Fully automatic segmentation of the brain in MRI

Vascular segmentation of phase contrast magnetic resonance angiograms based on statistical mixture modeling and local phase coherence

In this paper, we present an approach to segmenting the brain vasculature in phase contrast magnetic resonance angiography (PC-MRA). According to our prior work, we can describe the overall probability density function of a PC-MRA speed image as either a Maxwell-uniform (MU) or Maxwell-Gaussian-uniform (MGU) mixture model. An automatic mechanism based on Kullback-Leibler divergence is proposed for selecting between the MGU and MU models given a speed image volume. A coherence measure, namely local phase coherence (LPC), which incorporates information about the spatial relationships between neighboring flow vectors, is defined and shown to be more robust to noise than previously described coherence measures. A statistical measure from the speed images and the LPC measure from the phase images are combined in a probabilistic framework, based on the maximum a posteriori method and Markov random fields, to estimate the posterior probabilities of vessel and background for classification. It is shown that segmentation based on both measures gives a more accurate segmentation than using either speed or flow coherence information alone. The proposed method is tested on synthetic, flow phantom and clinical datasets. The results show that the method can segment normal vessels and vascular regions with relatively low flow rate and low signal-to-noise ratio, e.g., aneurysms and veins.

Sensitivity of EEG and MEG measurements to tissue conductivity

Monitoring the electrical activity inside the human brain using electrical and magnetic field measurements requires a mathematical head model. Using this model the potential distribution in the head and magnetic fields outside the head are computed for a given source distribution. This is called the forward problem of the electro-magnetic source imaging. Accurate representation of the source distribution requires a realistic geometry and an accurate conductivity model. Deviation from the actual head is one of the reasons for the localization errors. In this study, the mathematical basis for the sensitivity of voltage and magnetic field measurements to perturbations from the actual conductivity model is investigated. Two mathematical expressions are derived relating the changes in the potentials and magnetic fields to conductivity perturbations. These equations show that measurements change due to secondary sources at the perturbation points. A finite element method (FEM) based formulation is developed for computing the sensitivity of measurements to tissue conductivities efficiently. The sensitivity matrices are calculated for both a concentric spheres model of the head and a realistic head model. The rows of the sensitivity matrix show that the sensitivity of a voltage measurement is greater to conductivity perturbations on the brain tissue in the vicinity of the dipole, the skull and the scalp beneath the electrodes. The sensitivity values for perturbations in the skull and brain conductivity are comparable and they are, in general, greater than the sensitivity for the scalp conductivity. The effects of the perturbations on the skull are more pronounced for shallow dipoles, whereas, for deep dipoles, the measurements are more sensitive to the conductivity of the brain tissue near the dipole. The magnetic measurements are found to be more sensitive to perturbations near the dipole location. The sensitivity to perturbations in the brain tissue is much greater when the primary source is tangential and it decreases as the dipole depth increases. The resultant linear system of equations can be used to update the initially assumed conductivity distribution for the head. They may be further exploited to image the conductivity distribution of the head from EEG and/or MEG measurements. This may be a fast and promising new imaging modality.

A hybrid approach to the skull stripping problem in MRI

We present a novel skull-stripping algorithm based on a hybrid approach that combines watershed algorithms and deformable surface models. Our method takes advantage of the robustness of the former as well as the surface information available to the latter. The algorithm first localizes a single white matter voxel in a T1-weighted MRI image, and uses it to create a global minimum in the white matter before applying a watershed algorithm with a preflooding height. The watershed algorithm builds an initial estimate of the brain volume based on the three-dimensional connectivity of the white matter. This first step is robust, and performs well in the presence of intensity nonuniformities and noise, but may erode parts of the cortex that abut bright nonbrain structures such as the eye sockets, or may remove parts of the cerebellum. To correct these inaccuracies, a surface deformation process fits a smooth surface to the masked volume, allowing the incorporation of geometric constraints into the skull-stripping procedure. A statistical atlas, generated from a set of accurately segmented brains, is used to validate and potentially correct the segmentation, and the MRI intensity values are locally re-estimated at the boundary of the brain. Finally, a high-resolution surface deformation is performed that accurately matches the outer boundary of the brain, resulting in a robust and automated procedure. Studies by our group and others outperform other publicly available skull-stripping tools.

Putting our heads together: a consensus approach to brain/non-brain segmentation in T1-weighted MR volumes

We describe an approach to brain extraction from T1-weighted MR volumes that uses a hierarchy of masks created by different models to form a consensus mask. The algorithm (McStrip) incorporates atlas-based extraction via nonlinear warping, intensity-threshold masking with connectivity constraints, and edge-based masking with morphological operations. Volume and boundary metrics were computed to evaluate the reproducibility and accuracy of McStrip against manual brain extraction on 38 scans from normal and ataxic subjects. McStrip masks were reproducible across six repeat scans of a normal subject and were significantly more accurate than the masks produced by any of the individual algorithmic components.

Method for bias field correction of brain T1-weighted magnetic resonance images minimizing segmentation error

This work presents a new algorithm (nonuniform intensity correction; NIC) for correction of intensity inhomogeneities in T1-weighted magnetic resonance (MR) images. The bias field and a bias-free image are obtained through an iterative process that uses brain tissue segmentation. The algorithm was validated by means of realistic phantom images and a set of 24 real images. The first evaluation phase was based on a public domain phantom dataset, used previously to assess bias field correction algorithms. NIC performed similar to previously described methods in removing the bias field from phantom images, without introduction of degradation in the absence of intensity inhomogeneity. The real image dataset was used to compare the performance of this new algorithm to that of other widely used methods (N3, SPM'99, and SPM2). This dataset included both low and high bias field images from two different MR scanners of low (0.5 T) and medium (1.5 T) static fields. Using standard quality criteria for determining the goodness of the different methods, NIC achieved the best results, correcting the images of the real MR dataset, enabling its systematic use in images from both low and medium static field MR scanners. A limitation of our method is that it might fail if the bias field is so high that the initial histogram does not show bimodal distribution for white and gray matter.

Fetal Brain MRI: Segmentation and Biometric Analysis of the Posterior Fossa

This paper presents a novel approach to fetal magnetic resonance image segmentation and biometric analysis of the posterior fossa's midline structures. We developed a semi-automatic segmentation method (based on a region growing technique) and tested the algorithm on images of 104 normal fetuses. Using the segmented regions of interest (posterior fossa, vermis, and brainstem), we computed four relative area ratios. Statistical and clinical analysis of our results showed that the relative development of these structures appears to be independent of pregnancy term. In an additional study of 23 pathological cases, one of the four measurements was always significantly different from the corresponding value observed in normal cases.

Improved watershed transform for medical image segmentation using prior information

The watershed transform has interesting properties that make it useful for many different image segmentation applications: it is simple and intuitive, can be parallelized, and always produces a complete division of the image. However, when applied to medical image analysis, it has important drawbacks (oversegmentation, sensitivity to noise, poor detection of thin or low signal to noise ratio structures). We present an improvement to the watershed transform that enables the introduction of prior information in its calculation. We propose to introduce this information via the use of a previous probability calculation. Furthermore, we introduce a method to combine the watershed transform and atlas registration, through the use of markers. We have applied our new algorithm to two challenging applications: knee cartilage and gray matter/white matter segmentation in MR images. Numerical validation of the results is provided, demonstrating the strength of the algorithm for medical image segmentation.

Whole-brain atrophy in multiple sclerosis measured by two segmentation processes from various MRI sequences

Recent MRI and pathologic studies have drawn attention to the destructive nature of the multiple sclerosis (MS) disease process, including the early occurrence of axonal and neuronal loss, leading to macroscopic brain and spinal cord atrophy. Measurement of brain atrophy from MRI has emerged as a potential outcome measure and marker of disease severity in MS and neurodegenerative diseases such as Alzheimer's. However, the optimal method for quantifying atrophy has not been established, including the choice of pulse sequence and segmentation algorithm employed. Using two different MRI scanners to ensure generalizability of results, we compared the reproducibility of four pulse sequences and two analysis methods (fully automated [FA] and semi-automated [SA]) when obtaining brain parenchymal fraction (BPF), a normalized measure of whole-brain atrophy, in patients with MS (n=13) and normal controls (n=2). In order to ensure the validity of our fully automated analysis technique, we also used it to evaluate the atrophy rate over nine months in 57 MS patients from the placebo arm of a clinical trial. All pulse sequences were capable of yielding reproducibility of around 1% coefficient of variation (CoV) or better. The best reproducibility was obtained using 2D multi-slice sequences (conventional spin echo [SE] and fluid-attenuated inversion recovery [FLAIR]), with fully automated analysis. Fully automated analysis of the longitudinal data (conventional spin echo) showed an atrophy rate of -0.5% change in BPF per year, in line with previous findings from a similar cohort of patients. In conclusion, BPF measurement is affected by both pulse sequence and segmentation method. Automated measurement has high reproducibility especially when 2D sequences are used. Semi-automated measurement may have increased accuracy, but with a decreased efficiency and reliability.

Noise-adaptive nonlinear diffusion filtering of MR images with spatially varying noise levels

Anisotropic diffusion filtering is widely used for MR image enhancement. However, the anisotropic filter is nonoptimal for MR images with spatially varying noise levels, such as images reconstructed from sensitivity-encoded data and intensity inhomogeneity-corrected images. In this work, a new method for filtering MR images with spatially varying noise levels is presented. In the new method, a priori information regarding the image noise level spatial distribution is utilized for the local adjustment of the anisotropic diffusion filter. Our new method was validated and compared with the standard filter on simulated and real MRI data. The noise-adaptive method was demonstrated to outperform the standard anisotropic diffusion filter in both image error reduction and image signal-to-noise ratio (SNR) improvement. The method was also applied to inhomogeneity-corrected and sensitivity encoding (SENSE) images. The new filter was shown to improve segmentation of MR brain images with spatially varying noise levels.

Computer-assisted enhanced volumetric segmentation magnetic resonance imaging data using a mixture of artificial neural networks

An accurate computer-assisted method able to perform regional segmentation on 3D single modality images and measure its volume is designed using a mixture of unsupervised and supervised artificial neural networks. Firstly, an unsupervised artificial neural network is used to estimate representative textures that appear in the images. The region of interest of the resultant images is selected by means of a multi-layer perceptron after a training using a single sample slice, which contains a central portion of the 3D region of interest. The method was applied to magnetic resonance imaging data collected from an experimental acute inflammatory model (T(2) weighted) and from a clinical study of human Alzheimer's disease (T(1) weighted) to evaluate the proposed method. In the first case, a high correlation and parallelism was registered between the volumetric measurements, of the injured and healthy tissue, by the proposed method with respect to the manual measurements (r = 0.82 and p < 0.05) and to the histopathological studies (r = 0.87 and p < 0.05). The method was also applied to the clinical studies, and similar results were derived of the manual and semi-automatic volumetric measurement of both hippocampus and the corpus callosum (0.95 and 0.88).

Automated cardiac MR image segmentation: theory and measurement evaluation

We present a new approach to magnetic resonance image segmentation with a Gradient-Vector-Flow-based snake applied to selective smoothing filtered images. The system also allows automated image segmentation in the presence of grey scale inhomogeneity, as in cardiac Magnetic Resonance imaging. Removal of such inhomogeneities is a difficult task, but we proved that using non-linear anisotropic diffusion filtering, myocardium edges are selectively preserved. The approach allowed medical data to be automatically segmented in order to track not only endocardium, which is usually a less difficult task, but also epicardium in anatomic and perfusion studies with Magnetic Resonance. The method developed proceeds in three distinct phases: (a) an anisotropic diffusion filtering tool is used to reduce grey scale inhomogeneity and to selectively preserve edges; (b) a Gradient-Vector-Flow-based snake is applied on filtered images to allow capturing a snake from a long range and to move into concave boundary regions; and (c) an automatic procedure based on a snake is used to fit both endocardium and epicardium borders in a multiphase, multislice examination. A good agreement (P<0.001) between manual and automatic data analysis, based on the mean difference+/-SD, was assessed in a pool of 907 cardiac function and perfusion images.

Detection of spectral signatures in multispectral MR images for classification

This paper presents a new spectral signature detection approach to magnetic resonance (MR) image classification. It is called constrained energy minimization (CEM) method, which is derived from the minimum variance distortionless response in passive sensor array processing. It considers a bank of spectral channels as an array of sensors where each spectral channel represents a sensor and object spectral signature in multispectral MR images are viewed as signals impinging upon the array. The strength of the CEM lies on its ability in detection of spectral signatures of interest without knowing image background. The detected spectral signatures are then used for classification. The CEM makes use of a finite impulse response (FIR) filter to linearly constrain a desired object while minimizing interfering effects caused by other unknown signal sources. Unlike most spatial-based classification techniques, the proposed CEM takes advantage of spectral characteristics to achieve object detection and classification. A series of experiments is conducted and compared with the commonly used c-means method for performance evaluation. The results show that the CEM method is a promising and effective spectral technique for MR image classification.

Brain MRI lesion load quantification in multiple sclerosis: a comparison between automated multispectral and semi-automated thresholding computer-assisted techniques

Brain magnetic resonance imaging (MRI) lesion volume measurement is an advantageous tool for assessing disease burden in multiple sclerosis (MS). We have evaluated two computer-assisted techniques: MSA multispectral automatic technique that is based on bayesian classification of brain tissue and NIH image analysis technique that is based on local (lesion by lesion) thresholding, to establish reliability and repeatability values for each technique. Brain MRIs were obtained for 30 clinically definite relapsing-remitting MS patients using a 2.0 Tesla MR scanner with contiguous, 3 mm thick axial, T1, T2 and PD weighted modalities. Digital (Dicom 3) images were analyzed independently by three observers; each analyzed the images twice, using the two different techniques (Total 360 analyses). Accuracy of lesion load measurements using phantom images of known volumes showed significantly better results for the MSA multispectral technique (p < 0.001). The mean intra-and inter-observer variances were, respectively, 0.04 +/- 0.4 (range 0.04-0.13), and 0.09 +/- 0.6 (range 0.01-0.26) for the multispectral MSA analysis technique, 0.24 +/- 2.27 (range 0.23-0.72) and 0.33 +/- 3.8 (range 0.47-1.36) for the NIH threshold technique. These data show that the MSA multispectral technique is significantly more accurate in lesion volume measurements, with better results of within and between observers' assessments, and the lesion load measurements are not influenced by increased disease burden. Measurements by the MSA multispectral technique were also faster and decreased analysis time by 43%. The MSA multispectral technique is a promising tool for evaluating MS patients. Non-biased recognition and delineation algorithms enable high accuracy, low intra-and inter-observer variances and fast assessment of MS related lesion load.

Automated histogram-based brain segmentation in T1-weighted three-dimensional magnetic resonance head images

Current semiautomated magnetic resonance (MR)-based brain segmentation and volume measurement methods are complex and not sufficiently accurate for certain applications. We have developed a simpler, more accurate automated algorithm for whole-brain segmentation and volume measurement in T(1)-weighted, three-dimensional MR images. This histogram-based brain segmentation (HBRS) algorithm is based on histograms and simple morphological operations. The algorithm's three steps are foreground/background thresholding, disconnection of brain from skull, and removal of residue fragments (sinus, cerebrospinal fluid, dura, and marrow). Brain volume was measured by counting the number of brain voxels. Accuracy was determined by applying HBRS to both simulated and real MR data. Comparing the brain volume rendered by HBRS with the volume on which the simulation is based, the average error was 1.38%. By applying HBRS to 20 normal MR data sets downloaded from the Internet Brain Segmentation Repository and comparing them with expert segmented data, the average Jaccard similarity was 0.963 and the kappa index was 0.981. The reproducibility of brain volume measurements was assessed by comparing data from two sessions (four total data sets) with human volunteers. Intrasession variability of brain volumes for sessions 1 and 2 was 0.55 +/- 0.56 and 0.74 +/- 0.56%, respectively; the mean difference between the two sessions was 0.60 +/- 0.46%. These results show that the HBRS algorithm is a simple, fast, and accurate method to determine brain volume with high reproducibility. This algorithm may be applied to various research and clinical investigations in which brain segmentation and volume measurement involving MRI data are needed.

Automatic brain tissue extraction method using erosion-dilation treatment (BREED) from three-dimensional magnetic resonance imaging T1-weighted data

To improve the efficiency of brain image analysis, we propose a full-automatic method for extracting brain tissue from three-dimensional magnetic resonance imaging of T1-weighted data on the human head (brain tissue extraction method using erosion-dilation treatment [BREED]). The extraction processing is realized by combining signal intensity thresholding by means of the discriminant analysis method and an erosion-dilation treatment of the image. The accuracy of BREED is evaluated using both simulated and subject data. BREED can extract brain tissues with high accuracy (approximately 97%) for either simulated or subject data.

Fast robust automated brain extraction

An automated method for segmenting magnetic resonance head images into brain and non-brain has been developed. It is very robust and accurate and has been tested on thousands of data sets from a wide variety of scanners and taken with a wide variety of MR sequences. The method, Brain Extraction Tool (BET), uses a deformable model that evolves to fit the brain's surface by the application of a set of locally adaptive model forces. The method is very fast and requires no preregistration or other pre-processing before being applied. We describe the new method and give examples of results and the results of extensive quantitative testing against "gold-standard" hand segmentations, and two other popular automated methods.

An accurate and efficient bayesian method for automatic segmentation of brain MRI

Automatic three-dimensional (3-D) segmentation of the brain from magnetic resonance (MR) scans is a challenging problem that has received an enormous amount of attention lately. Of the techniques reported in the literature, very few are fully automatic. In this paper, we present an efficient and accurate, fully automatic 3-D segmentation procedure for brain MR scans. It has several salient features; namely, the following. 1) Instead of a single multiplicative bias field that affects all tissue intensities, separate parametric smooth models are used for the intensity of each class. 2) A brain atlas is used in conjunction with a robust registration procedure to find a nonrigid transformation that maps the standard brain to the specimen to be segmented. This transformation is then used to: segment the brain from nonbrain tissue; compute prior probabilities for each class at each voxel location and find an appropriate automatic initialization. 3) Finally, a novel algorithm is presented which is a variant of the expectation-maximization procedure, that incorporates a fast and accurate way to find optimal segmentations, given the intensity models along with the spatial coherence assumption. Experimental results with both synthetic and real data are included, as well as comparisons of the performance of our algorithm with that of other published methods.

Fusing speed and phase information for vascular segmentation of phase contrast MR angiograms

This paper presents a statistical approach to aggregating speed and phase (directional) information for vascular segmentation of phase contrast magnetic resonance angiograms (PC-MRA). Rather than relying on speed information alone, as done by others and in our own work, we demonstrate that including phase information as a priori knowledge in a Markov random field (MRF) model can improve the quality of segmentation. This is particularly true in the region within an aneurysm where there is a heterogeneous intensity pattern and significant vascular signal loss. We propose to use a Maxwell-Gaussian mixture density to model the background signal distribution and combine this with a uniform distribution for modelling vascular signal to give a Maxwell-Gaussian-uniform (MGU) mixture model of image intensity. The MGU model parameters are estimated by the modified expectation-maximisation (EM) algorithm. In addition, it is shown that the Maxwell-Gaussian mixture distribution (a) models the background signal more accurately than a Maxwell distribution, (b) exhibits a better fit to clinical data and (c) gives fewer false positive voxels (misclassified vessel voxels) in segmentation. The new segmentation algorithm is tested on an aneurysm phantom data set and two clinical data sets. The experimental results show that the proposed method can provide a better quality of segmentation when both speed and phase information are utilised.

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.

FLAIR histogram segmentation for measurement of leukoaraiosis volume

The purposes of this study were to develop a method to measure brain and white matter hyperintensity (leukoaraiosis) volume that is based on the segmentation of the intensity histogram of fluid-attenuated inversion recovery (FLAIR) images and to assess the accuracy and reproducibility of the method. Whole-head synthetic image phantoms with manually introduced leukoaraiosis lesions of varying severity were constructed. These synthetic image phantom sets incorporated image contrast and anatomic features that mimicked leukoaraiosis found in real life. One set of synthetic image phantoms was used to develop the segmentation algorithm (FLAIR-histoseg). A second set was used to measure its accuracy. Test retest reproducibility was assessed in 10 elderly volunteers who were imaged twice. The mean absolute error of the FLAIR-histoseg method was 6.6% for measurement of leukoaraiosis volume and 1.4% for brain volume. The mean test retest coefficient of variation was 1.4% for leukoaraiosis volume and 0.3% for brain volume. We conclude that the FLAIR-histoseg method is an accurate and reproducible method for measuring leukoaraiosis and whole-brain volume in elderly subjects.

Orthogonal subspace projection-based approaches to classification of MR image sequences

Orthogonal subspace projection (OSP) approach has shown success in hyperspectral image classification. Recently, the feasibility of applying OSP to multispectral image classification was also demonstrated via SPOT (Satellite Pour 1'Observation de la Terra) and Landsat (Land Satellite) images. Since an MR (magnetic resonance) image sequence is also acquired by multiple spectral channels (bands), this paper presents a new application of OSP in MR image classification. The idea is to model an MR image pixel in the sequence as a linear mixture of substances (such as white matter, gray matter, cerebral spinal fluid) of interest from which each of these substances can be classified by a specific subspace projection operator followed by a desired matched filter. The experimental results show that OSP provides a promising alternative to existing MR image classification techniques.

Three-dimensional segmentation of anatomical structures in MR images on large data bases

In this paper an image-based method founded on mathematical morphology is presented in order to facilitate the segmentation of cerebral structures over large data bases of 3D magnetic resonance images (MRIs). The segmentation is described as an immersion simulation, applied to the modified gradient image, modeled by a generated 3D-region adjacency graph (RAG). The segmentation relies on two main processes: homotopy modification and contour decision. The first one is achieved by a marker extraction stage where homogeneous 3D-regions are identified. This stage uses contrasted regions from morphological reconstruction and labeled flat regions constrained by the RAG. Then, the decision stage intends to precisely locate the contours of regions detected by the marker extraction. This decision is performed by a 3D extension of the watershed transform. The method has been applied on a data base of 3D brain MRIs composed of fifty patients. Results are illustrated by segmenting the ventricles, corpus callosum, cerebellum, hippocampus, pons, medulla and midbrain on our data base and the approach is validated on two phantom 3D MRIs.

Random-grid stereologic volumetry of MR head scans

Point count stereology is a useful tool in obtaining volumetric measures of objects in three-dimensional (3D) images when the segmentation of objects is not feasible. Presently, fixed-grid 3D stereology is being used where a 3D parallelepiped grid is randomly placed for sampling the image space in order to generate test points. Although this is a popular technique, the use of a fixed grid introduces errors in the final estimate in practice and makes the technique inefficient. Random-grid 3D stereology is introduced to improve the efficiency of the volume estimates in stereology. In this manuscript, we prove random-grid stereology as a more consistent technique than fixed-grid stereology and use it for volumetry of the brain and ventricles in magnetic resonance (MR) head scans. We demonstrate superior efficiency and accuracy of random-grid stereology with experiments. Also, the effects of grid sizes, the optimal directions of sectioning the object for volume estimates of the brain and ventricles, and the reliability of the technique are investigated. J. Magn. Reson. Imaging 2000;12:833-841.

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.

Estimating gain fields in multispectral MRI

An unsupervised, completely automatic method for gain field estimation and segmentation of multispectral magnetic resonance (MR) images is presented. This new adaptive algorithm is based on statistical modeling of MR images using finite mixtures. Variability of gain field artifact with imaging parameters (i.e. TE, TR, and TI) is considered in the estimation process. Beside gain field, partial volume artifact is also considered in the labeling phase. Quantitative analysis on experimental results shows an efficient and robust performance of the adaptive algorithm and that it outperforms even advanced nonadaptive intensity-based approaches.

Combining high-performance computing and networking for advanced 3-D cardiac imaging

This paper deals with the integration of a powerful parallel computer-based image analysis and visualization system for cardiology into a hospital information system. Further services are remote access to the hospital Web server through an internet network. The visualization system includes dynamic three-dimensional representation of two types of medical images (e.g., magnetic resonance and nuclear medicine) as well as two images in the same modality (e.g., basal versus stress images). A series of software tools for quantitative image analysis developed for supporting diagnosis of cardiac disease are also available, including automated image segmentation and quantitative time evaluation of left ventricular volumes and related indices during cardiac cycle, myocardial mass, and myocardial perfusion indices. The system has been tested both at a specialized cardiologic center and for remote consultation in diagnosis of cardiac disease by using anatomical and perfusion magnetic resonance images.

A wavelet-frame based image force model for active contouring algorithms

This paper proposes a directional image force (DIF) for active contouring. DIF is the inner product of the zero crossing strength (ZCS) of wavelet frame coefficients, and the normal of a snake, by representing strength and orientation of edges at multiple resolution levels. DIF markedly improves the immunity of snakes to noise and convexity.

Fast, accurate, and reproducible automatic segmentation of the brain in T1-weighted volume MRI data

A new fast automated algorithm has been developed to segment the brain from T1-weighted volume MR images. The algorithm uses automated thresholding and morphological operations. It is fully three-dimensional and therefore independent of scan orientation. The validity and the performance of the algorithm were evaluated by comparing the automatically calculated brain volume with semi-automated measurements in 10 subjects, by calculating the brain volume from repeated scans in another 10 subjects, and by visual inspection. The mean and standard deviation of the difference between semi-automated and automated measurements were 0.56% and 2.8% of the mean brain volume, respectively, which is within inter-observer variability of the semi-automated method. The mean and standard deviation of the difference between the total volumes calculated from repeated scans were 0.40% and 1.2% of the mean brain volume, respectively. Good results were also obtained from a scan of abnormal brains.

Alignment of magnetic-resonance brain datasets with the stereotactical coordinate system

Neuroanatomical and neurofunctional studies are often referenced to high-resolution magnetic-resonance brain datasets. For the analysis of the cortical surface, mapping of functional information on to the cortex or visualization, it is necessary to remove the outer surfaces of the brain. For intersubject comparison, it is useful to align the dataset with a coordinate system and introduce a spatial normalization. We describe an image processing chain that combines all of these steps in an interaction-free procedure. We report on a period of 2 years of routine application of this procedure, with >250 successfully processed datasets from healthy subjects and patients with various forms of brain damage.