Adaptive segmentation of MRI data

Global and regional effects of type 2 diabetes on brain tissue volumes and cerebral vasoreactivity

OBJECTIVE

The aim of this study was to evaluate the regional effects of type 2 diabetes and associated conditions on cerebral tissue volumes and cerebral blood flow (CBF) regulation.

RESEARCH DESIGN AND METHODS

CBF was examined in 26 diabetic (aged 61.6 +/- 6.6 years) and 25 control (aged 60.4 +/- 8.6 years) subjects using continuous arterial spin labeling (CASL) imaging during baseline, hyperventilation, and CO2 rebreathing. Regional gray and white matter, cerebrospinal fluid (CSF), and white matter hyperintensity (WMH) volumes were measured on a T1-weighted inversion recovery fast-gradient echo and a fluid attenuation inversion recovery magnetic resonance imaging at 3 Tesla.

RESULTS

The diabetic group had smaller global white (P = 0.006) and gray (P = 0.001) matter and larger CSF (36.3%, P < 0.0001) volumes than the control group. Regional differences were observed for white matter (-13.1%, P = 0.0008) and CSF (36.3%, P < 0.0001) in the frontal region, for CSF (20.9%, P = 0.0002) in the temporal region, and for gray matter (-3.0%, P = 0.04) and CSF (17.6%, P = 0.01) in the parieto-occipital region. Baseline regional CBF (P = 0.006) and CO2 reactivity (P = 0.005) were reduced in the diabetic group. Hypoperfusion in the frontal region was associated with gray matter atrophy (P < 0.0001). Higher A1C was associated with lower CBF (P < 0.0001) and greater CSF (P = 0.002) within the temporal region.

CONCLUSIONS

Type 2 diabetes is associated with cortical and subcortical atrophy involving several brain regions and with diminished regional cerebral perfusion and vasoreactivity. Uncontrolled diabetes may further contribute to hypoperfusion and atrophy. Diabetic metabolic disturbance and blood flow dysregulation that affects preferentially frontal and temporal regions may have implications for cognition and balance in elderly subjects with diabetes.

Occipital lobe gray matter volume in male patients with chronic schizophrenia: A quantitative MRI study

Schizophrenia is characterized by deficits in cognition as well as visual perception. There have, however, been few magnetic resonance imaging (MRI) studies of the occipital lobe as an anatomically defined region of interest in schizophrenia. To examine whether or not patients with chronic schizophrenia show occipital lobe volume abnormalities, we measured gray matter volumes for both the primary visual area (PVA) and the visual association areas (VAA) using MRI based neuroanatomical landmarks and three-dimensional information. PVA and VAA gray matter volumes were measured using high-spatial resolution MRI in 25 male patients diagnosed with chronic schizophrenia and in 28 male normal controls. Chronic schizophrenia patients showed reduced bilateral VAA gray matter volume (11%), compared with normal controls, whereas patients showed no group difference in PVA gray matter volume. These results suggest that reduced bilateral VAA may be a neurobiological substrate of some of the deficits observed in early visual processing in schizophrenia.

Genetic algorithms for finite mixture model based voxel classification in neuroimaging

Finite mixture models (FMMs) are an indispensable tool for unsupervised classification in brain imaging. Fitting an FMM to the data leads to a complex optimization problem. This optimization problem is difficult to solve by standard local optimization methods, such as the expectation-maximization (EM) algorithm, if a principled initialization is not available. In this paper, we propose a new global optimization algorithm for the FMM parameter estimation problem, which is based on real coded genetic algorithms. Our specific contributions are two-fold: 1) we propose to use blended crossover in order to reduce the premature convergence problem to its minimum and 2) we introduce a completely new permutation operator specifically meant for the FMM parameter estimation. In addition to improving the optimization results, the permutation operator allows for imposing biologically meaningful constraints to the FMM parameter values. We also introduce a hybrid of the genetic algorithm and the EM algorithm for efficient solution of multidimensional FMM fitting problems. We compare our algorithm to the self-annealing EM-algorithm and a standard real coded genetic algorithm with the voxel classification tasks within the brain imaging. The algorithms are tested on synthetic data as well as real three-dimensional image data from human magnetic resonance imaging, positron emission tomography, and mouse brain MRI. The tissue classification results by our method are shown to be consistently more reliable and accurate than with the competing parameter estimation methods.

Oriented speckle reducing anisotropic diffusion

Ultrasound imaging systems provide the clinician with noninvasive, low-cost, and real-time images that can help them in diagnosis, planning, and therapy. However, although the human eye is able to derive the meaningful information from these images, automatic processing is very difficult due to noise and artifacts present in the image. The speckle reducing anisotropic diffusion filter was recently proposed to adapt the anisotropic diffusion filter to the characteristics of the speckle noise present in the ultrasound images and to facilitate automatic processing of images. We analyze the properties of the numerical scheme associated with this filter, using a semi-explicit scheme. We then extend the filter to a matrix anisotropic diffusion, allowing different levels of filtering across the image contours and in the principal curvature directions. We also show a relation between the local directional variance of the image intensity and the local geometry of the image, which can justify the choice of the gradient and the principal curvature directions as a basis for the diffusion matrix. Finally, different filtering techniques are compared on a 2-D synthetic image with two different levels of multiplicative noise and on a 3-D synthetic image of a Y-junction, and the new filter is applied on a 3-D real ultrasound image of the liver.

On evaluating brain tissue classifiers without a ground truth

In this paper, we present a set of techniques for the evaluation of brain tissue classifiers on a large data set of MR images of the head. Due to the difficulty of establishing a gold standard for this type of data, we focus our attention on methods which do not require a ground truth, but instead rely on a common agreement principle. Three different techniques are presented: the Williams' index, a measure of common agreement; STAPLE, an Expectation Maximization algorithm which simultaneously estimates performance parameters and constructs an estimated reference standard; and Multidimensional Scaling, a visualization technique to explore similarity data. We apply these different evaluation methodologies to a set of eleven different segmentation algorithms on forty MR images. We then validate our evaluation pipeline by building a ground truth based on human expert tracings. The evaluations with and without a ground truth are compared. Our findings show that comparing classifiers without a gold standard can provide a lot of interesting information. In particular, outliers can be easily detected, strongly consistent or highly variable techniques can be readily discriminated, and the overall similarity between different techniques can be assessed. On the other hand, we also find that some information present in the expert segmentations is not captured by the automatic classifiers, suggesting that common agreement alone may not be sufficient for a precise performance evaluation of brain tissue classifiers.

Unifying the analyses of anatomical and diffusion tensor images using volume-preserved warping

PURPOSE

To introduce a framework that automatically identifies regions of anatomical abnormality within anatomical MR images and uses those regions in hypothesis-driven selection of seed points for fiber tracking with diffusion tensor (DT) imaging (DTI).

MATERIALS AND METHODS

Regions of interest (ROIs) are first extracted from MR images using an automated algorithm for volume-preserved warping (VPW) that identifies localized volumetric differences across groups. ROIs then serve as seed points for fiber tracking in coregistered DT images. Another algorithm automatically clusters and compares morphologies of detected fiber bundles. We tested our framework using datasets from a group of patients with Tourette's syndrome (TS) and normal controls.

RESULTS

Our framework automatically identified regions of localized volumetric differences across groups and then used those regions as seed points for fiber tracking. In our applied example, a comparison of fiber tracts in the two diagnostic groups showed that most fiber tracts failed to correspond across groups, suggesting that anatomical connectivity was severely disrupted in fiber bundles leading from regions of known anatomical abnormality.

CONCLUSION

Our framework automatically detects volumetric abnormalities in anatomical MRIs to aid in generating a priori hypotheses concerning anatomical connectivity that then can be tested using DTI. Additionally, automation enhances the reliability of ROIs, fiber tracking, and fiber clustering.

Coil sensitivity estimation for optimal SNR reconstruction and intensity inhomogeneity correction in phased array MR imaging

Magnetic resonance (MR) images can be acquired by multiple receiver coil systems to improve signal-to-noise ratio (SNR) and to decrease acquisition time. The optimal SNR images can be reconstructed from the coil data when the coil sensitivities are known. In typical MR imaging studies, the information about coil sensitivity profiles is not available. In such cases the sum-of-squares (SoS) reconstruction algorithm is usually applied. The intensity of the SoS reconstructed image is modulated by a spatially variable function due to the non-uniformity of coil sensitivities. Additionally, the SoS images also have sub-optimal SNR and bias in image intensity. All these effects might introduce errors when quantitative analysis and/or tissue segmentation are performed on the SoS reconstructed images. In this paper, we present an iterative algorithm for coil sensitivity estimation and demonstrate its applicability for optimal SNR reconstruction and intensity inhomogeneity correction in phased array MR imaging.

Highly accurate segmentation of brain tissue and subcortical gray matter from newborn MRI

The segmentation of newborn brain MRI is important for assessing and directing treatment options for premature infants at risk for developmental disorders, abnormalities, or even death. Segmentation of infant brain MRI is particularly challenging when compared with the segmentation of images acquired from older children and adults. We sought to develop a fully automated segmentation strategy and present here a Bayesian approach utilizing an atlas of priors derived from previous segmentations and a new scheme for automatically selecting and iteratively refining classifier training data using the STAPLE algorithm. Results have been validated by comparison to hand-drawn segmentations.

Regional whole body fat quantification in mice

Obesity has risen to epidemic levels in the United States and around the world. Global indices of obesity such as the body mass index (BMI) have been known to be inaccurate predictors of risk of diabetes, and it is commonly recognized that the distribution of fat in the body is a key measure. In this work, we describe the early development of image analysis methods to quantify regional body fat distribution in groups of both male and female wildtype mice using magnetic resonance images. In particular, we present a new formulation which extends the expectation-maximization formalism commonly applied in brain segmentation to multi-exponential data and applies it to the problem of regional whole body fat quantification. Previous segmentation approaches for multispectral data typically perform the classification on fitted parameters, such as the density and the relaxation times. In contrast, our method directly computes a likelihood term from the raw data and hence explicitly accounts for errors in the fitting process, while still using the fitted parameters to model the variation in the appearance of each tissue class. Early validation results, using magnetic resonance spectroscopic imaging as a gold standard, are encouraging. We also present results demonstrating differences in fat distribution between male and female mice.

A Dirichlet process mixture model for brain MRI tissue classification

Accurate classification of magnetic resonance images according to tissue type or region of interest has become a critical requirement in diagnosis, treatment planning, and cognitive neuroscience. Several authors have shown that finite mixture models give excellent results in the automated segmentation of MR images of the human normal brain. However, performance and robustness of finite mixture models deteriorate when the models have to deal with a variety of anatomical structures. In this paper, we propose a nonparametric Bayesian model for tissue classification of MR images of the brain. The model, known as Dirichlet process mixture model, uses Dirichlet process priors to overcome the limitations of current parametric finite mixture models. To validate the accuracy and robustness of our method we present the results of experiments carried out on simulated MR brain scans, as well as on real MR image data. The results are compared with similar results from other well-known MRI segmentation methods.

Atlas renormalization for improved brain MR image segmentation across scanner platforms

Atlas-based approaches have demonstrated the ability to automatically identify detailed brain structures from 3-D magnetic resonance (MR) brain images. Unfortunately, the accuracy of this type of method often degrades when processing data acquired on a different scanner platform or pulse sequence than the data used for the atlas training. In this paper, we improve the performance of an atlas-based whole brain segmentation method by introducing an intensity renormalization procedure that automatically adjusts the prior atlas intensity model to new input data. Validation using manually labeled test datasets has shown that the new procedure improves the segmentation accuracy (as measured by the Dice coefficient) by 10% or more for several structures including hippocampus, amygdala, caudate, and pallidum. The results verify that this new procedure reduces the sensitivity of the whole brain segmentation method to changes in scanner platforms and improves its accuracy and robustness, which can thus facilitate multicenter or multisite neuroanatomical imaging studies.

A nonparametric MRI inhomogeneity correction method

Magnetic resonance images are commonly affected by intensity inhomogeneities which make it difficult to obtain any quantitative measures from them. We present a new method of automatically correcting this artifact using a nonparametric coarse to fine approach which allows bias fields to be modeled with different frequency ranges without user supervision. We also propose a new entropy-related cost function based on the combination of intensity and gradient image features for more robust homogeneity measurement. The proposed methodology has been evaluated for both synthetic and real data and compared with state of the art methods, showing the best results in the comparison. The proposed method is fully automatic and has no input parameters, making it very easy to use in a clinical environment.

Restoration of MRI Data for Field Nonuniformities using High Order Neighborhood Statistics

MRI at high magnetic fields (> 3.0 T ) is complicated by strong inhomogeneous radio-frequency fields, sometimes termed the "bias field". These lead to nonuniformity of image intensity, greatly complicating further analysis such as registration and segmentation. Existing methods for bias field correction are effective for 1.5 T or 3.0 T MRI, but are not completely satisfactory for higher field data. This paper develops an effective bias field correction for high field MRI based on the assumption that the nonuniformity is smoothly varying in space. Also, nonuniformity is quantified and unmixed using high order neighborhood statistics of intensity cooccurrences. They are computed within spherical windows of limited size over the entire image. The restoration is iterative and makes use of a novel stable stopping criterion that depends on the scaled entropy of the cooccurrence statistics, which is a non monotonic function of the iterations; the Shannon entropy of the cooccurrence statistics normalized to the effective dynamic range of the image. The algorithm restores whole head data, is robust to intense nonuniformities present in high field acquisitions, and is robust to variations in anatomy. This algorithm significantly improves bias field correction in comparison to N3 on phantom 1.5 T head data and high field 4 T human head data.

Regional gray matter growth, sexual dimorphism, and cerebral asymmetry in the neonatal brain

Although there has been recent interest in the study of childhood and adolescent brain development, very little is known about normal brain development in the first few months of life. In older children, there are regional differences in cortical gray matter development, whereas cortical gray and white matter growth after birth has not been studied to a great extent. The adult human brain is also characterized by cerebral asymmetries and sexual dimorphisms, although very little is known about how these asymmetries and dimorphisms develop. We used magnetic resonance imaging and an automatic segmentation methodology to study brain structure in 74 neonates in the first few weeks after birth. We found robust cortical gray matter growth compared with white matter growth, with occipital regions growing much faster than prefrontal regions. Sexual dimorphism is present at birth, with males having larger total brain cortical gray and white matter volumes than females. In contrast to adults and older children, the left hemisphere is larger than the right hemisphere, and the normal pattern of fronto-occipital asymmetry described in older children and adults is not present. Regional differences in cortical gray matter growth are likely related to differential maturation of sensory and motor systems compared with prefrontal executive function after birth. These findings also indicate that whereas some adult patterns of sexual dimorphism and cerebral asymmetries are present at birth, others develop after birth.

A review of methods for correction of intensity inhomogeneity in MRI

Medical image acquisition devices provide a vast amount of anatomical and functional information, which facilitate and improve diagnosis and patient treatment, especially when supported by modern quantitative image analysis methods. However, modality specific image artifacts, such as the phenomena of intensity inhomogeneity in magnetic resonance images (MRI), are still prominent and can adversely affect quantitative image analysis. In this paper, numerous methods that have been developed to reduce or eliminate intensity inhomogeneities in MRI are reviewed. First, the methods are classified according to the inhomogeneity correction strategy. Next, different qualitative and quantitative evaluation approaches are reviewed. Third, 60 relevant publications are categorized according to several features and analyzed so as to reveal major trends, popularity, evaluation strategies and applications. Finally, key evaluation issues and future development of the inhomogeneity correction field, supported by the results of the analysis, are discussed.

MRI intensity nonuniformity correction using simultaneously spatial and gray-level histogram information

A novel approach for correcting intensity nonuniformity in magnetic resonance imaging (MRI) is presented. This approach is based on the simultaneous use of spatial and gray-level histogram information. Spatial information about intensity nonuniformity is obtained using cubic B-spline smoothing. Gray-level histogram information of the image corrupted by intensity nonuniformity is exploited from a frequential point of view. The proposed correction method is illustrated using both physical phantom and human brain images. The results are consistent with theoretical prediction, and demonstrate a new way of dealing with intensity nonuniformity problems. They are all the more significant as the ground truth on intensity nonuniformity is unknown in clinical images.

Exponential Entropy Driven HUM on Knee MR Images

A very important artifact corrupting Magnetic Resonance Images is the RF inhomogeneity. This kind of artifact generates variations of illumination which trouble both direct examination by the doctor and segmentation algorithms. Even if homomorphic filtering approaches have been presented in literature, none of them has developed a measure to determine the cut-off frequency. In this work we present a measure based on information theory with a large experimental setup aimed to demonstrate the validity of our approach.

Intensity Non-uniformity Correction of Magnetic Resonance Images Using a Fuzzy Segmentation Algorithm

Artifacts in magnetic resonance images can make conventional intensity-based segmentation methods very difficult, especially for the spatial intensity non-uniformity induced by the radio frequency (RF) coil. The non-uniformity introduces a slow-varying shading artifact across the images. Many advanced techniques, such as nonparametric, multi-channel methods, cannot solve the problem. In this paper, the extension of an improved fuzzy segmentation method, based on the traditional fuzzy c-means (FCM) algorithm and neighborhood attraction, is proposed to correct the intensity non-uniformity. Experimental results on both synthetic non-MR and MR images are given demonstrate the superiority of the algorithm.

MRI image intensity correction with extrapolation and smoothing

A class of methods of MR image intensity correction extracts the sensitivity map from the image. This usually causes the edge enhancement artifact in the corrected image. A novel method of extrapolating the image in advance is proposed to reduce this effect significantly. The closest point algorithm is used to perform extrapolation.

Magnetic resonance imaging segmentation techniques using batch-type learning vector quantization algorithms

In this article, we propose batch-type learning vector quantization (LVQ) segmentation techniques for the magnetic resonance (MR) images. Magnetic resonance imaging (MRI) segmentation is an important technique to differentiate abnormal and normal tissues in MR image data. The proposed LVQ segmentation techniques are compared with the generalized Kohonen's competitive learning (GKCL) methods, which were proposed by Lin et al. [Magn Reson Imaging 21 (2003) 863-870]. Three MRI data sets of real cases are used in this article. The first case is from a 2-year-old girl who was diagnosed with retinoblastoma in her left eye. The second case is from a 55-year-old woman who developed complete left side oculomotor palsy immediately after a motor vehicle accident. The third case is from an 84-year-old man who was diagnosed with Alzheimer disease (AD). Our comparisons are based on sensitivity of algorithm parameters, the quality of MRI segmentation with the contrast-to-noise ratio and the accuracy of the region of interest tissue. Overall, the segmentation results from batch-type LVQ algorithms present good accuracy and quality of the segmentation images, and also flexibility of algorithm parameters in all the comparison consequences. The results support that the proposed batch-type LVQ algorithms are better than the previous GKCL algorithms. Specifically, the proposed fuzzy-soft LVQ algorithm works well in segmenting AD MRI data set to accurately measure the hippocampus volume in AD MR images.

Volumetric texture segmentation by discriminant feature selection and multiresolution classification

In this paper, a multiresolution volumetric texture segmentation (M-VTS) algorithm is presented. The method extracts textural measurements from the Fourier domain of the data via subband filtering using an orientation pyramid (Wilson and Spann, 1988). A novel Bhattacharyya space, based on the Bhattacharyya distance, is proposed for selecting the most discriminant measurements and producing a compact feature space. An oct tree is built of the multivariate features space and a chosen level at a lower spatial resolution is first classified. The classified voxel labels are then projected to lower levels of the tree where a boundary refinement procedure is performed with a three-dimensional (3-D) equivalent of butterfly filters. The algorithm was tested with 3-D artificial data and three magnetic resonance imaging sets of human knees with encouraging results. The regions segmented from the knees correspond to anatomical structures that can be used as a starting point for other measurements such as cartilage extraction.

A Fuzzy, Nonparametric Segmentation Framework for DTI and MRI Analysis

This paper presents a novel statistical fuzzy-segmentation method for diffusion tensor (DT) images and magnetic resonance (MR) images. Typical fuzzy-segmentation schemes, e.g. those based on fuzzy-C-means (FCM), incorporate Gaussian class models which are inherently biased towards ellipsoidal clusters. Fiber bundles in DT images, however, comprise tensors that can inherently lie on more-complex manifolds. Unlike FCM-based schemes, the proposed method relies on modeling the manifolds underlying the classes by incorporating nonparametric data-driven statistical models. It produces an optimal fuzzy segmentation by maximizing a novel information-theoretic energy in a Markov-random-field framework. For DT images, the paper describes a consistent statistical technique for nonparametric modeling in Riemannian DT spaces that incorporates two very recent works. In this way, the proposed method provides uncertainties in the segmentation decisions, which stem from imaging artifacts including noise, partial voluming, and inhomogeneity. The paper shows results on synthetic and real, DT as well as MR images.

Volume of cerebellar vermis in monozygotic twins discordant for combat exposure: lack of relationship to post-traumatic stress disorder

Several functional neuroimaging studies have implicated the cerebellar vermis in post-traumatic stress disorder (PTSD), but there have been no structural neuroimaging studies of this brain structure in PTSD. We utilized magnetic resonance imaging (MRI) with manual tracing to quantify the volumes of three divisions of the mid-sagittal vermis, and their total, within an identical, co-twin control design that employed Vietnam veterans discordant for combat exposure in Vietnam. Each structure's volume was significantly correlated between twins, indicating a partial familial determination: for anterior superior vermis, r=0.73; for posterior superior vermis, r=0.47; for inferior posterior vermis, r=0.51; and for total vermis, r=0.57. There were no significant differences between the PTSD and non-PTSD veterans for any vermis volume, and no significant main effects or interactions when their non-combat-exposed co-twins were added to the analyses. Thus, the results do not support the structural abnormality of cerebellar vermis in combat-related PTSD.

A novel, fast entropy-minimization algorithm for bias field correction in MR images

A novel, fast entropy-minimization algorithm for bias field correction in magnetic resonance (MR) images is suggested to correct the intensity inhomogeneity degradation of MR images that has become an increasing problem with the use of phased-array coils. Four important modifications were made to the conventional algorithm: (a) implementation of a modified two-step sampling strategy for stacked 2D image data sets, which included reducing the size of the measured image on each slice with a simple averaging method without changing the number of slices and then using a binary mask generated by a histogram threshold method to define the sampled voxels in the reduced image; (b) improvement of the efficiency of the correction function by using a Legendre polynomial as an orthogonal base function polynomial; (c) use of a nonparametric Parzen window estimator with a Gaussian kernel to calculate the probability density function and Shannon entropy directly from the image data; and (d) performing entropy minimization with a conjugate gradient method. Results showed that this algorithm could correct different types of MR images from different types of coils acquired at different field strengths very efficiently and with decreased computational load.

Variational Bayes inference of spatial mixture models for segmentation

Mixture models are commonly used in the statistical segmentation of images. For example, they can be used for the segmentation of structural medical images into different matter types, or of statistical parametric maps into activating and nonactivating brain regions in functional imaging. Spatial mixture models have been developed to augment histogram information with spatial regularization using Markov random fields (MRFs). In previous work, an approximate model was developed to allow adaptive determination of the parameter controlling the strength of spatial regularization. Inference was performed using Markov Chain Monte Carlo (MCMC) sampling. However, this approach is prohibitively slow for large datasets. In this work, a more efficient inference approach is presented. This combines a variational Bayes approximation with a second-order Taylor expansion of the components of the posterior distribution, which would otherwise be intractable to Variational Bayes. This provides inference on fully adaptive spatial mixture models an order of magnitude faster than MCMC. We examine the behavior of this approach when applied to artificial data with different spatial characteristics, and to functional magnetic resonance imaging statistical parametric maps.

The fast automatic algorithm for correction of MR bias field

PURPOSE

To develop a method for efficient automatic correction of slow-varying nonuniformity in MR images.

MATERIALS AND METHODS

The original MR image is represented by a piecewise constant function, and the bias (nonuniformity) field of an MR image is modeled as multiplicative and slow varying, which permits to approximate it with a low-order polynomial basis in a "log-domain." The basis coefficients are determined by comparing partial derivatives of the modeled bias field with the original image.

RESULTS

We tested the resulting algorithm named derivative surface fitting (dsf) on simulated images and phantom and real data. A single iteration was sufficient in most cases to produce a significant improvement to the MR image's visual quality. dsf does not require prior knowledge of intensity distribution and was successfully used on brain and chest images. Due to its design, dsf can be applied to images of any modality that can be approximated as piecewise constant with a multiplicative bias field.

CONCLUSION

The resulting algorithm appears to be an efficient method for fast correction of slow varying nonuniformity in MR images.

Illumination Correction on MR Images

OBJECTIVE

An important artifact corrupting Magnetic Resonance Images is the rf inhomogeneity, also called bias artifact. This anomaly produces an abnormal illumination fluctuation on the image, due to variations of the device magnetic field. This artifact is particularly strong on images acquired with a device specialized on upper and lower limbs due to their coil configuration. A method based on homomorphic filtering aimed to suppress this artifact was proposed by Guillemaud. This filter has two faults: it doesn't provide an indication about the cutoff frequency (cf) and introduces another illumination artifact on the edges of the foreground. This work is an improvement to this method because it resolves both problems.

METHODS

The experimental setup has been performed on knee images obtained by 5 volunteers and acquired through an Artoscan device using the following parameters: Spin Echo sequence, Repetition time: 980 ms, Echo time: 26 ms, Slice thickness: 4 mm, Flip Angle: 90 degrees .

RESULTS

Two specialists in orthoptics evaluated the results of the proposed approach by examining the restored images and validating the results produced by the filter. A quantitative evaluation has been performed on a manually segmented restored image using the coefficient of variation (cv) measure.

CONCLUSIONS

Following the specialists qualitative evaluation, the illuminance of upper and lower peripheral zones results to be enhanced; a loose of contrast can be noted only in few cases. The Bias image exhibits an artifact focused usually on the central part of the foreground. The quantitative evaluation based on cv shows that this index is lowered for all the segmented regions with respect to the original value. The method is automatic and doesn't require any hypothesis on the tissues. A manual version of the algorithm can be also implemented allowing the physician to choose the preferred cf. In this case the value selected by the method can be considered as a default value.

Constrained Gaussian mixture model framework for automatic segmentation of MR brain images

An automated algorithm for tissue segmentation of noisy, low-contrast magnetic resonance (MR) images of the brain is presented. A mixture model composed of a large number of Gaussians is used to represent the brain image. Each tissue is represented by a large number of Gaussian components to capture the complex tissue spatial layout. The intensity of a tissue is considered a global feature and is incorporated into the model through tying of all the related Gaussian parameters. The expectation-maximization (EM) algorithm is utilized to learn the parameter-tied, constrained Gaussian mixture model. An elaborate initialization scheme is suggested to link the set of Gaussians per tissue type, such that each Gaussian in the set has similar intensity characteristics with minimal overlapping spatial supports. Segmentation of the brain image is achieved by the affiliation of each voxel to the component of the model that maximized the a posteriori probability. The presented algorithm is used to segment three-dimensional, T1-weighted, simulated and real MR images of the brain into three different tissues, under varying noise conditions. Results are compared with state-of-the-art algorithms in the literature. The algorithm does not use an atlas for initialization or parameter learning. Registration processes are therefore not required and the applicability of the framework can be extended to diseased brains and neonatal brains.

Model-based region-of-interest selection in dynamic breast MRI

Magnetic resonance imaging (MRI) is emerging as a powerful tool for the diagnosis of breast abnormalities. Dynamic analysis of the temporal pattern of contrast uptake has been applied in differential diagnosis of benign and malignant lesions to improve specificity. Selecting a region of interest (ROI) is an almost universal step in the process of examining the contrast uptake characteristics of a breast lesion. We propose an ROI selection method that combines model-based clustering of the pixels with Bayesian morphology, a new statistical image segmentation method. We then investigate tools for subsequent analysis of signal intensity time course data in the selected region. Results on a database of 19 patients indicate that the method provides informative segmentations and good detection rates.

A Review on MR Image Intensity Inhomogeneity Correction

Intensity inhomogeneity (IIH) is often encountered in MR imaging, and a number of techniques have been devised to correct this artifact. This paper attempts to review some of the recent developments in the mathematical modeling of IIH field. Low-frequency models are widely used, but they tend to corrupt the low-frequency components of the tissue. Hypersurface models and statistical models can be adaptive to the image and generally more stable, but they are also generally more complex and consume more computer memory and CPU time. They are often formulated together with image segmentation within one framework and the overall performance is highly dependent on the segmentation process. Beside these three popular models, this paper also summarizes other techniques based on different principles. In addition, the issue of quantitative evaluation and comparative study are discussed.

Intensity inhomogeneity correction of multispectral MR images

Intensity inhomogeneity in MR images is an undesired phenomenon, which often hampers different steps of quantitative image analysis such as segmentation or registration. In this paper, we propose a novel fully automated method for retrospective correction of intensity inhomogeneity. The basic assumption is that inhomogeneity correction could be improved by integrating spatial and intensity information from multiple MR channels, i.e., T1, T2, and PD weighted images. Intensity inhomogeneities of such multispectral images are removed simultaneously in a four-step iterative procedure. First, the probability distribution of image intensities and corresponding spatial features is calculated. In the second step, intensity correction forces that tend to minimize joint entropy of multispectral image are estimated for all image voxels. Third, independent inhomogeneity correction fields are obtained for each channel by regularization and normalization of voxel forces, and last, corresponding partial inhomogeneity corrections are performed separately for each channel. The method was quantitatively evaluated on simulated and real MR brain images and compared to three other methods.

Cerebral blood flow velocity and periventricular white matter hyperintensities in type 2 diabetes

OBJECTIVE

Diabetes increases the risk for cerebromicrovascular disease, possibly through its effects on blood flow regulation. The aim of this study was to assess the effects of type 2 diabetes on blood flow velocities (BFVs) in the middle cerebral arteries and to determine the relationship between white matter hyperintensities (WMHs) on magnetic resonance imaging (MRI) and BFVs.

RESEARCH DESIGN AND METHODS

We measured BFVs in 28 type 2 diabetic and 22 control subjects (aged 62.3 +/- 7.2 years) using transcranial Doppler ultrasound during baseline, hyperventilation, and CO(2) rebreathing. WMHs were graded, and their volume was quantified from fluid-attenuated inversion recovery images on a 3.0 Tesla MRI.

RESULTS

The diabetic group demonstrated decreased mean BFVs and increased cerebrovascular resistance during baseline, hypo- and hypercapnia (P < 0.0001), and impaired CO(2) reactivity (P = 0.05). WMH volume was negatively correlated with baseline BFV (P < 0.0001). A regression model revealed that baseline BFVs were negatively associated with periventricular WMHs, HbA(1c) (A1C), and inflammatory markers and positively associated with systolic blood pressure (R(2) = 0.86, P < 0.0001).

CONCLUSIONS

Microvascular disease in type 2 diabetes, which manifests as white matter abnormalities on MRI, is associated with reduced cerebral BFVs, increased resistance in middle cerebral arteries, and inflammation. These findings are clinically relevant as a potential mechanism for cerebrovascular disease in elderly with type 2 diabetes.

Automated segmentation of multiple sclerosis lesion subtypes with multichannel MRI

PURPOSE

To automatically segment multiple sclerosis (MS) lesions into three subtypes (i.e., enhancing lesions, T1 "black holes", T2 hyperintense lesions).

MATERIALS AND METHODS

Proton density-, T2- and contrast-enhanced T1-weighted brain images of 12 MR scans were pre-processed through intracranial cavity (IC) extraction, inhomogeneity correction and intensity normalization. Intensity-based statistical k-nearest neighbor (k-NN) classification was combined with template-driven segmentation and partial volume artifact correction (TDS+) for segmentation of MS lesions subtypes and brain tissue compartments. Operator-supervised tissue sampling and parameter calibration were performed on 2 randomly selected scans and were applied automatically to the remaining 10 scans. Results from this three-channel TDS+ (3ch-TDS+) were compared to those from a previously validated two-channel TDS+ (2ch-TDS+) method. The results of both the 3ch-TDS+ and 2ch-TDS+ were also compared to manual segmentation performed by experts.

RESULTS

Intra-class correlation coefficients (ICC) of 3ch-TDS+ for all three subtypes of lesions were higher (ICC between 0.95 and 0.96) than that of 2ch-TDS+ for T2 lesions (ICC = 0.82). The 3ch-TDS+ also identified the three lesion subtypes with high specificity (98.7-99.9%) and accuracy (98.5-99.9%). Sensitivity of 3ch-TDS+ for T2 lesions was 16% higher than with 2ch-TDS+. Enhancing lesions were segmented with the best sensitivity (81.9%). "Black holes" were segmented with the least sensitivity (62.3%).

CONCLUSION

3ch-TDS+ is a promising method for automated segmentation of MS lesion subtypes.

Computation of transmitted and received B1 fields in magnetic resonance imaging

Computation of B1 fields is a key issue for determination and correction of intensity nonuniformity in magnetic resonance images. This paper presents a new method for computing transmitted and received B1 fields. Our method combines a modified MRI acquisition protocol and an estimation technique based on the Levenberg-Marquardt algorithm and spatial filtering. It enables accurate estimation of transmitted and received B1 fields for both homogeneous and heterogeneous objects. The method is validated using numerical simulations and experimental data from phantom and human scans. The experimental results are in agreement with theoretical expectations.

MRI tissue classification with neighborhood statistics: a nonparametric, entropy-minimizing approach

We introduce a novel approach for magnetic resonance image (MRI) brain tissue classification by learning image neighborhood statistics from noisy input data using nonparametric density estimation. The method models images as random fields and relies on minimizing an entropy-based metric defined on high dimensional probability density functions. Combined with an atlas-based initialization, it is completely automatic. Experiments on real and simulated data demonstrate the advantages of the method in comparison to other approaches.

Skull-stripping magnetic resonance brain images using a model-based level set

The segmentation of brain tissue from nonbrain tissue in magnetic resonance (MR) images, commonly referred to as skull stripping, is an important image processing step in many neuroimage studies. A new mathematical algorithm, a model-based level set (MLS), was developed for controlling the evolution of the zero level curve that is implicitly embedded in the level set function. The evolution of the curve was controlled using two terms in the level set equation, whose values represented the forces that determined the speed of the evolving curve. The first force was derived from the mean curvature of the curve, and the second was designed to model the intensity characteristics of the cortex in MR images. The combination of these forces in a level set framework pushed or pulled the curve toward the brain surface. Quantitative evaluation of the MLS algorithm was performed by comparing the results of the MLS algorithm to those obtained using expert segmentation in 29 sets of pediatric brain MR images and 20 sets of young adult MR images. Another 48 sets of elderly adult MR images were used for qualitatively evaluating the algorithm. The MLS algorithm was also compared to two existing methods, the brain extraction tool (BET) and the brain surface extractor (BSE), using the data from the Internet brain segmentation repository (IBSR). The MLS algorithm provides robust skull-stripping results, making it a promising tool for use in large, multi-institutional, population-based neuroimaging studies.

Estimating linear cortical magnification in human primary visual cortex via dynamic programming

Human primary visual cortex is organized retinotopically, with adjacent locations in cortex representing adjacent locations on the retina. The spatial sampling in cortex is highly nonuniform: the amount of cortex devoted to a unit area of retina decreases with increasing retinal eccentricity. This sampling property can be quantified by the linear cortical magnification factor, which is expressed in terms of millimeters of cortex per degree of visual angle. In this paper, we present a new method using dynamic programming and fMRI retinotopic eccentricity mapping to estimate the linear cortical magnification factor in human primary visual cortex (V1). We localized cortical activity while subjects viewed each of seven stationary contrast- reversing radial checkerboard rings of equal thickness that tiled the visual field from 1.62 to 12.96 degrees of eccentricity. Imaging data from all epochs of each ring were contrasted with data from fixation epochs on a subject-by-subject basis. The resulting t statistic maps were then superimposed on a local coordinate system constructed from the gray/white matter boundary surface of each individual subject's occipital lobe, separately for each ring. Smoothed maps of functional activity on the cortical surface were constructed using orthonormal bases of the Laplace-Beltrami operator that incorporate the geometry of the cortical surface. This allowed us to stably track the ridge of maximum activation due to each ring via dynamic programming optimization over all possible paths on the cortical surface. We estimated the linear cortical magnification factor by calculating geodesic distances between activation ridges on the cortical surface in a population of five normal subjects. The reliability of these estimates was assessed by comparing results based on data from one quadrant to those based on data from the full hemifield along with a split-half reliability analysis.

Method to correct intensity inhomogeneity in MR images for atherosclerosis characterization

We are developing methods to characterize atherosclerotic disease in human carotid arteries using multiple MR images having different contrast mechanisms (T1W, T2W, PDW). To enable the use of voxel gray values for interpretation of disease, we created a new method, local entropy minimization with a bicubic spline model (LEMS), to correct the severe (approximately 80%) intensity inhomogeneity that arises from the surface coil array. This entropy-based method does not require classification and robustly addresses some problems that are more severe than those found in brain imaging, including noise, steep bias field, sensitivity of artery wall voxels to edge artifacts, and signal voids near the artery wall. Validation studies were performed on a synthetic digital phantom with realistic intensity inhomogeneity, a physical phantom roughly mimicking the neck, and patient carotid artery images. We compared LEMS to a modified fuzzy c-means segmentation based method (mAFCM), and a linear filtering method (LINF). Following LEMS correction, skeletal muscles in patient images were relatively isointense across the field of view. In the physical phantom, LEMS reduced the variation in the image to 1.9% and across the vessel wall region to 2.5%, a value which should be sufficient to distinguish plaque tissue types, based on literature measurements. In conclusion, we believe that the correction method shows promise for aiding human and computerized tissue classification from MR signal intensities.

A hybrid region-boundary model for cerebral cortical segmentation in MRI

Automatic segmentation of cerebral cortex in magnetic resonance imaging (MRI) is a challenging problem in understanding brain anatomy and functions. The difficulty is mainly due to variable brain structures, various MRI artifacts and restrictive body scanning methods. This paper describes a hybrid model-based method for obtaining an accurate and topologically-preserving segmentation of the brain cortex. The approach is based on defining region and boundary information using, respectively, level set and Bayesian techniques, and fusing these two types of information to achieve cerebral cortex segmentation. It is automatic and robust to noise, intensity inhomogeneities, and partial volume effect. Another particularity of the proposed approach is that bias field is corrected during segmentation process and that the central layer of the cortex is accurately obtained through a topology correction step. The proposed method is evaluated on both simulated and real data, and compared with existing segmentation techniques. The obtained results have demonstrated its improved performance and robustness.

Measurement of Cortical Thickness in 3D Brain MRI Data: Validation of the Laplacian Method

OBJECTIVES

We aimed to determine the precision of the Laplacian approach for cortical thickness measurement due to changes in computational and acquisition parameters. We compared these results to two other methods widely used in clinical research using brain MRI data.

MATERIALS AND METHODS

Brain MRI scans were obtained in 10 healthy adults using three different sets of acquisition parameters. The first and the second acquisitions used different slice thickness but the same head position. The third scan was performed after head repositioning. We measured cerebral cortical thickness in all brain segmentations using three thickness methods: Laplacian, nearest distance, and the orthogonal projection.

RESULTS

The Laplacian method demonstrated the least variability with regard to the effect of interchange of boundaries, slice thickness, and repositioning of the head, compared with the other two methods.

CONCLUSION

The Laplacian method is the most precise and reliable tool for in vivo cortical thickness measurement using brain MRI data.

Multiple sclerosis medical image analysis and information management

Magnetic resonance imaging (MRI) has become a central tool for patient management, as well as research, in multiple sclerosis (MS). Measurements of disease burden and activity derived from MRI through quantitative image analysis techniques are increasingly being used. There are many complexities and challenges in building computerized processing pipelines to ensure efficiency, reproducibility, and quality control for MRI scans from MS patients. Such paradigms require advanced image processing and analysis technologies, as well as integrated database management systems to ensure the most utility for clinical and research purposes. This article reviews pipelines available for quantitative clinical MRI research in MS, including image segmentation, registration, time-series analysis, performance validation, visualization techniques, and advanced medical imaging software packages. To address the complex demands of the sequential processes, the authors developed a workflow management system that uses a centralized database and distributed computing system for image processing and analysis. The implementation of their system includes a web-form-based Oracle database application for information management and event dispatching, and multiple modules for image processing and analysis. The seamless integration of processing pipelines with the database makes it more efficient for users to navigate complex, multistep analysis protocols, reduces the user's learning curve, reduces the time needed for combining and activating different computing modules, and allows for close monitoring for quality-control purposes. The authors' system can be extended to general applications in clinical trials and to routine processing for image-based clinical research.

Unified approach for multiple sclerosis lesion segmentation on brain MRI

The presence of large number of false lesion classification on segmented brain MR images is a major problem in the accurate determination of lesion volumes in multiple sclerosis (MS) brains. In order to minimize the false lesion classifications, a strategy that combines parametric and nonparametric techniques is developed and implemented. This approach uses the information from the proton density (PD)- and T2-weighted and fluid attenuation inversion recovery (FLAIR) images. This strategy involves CSF and lesion classification using the Parzen window classifier. Image processing, morphological operations, and ratio maps of PD- and T2-weighted images are used for minimizing false positives. Contextual information is exploited for minimizing the false negative lesion classifications using hidden Markov random field-expectation maximization (HMRF-EM) algorithm. Lesions are delineated using fuzzy connectivity. The performance of this algorithm is quantitatively evaluated on 23 MS patients. Similarity index, percentages of over, under, and correct estimations of lesions are computed by spatially comparing the results of present procedure with expert manual segmentation. The automated processing scheme detected 80% of the manually segmented lesions in the case of low lesion load and 93% of the lesions in those cases with high lesion load.

Unified approach for multiple sclerosis lesion segmentation on brain MRI

The presence of large number of false lesion classification on segmented brain MR images is a major problem in the accurate determination of lesion volumes in multiple sclerosis (MS) brains. In order to minimize the false lesion classifications, a strategy that combines parametric and nonparametric techniques is developed and implemented. This approach uses the information from the proton density (PD)- and T2-weighted and fluid attenuation inversion recovery (FLAIR) images. This strategy involves CSF and lesion classification using the Parzen window classifier. Image processing, morphological operations, and ratio maps of PD- and T2-weighted images are used for minimizing false positives. Contextual information is exploited for minimizing the false negative lesion classifications using hidden Markov random field-expectation maximization (HMRF-EM) algorithm. Lesions are delineated using fuzzy connectivity. The performance of this algorithm is quantitatively evaluated on 23 MS patients. Similarity index, percentages of over, under, and correct estimations of lesions are computed by spatially comparing the results of present procedure with expert manual segmentation. The automated processing scheme detected 80% of the manually segmented lesions in the case of low lesion load and 93% of the lesions in those cases with high lesion load.

Segmentation of trabeculated structures using an anisotropic Markov random field: application to the study of the optic nerve head in glaucoma

The study of the architecture of the optic nerve head (ONH) may provide valuable information about the development and progression of glaucoma. To this end, we have generated three-dimensional datasets from monkey eyes under controlled intraocular pressure (IOP). Segmentation of the connective tissues in this area is crucial to obtain an accurate measurement of geometrical parameters and to build mechanical models. However, this segmentation is made difficult by the complicated geometry and the artifacts introduced in the dataset building process. We present a novel segmentation algorithm, based on expectation-maximization, which incorporates an anisotropic Markov random field (MRF) to introduce prior knowledge about the geometry of the structure. The structure tensor is used to characterize the predominant structure direction and the spatial coherence at each point. The algorithm, which has been validated on an artificial validation dataset that mimics our ONH datasets, shows significant improvement over an isotropic MRF. Results on the real datasets demonstrate the ability of the new algorithm to obtain accurate, spatially consistent segmentations of this structure.

A hybrid tissue segmentation approach for brain MR images

A novel hybrid algorithm for the tissue segmentation of brain magnetic resonance images is proposed. The core of the algorithm is a probabilistic neural network (PNN) in which weighting factors are added to the summation layer, such that partial volume effects can be taken into account in the modeling process. The mean vectors for the probability density function estimation and the corresponding weighting factors are generated by a hierarchical scheme involving a self-organizing map neural network and an expectation maximization algorithm. Unlike conventional PNN, this approach circumvents the need for training sets. Tissue segmentation results from various algorithms are compared and the effectiveness and robustness of the proposed approach are demonstrated.

A Bayesian model for joint segmentation and registration

A statistical model is presented that combines the registration of an atlas with the segmentation of magnetic resonance images. We use an Expectation Maximization-based algorithm to find a solution within the model, which simultaneously estimates image artifacts, anatomical labelmaps, and a structure-dependent hierarchical mapping from the atlas to the image space. The algorithm produces segmentations for brain tissues as well as their substructures. We demonstrate the approach on a set of 22 magnetic resonance images. On this set of images, the new approach performs significantly better than similar methods which sequentially apply registration and segmentation.

Data driven image models through continuous joint alignment

This paper presents a family of techniques that we call congealing for modeling image classes from data. The idea is to start with a set of images and make them appear as similar as possible by removing variability along the known axes of variation. This technique can be used to eliminate "nuisance" variables such as affine deformations from handwritten digits or unwanted bias fields from magnetic resonance images. In addition to separating and modeling the latent images-i.e., the images without the nuisance variables-we can model the nuisance variables themselves, leading to factorized generative image models. When nuisance variable distributions are shared between classes, one can share the knowledge learned in one task with another task, leading to efficient learning. We demonstrate this process by building a handwritten digit classifier from just a single example of each class. In addition to applications in handwritten character recognition, we describe in detail the application of bias removal from magnetic resonance images. Unlike previous methods, we use a separate, nonparametric model for the intensity values at each pixel. This allows us to leverage the data from the MR images of different patients to remove bias from each other. Only very weak assumptions are made about the distributions of intensity values in the images. In addition to the digit and MR applications, we discuss a number of other uses of congealing and describe experiments about the robustness and consistency of the method.