Partial-volume Bayesian classification of material mixtures in MR volume data using voxel histograms

Local histograms for design of transfer functions in direct volume rendering

Direct Volume Rendering (DVR) is of increasing diagnostic value in the analysis of data sets captured using the latest medical imaging modalities. The deployment of DVR in everyday clinical work, however, has so far been limited. One contributing factor is that current Transfer Function (TF) models can encode only a small fraction of the user's domain knowledge. In this paper, we use histograms of local neighborhoods to capture tissue characteristics. This allows domain knowledge on spatial relations in the data set to be integrated into the TF. As a first example, we introduce Partial Range Histograms in an automatic tissue detection scheme and present its effectiveness in a clinical evaluation. We then use local histogram analysis to perform a classification where the tissue-type certainty is treated as a second TF dimension. The result is an enhanced rendering where tissues with overlapping intensity ranges can be discerned without requiring the user to explicitly define a complex, multidimensional TF.

Left-ventricle myocardium segmentation using a coupled level-set with a priori knowledge

This paper presents a coupled level-set segmentation of the myocardium of the left ventricle of the heart using a priori information. From a fast marching initialisation, two fronts representing the endocardium and epicardium boundaries of the left ventricle are evolved as the zero level-set of a higher dimension function. We introduce a novel and robust stopping term using both gradient and region-based information. The segmentation is supervised both with a coupling function and using a probabilistic model built from training instances. The robustness of the segmentation scheme is evaluated by performing a segmentation on four unseen data-sets containing high variation and the performance of the segmentation is quantitatively assessed.

Level set based cerebral vasculature segmentation and diameter quantification in CT angiography

A level set based method is presented for cerebral vascular tree segmentation from computed tomography angiography (CTA) data. The method starts with bone masking by registering a contrast enhanced scan with a low-dose mask scan in which the bone has been segmented. Then an estimate of the background and vessel intensity distributions is made based on the intensity histogram which is used to steer the level set to capture the vessel boundaries. The relevant parameters of the level set evolution are optimized using a training set. The method is validated by a diameter quantification study which is carried out on phantom data, representing ground truth, and 10 patient data sets. The results are compared to manually obtained measurements by two expert observers. In the phantom study, the method achieves similar accuracy as the observers, but is unbiased whereas the observers are biased, i.e., the results are 0.00+/-0.23 vs. -0.32+/-0.23 mm. Also, the method's reproducibility is slightly better than the inter-and intra-observer variability. In the patient study, the method is in agreement with the observers and also, the method's reproducibility -0.04+/-0.17 mm is similar to the inter-observer variability 0.06+/-0.17 mm. Since the method achieves comparable accuracy and reproducibility as the observers, and since the method achieves better performance than the observers with respect to ground truth, we conclude that the level set based vessel segmentation is a promising method for automated and accurate CTA diameter quantification.

Partial volume reduction by interpolation with reverse diffusion

Many medical images suffer from the partial volume effect where a boundary between two structures of interest falls in the midst of a voxel giving a signal value that is a mixture of the two. We propose a method to restore the ideal boundary by splitting a voxel into subvoxels and reapportioning the signal into the subvoxels. Each voxel is divided by nearest neighbor interpolation. The gray level of each subvoxel is considered as “material” able to move between subvoxels but not between voxels. A partial differential equation is written to allow the material to flow towards the highest gradient direction, creating a “reverse” diffusion process. Flow is subject to constraints that tend to create step edges. Material is conserved in the process thereby conserving signal. The method proceeds until the flow decreases to a low value. To test the method, synthetic images were downsampled to simulate the partial volume artifact and restored. Corrected images were remarkably closer both visually and quantitatively to the original images than those obtained from common interpolation methods: on simulated data standard deviation of the errors were 3.8%, 6.6%, and 7.1% of the dynamic range for the proposed method, bicubic, and bilinear interpolation, respectively. The method was relatively insensitive to noise. On gray level, scanned text, MRI physical phantom, and brain images, restored images processed with the new method were visually much closer to high-resolution counterparts than those obtained with common interpolation methods.

Diffusion tensor imaging in primary brain tumors: reproducible quantitative analysis of corpus callosum infiltration and contralateral involvement using a probabilistic mixture model

Diffusion tensor imaging (DTI) has been advocated as a promising tool for delineation of the extent of tumor infiltration by primary brain tumors. First reports show conflicting results mainly due to difficulties in reproducible determination of DTI-derived parameters. A novel method based on probabilistic voxel classification for a user-independent analysis of DTI-derived parameters is presented and tested in healthy controls and patients with primary brain tumors. The proposed quantification method proved to be highly reproducible both in healthy controls and patients. Fiber integrity in the corpus callosum (CC) was measured using this quantification method, and the profiles of fractional anisotropy (FA) provided additional information of the possible extent of infiltration of primary brain tumors when compared to conventional imaging. This yielded additional information on the nature of ambiguous contralateral lesions in patients with primary brain tumors. The results show that DTI-derived parameters can be determined reproducibly and may have a strong impact on evaluation of contralateral extent of primary brain tumors.

Super-resolution registration using tissue-classified distance fields

We present a method for registering the position and orientation of bones across multiple computed-tomography (CT) volumes of the same subject. The method is subvoxel accurate, can operate on multiple bones within a set of volumes, and registers bones that have features commensurate in size to the voxel dimension. First, a geometric object model is extracted from a reference volume image. We use then unsupervised tissue classification to generate from each volume to be registered a super-resolution distance field--a scalar field that specifies, at each point, the signed distance from the point to a material boundary. The distance fields and the geometric bone model are finally used to register an object through the sequence of CT images. In the case of multiobject structures, we infer a motion-directed hierarchy from the distance-field information that allows us to register objects that are not within each other's capture region. We describe a validation framework and evaluate the new technique in contrast with grey-value registration. Results on human wrist data show average accuracy improvements of 74% over grey-value registration. The method is of interest to any intrasubject, same-modality registration applications where subvoxel accuracy is desired.

Comparison and validation of tissue modelization and statistical classification methods in T1-weighted MR brain images

This paper presents a validation study on statistical nonsupervised brain tissue classification techniques in magnetic resonance (MR) images. Several image models assuming different hypotheses regarding the intensity distribution model, the spatial model and the number of classes are assessed. The methods are tested on simulated data for which the classification ground truth is known. Different noise and intensity nonuniformities are added to simulate real imaging conditions. No enhancement of the image quality is considered either before or during the classification process. This way, the accuracy of the methods and their robustness against image artifacts are tested. Classification is also performed on real data where a quantitative validation compares the methods' results with an estimated ground truth from manual segmentations by experts. Validity of the various classification methods in the labeling of the image as well as in the tissue volume is estimated with different local and global measures. Results demonstrate that methods relying on both intensity and spatial information are more robust to noise and field inhomogeneities. We also demonstrate that partial volume is not perfectly modeled, even though methods that account for mixture classes outperform methods that only consider pure Gaussian classes. Finally, we show that simulated data results can also be extended to real data.

Estimation of the content of fat and parenchyma in breast tissue using MRI T1 histograms and phantoms

Mammographic breast density has been correlated with breast cancer risk. Estimation of the volumetric composition of breast tissue using three-dimensional MRI has been proposed, but accuracy depends upon the estimation methods employed. The use of segmentation based on T1 relaxation rates allows quantitative estimates of fat and parenchyma volume, but is limited by partial volume effects. An investigation employing phantom breast tissue composed of various combinations of chicken breast (to represent parenchyma) and cooking fats was carried out to elucidate the factors that influence MRI T1 histograms. Using the phantoms, T1 histograms and their known fat and parenchyma composition, a logistic distribution function was derived to describe the apportioning of the T1 histogram to fat and parenchyma. This function and T1 histograms were then used to predict the fat and parenchyma content of breasts from 14 women. Using this method, the composition of the breast tissue in the study population was as follows: fat 69.9+/-22.9% and parenchyma 30.1+/-22.9%.

Muscle and fat quantification in MRI gradient echo images using a partial volume detection method. Application to the characterization of pig belly tissue

Complete dissection is the current reference method to quantify muscle and fat tissue on pig carcasses. Magnetic resonance imaging (MRI) is an appropriate nondestructive alternative method that can provide reliable and quantitative information on pig carcass composition without losing the spatial information. We have developed a method to quantify the amount of fat tissue and muscle in gradient echo MR images. This method is based on the method proposed by Shattuck et al. [12]. It provides segmentation of pure tissue and partial volume voxels, which allows separation of muscle and fat tissue including the fine insertions of intermuscular fat. Partial volume voxel signal is expected to be proportional to the signals of pure tissue constituting them or at least to vary monotonously with the proportion of each tissue. However, it is not always the case with gradient echo sequence due to the chemical shift effect. We studied this effect on a fat tissue/muscle interface model with variable proportion of water in the fat tissue and variable TE. We found that at TE=8 ms, for a 0.2-T MRI system, the requirement of Shattuck's method were filled thanks to the presence of water in fat tissue. Moreover, we extended the segmentation method with a simple correction scheme to compute more accurately the proportions of each tissue in partial volume voxels. We used this method to evaluate the fat tissue and muscle on 24 pig bellies using a gradient echo sequence (TR 700 ms, TE 8 ms, slice thickness 8 mm, number of averages 8, flip angle 90 degrees , FOV 512 mm, matrix 512*512, Rect. FOV 4/8, 19 slices, space between slices 2 mm). The image analysis results were compared with dissection results giving a prediction error of the muscle content (mean=2.7 kg) of 88.9 g and of the fat content (mean=2.7 kg) of 115.8 g without correction of the chemical shift effect in the computation of partial volume fat content. The correction scheme improved these results to, respectively, 81.5 and 107.1 g.

Opacity transfer function optimization for volume-rendered computed tomography images of the prostate

RATIONALE AND OBJECTIVES

The selection of an opacity transfer function is essential for volume visualization. Computed tomography (CT) scans of the pelvis were used to determine an optimal opacity transfer function for use in radiotherapy.

MATERIALS AND METHODS

On sample datasets (a mathematical phantom and a patient pelvis CT scan), standard viewing orientations were selected to render the prostate. Opacity functions were selected via (1) trapezoidal manual selection, (2) trapezoidal semiautomatic selection, and (3) histogram volume-based selection. Using an established metric, the errors using each of these methods were computed.

RESULTS

Trapezoidal manual opacity function optimization resulted in visually acceptable images, but the errors were considerable (6.3-9.1 voxel units). These errors could be reduced with the use of trapezoidal semiautomatic selection (4.9-6.2 voxel units) or with histogram volume-based selection (4.8-7.9 voxel units). As each visualization algorithm focused on enhancing the boundary of the prostate using a different approach, the scene information was considerably different using the three techniques.

CONCLUSION

Improved volume visualization of soft tissue interfaces was achieved using automated optimal opacity function determination, compared with manual selection.

CT volumetry of intravertebral cement after kyphoplasty. Comparison of polymethylmethacrylate and calcium phosphate in a 12-month follow-up

This study was intended to measure the volume of intravertebral cement after balloon kyphoplasty with high resolution computed tomography (CT) and dedicated software. Volume changes of biocompatible calcium phosphate cement (CPC) were detected during a follow-up of 12 months. Measurements were compared with a control group of patients treated with polymethylmethacrylate (PMMA). Twenty-three vertebrae (14 CPC, 9 PMMA) of 12 patients were examined with CT using an identical imaging protocol. Dedicated software was used to quantify intravertebral cement volume in subvoxel resolution by analyzing each cement implant with a density-weighted algorithm. The mean volume reduction of CPC was 0.08 ml after 12 months, which corresponds to an absorption rate of 2 vol%. However, the difference did not reach significance level (P>0.05). The mean error estimate was 0.005 ml, indicating excellent precision of the method. CT volumetry appears a precise tool for measurement of intravertebral cement volume. CT volumetry offers the possibility of in vivo measurement of CPC resorption.

Unified segmentation

A probabilistic framework is presented that enables image registration, tissue classification, and bias correction to be combined within the same generative model. A derivation of a log-likelihood objective function for the unified model is provided. The model is based on a mixture of Gaussians and is extended to incorporate a smooth intensity variation and nonlinear registration with tissue probability maps. A strategy for optimising the model parameters is described, along with the requisite partial derivatives of the objective function.

Voxel based analysis of tissue volume from MRI data

There are many techniques available for the analysis of MRI data. Often these methods are presented as completed algorithms, which specify what processing must be performed, but they are rarely presented in a way which makes clear the assumptions that must hold in order that these algorithms will provide valid results. The aim of this review article is to relate the common forms of algorithms and to explain the assumptions behind them. This is done in the context of the use of quantitative statistical methods, which we understand to be the only self-consistent method for any data analysis. We hope that this will go some way towards helping with the choice of which algorithm to use for particular analysis tasks.

Robust unsupervised segmentation of infarct lesion from diffusion tensor MR images using multiscale statistical classification and partial volume voxel reclassification

Manual region tracing method for segmentation of infarction lesions in images from diffusion tensor magnetic resonance imaging (DT-MRI) is usually used in clinical works, but it is time consuming. A new unsupervised method has been developed, which is a multistage procedure, involving image preprocessing, calculation of tensor field and measurement of diffusion anisotropy, segmentation of infarction volume based on adaptive multiscale statistical classification (MSSC), and partial volume voxel reclassification (PVVR). The method accounts for random noise, intensity overlapping, partial volume effect (PVE), and intensity shading artifacts, which always appear in DT-MR images. The proposed method was applied to 20 patients with clinically diagnosed brain infarction by DT-MRI scans. The accuracy and reproducibility in terms of identifying the infarction lesion have been confirmed by clinical experts. This automatic segmentation method is promising not only in detecting the location and the size of infarction lesion in stroke patient but also in quantitatively analyzing diffusion anisotropy of lesion to guide clinical diagnoses and therapy.

Volume rendering in the presence of partial volume effects

In tomographic imagery, partial volume effects (PVEs) cause several artifacts in volume renditions. In X-ray computed tomography (CT), for example, soft-tissue-like pseudo structures appear in bone-to-air and bone-to-fat interfaces. Further, skin, which is identical to soft tissue in terms of CT number, obscures the rendition of the latter. The purpose of this paper is to demonstrate these phenomena and to provide effective solutions that yield significantly improved renditions. We introduce two methods that detect and classify voxels with PVE in X-ray CT. Further, a method is described to automatically peel skin so that PVE-resolved renditions of bone and soft tissue reveal considerably more detail. In the first method to address PVE, called the fraction measure (FM) method, the fraction of each tissue material in each voxel v is estimated by taking into account the intensities of the voxels neighboring v. The second method, called uncertainty principle (UP) method, is based on the following postulate (Saha and Udupa, 2001): In any acquired image, voxels with the highest uncertainty occur in the vicinity of object boundaries. The removal of skin is achieved by means of mathematical morphology. Volume renditions have been created before and after applying the methods for several patient CT datasets. A mathematical phantom experiment involving different levels of PVE has been conducted by adding different degrees of noise and blurring. A quantitative evaluation is done utilizing the mathematical phantom and clinical CT data wherein an operator carefully masked out voxels with PVE in the segmented images. All results have demonstrated the enhanced quality of display of bone and soft tissue after applying the proposed methods. The quantitative evaluations indicate that more than 98% of the voxels with PVE are removed by the two methods and the second method performs slightly better than the first. Further, skin peeling vividly reveals fine details in the soft tissue structures.

Fast and robust parameter estimation for statistical partial volume models in brain MRI

Due to the finite spatial resolution of imaging devices, a single voxel in a medical image may be composed of mixture of tissue types, an effect known as partial volume effect (PVE). Partial volume estimation, that is, the estimation of the amount of each tissue type within each voxel, has received considerable interest in recent years. Much of this work has been focused on the mixel model, a statistical model of PVE. We propose a novel trimmed minimum covariance determinant (TMCD) method for the estimation of the parameters of the mixel PVE model. In this method, each voxel is first labeled according to the most dominant tissue type. Voxels that are prone to PVE are removed from this labeled set, following which robust location estimators with high breakdown points are used to estimate the mean and the covariance of each tissue class. Comparisons between different methods for parameter estimation based on classified images as well as expectation--maximization-like (EM-like) procedure for simultaneous parameter and partial volume estimation are reported. The robust estimators based on a pruned classification as presented here are shown to perform well even if the initial classification is of poor quality. The results obtained are comparable to those obtained using the EM-like procedure, but require considerably less computation time. Segmentation results of real data based on partial volume estimation are also reported. In addition to considering the parameter estimation problem, we discuss differences between different approximations to the complete mixel model. In summary, the proposed TMCD method allows for the accurate, robust, and efficient estimation of partial volume model parameters, which is crucial to a variety of brain MRI data analysis procedures such as the accurate estimation of tissue volumes and the accurate delineation of the cortical surface.

Automated segmentation of human brain MR images using a multi-agent approach

Image interpretation consists in finding a correspondence between radiometric information and symbolic labeling with respect to specific spatial constraints. It is intrinsically a distributed process in terms of goals to be reached, zones in the image to be processed and methods to be applied. To cope the the difficulty inherent in this process, several information processing steps are required to gradually extract information. In this paper we advocate the use of situated cooperative agents as a framework for managing such steps. Dedicated agent behaviors are dynamically adapted depending on their position in the image, of their topographic relationships and of the radiometric information available. The information collected by the agents is gathered, shared via qualitative maps, or used as soon as available by acquaintances. Incremental refinement of interpretation is obtained through a coarse to fine strategy. Our work is essentially focused on radiometry-based tissue interpretation where knowledge is introduced or extracted at several levels to estimate models for tissue-intensity distribution and to cope with noise, intensity non-uniformity and partial volume effect. Several experiments on phantom and real images were performed. A complete volume can be segmented in less than 5 min with about 0.84% accuracy of the segmented reference. Comparison with other techniques demonstrates the potential interest of our approach for magnetic resonance imaging (MRI) brain scan interpretation.

Evaluation of voxel-based morphometry for focal lesion detection in individuals

Voxel-based morphometry (VBM) is an automated statistical technique used to detect regional differences in tissue density and tissue amount based on spatially standardized structural magnetic resonance (MR) images. Developed initially to discern differences between groups of subjects, VBM is now being used to characterize structural abnormalities in individual brains. While VBM performance has been qualitatively assessed for this purpose, to date no quantitative validation study has been performed. This study evaluated several commonly used variants of VBM for detecting structural differences at the individual level by assessing their performance in MR images of 10 subjects with stable focal brain lesions. Results were quantitatively compared to expert tracings of the lesions, the current gold standard for lesion detection and delineation. Additionally, analyses using two sets of simulated lesion data were performed to examine the relative impact of the underlying processing steps on VBM results. Performance metrics revealed that (1) for this application, VBM had low sensitivity; (2) detection sensitivity was altered by model parameterization; (3) underperformance was due to the adverse influence of lesions on the preprocessing steps and to insufficient statistical power; and (4) VBM could not satisfactorily delineate the spatial extent of lesions, even in simulations that avoided preprocessing artifacts. In its current form, VBM is not a suitable stand-alone technique for detecting or spatially characterizing focal lesions.

A fully automatic and robust brain MRI tissue classification method

A novel, fully automatic, adaptive, robust procedure for brain tissue classification from 3D magnetic resonance head images (MRI) is described in this paper. The procedure is adaptive in that it customizes a training set, by using a 'pruning' strategy, such that the classification is robust against anatomical variability and pathology. Starting from a set of samples generated from prior tissue probability maps (a 'model') in a standard, brain-based coordinate system ('stereotaxic space'), the method first reduces the fraction of incorrectly labeled samples in this set by using a minimum spanning tree graph-theoretic approach. Then, the corrected set of samples is used by a supervised kNN classifier for classifying the entire 3D image. The classification procedure is robust against variability in the image quality through a non-parametric implementation: no assumptions are made about the tissue intensity distributions. The performance of this brain tissue classification procedure is demonstrated through quantitative and qualitative validation experiments on both simulated MRI data (10 subjects) and real MRI data (43 subjects). A significant improvement in output quality was observed on subjects who exhibit morphological deviations from the model due to aging and pathology.

Construction of an abdominal probabilistic atlas and its application in segmentation

There have been significant efforts to build a probabilistic atlas of the brain and to use it for many common applications, such as segmentation and registration. Though the work related to brain atlases can be applied to nonbrain organs, less attention has been paid to actually building an atlas for organs other than the brain. Motivated by the automatic identification of normal organs for applications in radiation therapy treatment planning, we present a method to construct a probabilistic atlas of an abdomen consisting of four organs (i.e., liver, kidneys, and spinal cord). Using 32 noncontrast abdominal computed tomography (CT) scans, 31 were mapped onto one individual scan using thin plate spline as the warping transform and mutual information (MI) as the similarity measure. Except for an initial coarse placement of four control points by the operators, the MI-based registration was automatic. Additionally, the four organs in each of the 32 CT data sets were manually segmented. The manual segmentations were warped onto the "standard" patient space using the same transform computed from their gray scale CT data set and a probabilistic atlas was calculated. Then, the atlas was used to aid the segmentation of low-contrast organs in an additional 20 CT data sets not included in the atlas. By incorporating the atlas information into the Bayesian framework, segmentation results clearly showed improvements over a standard unsupervised segmentation method.

Segmentation of carpal bones from CT images using skeletally coupled deformable models

The in vivo investigation of joint kinematics in normal and injured wrist requires the segmentation of carpal bones from 3D (CT) images, and their registration over time. The non-uniformity of bone tissue, ranging from dense cortical bone to textured spongy bone, the irregular shape of closely packed carpal bones, small inter-bone spaces compared to the resolution of CT images, along with the presence of blood vessels, and the inherent blurring of CT imaging render the segmentation of carpal bones a challenging task. We review the performance of statistical classification, deformable models (active contours), region growing, region competition, and morphological operations for this application. We then propose a model which combines several of these approaches in a unified framework. Specifically, our approach is to use a curve evolution implementation of region growing from initialized seeds, where growth is modulated by a skeletally-mediated competition between neighboring regions. The inter-seed skeleton, which we interpret as the predicted boundary of collision between two regions, is used to couple the growth of seeds and to mediate long-range competition between them. The implementation requires subpixel representations of each growing region as well as the inter-region skeleton. This method combines the advantages of active contour models, region growing, and both local and global region competition methods. We demonstrate the effectiveness of this approach for our application where many of the difficulties presented above are overcome as illustrated by synthetic and real examples. Since this segmentation method does not rely on domain-specific knowledge, it should be applicable to a range of other medical imaging segmentation tasks.

A unifying framework for partial volume segmentation of brain MR images

Accurate brain tissue segmentation by intensity-based voxel classification of magnetic resonance (MR) images is complicated by partial volume (PV) voxels that contain a mixture of two or more tissue types. In this paper, we present a statistical framework for PV segmentation that encompasses and extends existing techniques. We start from a commonly used parametric statistical image model in which each voxel belongs to one single tissue type, and introduce an additional downsampling step that causes partial voluming along the borders between tissues. An expectation-maximization approach is used to simultaneously estimate the parameters of the resulting model and perform a PV classification. We present results on well-chosen simulated images and on real MR images of the brain, and demonstrate that the use of appropriate spatial prior knowledge not only improves the classifications, but is often indispensable for robust parameter estimation as well. We conclude that general robust PV segmentation of MR brain images requires statistical models that describe the spatial distribution of brain tissues more accurately than currently available models.

Estimators of tissue proportions from X-ray CT images

Estimators are derived of tissue proportions from X-ray computed tomography (CT) images. These take into account that many pixels in such images are responses to mixtures of tissue types. The problem is motivated by an application involving estimation of sheep tissue weights. The standard estimator, a count of the number of pixels in a particular range of values, is compared with the maximum likelihood fit of a mixed-pixel distribution and a moment-based estimator. Both simulations and the application show the moment estimator to be best.

A robust method for extraction and automatic segmentation of brain images

A new protocol is introduced for brain extraction and automatic tissue segmentation of MR images. For the brain extraction algorithm, proton density and T2-weighted images are used to generate a brain mask encompassing the full intracranial cavity. Segmentation of brain tissues into gray matter (GM), white matter (WM), and cerebral spinal fluid (CSF) is accomplished on a T1-weighted image after applying the brain mask. The fully automatic segmentation algorithm is histogram-based and uses the Expectation Maximization algorithm to model a four-Gaussian mixture for both global and local histograms. The means of the local Gaussians for GM, WM, and CSF are used to set local thresholds for tissue classification. Reproducibility of the extraction procedure was excellent, with average variation in intracranial capacity (TIC) of 0.13 and 0.66% TIC in 12 healthy normal and 33 Alzheimer brains, respectively. Repeatability of the segmentation algorithm, tested on healthy normal images, indicated scan-rescan differences in global tissue volumes of less than 0.30% TIC. Reproducibility at the regional level was established by comparing segmentation results within the 12 major Talairach subdivisions. Accuracy of the algorithm was tested on a digital brain phantom, and errors were less than 1% of the phantom volume. Maximal Type I and Type II classification errors were low, ranging between 2.2 and 4.3% of phantom volume. The algorithm was also insensitive to variation in parameter initialization values. The protocol is robust, fast, and its success in segmenting normal as well as diseased brains makes it an attractive clinical application.

Segmentation of fat and muscle from MR images of the thigh by a possibilistic clustering algorithm

Physical training is proved to induce changes in physical capacity and body composition. We propose in this article a fast, unsupervised and fully three-dimensional automatic method to extract muscle and fat volumes from magnetic resonance images of thighs in order to assess these changes. The technique relies on the use of a fuzzy clustering algorithm and post-processings to accurately process the body composition of thighs. Results are compared on 11 healthy voluntary elderly people with those provided on the same data by a validated method already published, and its reliability is assessed on repeated measures on three subjects. The two methods statistically agree when computing muscle and fat volumes, and clinical implications of this fully automatic method are important for medicine, physical conditioning, weight-loss programs and predictions of optimal body weight.

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.

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.

Hybrid artificial neural network segmentation of precise and accurate inversion recovery (PAIR) images from normal human brain

This paper presents a novel semi-automated segmentation and classification method based on raw signal intensities from a quantitative T1 relaxation technique with two novel approaches for the removal of partial volume effects. The segmentation used a Kohonen Self Organizing Map that eliminated inter- and intra-operator variability. A Multi-layered Backpropagation Neural Network was able to classify the test data with a predicted accuracy of 87.2% when compared to manual classification. A linear interpolation of the quantitative T1 information by region and on a pixel-by-pixel basis was used to redistribute voxels containing a partial volume of gray matter (GM) and white matter (WM) or a partial volume of GM and cerebrospinal fluid (CSF) into the principal components of GM, WM, and CSF. The method presented was validated against manual segmentation of the base images by three experienced observers. Comparing segmented outputs directly to the manual segmentation revealed a difference of less than 2% in GM and less than 6% in WM for pure tissue estimations for both the regional and pixel-by-pixel redistribution techniques. This technique produced accurate estimates of the amounts of GM and WM while providing a reliable means of redistributing partial volume effects.

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.

Segmentation of the skull in MRI volumes using deformable model and taking the partial volume effect into account

Segmentation of the skull in medical imagery is an important stage in applications that require the construction of realistic models of the head. Such models are used, for example, to simulate the behavior of electro-magnetic fields in the head and to model the electrical activity of the cortex in EEG and MEG data. In this paper, we present a new approach for segmenting regions of bone in MRI volumes using deformable models. Our method takes into account the partial volume effects that occur with MRI data, thus permitting a precise segmentation of these bone regions. At each iteration of the propagation of the model, partial volume is estimated in a narrow band around the deformable model. Our segmentation method begins with a pre-segmentation stage, in which a preliminary segmentation of the skull is constructed using a region-growing method. The surface that bounds the pre-segmented skull region offers an automatic 3D initialization of the deformable model. This surface is then propagated (in 3D) in the direction of its normal. This propagation is achieved using level set method, thus permitting changes to occur in the topology of the surface as it evolves, an essential capability for our problem. The speed at which the surface evolves is a function of the estimated partial volume. This provides a sub-voxel accuracy in the resulting segmentation.

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.

Improved phase-contrast flow quantification by three-dimensional vessel localization

In this paper, a method of three-dimensional (3D) vessel localization is presented to allow the identification of a vessel of interest, the selection of a vessel segment, and the determination of a slice orientation to improve the accuracy of phase-contrast magnetic resonance (PCMR) angiography. A marching-cube surface-rendering algorithm was used to reconstruct the 3D vasculature. Surface-rendering was obtained using an iso-surface value determined from a maximum intensity projection (MIP) image. This 3D vasculature was used to find a vessel of interest, select a vessel segment, and to determine the slice orientation perpendicular to the vessel axis. Volumetric flow rate (VFR) was obtained in a phantom model and in vivo using 3D localization with double oblique cine PCMR scanning. PCMR flow measurements in the phantom showed 5. 2% maximum error and a standard deviation of 9 mL/min during steady flow, 7.9% maximum error and a standard deviation of 13 mL/min during pulsatile flow compared with measurements using an ultrasonic transit-time flowmeter. PCMR VFR measurement error increased with misalignment at 10, 20, and 30 degrees oblique to the perpendicular slice in vitro and in vivo. The 3D localization technique allowed precise localization of the vessel of interest and optimal placement of the slice orientation for minimum error in flow measurements.

Bayesian estimation of relaxation times T(1) in MR images of irradiated Fricke-agarose gels

The authors present a novel method for processing T(1)-weighted images acquired with Inversion-Recovery (IR) sequence. The method, developed within the Bayesian framework, takes into account a priori knowledge about the spatial regularity of the parameters to be estimated. Inference is drawn by means of Markov Chains Monte Carlo algorithms. The method has been applied to the processing of IR images from irradiated Fricke-agarose gels, proposed in the past as relative dosimeter to verify radiotherapeutic treatment planning systems. Comparison with results obtained from a standard approach shows that signal-to noise ratio (SNR) is strongly enhanced when the estimation of the longitudinal relaxation rate (R1) is performed with the newly proposed statistical approach. Furthermore, the method allows the use of more complex models of the signal. Finally, an appreciable reduction of total acquisition time can be obtained due to the possibility of using a reduced number of images. The method can also be applied to T(1) mapping of other systems.

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.

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.

Estimation and detection of myocardial tags in MR image without user-defined myocardial contours

Magnetic resonance (MR) tagging has been shown to be a useful technique for noninvasively measuring the deformation of an in vivo heart. An important step in analyzing tagged images is the identification of tag lines in each image of a cine sequence. Most existing tag identification algorithms require user defined myocardial contours. Contour identification, however, is time consuming and requires a considerable amount of user intervention. In this paper, a new method for identifying tag lines, which we call the ML/MAP method, is presented that does not require user defined myocardial contours. The ML/MAP method is composed of three stages. First, a set of candidate tag line centers is estimated across the entire region-of-interest (ROI) with a snake algorithm based on a maximum-likelihood (ML) estimate of the tag center. Next, a maximum a posteriori (MAP) hypothesis test is used to detect the candidate tag centers that are actually part of a tag line. Finally, a pruning algorithm is used to remove any detected tag line centers that do not meet a spatio-temporal continuity criterion. The ML/MAP method is demonstrated on data from ten in vivo human hearts.