Improvements to the quality of MRI cluster analysis

Fast and accurate pseudo multispectral technique for whole-brain MRI tissue classification

Numerous strategies have been proposed to classify brain tissues into gray matter (GM), white matter (WM) and cerebrospinal fluid (CSF). However, many of them fail when classifying specific regions with low contrast between tissues. In this work, we propose an alternative pseudo multispectral classification (PMC) technique using CIE LAB spaces instead of gray scale T1-weighted MPRAGE images, combined with a new preprocessing technique for contrast enhancement and an optimized iterative K-means clustering. To improve the accuracy of the classification process, gray scale images were converted to multispectral CIE LAB data by applying several transformation matrices. Thus, the amount of information associated with each image voxel was increased. The image contrast was then enhanced by applying a real time function that separates brain tissue distributions and improve image contrast in certain brain regions. The data were then classified using an optimized iterative and convergent K-means classifier. The performance of the proposed approach was assessed using simulation and in vivo human studies through comparison with three common software packages used for brain MR image segmentation, namely FSL, SPM8 and K-means clustering. In the presence of high SNR, the results showed that the four algorithms achieve a good classification. Conversely, in the presence of low SNR, PMC was shown to outperform the other methods by accurately recovering all tissue volumes. The quantitative assessment of brain tissue classification for simulated studies showed that the PMC algorithm resulted in a mean Jaccard index (JI) of 0.74 compared to 0.75 for FSL, 0.7 for SPM and 0.8 for K-means. The in vivo human studies showed that the PMC algorithm resulted in a mean JI of 0.92, which reflects a good spatial overlap between segmented and actual volumes, compared to 0.84 for FSL, 0.78 for SPM and 0.66 for K-means. The proposed algorithm presents a high potential for improving the accuracy of automatic brain tissues classification and was found to be accurate even in the presence of high noise level.

Automated segmentation and classification of high throughput yeast assay spots

Several technologies for characterizing genes and proteins from humans and other organisms use yeast growth or color development as read outs. The yeast two-hybrid assay, for example, detects protein-protein interactions by measuring the growth of yeast on a specific solid medium, or the ability of the yeast to change color when grown on a medium containing a chromogenic substrate. Current systems for analyzing the results of these types of assays rely on subjective and inefficient scoring of growth or color by human experts. Here, an image analysis system is described for scoring yeast growth and color development in high throughput biological assays. The goal is to locate the spots and score them in color images of two types of plates named "X-Gal" and "growth assay" plates, with uniformly placed spots (cell areas) on each plate (both plates in one image). The scoring system relies on color for the X-Gal spots, and texture properties for the growth assay spots. A maximum likelihood projection-based segmentation is developed to automatically locate spots of yeast on each plate. Then color histogram and wavelet texture features are extracted for scoring using an optimal linear transformation. Finally, an artificial neural network is used to score the X-Gal and growth assay spots using the extracted features. The performance of the system is evaluated using spots of 60 images. After training the networks using training and validation sets, the system was assessed on the test set. The overall accuracies of 95.4% and 88.2% are achieved, respectively, for scoring the X-Gal and growth assay spots.

Magnetic resonance imaging with T1 dispersion contrast

Prepolarized MRI uses pulsed magnetic fields to produce MR images by polarizing the sample at one field strength (approximately 0.5 T) before imaging at a much lower field (approximately 50 mT). Contrast reflecting the T(1) of the sample at an intermediate field strength is achieved by polarizing the sample and then allowing the magnetization to decay at a chosen "evolution" field before imaging. For tissues whose T(1) varies with field strength (T(1) dispersion), the difference between two images collected with different evolution fields yields an image with contrast reflecting the slope of the T(1) dispersion curve between those fields. Tissues with high protein content, such as muscle, exhibit rapid changes in their T(1) dispersion curves at 49 and 65 mT due to cross-relaxation with nitrogen nuclei in protein backbones. Tissues without protein, such as fat, have fairly constant T(1) over this range; subtracting images with two different evolution fields eliminates signal from flat T(1) dispersion species. T(1) dispersion protein-content images of the human wrist and foot are presented, showing clear differentiation between muscle and fat. This technique may prove useful for delineating regions of muscle tissue in the extremities of patients with diseases affecting muscle viability, such as diabetic neuropathy, and for visualizing the protein content of tissues in vivo.

Detection of structural differences between the brains of schizophrenic patients and controls

This paper investigates the validity of the null hypothesis: there are no structural differences between the brains of schizophrenic and normal control subjects that manifest themselves in MRI-T(2) data and distinguish the two populations in a statistically significant way. The data used refer to 21 schizophrenic patients and 19 normal controls, matched for age, sex and social background. The methodology used is based on three-dimensional texture analysis, which is used to quantify anisotropy in the data at scales of the order of a few millimetres. These data reject the null hypothesis. In addition, this article attempts to identify the regions of the brain that are responsible for the morphological characteristics that distinguish the two populations. For this purpose, it utilises a second texture analysis method that, in spite of being a global method, allows one to trace back to the data the origin of the features that most distinctly distinguish the two populations. This method indicates that the features that distinguish the two populations with P values smaller than 10(-6) are located in the most inferior part of the brain and in particular in the tissue that makes up the sulci. It is stressed that in order to preserve the integrity of the data for texture calculations, no registration of anatomical structures is performed, and the most inferior part of the brain is identified as referring to those slices of the scans that visually correspond to slices 1-12 of the Talairach and Tournoux brain atlas.

Directional correlation characterization and classification of white matter tracts

To study the architectural characteristics of white matter (WM) tracts, the directional correlation (DC), defined as the inner product of the major eigenvector of adjacent pixels, was used as a quantitative index to investigate directional similarity in WM tracts. A region-growing algorithm was employed to propagate an area from a seed point as a function of the DC threshold (DCt) to critically evaluate the directional properties of WM tracts. As the DCt was increased, more pixels were excluded from the propagated region as their DC fell below the DCt, and neighboring WM tracts could be distinguished as the area decreased. Taking the DC into account, a systematic classification routine for WM tracts was devised and tested on a mouse brain in vivo. The results show that individual WM tracts possess a high degree of directional similarity, and, by careful choice of the DCt value, the proposed classification algorithm can recognize all possible WM tracts in a given data set.

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

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

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.

An algorithm for automatic segmentation and classification of magnetic resonance brain images

In this article, we describe the development and validation of an automatic algorithm to segment brain from extracranial tissues, and to classify intracranial tissues as cerebrospinal fluid (CSF), gray matter (GM), white matter (WM) or pathology. T1 weighted spin echo, dual echo fast spin echo (T2 weighted and proton density (PD) weighted images) and fast Fluid Attenuated Inversion Recovery (FLAIR) magnetic resonance (MR) images were acquired in 100 normal patients and 9 multiple sclerosis (MS) patients. One of the normal studies had synthesized MS-like lesions superimposed. This allowed precise measurement of the accuracy of the classification. The 9 MS patients were imaged twice in one week. The algorithm was applied to these data sets to measure reproducibility. The accuracy was measured based on the synthetic lesion images, where the true voxel class was known. Ninety-six percent of normal intradural tissue voxels (GM, WM, and CSF) were labeled correctly, and 94% of pathological tissues were labeled correctly. A low coefficient of variation (COV) was found (mean, 4.1%) for measurement of brain tissues and pathology when comparing MRI scans on the 9 patients. A totally automatic segmentation algorithm has been described which accurately and reproducibly segments and classifies intradural tissues based on both synthetic and actual images.

Reliability and validity of an algorithm for fuzzy tissue segmentation of MRI

PURPOSE

A new multistep, volumetric-based tissue segmentation algorithm that results in fuzzy (or probabilistic) voxel description is described. This algorithm is designed to accurately segment gray matter, white matter, and CSF and can be applied to both single channel high resolution and multispectral (multiecho) MR images.

METHOD

The reliability and validity of this method are evaluated by assessing (a) the stability of the algorithm across time, rater, and pulse sequence; (b) the accuracy of the method when applied to both real and synthetic image datasets; and (c) differences in specific tissue volumes between individuals with a specific genetic condition (fragile X syndrome) and normal control subjects.

RESULTS

The algorithm was found to have high reliability, accuracy, and validity. The finding of increased caudate gray matter volume associated with the fragile X syndrome is replicated in this sample.

CONCLUSION

Since this segmentation approach incorporates "fuzzy" or probabilistic methods, it has the potential to more accurately address partial volume effects, anatomical variation within "pure" tissue compartments, and more subtle changes in tissue volumes as a result of disease and treatment. The method is a component of software that is available in the public domain and has been implemented on an inexpensive personal computer thus offering an attractive and promising method for determining the status and progression of both normal development and pathology of the CNS.

Optimized homomorphic unsharp masking for MR grayscale inhomogeneity correction

Grayscale inhomogeneities in magnetic resonance (MR) images confound quantitative analysis of these images. Homomorphic unsharp masking and its variations have been commonly used as a post-processing method to remove inhomogeneities in MR images. However, little data is available in the literature assessing the relative effectiveness of these algorithms to remove inhomogeneities, or describing how these algorithms can affect image data. In this study, we address these questions quantitatively using simulated images with artificially constructed and empirically measured bias fields. Our results show that mean-based filtering is consistently more effective than median-based algorithms for removing inhomogeneities in MR images, and that artifacts are frequently introduced into images at the most commonly used window sizes. Our results demonstrate dramatic improvement in the effectiveness of the algorithms with significantly larger windows than are commonly used.

Post-acquisition correction of MR inhomogeneities

Signal inhomogeneities in volumetric head MR scans are a major obstacle to segmentation and neuromorphometry. The fuzzy c-means (FCM) statistical clustering algorithm was extended to estimate and retrospectively correct a multiplicative inhomogeneity field in T1-weighted head MR scans. The method was tested on a mathematically simulated object and on seven whole head 3D MR scans. Once initial parameters governing operation of the algorithm were chosen for this class of images, results were obtained without intervention for individual MR studies. Post-acquisition inhomogeneity correction by extended FCM clustering improved overall image uniformity and separability of gray and white matter intensities.

Simulation of MRI cluster plots and application to neurological segmentation

The advent of magnetic resonance imaging has provided new opportunities for volume measurement of tissues, with applications increasing dramatically in recent years. Cluster classification techniques have proved the most popular for volume measurement, yet little attention has been paid to how the choice of images for analysis affects the quality and ease of segmentation. To address this issue, we have developed a system to simulate MRI cluster plots using multicompartmental anthropomorphic software models of anatomy, and components for image contrast, signal-to-noise ratio, image nonuniformity, tissue heterogeneity, imager field strength, the partial volume effect, correlation between proton density, T1 and T2, and a variety of data preprocessing techniques. The effect of these components on tissue cluster size, shape, orientation, and separation is demonstrated. The simulation allows an informed choice of pulse sequence, acquisition parameters, and data preprocessing for cluster classification to be made as well as providing an aid to interpretation of acquired data cluster plots and a valuable educational tool. The system has been used to choose suitable images for neurological segmentation of grey matter, white matter, CSF, and multiple sclerosis lesions using spin-echo, inversion recovery, and gradient-echo pulse sequences. Constraints on image selection are discussed.