Brain tissue classification of magnetic resonance images using partial volume modeling

Atlas-based automatic segmentation of MR images: validation study on the brainstem in radiotherapy context

PURPOSE

Brain tumor radiotherapy requires the volume measurements and the localization of several individual brain structures. Any tool that can assist the physician to perform the delineation would then be of great help. Among segmentation methods, those that are atlas-based are appealing because they are able to segment several structures simultaneously, while preserving the anatomy topology. This study aims to evaluate such a method in a clinical context.

METHODS AND MATERIALS

The brain atlas is made of two three-dimensional (3D) volumes: the first is an artificial 3D magnetic resonance imaging (MRI); the second consists of the segmented structures in this artificial MRI. The elastic registration of the artificial 3D MRI against a patient 3D MRI dataset yields an elastic transformation that can be applied to the labeled image. The elastic transformation is obtained by minimizing the sum of the square differences of the image intensities and derived from the optical flow principle. This automatic delineation (AD) enables the mapping of the segmented structures onto the patient MRI. Parameters of the AD have been optimized on a set of 20 patients. Results are obtained on a series of 6 patients' MRI. A comprehensive validation of the AD has been conducted on performance of atlas-based segmentation in a clinical context with volume, position, sensitivity, and specificity that are compared by a panel of seven experimented physicians for the brain tumor treatments.

RESULTS

Expert interobserver volume variability ranged from 16.70 cm(3) to 41.26 cm(3). For patients, the ratio of minimal to maximal volume ranged from 48% to 70%. Median volume varied from 19.47 cm(3) to 27.66 cm(3) and volume of the brainstem calculated by AD varied from 17.75 cm(3) to 24.54 cm(3). Medians of experts ranged, respectively, for sensitivity and specificity, from 0.75 to 0.98 and from 0.85 to 0.99. Median of AD were, respectively, 0.77 and 0.97. Mean of experts ranged, respectively, from 0.78 to 0.97 and from 0.86 to 0.99. Mean of AD were, respectively, 0.76 and 0.97.

CONCLUSIONS

Results demonstrate that the method is repeatable, provides a good trade-off between accuracy and robustness, and leads to reproducible segmentation and labeling. These results can be improved by enriching the atlas with the rough information of tumor or by using different laws of deformation for the different structures. Qualitative results also suggest that this method can be used for automatic segmentation of other organs such as neck, thorax, abdomen, pelvis, and limbs.

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.

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.

Wavelet-based multifractal analysis of fMRI time series

Functional magnetic resonance imaging (fMRI) time series are investigated with a multifractal method based on the Wavelet Modulus Maxima (WTMM) method to extract local singularity ("fractal") exponents. The spectrum of singularity exponents of each fMRI time series is quantified by spectral characteristics including its maximum and the corresponding dimension. We found that the range of Hölder exponents in voxels with activation is close to 1, whereas exponents are close to 0.5 in white matter voxels without activation. The maximum dimension decreases going from white matter to gray matter, and is lower still for activated time series. The full-width-at-half-maximum of the spectra is higher in activated areas. The proposed method becomes particularly effective when combining these spectral characteristics into a single parameter. Using these multifractal parameters, it is possible to identify activated areas in the human brain in both hybrid and in vivo fMRI data sets without knowledge of the stimulation paradigm applied.

Traitement des images et radiothérapie

Medical images are of great importance in radiotherapy, which became a privileged application field for image processing techniques. Moreover, because of the progression of the computers' performances, these techniques are also in full expansion. Today, the recent developments of the radiotherapy (3DCR, IMRT) offer a huge place to them. Effectively, they can potentially answer to the precision requirements of the modern radiotherapy, and may then contribute to improve the delivered treatments. The purpose of this article is to present the different image processing techniques that are currently used in radiotherapy (including image matching and segmentation) as they are described in the literature.

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.

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.

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.

Whole brain segmentation: automated labeling of neuroanatomical structures in the human brain

We present a technique for automatically assigning a neuroanatomical label to each voxel in an MRI volume based on probabilistic information automatically estimated from a manually labeled training set. In contrast to existing segmentation procedures that only label a small number of tissue classes, the current method assigns one of 37 labels to each voxel, including left and right caudate, putamen, pallidum, thalamus, lateral ventricles, hippocampus, and amygdala. The classification technique employs a registration procedure that is robust to anatomical variability, including the ventricular enlargement typically associated with neurological diseases and aging. The technique is shown to be comparable in accuracy to manual labeling, and of sufficient sensitivity to robustly detect changes in the volume of noncortical structures that presage the onset of probable Alzheimer's disease.

Current awareness

In order to keep subscribers up-to-date with the latest developments in their field, John Wiley & Sons are providing a current awareness service in each issue of the journal. The bibliography contains newly published material in the field of NMR in biomedicine. Each bibliography is divided into 9 sections: 1 Books, Reviews ' Symposia; 2 General; 3 Technology; 4 Brain and Nerves; 5 Neuropathology; 6 Cancer; 7 Cardiac, Vascular and Respiratory Systems; 8 Liver, Kidney and Other Organs; 9 Muscle and Orthopaedic. Within each section, articles are listed in alphabetical order with respect to author. If, in the preceding period, no publications are located relevant to any one of these headings, that section will be omitted.