 consecutive days, followed by 5 mug/kg/d of granulocyte colony-stimulating factor 6 days after completion of HiCy treatment, until the absolute neutrophil count exceeded 1.0 x 10(9) cells/L for 2 consecutive days.

MAIN OUTCOME MEASURES

The primary outcome of the study was the safety and tolerability of HiCy in patients with RRMS. Secondary outcome measures included a change in gadolinium-enhancing lesions on magnetic resonance images and a change in disability measures (EDSS and Multiple Sclerosis Functional Composite).

RESULTS

Nine patients were treated and followed up for a mean period of 23 months. Eight patients had failed conventional therapy and 1 was treatment naive. The median age at time of entry was 29 years (range, 20-47 years). All patients developed transient total or near-total pancytopenia as expected, followed by hematopoietic recovery in 10 to 17 days, stimulated by granulocyte colony-stimulating factor. There were no deaths or unexpected serious adverse events. There was a statistically significant reduction in disability (EDSS) at follow-up (mean [SD] decrease, 2.11 [1.97]; 39.4%; P = .02). The mean (SD) number of gadolinium-enhancing lesions on the 2 pretreatment scans were 6.5 (2.1) and 1.2 (2.3) at follow-up (81.4% reduction; P = .01). Two patients required rescue treatment with other immunomodulatory therapies during the study owing to MS exacerbations.

CONCLUSION

Treatment with HiCy was safe and well tolerated in our patients with MS. Patients experienced a pronounced reduction in disease activity and disability after HiCy treatment. This immunoablative regimen of cyclophosphamide for patients with aggressive MS is worthy of further study and may be an alternative to bone marrow transplantation. Published online June 9, 2008 (doi:10.1001/archneurol.65.8.noc80042).

Generalized fuzzy clustering for segmentation of multi-spectral magnetic resonance images

An integrated approach for multi-spectral segmentation of MR images is presented. This method is based on the fuzzy c-means (FCM) and includes bias field correction and contextual constraints over spatial intensity distribution and accounts for the non-spherical cluster's shape in the feature space. The bias field is modeled as a linear combination of smooth polynomial basis functions for fast computation in the clustering iterations. Regularization terms for the neighborhood continuity of intensity are added into the FCM cost functions. To reduce the computational complexity, the contextual regularizations are separated from the clustering iterations. Since the feature space is not isotropic, distance measure adopted in Gustafson-Kessel (G-K) algorithm is used instead of the Euclidean distance, to account for the non-spherical shape of the clusters in the feature space. These algorithms are quantitatively evaluated on MR brain images using the similarity measures.

Manganese-enhanced MRI of brain plasticity in relation to functional recovery after experimental stroke

Restoration of function after stroke may be associated with structural remodeling of neuronal connections outside the infarcted area. However, the spatiotemporal profile of poststroke alterations in neuroanatomical connectivity in relation to functional recovery is still largely unknown. We performed in vivo magnetic resonance imaging (MRI)-based neuronal tract tracing with manganese in combination with immunohistochemical detection of the neuronal tracer wheat-germ agglutinin horseradish peroxidase (WGA-HRP), to assess changes in intra- and interhemispheric sensorimotor network connections from 2 to 10 weeks after unilateral stroke in rats. In addition, functional recovery was measured by repetitive behavioral testing. Four days after tracer injection in perilesional sensorimotor cortex, manganese enhancement and WGA-HRP staining were decreased in subcortical areas of the ipsilateral sensorimotor network at 2 weeks after stroke, which was restored at later time points. At 4 to 10 weeks after stroke, we detected significantly increased manganese enhancement in the contralateral hemisphere. Behaviorally, sensorimotor functions were initially disturbed but subsequently recovered and plateaued 17 days after stroke. This study shows that manganese-enhanced MRI can provide unique in vivo information on the spatiotemporal pattern of neuroanatomical plasticity after stroke. Our data suggest that the plateau stage of functional recovery is associated with restoration of ipsilateral sensorimotor pathways and enhanced interhemispheric connectivity.

Regional white matter hyperintensity burden in automated segmentation distinguishes late-life depressed subjects from comparison subjects matched for vascular risk factors

OBJECTIVE

Segmented brain white matter hyperintensities were compared between subjects with late-life depression and age-matched subjects with similar vascular risk factor scores. Correlations between neuropsychological performance and whole brain-segmented white matter hyperintensities and white and gray matter volumes were also examined.

METHOD

Eighty-three subjects with late-life depression and 32 comparison subjects underwent physical examination, psychiatric evaluation, neuropsychological testing, vascular risk factor assessment, and brain magnetic resonance imaging (MRI). Automated segmentation methods were used to compare the total brain and regional white matter hyperintensity burden between depressed patients and comparison subjects.

RESULTS

Depressed patients and comparison subjects did not differ in demographic variables, including vascular risk factor, or whole brain-segmented volumes. However, depressed subjects had seven regions of greater white matter hyperintensities located in the following white matter tracts: the superior longitudinal fasciculus, fronto-occipital fasciculus, uncinate fasciculus, extreme capsule, and inferior longitudinal fasciculus. These white matter tracts underlie brain regions associated with cognitive and emotional function. In depressed patients but not comparison subjects, volumes of three of these regions correlated with executive function; whole brain white matter hyperintensities correlated with executive function; whole brain white matter correlated with episodic memory, processing speed, and executive function; and whole brain gray matter correlated with processing speed.

CONCLUSIONS

These findings support the hypothesis that the strategic location of white matter hyperintensities may be critical in late-life depression. Further, the correlation of neuropsychological deficits with the volumes of whole brain white matter hyperintensities and gray and white matter in depressed subjects but not comparison subjects supports the hypothesis of an interaction between these structural brain components and depressed status.

Structural and functional biomarkers of prodromal Alzheimer's disease: a high-dimensional pattern classification study

This work builds upon previous studies that reported high sensitivity and specificity in classifying individuals with mild cognitive impairment (MCI), which is often a prodromal phase of Alzheimer's disease (AD), via pattern classification of MRI scans. The current study integrates MRI and PET (15)O water scans from 30 participants in the Baltimore Longitudinal Study of Aging, and tests the hypothesis that joint evaluation of structure and function can yield higher classification accuracy than either alone. Classification rates of up to 100% accuracy were achieved via leave-one-out cross-validation, whereas conservative estimates of generalization performance in new scans, evaluated via bagging cross-validation, yielded an area under the receiver operating characteristic (ROC) curve equal to 0.978 (97.8%), indicating excellent diagnostic accuracy. Spatial maps of regions determined to contribute the most to the classification implicated many temporal, prefrontal, orbitofrontal, and parietal regions. Detecting complex patterns of brain abnormality in early stages of cognitive impairment has pivotal importance for the detection and management of AD.

A variational level set approach to segmentation and bias correction of images with intensity inhomogeneity

This paper presents a variational level set approach to joint segmentation and bias correction of images with intensity inhomogeneity. Our method is based on an observation that intensities in a relatively small local region are separable, despite of the inseparability of the intensities in the whole image caused by the intensity inhomogeneity. We first define a weighted K-means clustering objective function for image intensities in a neighborhood around each point, with the cluster centers having a multiplicative factor that estimates the bias within the neighborhood. The objective function is then integrated over the entire domain and incorporated into a variational level set formulation. The energy minimization is performed via a level set evolution process. Our method is able to estimate bias of quite general profiles. Moreover, it is robust to initialization, and therefore allows automatic applications. The proposed method has been used for images of various modalities with promising results.

Entropy-controlled quadratic markov measure field models for efficient image segmentation

We present a new Markov random field (MRF) based model for parametric image segmentation. Instead of directly computing a label map, our method computes the probability that the observed data at each pixel is generated by a particular intensity model. Prior information about segmentation smoothness and low entropy of the probability distribution maps is codified in the form of a MRF with quadratic potentials so that the optimal estimator is obtained by solving a quadratic cost function with linear constraints. Although, for segmentation purposes, the mode of the probability distribution at each pixel is naturally used as an optimal estimator, our method permits the use of other estimators, such as the mean or the median, which may be more appropriate for certain applications. Numerical experiments and comparisons with other published schemes are performed, using both synthetic images and real data of brain MRI for which expert hand-made segmentations are available. Finally, we show that the proposed methodology may be easily extended to other problems, such as stereo disparity estimation.

Segmentation of brain parenchyma using bilateral filtering and region growing

When the non-diffusion weighted images (non-DWIs) and the diffusion weighted images (DWIs) are acquired by a fast imaging sequence, they suffer from several artifacts such as N/2 ghost, subject motion, eddy current, etc. These artifacts act as a noise in the background area of the human brain. To extract the brain region from the noisy background, brain parenchyma segmentation has been used. Several segmentation methods presented so far cannot address this problem well. In this study, we propose a novel segmentation method of brain contour in non-DWIs using bilateral filtering, which can reduce the background noise while edge-preserving, and region growing. We compare the segmentation results from various methods, and the proposed method shows better segmentation results than those from other schemes.

Spatial patterns of brain atrophy in MCI patients, identified via high-dimensional pattern classification, predict subsequent cognitive decline

Spatial patterns of brain atrophy in mild cognitive impairment (MCI) and Alzheimer's disease (AD) were measured via methods of computational neuroanatomy. These patterns were spatially complex and involved many brain regions. In addition to the hippocampus and the medial temporal lobe gray matter, a number of other regions displayed significant atrophy, including orbitofrontal and medial-prefrontal grey matter, cingulate (mainly posterior), insula, uncus, and temporal lobe white matter. Approximately 2/3 of the MCI group presented patterns of atrophy that overlapped with AD, whereas the remaining 1/3 overlapped with cognitively normal individuals, thereby indicating that some, but not all, MCI patients have significant and extensive brain atrophy in this cohort of MCI patients. Importantly, the group with AD-like patterns presented much higher rate of MMSE decline in follow-up visits; conversely, pattern classification provided relatively high classification accuracy (87%) of the individuals that presented relatively higher MMSE decline within a year from baseline. High-dimensional pattern classification, a nonlinear multivariate analysis, provided measures of structural abnormality that can potentially be useful for individual patient classification, as well as for predicting progression and examining multivariate relationships in group analyses.

Masseter segmentation using an improved watershed algorithm with unsupervised classification

The watershed algorithm always produces a complete division of the image. However, it is susceptible to over-segmentation and sensitivity to false edges. In medical images this leads to unfavorable representations of the anatomy. We address these drawbacks by introducing automated thresholding and post-segmentation merging. The automated thresholding step is based on the histogram of the gradient magnitude map while post-segmentation merging is based on a criterion which measures the similarity in intensity values between two neighboring partitions. Our improved watershed algorithm is able to merge more than 90% of the initial partitions, which indicates that a large amount of over-segmentation has been reduced. To further improve the segmentation results, we make use of K-means clustering to provide an initial coarse segmentation of the highly textured image before the improved watershed algorithm is applied to it. When applied to the segmentation of the masseter from 60 magnetic resonance images of 10 subjects, the proposed algorithm achieved an overlap index (kappa) of 90.6%, and was able to merge 98% of the initial partitions on average. The segmentation results are comparable to those obtained using the gradient vector flow snake.

Brain tissue segmentation based on DTI data

We present a method for automated brain tissue segmentation based on the multi-channel fusion of diffusion tensor imaging (DTI) data. The method is motivated by the evidence that independent tissue segmentation based on DTI parametric images provides complementary information of tissue contrast to the tissue segmentation based on structural MRI data. This has important applications in defining accurate tissue maps when fusing structural data with diffusion data. In the absence of structural data, tissue segmentation based on DTI data provides an alternative means to obtain brain tissue segmentation. Our approach to the tissue segmentation based on DTI data is to classify the brain into two compartments by utilizing the tissue contrast existing in a single channel. Specifically, because the apparent diffusion coefficient (ADC) values in the cerebrospinal fluid (CSF) are more than twice that of gray matter (GM) and white matter (WM), we use ADC images to distinguish CSF and non-CSF tissues. Additionally, fractional anisotropy (FA) images are used to separate WM from non-WM tissues, as highly directional white matter structures have much larger fractional anisotropy values. Moreover, other channels to separate tissue are explored, such as eigenvalues of the tensor, relative anisotropy (RA), and volume ratio (VR). We developed an approach based on the Simultaneous Truth and Performance Level Estimation (STAPLE) algorithm that combines these two-class maps to obtain a complete tissue segmentation map of CSF, GM, and WM. Evaluations are provided to demonstrate the performance of our approach. Experimental results of applying this approach to brain tissue segmentation and deformable registration of DTI data and spoiled gradient-echo (SPGR) data are also provided.

Texture-based segmentation of diffuse lesions of the brain's white matter

Diffuse lesions of the white matter of the human brain are common pathological findings in magnetic resonance images of elderly subjects. These lesions are typically caused by small vessel diseases (e.g., due to hypertension, diabetes), and related to cognitive decline. Because these lesions are inhomogeneous, unsharp, and faint, but show an intensity pattern that is different from the adjacent healthy tissue, a segmentation based on texture properties is proposed here. This method was successfully applied to a set of 116 image data sets of elderly subjects. Quantitative measures for the lesion load are derived that compare well with results from experts that visually rated lesions on a semiquantitative scale. Texture-based segmentation can be considered as a general method for lesion segmentation, and an outline for adapting this method to similar problems is presented.