Adaptive segmentation of MRI data

Current methods in medical image segmentation

Image segmentation plays a crucial role in many medical-imaging applications, by automating or facilitating the delineation of anatomical structures and other regions of interest. We present a critical appraisal of the current status of semi-automated and automated methods for the segmentation of anatomical medical images. Terminology and important issues in image segmentation are first presented. Current segmentation approaches are then reviewed with an emphasis on the advantages and disadvantages of these methods for medical imaging applications. We conclude with a discussion on the future of image segmentation methods in biomedical research.

Segmentation of ultrasound B-mode images with intensity inhomogeneity correction

Displayed ultrasound (US) B-mode images often exhibit tissue intensity inhomogeneities dominated by nonuniform beam attenuation within the body. This is a major problem for intensity-based, automatic segmentation of video-intensity images because conventional threshold-based or intensity-statistic-based approaches do not work well in the presence of such image distortions. Time gain compensation (TGC) is typically used in standard US machines in an attempt to overcome this. However this compensation method is position-dependent which means that different tissues in the same TGC time-range (or corresponding depth range) will be, incorrectly, compensated by the same amount. Compensation should really be tissue-type dependent but automating this step is difficult. The main contribution of this paper is to develop a method for simultaneous estimation of video-intensity inhomogeities and segmentation of US image tissue regions. The method uses a combination of the maximum a posteriori (MAP) and Markov random field (MRF) methods to estimate the US image distortion field assuming it follows a multiplicative model while at the same time labeling image regions based on the corrected intensity statistics. The MAP step is used to estimate the intensity model parameters while the MRF step provides a novel way of incorporating the distributions of image tissue classes as a spatial smoothness constraint. We explain how this multiplicative model can be related to the ultrasonic physics of image formation to justify our approach. Experiments are presented on synthetic images and a gelatin phantom to evaluate quantitatively the accuracy of the method. We also discuss qualitatively the application of the method to clinical breast and cardiac US images. Limitations of the method and potential clinical applications are outlined in the conclusion.

MR image-based measurement of rates of change in volumes of brain structures. Part I: method and validation

A detailed analysis procedure is described for evaluating rates of volumetric change in brain structures based on structural magnetic resonance (MR) images. In this procedure, a series of image processing tools have been employed to address the problems encountered in measuring rates of change based on structural MR images. These tools include an algorithm for intensity non-uniformity correction, a robust algorithm for three-dimensional image registration with sub-voxel precision and an algorithm for brain tissue segmentation. However, a unique feature in the procedure is the use of a fractional volume model that has been developed to provide a quantitative measure for the partial volume effect. With this model, the fractional constituent tissue volumes are evaluated for voxels at the tissue boundary that manifest partial volume effect, thus allowing tissue boundaries be defined at a sub-voxel level and in an automated fashion. Validation studies are presented on key algorithms including segmentation and registration. An overall assessment of the method is provided through the evaluation of the rates of brain atrophy in a group of normal elderly subjects for which the rate of brain atrophy due to normal aging is predictably small. An application of the method is given in Part II where the rates of brain atrophy in various brain regions are studied in relation to normal aging and Alzheimer's disease.

Retrospective correction of MR intensity inhomogeneity by information minimization

In this paper, the problem of retrospective correction of intensity inhomogeneity in magnetic resonance (MR) images is addressed. A novel model-based correction method is proposed, based on the assumption that an image corrupted by intensity inhomogeneity contains more information than the corresponding uncorrupted image. The image degradation process is described by a linear model, consisting of a multiplicative and an additive component which are modeled by a combination of smoothly varying basis functions. The degraded image is corrected by the inverse of the image degradation model. The parameters of this model are optimized such that the information of the corrected image is minimized while the global intensity statistic is preserved. The method was quantitatively evaluated and compared to other methods on a number of simulated and real MR images and proved to be effective, reliable, and computationally attractive. The method can be widely applied to different types of MR images because it solely uses the information that is naturally present in an image, without making assumptions on its spatial and intensity distribution. Besides, the method requires no preprocessing, parameter setting, nor user interaction. Consequently, the proposed method may be a valuable tool in MR image analysis.

Enhancement of contrast regions in suboptimal ultrasound images with application to echocardiography

In this paper we propose a novel feature-based contrast enhancement approach to enhance the quality of noisy ultrasound (US) images. Our approach uses a phase-based feature detection algorithm, followed by sparse surface interpolation and subsequent nonlinear postprocessing. We first exploited the intensity-invariant property of phase-based acoustic feature detection to select a set of relevant image features in the data. Then, an approximation to the low-frequency components of the sparse set of selected features was obtained using a fast surface interpolation algorithm. Finally, a nonlinear postprocessing step was applied. Results of applying the method to echocardiographic sequences (2-D + T) are presented. The results demonstrate that the method can successfully enhance the intensity of the interesting features in the image. Better balanced contrasted images are obtained, which is important and useful both for manual processing and assessment by a clinician, and for computer analysis of the sequence. An evaluation protocol is proposed in the case of echocardiographic data and quantitative results are presented. We show that the correction is consistent over time and does not introduce any temporal artefacts.

Prefrontal cortex, negative symptoms, and schizophrenia: an MRI study

The present study measured prefrontal cortical gray and white matter volume in chronic, male schizophrenic subjects who were characterized by a higher proportion of mixed or negative symptoms than previous patients that we have evaluated. Seventeen chronic male schizophrenic subjects and 17 male control subjects were matched on age and handedness. Regions of interest (ROI) were measured using high-resolution magnetic resonance (MR) acquisitions consisting of contiguous 1.5-mm slices of the entire brain. No significant differences were found between schizophrenic and control subjects in mean values for prefrontal gray matter volume in either hemisphere. However, right prefrontal white matter was significantly reduced in the schizophrenic group. In addition, right prefrontal gray matter volume was significantly correlated with right hippocampal volume in the schizophrenic, but not in the control group. Furthermore, an analysis in which the current data were combined with those from a previous study showed that schizophrenic subjects with high negative symptom scores had significantly smaller bilateral white matter volumes than those with low negative symptom scores. White matter was significantly reduced in the right hemisphere in this group of schizophrenic subjects. Prefrontal volumes were also associated with negative symptom severity and with volumes of medial-temporal lobe regions - two results that were also found previously in schizophrenic subjects with mostly positive symptoms. These results underscore the importance of temporal-prefrontal pathways in the symptomatology of schizophrenia, and they suggest an association between prefrontal abnormalities and negative symptoms.

Interactive 3-dimensional segmentation of MRI data in personal computer environment

We describe a method of interactive three-dimensional segmentation and visualization for anatomical magnetic resonance imaging (MRI) data in a personal computer environment. The visual feedback necessary during 3-D segmentation was provided by a ray casting algorithm, which was designed to allow users to interactively decide the visualization quality depending on the task-requirement. Structures such as gray matter, white matter, and facial skin from T1-weighted high-resolution MRI data were segmented and later visualized with surface rendering. Personal computers with central processing unit (CPU) speeds of 266, 400, and 700 MHz, were used for the implementation. The 3-D visualization upon each execution of the segmentation operation was achieved in the order of 2 s with a 700 MHz CPU. Our results suggest that 3-D volume segmentation with semi real-time visual feedback could be effectively implemented in a PC environment without the need for dedicated graphics processing hardware.

Improved high resolution MR imaging for surface coils using automated intensity non-uniformity correction: feasibility study in the orbit

This study examined the effects of a recently developed automated intensity non-uniformity correction on surface coil images using the orbit as an exemplar. Images were obtained using a standard head coil and a range of surface coils. Slices through the optic nerve head and cavernous sinus were subjected to the correction algorithm. Blind forced-choice rankings of the subjective image quality were performed. Quantitative measurements were taken of the similarity between vitreous humor at two depths from the coil, and of the conspicuity between orbital fat and temporalis muscle intensities. The combined qualitative ranks for corrected surface coil images were higher than for the equivalent uncorrected images in all cases. Intensity non-uniformity correction produced statistically significant improvements in orbital surface coil images, bringing their intensity uniformity in homogeneous tissue to the level of head coil images. The subjective quality of the corrected surface coil images was superior to head coil images, due to increased spatial resolution combined with improved signal to noise ratio across the image.

LIPSIA--a new software system for the evaluation of functional magnetic resonance images of the human brain

This paper describes the non-commercial software system LIPSIA that was developed for the processing of functional magnetic resonance images (fMRI) of the human brain. The analysis of fMRI data comprises various aspects including filtering, spatial transformation, statistical evaluation as well as segmentation and visualization. In LIPSIA, particular emphasis was placed on the development of new visualization and segmentation techniques that support visualizations of individual brain anatomy so that experts can assess the exact location of activation patterns in individual brains. As the amount of data that must be handled is enormous, another important aspect in the development LIPSIA was the efficiency of the software implementation. Well established statistical techniques were used whenever possible.

Validating cortical surface analysis of medial prefrontal cortex

This paper describes cortical analysis of 19 high resolution MRI subvolumes of medial prefrontal cortex (MPFC), a region that has been implicated in major depressive disorder. An automated Bayesian segmentation is used to delineate the MRI subvolumes into cerebrospinal fluid (CSF), gray matter (GM), white matter (WM), and partial volumes of either CSF/GM or GM/WM. The intensity value at which there is equal probability of GM and GM/WM partial volume is used to reconstruct MPFC cortical surfaces based on a 3-D isocontouring algorithm. The segmented data and the generated surfaces are validated by comparison with hand segmented data and semiautomated contours, respectively. The L(1) distances between Bayesian and hand segmented data are 0.05-0.10 (n = 5). Fifty percent of the voxels of the reconstructed surface lie within 0.12-0.28 mm (n = 14) from the semiautomated contours. Cortical thickness metrics are generated in the form of frequency of occurrence histograms for GM and WM labelled voxels as a function of their position from the cortical surface. An algorithm to compute the surface area of the GM/WM interface of the MPFC subvolume is described. These methods represent a novel approach to morphometric chacterization of regional cortex features which may be important in the study of psychiatric disorders such as major depression.

A method of radio-frequency inhomogeneity correction for brain tissue segmentation in MRI

An automatic method of correcting radio-frequency (RF) inhomogeneity in magnetic resonance images is presented. The method considers that image intensity variation due to radio-frequency inhomogeneity contains not only low frequency components, but also high frequency components. The variation is regarded as a multiplication of low frequency (capacity variation of coil) and the frequency of object (true image). The efficiency of the proposed method is illustrated with the aid of both phantom and physical images. The impact of the inhomogeneity correction on brain tissue segmentation is studied in detail. The results show significant improvement of the tissue segmentation after inhomogeneity correction.

Automated segmentation of multiple sclerosis lesions by model outlier detection

This paper presents a fully automated algorithm for segmentation of multiple sclerosis (MS) lesions from multispectral magnetic resonance (MR) images. The method performs intensity-based tissue classification using a stochastic model for normal brain images and simultaneously detects MS lesions as outliers that are not well explained by the model. It corrects for MR field inhomogeneities, estimates tissue-specific intensity models from the data itself, and incorporates contextual information in the classification using a Markov random field. The results of the automated method are compared with lesion delineations by human experts, showing a high total lesion load correlation. When the degree of spatial correspondence between segmentations is taken into account, considerable disagreement is found, both between expert segmentations, and between expert and automatic measurements.

Magnetic resonance image tissue classification using a partial volume model

We describe a sequence of low-level operations to isolate and classify brain tissue within T1-weighted magnetic resonance images (MRI). Our method first removes nonbrain tissue using a combination of anisotropic diffusion filtering, edge detection, and mathematical morphology. We compensate for image nonuniformities due to magnetic field inhomogeneities by fitting a tricubic B-spline gain field to local estimates of the image nonuniformity spaced throughout the MRI volume. The local estimates are computed by fitting a partial volume tissue measurement model to histograms of neighborhoods about each estimate point. The measurement model uses mean tissue intensity and noise variance values computed from the global image and a multiplicative bias parameter that is estimated for each region during the histogram fit. Voxels in the intensity-normalized image are then classified into six tissue types using a maximum a posteriori classifier. This classifier combines the partial volume tissue measurement model with a Gibbs prior that models the spatial properties of the brain. We validate each stage of our algorithm on real and phantom data. Using data from the 20 normal MRI brain data sets of the Internet Brain Segmentation Repository, our method achieved average kappa indices of kappa = 0.746 +/- 0.114 for gray matter (GM) and kappa = 0.798 +/- 0.089 for white matter (WM) compared to expert labeled data. Our method achieved average kappa indices kappa = 0.893 +/- 0.041 for GM and kappa = 0.928 +/- 0.039 for WM compared to the ground truth labeling on 12 volumes from the Montreal Neurological Institute's BrainWeb phantom.

Volumetric quantification of brain swelling after hypobaric hypoxia exposure

We applied a novel MR imaging technique to investigate the effect of acute mountain sickness on cerebral tissue water. Nine volunteers were exposed to hypobaric hypoxia corresponding to 4572 m altitude for 32 h. Such an exposure may cause acute mountain sickness. We imaged the brains of the volunteers before and at 32 h of hypobaric exposure with two different MRI techniques with subsequent data processing. (1) Brain volumes were calculated from 3D MRI data sets by applying a computerized brain segmentation algorithm. For this specific purpose a novel adaptive 3D segmentation program was used with an automatic correction algorithm for RF field inhomogeneity. (2) T(2) decay rates were analyzed in the white matter. The results demonstrated that a significant brain swelling of 36.2 +/- 19.6 ml (2.77 +/- 1.47%, n = 9, P < 0.001) developed after the 32-h hypobaric hypoxia exposure with a maximal observed volume increase of 5.8% (71.3 ml). These volume changes were significant only for the gray matter structures in contrast to the unremarkable changes seen in the white matter. The same study repeated 3 weeks later in 6 of 9 original subjects demonstrated that the brains recovered and returned approximately to the initially determined sea-level brain volume while hypobaric hypoxia exposure once again led to a significant new brain swelling (24.1 +/- 12.1 ml, 1.92 +/- 0.96%, n = 6, P < 0.005). On the contrary, the T(2) mapping technique did not reveal any significant effect of hypobaria on white matter. We present here a technique which is able to detect reversible brain volume changes as they may occur in patients with diffuse brain edema or increased cerebral blood volume, and which may represent a useful noninvasive tool for future evaluations of antiedematous drugs.

Automated manifold surgery: constructing geometrically accurate and topologically correct models of the human cerebral cortex

Highly accurate surface models of the cerebral cortex are becoming increasingly important as tools in the investigation of the functional organization of the human brain. The construction of such models is difficult using current neuroimaging technology due to the high degree of cortical folding. Even single voxel misclassifications can result in erroneous connections being created between adjacent banks of a sulcus, resulting in a topologically inaccurate model. These topological defects cause the cortical model to no longer be homeomorphic to a sheet, preventing the accurate inflation, flattening, or spherical morphing of the reconstructed cortex. Surface deformation techniques can guarantee the topological correctness of a model, but are time-consuming and may result in geometrically inaccurate models. In order to address this need we have developed a technique for taking a model of the cortex, detecting and fixing the topological defects while leaving that majority of the model intact, resulting in a surface that is both geometrically accurate and topologically correct.

Automated separation of gray and white matter from MR images of the human brain

A simple automatic procedure for segmentation of gray and white matter in high resolution 1.5T T1-weighted MR human brain images was developed and validated. The algorithm is based on histogram shape analysis of MR images that were corrected for scanner nonuniformity. Calibration and validation was done on a set of 80 MR images of human brains. The automatic method's values for the gray and white matter volumes were compared with the values from thresholds set twice by the best three of six raters. The automatic procedure was shown to perform as good as the best rater, where the average result of the best three raters was taken as reference. The method was also compared with two other histogram-based threshold methods, which yielded comparable results. The conclusion of the study thus is that automated threshold based methods can separate gray and white matter from MR brain images as reliably as human raters using a thresholding procedure.

Segmentation of brain MR images through a hidden Markov random field model and the expectation-maximization algorithm

The finite mixture (FM) model is the most commonly used model for statistical segmentation of brain magnetic resonance (MR) images because of its simple mathematical form and the piecewise constant nature of ideal brain MR images. However, being a histogram-based model, the FM has an intrinsic limitation--no spatial information is taken into account. This causes the FM model to work only on well-defined images with low levels of noise; unfortunately, this is often not the the case due to artifacts such as partial volume effect and bias field distortion. Under these conditions, FM model-based methods produce unreliable results. In this paper, we propose a novel hidden Markov random field (HMRF) model, which is a stochastic process generated by a MRF whose state sequence cannot be observed directly but which can be indirectly estimated through observations. Mathematically, it can be shown that the FM model is a degenerate version of the HMRF model. The advantage of the HMRF model derives from the way in which the spatial information is encoded through the mutual influences of neighboring sites. Although MRF modeling has been employed in MR image segmentation by other researchers, most reported methods are limited to using MRF as a general prior in an FM model-based approach. To fit the HMRF model, an EM algorithm is used. We show that by incorporating both the HMRF model and the EM algorithm into a HMRF-EM framework, an accurate and robust segmentation can be achieved. More importantly, the HMRF-EM framework can easily be combined with other techniques. As an example, we show how the bias field correction algorithm of Guillemaud and Brady (1997) can be incorporated into this framework to achieve a three-dimensional fully automated approach for brain MR image segmentation.

Integration of interventional MRI with computer-assisted surgery

Interventional MRI (IMRI) has entered into a new stage in which computer-based techniques play an increasing role in planning, monitoring, and controlling the procedures. The use of interactive imaging, navigational image guidance techniques, and image processing methods is demonstrated in various applications. The integration of intraoperative MRI guidance and computer-assisted surgery will greatly accelerate the clinical utility of image-guided therapy in general and interventional MRI in particular. J. Magn. Reson. Imaging 2001;13:69-77.

Validation of partial tissue segmentation of single-channel magnetic resonance images of the brain

We describe and evaluate a practical, automated algorithm based on local statistical mixture modeling for segmenting single-channel, T1-weighted volumetric magnetic resonance images of the brain into gray matter, white matter, and cerebrospinal fluid. We employed a stereological sampling method to assess, prospectively, the performance of the method with respect to human experts on 10 normal T1-weighted brain scans acquired with a three-dimensional gradient echo pulse sequence. The overall kappa statistic for the concordance of the algorithm with the human experts was 0.806, while that among raters, excluding the algorithm, was 0.802. The algorithm had better agreement with the modal expert decision (kappa = 0.878). The algorithm could not be distinguished from the experts by this measure. We also validated the algorithm on a simulated MR scan of a digital brain phantom with known tissue composition. Global gray matter and white matter errors were 1% and <1%, respectively, and correlation coefficients with the underlying tissue model were 0.95 for gray matter, 0.98 for white matter, and 0.95 for cerebrospinal fluid. In both approaches to validation, we evaluated both local and global performance of the algorithm. Human experts generated slightly higher global gray matter proportion estimates on the test brain scans relative to the algorithm (3.7%) and on the simulated MR scan relative to the true tissue model (4.4%). The algorithm underestimated gray in some subcortical nuclei which contain admixed gray and white matter. We demonstrate the reliability of the method on individual 1 NEX data sets of the test subjects, and its insensitivity to the precise values of initial model parameters. The output of this algorithm is suitable for quantifying cerebral cortical tissue, using a commonly performed commercial pulse sequence.

Automatic morphology-based brain segmentation (MBRASE) from MRI-T1 data

A method called morphology-based brain segmentation (MBRASE) has been developed for fully automatic segmentation of the brain from T1-weighted MR image data. The starting point is a supervised segmentation technique, which has proven highly effective and accurate for quantitation and visualization purposes. The proposed method automates the required user interaction, i.e., defining a seed point and a threshold range, and is based on the simple operations thresholding, erosion, and geodesic dilation. The thresholds are detected in a region growing process and are defined by connections of the brain to other tissues. The method is first evaluated on three computer simulated datasets by comparing the automated segmentations with the original distributions. The second evaluation is done on a total of 30 patient datasets, by comparing the automated segmentations with supervised segmentations carried out by a neuroanatomy expert. The comparison between two binary segmentations is performed both quantitatively and qualitatively. The automated segmentations are found to be accurate and robust. Consequently, the proposed method can be used as a default segmentation for quantitation and visualization of the human brain from T1-weighted MR images in routine clinical procedures.

Brain tissue classification of magnetic resonance images using partial volume modeling

This paper presents a fully automatic three-dimensional classification of brain tissues for Magnetic Resonance (MR) images. An MR image volume may be composed of a mixture of several tissue types due to partial volume effects. Therefore, we consider that in a brain dataset there are not only the three main types of brain tissue: gray matter, white matter, and cerebro spinal fluid, called pure classes, but also mixtures, called mixclasses. A statistical model of the mixtures is proposed and studied by means of simulations. It is shown that it can be approximated by a Gaussian function under some conditions. The D'Agostino-Pearson normality test is used to assess the risk alpha of the approximation. In order to classify a brain into three types of brain tissue and deal with the problem of partial volume effects, the proposed algorithm uses two steps: 1) segmentation of the brain into pure and mixclasses using the mixture model; 2) reclassification of the mixclasses into the pure classes using knowledge about the obtained pure classes. Both steps use Markov random field (MRF) models. The multifractal dimension, describing the topology of the brain, is added to the MRFs to improve discrimination of the mixclasses. The algorithm is evaluated using both simulated images and real MR images with different T1-weighted acquisition sequences.

Numerical tissue characterization in MS via standardization of the MR image intensity scale

Image intensity standardization is a recently developed postprocessing method that is capable of correcting the signal intensity variations in MR images. We evaluated signal intensity of healthy and diseased tissues in 10 multiple sclerosis (MS) patients based on standardized dual fast spin-echo MR images using a numerical postprocessing technique. The main idea of this technique is to deform the volume image histogram of each study to match a standard histogram and to utilize the resulting transformation to map the image intensities into standard scale. Upon standardization, the coefficients of variation of signal intensities for each segmented tissue (gray matter, white matter, lesion plaques, and diffuse abnormal white matter) in all patients were significantly smaller (2.3-9.2 times) than in the original images, and the same tissues from different patients looked alike, with similar intensity characteristics. Numerical tissue characterizability of different tissues in MS achieved by standardization offers a fixed tissue-specific meaning for the numerical values and can significantly facilitate image segmentation and analysis.

Segmentation and measurement of brain structures in MRI including confidence bounds

The advent of new and improved imaging devices has allowed an impressive increase in the accuracy and precision of MRI acquisitions. However, the volumetric nature of the image formation process implies an inherent uncertainty, known as the partial volume effect, which can be further affected by artifacts such as magnetic inhomogeneities and noise. These degradations seriously challenge the application to MRI of any segmentation method, especially on data sets where the size of the object or effect to be studied is small relative to the voxel size, as is the case in multiple sclerosis and schizophrenia. We develop an approach to this problem by estimating a set of bounds on the spatial location of each organ to be segmented. First, we describe a method for 3D segmentation from voxel data which combines statistical classification and geometry-driven segmentation; then we discuss how the partial volume effect is estimated and object measurements are obtained. A comprehensive validation study and a set of results on clinical applications are also described.

Fast re-rendering of volume and surface graphics by depth, color, and opacity buffering

A method for quickly re-rendering volume data consisting of several distinct materials and intermixed with moving geometry is presented. The technique works by storing depth, color and opacity information, to a given approximation, which facilitates accelerated rendering of fixed views at moderate storage overhead without re-scanning the entire volume. Storage information in the ray direction (what we have called super-r depth buffering), allows rapid transparency and color changes of materials, position changes of sub-objects, dealing explicitly with regions of overlap, and the intermixing or separately rendered geometry. The rendering quality can be traded-off against the relative storage cost and we present an empirical analysis of output error together with typical figures for its storage complexity. The method has been applied to the visualization of medical image data for surgical planning and guidance, and presented results include typical clinical data. We discuss the implications of our method for haptic (or tactile) rendering systems, such as for surgical simulation, and present preliminary results of rendering polygonal objects in the volume rendered scene.

A cooperative framework for segmentation of MRI brain scans

Automatic segmentation of MRI brain scans is a complex task for two main reasons: the large variability of the human brain anatomy, which limits the use of general knowledge and, inherent to MRI acquisition, the artifacts present in the images that are difficult to process. To tackle these difficulties, we propose to mix, in a cooperative framework, several types of information and knowledge provided and used by complementary individual systems: presently, a multi-agent system, a deformable model and an edge detector. The outcome is a cooperative segmentation performed by a set of region and edge agents constrained automatically and dynamically by both, the specific gray levels in the considered image, statistical models of the brain structures and general knowledge about MRI brain scans. Interactions between the individual systems follow three modes of cooperation: integrative, augmentative and confrontational cooperation, combined during the three steps of the segmentation process namely, the specialization of the seeded-region-growing agents, the fusion of heterogeneous information and the retroaction over slices. The described cooperative framework allows the dynamic adaptation of the segmentation process to the own characteristics of each MRI brain scan. Its evaluation using realistic brain phantoms is reported.

Rapid and effective correction of RF inhomogeneity for high field magnetic resonance imaging

The well-known variability in the distribution of high frequency electromagnetic fields in the human body causes problems in the analysis of structural information in high field magnetic resonance images. We describe a method of compensating for the purely intensity-based effects. In our simple and rapid correction algorithm, we first use statistical means to determine the background image noise level and the edges of the image features. We next populate all "noise" pixels with the mean signal intensity of the image features. These data are then smoothed by convolution with a gaussian filter using Fourier methods. Finally, the original data that are above the noise level are normalized to the smoothed images, thereby eliminating the lowest spatial frequencies in the final, corrected data. Processing of a 124 slice, 256 x 256 volume dataset requires under 70 sec on a laptop personal computer. Overall, the method is less prone to artifacts from edges or from sensitivity to absolute head position than are other correction techniques. Following intensity correction, the images demonstrated obvious qualitative improvement and, when subjected to automated segmentation tools, the accuracy of segmentation improved, in one example, from 35.3% to 84.7% correct, as compared to a manually-constructed gold standard.

Affine adaptive filtering of CT data

A novel method for resampling and enhancing image data using multidimensional adaptive filters is presented. The underlying issue that this paper addresses is segmentation of image structures that are close in size to the voxel geometry. Adaptive filtering is used to reduce both the effects of partial volume averaging by resampling the data to a lattice with higher sample density and to reduce the image noise level. Resampling is achieved by constructing filter sets that have subpixel offsets relative to the original sampling lattice. The filters are also frequency corrected for ansisotropic voxel dimensions. The shift and the voxel dimensions are described by an affine transform and provides a model for tuning the filter frequency functions. The method has been evaluated on CT data where the voxels are in general non cubic. The in-plane resolution in CT image volumes is often higher by a factor of 3-10 than the through-plane resolution. The method clearly shows an improvement over conventional resampling techniques such as cubic spline interpolation and sinc interpolation.

Volume distribution of cerebrospinal fluid using multispectral MR imaging

The goal of this study was to design a reliable method to quantify and visualize the anatomical distribution of cerebrospinal fluid (CSF) intracranially. The method should be clinically applicable and based on multispectral analysis of three-dimensional (3D) magnetic resonance images. T1-weighted, T2-weighted and proton density-weighted fast 3D gradient pulse sequences were used to form high resolution multispectral 3D images of the entire head. Training on single 2D slices, the Mahalanobis distances between the resulting multivariate tissue-specific densities were studied as functions of the feature vector composition and dimension. Multispectral analysis was applied to the images of four human brains. One feature vector with three components gave CSF volumes that were in the normal range and corresponding anatomical distributions that largely agreed with general anatomical knowledge. The exception was CSF missing around the basal parts of the brain due to signal artifacts. These artifacts were almost certainly due to the coil effect and magnetic field inhomogeneities induced by the imaged head. Such misclassifications could probably be reduced by bias field estimation and proper image restoration. Most CSF voxels formed large connected components that were found automatically, so the manual post-processing of the classified 3D image to locate CSF voxels was moderate. It is concluded that some of the fast, high resolution 3D gradient echo pulse sequences that have become available on conventional clinical scanners can be used to obtain good estimates of brain cerebrospinal fluid anatomical distribution and volume.

In vivo determination of body composition of rats using magnetic resonance imaging

Magnetic resonance imaging (MRI) has potential as an instrument to measure body composition because it can discriminate various soft tissues in vivo. These soft tissues include adipose tissue, muscle, organs, and brain. We report on preliminary studies using a 4.2-tesla MRI for measuring body composition in the mouse and rat. We employed image segmentation methods that include an image correction method, a necessary requirement when the images are taken in the presence of nonuniform radio-frequency (RF) coil response. The software for 3-D data segmentation, quantification, correction, image manipulation, and visualization has been developed as a research tool. This method currently is being validated.

Serial magnetic resonance imaging in multiple sclerosis: correlation with attacks, disability, and disease stage

Serial MRI and clinical testing was performed on 45 well-defined untreated multiple sclerosis patients in different categories of disease (relapsing-remitting, progressive, stable). Up to 24 MRIs were scheduled over a 1-year period for each patient. Clinical evaluation was performed monthly and at times of attacks using the Expanded Disability Status Scale (EDSS) and the Ambulation Index (AI). MRI scans were performed both with and without gadolinium enhancement. MRI lesion volume was determined by computerized analysis and gadolinium-enhancing lesions were counted by radiologists. We observed an increase in lesion volume over 1 year in all patient groups except those classified clinically as stable. In relapsing-remitting patients there were correlations between increases in the number of gadolinium enhancing lesions and increases in EDSS and the occurrence of attacks. In chronic progressive patients, increases in lesion volume were correlated with both increases in EDSS and AI. These results demonstrate a linkage between MRI and clinical disease that depends both on the stage of MS and the MRI measures used and support the use of MRI as a surrogate marker of clinical disability in the study of multiple sclerosis.

Parametric estimate of intensity inhomogeneities applied to MRI

This paper presents a new approach to the correction of intensity inhomogeneities in magnetic resonance imaging (MRI) that significantly improves intensity-based tissue segmentation. The distortion of the image brightness values by a low-frequency bias field impedes visual inspection and segmentation. The new correction method called parametric bias field correction (PABIC) is based on a simplified model of the imaging process, a parametric model of tissue class statistics, and a polynomial model of the inhomogeneity field. We assume that the image is composed of pixels assigned to a small number of categories with a priori known statistics. Further we assume that the image is corrupted by noise and a low-frequency inhomogeneity field. The estimation of the parametric bias field is formulated as a nonlinear energy minimization problem using an evolution strategy (ES). The resulting bias field is independent of the image region configurations and thus overcomes limitations of methods based on homomorphic filtering. Furthermore, PABIC can correct bias distortions much larger than the image contrast. Input parameters are the intensity statistics of the classes and the degree of the polynomial function. The polynomial approach combines bias correction with histogram adjustment, making it well suited for normalizing the intensity histogram of datasets from serial studies. We present simulations and a quantitative validation with phantom and test images. A large number of MR image data acquired with breast, surface, and head coils, both in two dimensions and three dimensions, have been processed and demonstrate the versatility and robustness of this new bias correction scheme.

Adaptive, template moderated, spatially varying statistical classification

A novel image segmentation algorithm was developed to allow the automatic segmentation of both normal and abnormal anatomy from medical images. The new algorithm is a form of spatially varying statistical classification, in which an explicit anatomical template is used to moderate the segmentation obtained by statistical classification. The algorithm consists of an iterated sequence of spatially varying classification and nonlinear registration, which forms an adaptive, template moderated (ATM), spatially varying statistical classification (SVC). Classification methods and nonlinear registration methods are often complementary, both in the tasks where they succeed and in the tasks where they fail. By integrating these approaches the new algorithm avoids many of the disadvantages of each approach alone while exploiting the combination. The ATM SVC algorithm was applied to several segmentation problems, involving different image contrast mechanisms and different locations in the body. Segmentation and validation experiments were carried out for problems involving the quantification of normal anatomy (MRI of brains of neonates) and pathology of various types (MRI of patients with multiple sclerosis, MRI of patients with brain tumors, MRI of patients with damaged knee cartilage). In each case, the ATM SVC algorithm provided a better segmentation than statistical classification or elastic matching alone.

A new variational shape-from-orientation approach to correcting intensity inhomogeneities in magnetic resonance images

A new intensity inhomogeneity correction algorithm based on a variational shape-from-orientation formulation is presented. Unlike most previous methods, the proposed algorithm is fully automatic, widely applicable and very efficient. Since no prior classification knowledge about the image is assumed in the proposed algorithm, it can be applied to correct intensity inhomogeneities for a wide variety of medical images. In this paper, a finite-element method is used to model the smooth bias-field function. Orientation constraints for the bias-field function are computed at the nodal locations of the regular discretization grid away from the boundary between different class regions. The selection of reliable orientation constraints is facilitated by the goodness of fit of a first-order polynomial model to the neighborhood of each nodal location. The automatically selected orientation constraints are integrated in a regularization framework, which leads to minimization of a convex and quadratic energy function. This energy minimization is accomplished by solving a linear system with a large, sparse, symmetric and positive semi-definite stiffness matrix. We employ an adaptive preconditioned conjugate-gradient algorithm to solve the linear system very efficiently. Experimental results on a variety of magnetic resonance images are given to demonstrate the effectiveness and efficiency of the proposed algorithm.

Automated model-based tissue classification of MR images of the brain

We describe a fully automated method for model-based tissue classification of magnetic resonance (MR) images of the brain. The method interleaves classification with estimation of the model parameters, improving the classification at each iteration. The algorithm is able to segment single- and multispectral MR images, corrects for MR signal inhomogeneities, and incorporates contextual information by means of Markov random Fields (MRF's). A digital brain atlas containing prior expectations about the spatial location of tissue classes is used to initialize the algorithm. This makes the method fully automated and therefore it provides objective and reproducible segmentations. We have validated the technique on simulated as well as on real MR images of the brain.

Segmentation and measurement of the cortex from 3-D MR images using coupled-surfaces propagation

The cortex is the outermost thin layer of gray matter in the brain; geometric measurement of the cortex helps in understanding brain anatomy and function. In the quantitative analysis of the cortex from MR images, extracting the structure and obtaining a representation for various measurements are key steps. While manual segmentation is tedious and labor intensive, automatic reliable efficient segmentation and measurement of the cortex remain challenging problems, due to its convoluted nature. Here we present a new approach of coupled-surfaces propagation, using level set methods to address such problems. Our method is motivated by the nearly constant thickness of the cortical mantle and takes this tight coupling as an important constraint. By evolving two embedded surfaces simultaneously, each driven by its own image-derived information while maintaining the coupling, a final representation of the cortical bounding surfaces and an automatic segmentation of the cortex are achieved. Characteristics of the cortex, such as cortical surface area, surface curvature, and cortical thickness, are then evaluated. The level set implementation of surface propagation offers the advantage of easy initialization, computational efficiency, and the ability to capture deep sulcal folds. Results and validation from various experiments on both simulated and real three-dimensional (3-D) MR images are provided.

Automated model-based bias field correction of MR images of the brain

We propose a model-based method for fully automated bias field correction of MR brain images. The MR signal is modeled as a realization of a random process with a parametric probability distribution that is corrupted by a smooth polynomial inhomogeneity or bias field. The method we propose applies an iterative expectation-maximization (EM) strategy that interleaves pixel classification with estimation of class distribution and bias field parameters, improving the likelihood of the model parameters at each iteration. The algorithm, which can handle multichannel data and slice-by-slice constant intensity offsets, is initialized with information from a digital brain atlas about the a priori expected location of tissue classes. This allows full automation of the method without need for user interaction, yielding more objective and reproducible results. We have validated the bias correction algorithm on simulated data and we illustrate its performance on various MR images with important field inhomogeneities. We also relate the proposed algorithm to other bias correction algorithms.

A fast model independent method for automatic correction of intensity nonuniformity in MRI data

A novel nonparametric approach for correcting intensity nonuniformity in magnetic resonance (MR) images is described. This approach is based solely on the assumption that the various sources of nonuniformity in MR imaging give rise to smooth variations in image intensity, and that these variations can be extracted and corrected for. The advantage of this computationally fast method is that it can be applied early in quantitative analysis while being independent of pulse sequence and is insensitive to pathological processes. This algorithm has been tested on both simulated and real data. Application to tissue segmentation and functional MR imaging has shown a marked improvement in quantitative analysis. J. Magn. Reson. Imaging 1999;10:550-562.

An adaptive segmentation algorithm for time-of-flight MRA data

A three-dimensional (3-D) representation of cerebral vessel morphology is essential for neuroradiologists treating cerebral aneurysms. However, current imaging techniques cannot provide such a representation. Slices of MR angiography (MRA) data can only give two-dimensional (2-D) descriptions and ambiguities of aneurysm position and size arising in X-ray projection images can often be intractable. To overcome these problems, we have established a new automatic statistically based algorithm for extracting the 3-D vessel information from time-of-flight (TOF) MRA data. We introduce distributions for the data, motivated by a physical model of blood flow, that are used in a modified version of the expectation maximization (EM) algorithm. The estimated model parameters are then used to classify statistically the voxels into vessel or other brain tissue classes. The algorithm is adaptive because the model fitting is performed recursively so that classifications are made on local subvolumes of data. We present results from applying our algorithm to several real data sets that contain both artery and aneurysm structures of various sizes.