Segmentation of magnetic resonance brain images through discriminant analysis

Marmoset brain segmentation from deconvolved magnetic resonance images and estimated label maps

PURPOSE

The proposed method aims to create label maps that can be used for the segmentation of animal brain MR images without the need of a brain template. This is achieved by performing a joint deconvolution and segmentation of the brain MR images.

METHODS

It is based on modeling locally the image statistics using a generalized Gaussian distribution (GGD) and couples the deconvolved image and its corresponding labels map using the GGD-Potts model. Because of the complexity of the resulting Bayesian estimators of the unknown model parameters, a Gibbs sampler is used to generate samples following the desired posterior probability.

RESULTS

The performance of the proposed algorithm is assessed on simulated and real MR images by the segmentation of enhanced marmoset brain images into its main compartments using the corresponding label maps created. Quantitative assessment showed that this method presents results that are comparable to those obtained with the classical method-registering the volumes to a brain template.

CONCLUSION

The proposed method of using labels as prior information for brain segmentation provides a similar or a slightly better performance compared with the classical reference method based on a dedicated template.

Performance comparison of 10 different classification techniques in segmenting white matter hyperintensities in aging

INTRODUCTION

White matter hyperintensities (WMHs) are areas of abnormal signal on magnetic resonance images (MRIs) that characterize various types of histopathological lesions. The load and location of WMHs are important clinical measures that may indicate the presence of small vessel disease in aging and Alzheimer's disease (AD) patients. Manually segmenting WMHs is time consuming and prone to inter-rater and intra-rater variabilities. Automated tools that can accurately and robustly detect these lesions can be used to measure the vascular burden in individuals with AD or the elderly population in general. Many WMH segmentation techniques use a classifier in combination with a set of intensity and location features to segment WMHs, however, the optimal choice of classifier is unknown.

METHODS

We compare 10 different linear and nonlinear classification techniques to identify WMHs from MRI data. Each classifier is trained and optimized based on a set of features obtained from co-registered MR images containing spatial location and intensity information. We further assess the performance of the classifiers using different combinations of MRI contrast information. The performances of the different classifiers were compared on three heterogeneous multi-site datasets, including images acquired with different scanners and different scan-parameters. These included data from the ADC study from University of California Davis, the NACC database and the ADNI study. The classifiers (naïve Bayes, logistic regression, decision trees, random forests, support vector machines, k-nearest neighbors, bagging, and boosting) were evaluated using a variety of voxel-wise and volumetric similarity measures such as Dice Kappa similarity index (SI), Intra-Class Correlation (ICC), and sensitivity as well as computational burden and processing times. These investigations enable meaningful comparisons between the performances of different classifiers to determine the most suitable classifiers for segmentation of WMHs. In the spirit of open-source science, we also make available a fully automated tool for segmentation of WMHs with pre-trained classifiers for all these techniques.

RESULTS

Random Forests yielded the best performance among all classifiers with mean Dice Kappa (SI) of 0.66±0.17 and ICC=0.99 for the ADC dataset (using T1w, T2w, PD, and FLAIR scans), SI=0.72±0.10, ICC=0.93 for the NACC dataset (using T1w and FLAIR scans), SI=0.66±0.23, ICC=0.94 for ADNI1 dataset (using T1w, T2w, and PD scans) and SI=0.72±0.19, ICC=0.96 for ADNI2/GO dataset (using T1w and FLAIR scans). Not using the T2w/PD information did not change the performance of the Random Forest classifier (SI=0.66±0.17, ICC=0.99). However, not using FLAIR information in the ADC dataset significantly decreased the Dice Kappa, but the volumetric correlation did not drastically change (SI=0.47±0.21, ICC=0.95).

CONCLUSION

Our investigations showed that with appropriate features, most off-the-shelf classifiers are able to accurately detect WMHs in presence of FLAIR scan information, while Random Forests had the best performance across all datasets. However, we observed that the performances of most linear classifiers and some nonlinear classifiers drastically decline in absence of FLAIR information, with Random Forest still retaining the best performance.

Self-Trained Supervised Segmentation of Subcortical Brain Structures Using Multispectral Magnetic Resonance Images

The aim of this paper is investigate the feasibility of automatically training supervised methods, such as k-nearest neighbor (kNN) and principal component discriminant analysis (PCDA), and to segment the four subcortical brain structures: caudate, thalamus, pallidum, and putamen. The adoption of supervised classification methods so far has been limited by the need to define a representative training dataset, operation that usually requires the intervention of an operator. In this work the selection of the training data was performed on the subject to be segmented in a fully automated manner by registering probabilistic atlases. Evaluation of automatically trained kNN and PCDA classifiers that combine voxel intensities and spatial coordinates was performed on 20 real datasets selected from two publicly available sources of multispectral magnetic resonance studies. The results demonstrate that atlas-guided training is an effective way to automatically define a representative and reliable training dataset, thus giving supervised methods the chance to successfully segment magnetic resonance brain images without the need for user interaction.

SEGMENTATION OF BRAIN MRIs BY SUPPORT VECTOR MACHINE: DETECTION AND CHARACTERIZATION OF STROKES

The aim of our work is the segmentation of healthy and pathological brains to obtain brain structures and extract strokes. We used real magnetic resonance (MR) images weighted on diffusion. The brain was isolated, and the images were filtered by an anisotropic filter, and then segmented by support vector machines (SVMs). We first applied the method on synthetic images to test the performance of the algorithm and adjust the parameters. Then, we compared our results with those obtained by a cooperative approach proposed in a previous paper.

Multiscale segmentation of the skull in MR images for MRI-based attenuation correction of combined MR/PET

BACKGROUND AND OBJECTIVE

Combined magnetic resonance/positron emission tomography (MR/PET) is a relatively new, hybrid imaging modality. MR-based attenuation correction often requires segmentation of the bone on MR images. In this study, we present an automatic segmentation method for the skull on MR images for attenuation correction in brain MR/PET applications.

MATERIALS AND METHODS

Our method transforms T1-weighted MR images to the Radon domain and then detects the features of the skull image. In the Radon domain we use a bilateral filter to construct a multiscale image series. For the repeated convolution we increase the spatial smoothing in each scale and make the width of the spatial and range Gaussian function doubled in each scale. Two filters with different kernels along the vertical direction are applied along the scales from the coarse to fine levels. The results from a coarse scale give a mask for the next fine scale and supervise the segmentation in the next fine scale. The use of the multiscale bilateral filtering scheme is to improve the robustness of the method for noise MR images. After combining the two filtered sinograms, the reciprocal binary sinogram of the skull is obtained for the reconstruction of the skull image.

RESULTS

This method has been tested with brain phantom data, simulated brain data, and real MRI data. For real MRI data the Dice overlap ratios are 92.2%±1.9% between our segmentation and manual segmentation.

CONCLUSIONS

The multiscale segmentation method is robust and accurate and can be used for MRI-based attenuation correction in combined MR/PET.

A critical assessment of feature selection methods for biomarker discovery in clinical proteomics

In this paper, we compare the performance of six different feature selection methods for LC-MS-based proteomics and metabolomics biomarker discovery-t test, the Mann-Whitney-Wilcoxon test (mww test), nearest shrunken centroid (NSC), linear support vector machine-recursive features elimination (SVM-RFE), principal component discriminant analysis (PCDA), and partial least squares discriminant analysis (PLSDA)-using human urine and porcine cerebrospinal fluid samples that were spiked with a range of peptides at different concentration levels. The ideal feature selection method should select the complete list of discriminating features that are related to the spiked peptides without selecting unrelated features. Whereas many studies have to rely on classification error to judge the reliability of the selected biomarker candidates, we assessed the accuracy of selection directly from the list of spiked peptides. The feature selection methods were applied to data sets with different sample sizes and extents of sample class separation determined by the concentration level of spiked compounds. For each feature selection method and data set, the performance for selecting a set of features related to spiked compounds was assessed using the harmonic mean of the recall and the precision (f-score) and the geometric mean of the recall and the true negative rate (g-score). We conclude that the univariate t test and the mww test with multiple testing corrections are not applicable to data sets with small sample sizes (n = 6), but their performance improves markedly with increasing sample size up to a point (n > 12) at which they outperform the other methods. PCDA and PLSDA select small feature sets with high precision but miss many true positive features related to the spiked peptides. NSC strikes a reasonable compromise between recall and precision for all data sets independent of spiking level and number of samples. Linear SVM-RFE performs poorly for selecting features related to the spiked compounds, even though the classification error is relatively low.

A comprehensive testing protocol for MRI neuroanatomical segmentation techniques: Evaluation of a novel lateral ventricle segmentation method

Although a wide range of approaches have been developed to automatically assess the volume of brain regions from MRI, the reproducibility of these algorithms across different scanners and pulse sequences, their accuracy in different clinical populations and sensitivity to real changes in brain volume have not always been comprehensively examined. Firstly we present a comprehensive testing protocol which comprises 312 freely available MR images to assess the accuracy, reproducibility and sensitivity of automated brain segmentation techniques. Accuracy is assessed in infants, young adults and patients with Alzheimer's disease in comparison to gold standard measures by expert observers using a manual technique based on Cavalieri's principle. The protocol determines the reliability of segmentation between scanning sessions, different MRI pulse sequences and 1.5T and 3T field strengths and examines their sensitivity to small changes in volume using a large longitudinal dataset. Secondly we apply this testing protocol to a novel algorithm for segmenting the lateral ventricles and compare its performance to the widely used FSL FIRST and FreeSurfer methods. The testing protocol produced quantitative measures of accuracy, reliability and sensitivity of lateral ventricle volume estimates for each segmentation method. The novel algorithm showed high accuracy in all populations (intraclass correlation coefficient, ICC>0.95), good reproducibility between MRI pulse sequences (ICC>0.99) and was sensitive to age related changes in longitudinal data. FreeSurfer demonstrated high accuracy (ICC>0.95), good reproducibility (ICC>0.99) and sensitivity whilst FSL FIRST showed good accuracy in young adults and infants (ICC>0.90) and good reproducibility (ICC=0.98), but was unable to segment ventricular volume in patients with Alzheimer's disease or healthy subjects with large ventricles. Using the same computer system, the novel algorithm and FSL FIRST processed a single MRI image in less than 10min while FreeSurfer took approximately 7h. The testing protocol presented enables the accuracy, reproducibility and sensitivity of different algorithms to be compared. We also demonstrate that the novel segmentation algorithm and FreeSurfer are both effective in determining lateral ventricular volume and are well suited for multicentre and longitudinal MRI studies.

Brain MRI tissue classification based on local Markov random fields

A new method for tissue classification of brain magnetic resonance images (MRI) of the brain is proposed. The method is based on local image models where each models the image content in a subset of the image domain. With this local modeling approach, the assumption that tissue types have the same characteristics over the brain needs not to be evoked. This is important because tissue type characteristics, such as T1 and T2 relaxation times and proton density, vary across the individual brain and the proposed method offers improved protection against intensity non-uniformity artifacts that can hamper automatic tissue classification methods in brain MRI. A framework in which local models for tissue intensities and Markov Random Field (MRF) priors are combined into a global probabilistic image model is introduced. This global model will be an inhomogeneous MRF and it can be solved by standard algorithms such as iterative conditional modes. The division of the whole image domain into local brain regions possibly having different intensity statistics is realized via sub-volume probabilistic atlases. Finally, the parameters for the local intensity models are obtained without supervision by maximizing the weighted likelihood of a certain finite mixture model. For the maximization task, a novel genetic algorithm almost free of initialization dependency is applied. The algorithm is tested on both simulated and real brain MR images. The experiments confirm that the new method offers a useful improvement of the tissue classification accuracy when the basic tissue characteristics vary across the brain and the noise level of the images is reasonable. The method also offers better protection against intensity non-uniformity artifact than the corresponding method based on a global (whole image) modeling scheme.

A phantom study on component segregation for MR images using ICA

RATIONALE AND OBJECTIVES

A phantom set was devised to evaluate capability of independent component analysis (ICA) as an image filter for magnetic resonance (MR) images to segregate components.

MATERIALS AND METHODS

Four components (free water [FW], olive oil [OL], 2% and 4% agar gels [2A and 4A, respectively]) were arranged in a phantom set. Seven MR images were obtained with different echo time and repetition time. ICA was performed on 23 combinations of four components. A segregation rate higher than 70% was defined as effective.

RESULTS

Four-component segregation was obtained in 5 of 23 combinations. The best result showed a mean of 87% across the four components. For each component, there were 20 of 23 for FW, 22 for OL, 9 for 2A, and 16 for 4A.

CONCLUSIONS

The results demonstrated ICA works as an image filter and provides new contrast images that unambiguously segregate components in MR images. For practical application, the best performance should be obtained when T(1)W, T(2)W, and proton density images are included in the dataset for ICA.

Multispectral analysis of multimodal images

INTRODUCTION

An increasing number of multimodal images represent a valuable increase in available image information, but at the same time it complicates the extraction of diagnostic information across the images. Multispectral analysis (MSA) has the potential to simplify this problem substantially as unlimited number of images can be combined, and tissue properties across the images can be extracted automatically.

MATERIALS AND METHODS

We have developed a software solution for MSA containing two algorithms for unsupervised classification, an EM-algorithm finding multinormal class descriptions and the k-means clustering algorithm, and two for supervised classification, a Bayesian classifier using multinormal class descriptions and a kNN-algorithm. The software has an efficient user interface for the creation and manipulation of class descriptions, and it has proper tools for displaying the results.

RESULTS

The software has been tested on different sets of images. One application is to segment cross-sectional images of brain tissue (T1- and T2-weighted MR images) into its main normal tissues and brain tumors. Another interesting set of images are the perfusion maps and diffusion maps, derived images from raw MR images. The software returns segmentations that seem to be sensible.

DISCUSSION

The MSA software appears to be a valuable tool for image analysis with multimodal images at hand. It readily gives a segmentation of image volumes that visually seems to be sensible. However, to really learn how to use MSA, it will be necessary to gain more insight into what tissues the different segments contain, and the upcoming work will therefore be focused on examining the tissues through for example histological sections.

White matter lesion extension to automatic brain tissue segmentation on MRI

A fully automated brain tissue segmentation method is optimized and extended with white matter lesion segmentation. Cerebrospinal fluid (CSF), gray matter (GM) and white matter (WM) are segmented by an atlas-based k-nearest neighbor classifier on multi-modal magnetic resonance imaging data. This classifier is trained by registering brain atlases to the subject. The resulting GM segmentation is used to automatically find a white matter lesion (WML) threshold in a fluid-attenuated inversion recovery scan. False positive lesions are removed by ensuring that the lesions are within the white matter. The method was visually validated on a set of 209 subjects. No segmentation errors were found in 98% of the brain tissue segmentations and 97% of the WML segmentations. A quantitative evaluation using manual segmentations was performed on a subset of 6 subjects for CSF, GM and WM segmentation and an additional 14 for the WML segmentations. The results indicated that the automatic segmentation accuracy is close to the interobserver variability of manual segmentations.

Evaluation of automated brain MR image segmentation and volumetry methods

We compare three widely used brain volumetry methods available in the software packages FSL, SPM5, and FreeSurfer and evaluate their performance using simulated and real MR brain data sets. We analyze the accuracy of gray and white matter volume measurements and their robustness against changes of image quality using the BrainWeb MRI database. These images are based on "gold-standard" reference brain templates. This allows us to assess between- (same data set, different method) and also within-segmenter (same method, variation of image quality) comparability, for both of which we find pronounced variations in segmentation results for gray and white matter volumes. The calculated volumes deviate up to >10% from the reference values for gray and white matter depending on method and image quality. Sensitivity is best for SPM5, volumetric accuracy for gray and white matter was similar in SPM5 and FSL and better than in FreeSurfer. FSL showed the highest stability for white (<5%), FreeSurfer (6.2%) for gray matter for constant image quality BrainWeb data. Between-segmenter comparisons show discrepancies of up to >20% for the simulated data and 24% on average for the real data sets, whereas within-method performance analysis uncovered volume differences of up to >15%. Since the discrepancies between results reach the same order of magnitude as volume changes observed in disease, these effects limit the usability of the segmentation methods for following volume changes in individual patients over time and should be taken into account during the planning and analysis of brain volume studies.

MR image segmentation using a power transformation approach

This study proposes a segmentation method for brain MR images using a distribution transformation approach. The method extends traditional Gaussian mixtures expectation-maximization segmentation to a power transformed version of mixed intensity distributions, which includes Gaussian mixtures as a special case. As MR intensities tend to exhibit non-Gaussianity due to partial volume effects, the proposed method is designed to fit non-Gaussian tissue intensity distributions. One advantage of the method is that it is intuitively appealing and computationally simple. To avoid performance degradation caused by intensity inhomogeneity, different methods for correcting bias fields were applied prior to image segmentation, and their correction effects on the segmentation results were examined in the empirical study. The partitions of brain tissues (i.e., gray and white matter) resulting from the method were validated and evaluated against manual segmentation results based on 38 real T1-weighted image volumes from the internet brain segmentation repository, and 18 simulated image volumes from BrainWeb. The Jaccard and Dice similarity indexes were computed to evaluate the performance of the proposed approach relative to the expert segmentations. Empirical results suggested that the proposed segmentation method yielded higher similarity measures for both gray matter and white matter as compared with those based on the traditional segmentation using the Gaussian mixtures approach.

Automated segmentation of mouse brain images using extended MRF

We introduce an automated segmentation method, extended Markov random field (eMRF), to classify 21 neuroanatomical structures of mouse brain based on three dimensional (3D) magnetic resonance images (MRI). The image data are multispectral: T2-weighted, proton density-weighted, diffusion x, y and z weighted. Earlier research (Ali, A.A., Dale, A.M., Badea, A., Johnson, G.A., 2005. Automated segmentation of neuroanatomical structures in multispectral MR microscopy of the mouse brain. NeuroImage 27 (2), 425-435) successfully explored the use of MRF for mouse brain segmentation. In this research, we study the use of information generated from support vector machine (SVM) to represent the probabilistic information. Since SVM in general has a stronger discriminative power than the Gaussian likelihood method and is able to handle nonlinear classification problems, integrating SVM into MRF improved the classification accuracy. The eMRF employs the posterior probability distribution obtained from SVM to generate a classification based on the MR intensity. Secondly, the eMRF introduces a new potential function based on location information. Third, to maximize the classification performance, the eMRF uses the contribution weights optimally determined for each of the three potential functions: observation, location and contextual functions, which are traditionally equally weighted. We use the voxel overlap percentage and volume difference percentage to evaluate the accuracy of eMRF segmentation and compare the algorithm with three other segmentation methods--mixed ratio sampling SVM (MRS-SVM), atlas-based segmentation and MRF. Validation using classification accuracy indices between automatically segmented and manually traced data shows that eMRF outperforms other methods.

Automatic segmentation of magnetic resonance images using a decision tree with spatial information

Here we proposed an automatic segmentation method based on a decision tree to classify the brain tissues in magnetic resonance (MR) images. Two types of data - phantom MR images obtained from IBSR (http://www.cma.mgh.harvard.edu/ibsr) and simulated brain MR images obtained from BrainWeb (http://www.bic.mni.mcgill.ca/brainweb) - were segmented using an automatic decision tree algorithm to obtain images with improved visual rendition. Spatial information on the general gray level (G), spatial gray level (S), and two-dimensional wavelet transform (W) was combined in-plane in two coordinate systems (Euclidean coordinates (x, y) or polar coordinates (r, theta)). The decision tree was constructed based on a binary tree with nodes created by splitting the distribution of input features of the tree. The spatial information obtained from MR images with different noise levels and inhomogeneities were segmented to compare whether the use of a decision tree improved the identification of human anatomical structures in a neuroimage. The average accuracy rates of segmentation for phantom images with a noise variation of 15 gray levels were 0.9999 and 0.9973 with spatial information (G, x, y, r, theta) and (S, x, y, r, theta), respectively, and 0.9999 and 0.9819 with spatial information (G, x, y, S, r, theta) and (W, x, y, G, r, theta). The average accuracy rates of segmentation for simulated MR images with a noise level of 5% were 0.9532 and 0.9439 with spatial information (G, x, y, r, theta) and (S, x, y, r, theta), respectively, and 0.9446 and 0.9287 with spatial information (G, x, y, S, r, theta) and (W, x, y, G, r, theta). The accuracy rates of segmentation were highest for both simulated phantom and brain MR images, having the lowest noise levels, from a reduction of overlapping gray levels in the images. The accuracies of segmentation were higher when the spatial information included the general gray level than when it included the spatial gray level, which in turn were higher than when it included the wavelet transform. Furthermore, the performance of segmentation was also evaluated with a boundary detection methodology that is based on the Hausdorff distance to compare with the mean computer to observer difference (COD) and mean interobserver difference (IOD) for gray matter (GM), white matter (WM), and all areas (ALL) from images segmented using the decision tree. The values of mean COD are similar and around 12mm for GM segmented using the decision tree. Our segmentation method based on a decision tree algorithm presented an easy way to perform automatic segmentation for both phantom and tissue regions in brain MR images.

Segmentation of brain magnetic resonance images for measurement of gray matter atrophy in multiple sclerosis patients

Multiple sclerosis (MS) affects both white matter and gray matter (GM). Measurement of GM volumes is a particularly useful method to estimate the total extent of GM tissue damage because it can be done with conventional magnetic resonance images (MRI). Many algorithms exist for segmentation of GM, but none were specifically designed to handle issues associated with MS, such as atrophy and the effects that MS lesions may have on the classification of GM. A new GM segmentation algorithm has been developed specifically for calculation of GM volumes in MS patients. The new algorithm uses a combination of intensity, anatomical, and morphological probability maps. Several validation tests were performed to evaluate the algorithm in terms of accuracy, reproducibility, and sensitivity to MS lesions. The accuracy tests resulted in error rates of 1.2% and 3.1% for comparisons to BrainWeb and manual tracings, respectively. Similarity indices indicated excellent agreement with the BrainWeb segmentation (0.858-0.975, for various levels of noise and rf inhomogeneity). The scan-rescan reproducibility test resulted in a mean coefficient of variation of 1.1% for GM fraction. Tests of the effects of varying the size of MS lesions revealed a moderate and consistent dependence of GM volumes on T2 lesion volume, which suggests that GM volumes should be corrected for T2 lesion volumes using a simple scale factor in order to eliminate this technical artifact. The new segmentation algorithm can be used for improved measurement of GM volumes in MS patients, and is particularly applicable to retrospective datasets.

Misclassified Tissue Volumes in Alzheimer Disease Patients With White Matter Hyperintensities

Background and Purpose— MRI-based quantification of gray and white matter volume is common in studies involving elderly patient populations. The aim of the present study was to describe the effects of not accounting for subcortical white matter hyperintensities (WMH) on tissue volumes in Alzheimer Disease patients with varying degrees of WMH (mild: n=19, moderate: n=22, severe: n=18).

Methods— An automated tissue segmentation protocol that was optimized for an elderly population, a brain regional parcellation procedure, and a lesion segmentation protocol were applied to measure tissue volumes (whole brain and regional lobar volumes) with and without lesion segmentation to quantify the volume of misclassified tissue.

Results— After application of the tissue segmentation protocol and lesion analysis, mean total percentage misclassified volume across all subjects was 2% (17.9 cm 3 ) of whole brain volume (corrected for total intracranial capacity). Mean percentage of misclassified tissue volumes for the severe group was 4.8% of whole brain, which translates to a mean volume 42.2 cm 3 . Gray matter volume was most overestimated in the severe group, where 6.4% of the total gray matter volume was derived from misclassified WMH. The regional analysis showed that frontal (41%, 7.4 cm 3 ) and inferior parietal (18%, 3.25 cm 3 ) lobes were most affected by tissue misclassification.

Conclusion— MRI-based volumetric studies of Alzheimer Disease that do not account for WMH can expect an erroneous inflation of gray or white matter volumes, especially in the frontal and inferior parietal regions. To avoid this source of error, MRI-based volumetric studies in patient populations susceptible to hyperintensities should include a WMH segmentation protocol.

Probabilistic brain tissue segmentation in neonatal magnetic resonance imaging

A fully automated method has been developed for segmentation of four different structures in the neonatal brain: white matter (WM), central gray matter (CEGM), cortical gray matter (COGM), and cerebrospinal fluid (CSF). The segmentation algorithm is based on information from T2-weighted (T2-w) and inversion recovery (IR) scans. The method uses a K nearest neighbor (KNN) classification technique with features derived from spatial information and voxel intensities. Probabilistic segmentations of each tissue type were generated. By applying thresholds on these probability maps, binary segmentations were obtained. These final segmentations were evaluated by comparison with a gold standard. The sensitivity, specificity, and Dice similarity index (SI) were calculated for quantitative validation of the results. High sensitivity and specificity with respect to the gold standard were reached: sensitivity >0.82 and specificity >0.9 for all tissue types. Tissue volumes were calculated from the binary and probabilistic segmentations. The probabilistic segmentation volumes of all tissue types accurately estimated the gold standard volumes. The KNN approach offers valuable ways for neonatal brain segmentation. The probabilistic outcomes provide a useful tool for accurate volume measurements. The described method is based on routine diagnostic magnetic resonance imaging (MRI) and is suitable for large population studies.

Synthetic T1-weighted brain image generation with incorporated coil intensity correction using DESPOT1

The increased use of phased-array and surface coils in magnetic resonance imaging, the push toward increased field strength and the need for standardized imaging across multiple sites during clinical trials have resulted in the need for methods that can ensure consistency of intensity both within the image and across multiple subjects/sites. Here, we describe a means of addressing these concerns through an extension of the rapid T(1) mapping technique - driven equilibrium single-pulse observation of T(1). The effectiveness of the proposed approach was evaluated using human brain T(1) maps acquired at 1.5 T with a multichannel phased-array coil. Corrected "synthetic" T(1)-weighted images were reconstructed by substituting the T(1) values back into the governing signal intensity equation while assuming a constant value for the equilibrium magnetization. To demonstrate signal normalization across a longitudinal study, we calculated synthetic T(1)-weighted images from data acquired from the same healthy subject at four different time points. Signal intensity profiles between the acquired and synthetic images were compared to determine the improvements with our proposed approach. Following correction, the images demonstrate obvious qualitative improvement with increased signal uniformity across the image. Near-perfect signal normalization was also observed across the longitudinal study, allowing direct comparison between the images. In addition, we observe an increase in contrast-to-noise ratio (compared with regular T(1)-weighted images) for synthetic images created, assuming uniform proton density throughout the volume. The proposed approach permits rapid correction for signal intensity inhomogeneity without significantly lengthening exam time or reducing image signal-to-noise ratio. This technique also provides a robust method for signal normalization, which is useful in multicenter longitudinal MR studies of disease progression, and allows the user to reconstruct T(1)-weighted images with arbitrary T(1) weighting.

Intensity inhomogeneity correction of multispectral MR images

Intensity inhomogeneity in MR images is an undesired phenomenon, which often hampers different steps of quantitative image analysis such as segmentation or registration. In this paper, we propose a novel fully automated method for retrospective correction of intensity inhomogeneity. The basic assumption is that inhomogeneity correction could be improved by integrating spatial and intensity information from multiple MR channels, i.e., T1, T2, and PD weighted images. Intensity inhomogeneities of such multispectral images are removed simultaneously in a four-step iterative procedure. First, the probability distribution of image intensities and corresponding spatial features is calculated. In the second step, intensity correction forces that tend to minimize joint entropy of multispectral image are estimated for all image voxels. Third, independent inhomogeneity correction fields are obtained for each channel by regularization and normalization of voxel forces, and last, corresponding partial inhomogeneity corrections are performed separately for each channel. The method was quantitatively evaluated on simulated and real MR brain images and compared to three other methods.

Implementation of high-dimensional feature map for segmentation of MR images

A method that considerably reduces the computational and memory complexities associated with the generation of high-dimensional (> or =3) feature maps for image segmentation is described. The method is based on the K-nearest neighbor (KNN) classification and consists of two parts: preprocessing of feature space and fast KNN. This technique is implemented on a PC and applied for generating 3D and 4D feature maps for segmenting MR brain images of multiple sclerosis patients.

Probabilistic segmentation of brain tissue in MR imaging

A new method has been developed for probabilistic segmentation of five different types of brain structures: white matter, gray matter, cerebro-spinal fluid without ventricles, ventricles and white matter lesion in cranial MR imaging. The algorithm is based on information from T1-weighted (T1-w), inversion recovery (IR), proton density-weighted (PD), T2-weighted (T2-w) and fluid attenuation inversion recovery (FLAIR) scans. It uses the K-Nearest Neighbor classification technique that builds a feature space from spatial information and voxel intensities. The technique generates for each tissue type an image representing the probability per voxel being part of it. By application of thresholds on these probability maps, binary segmentations can be obtained. A similarity index (SI) and a probabilistic SI (PSI) were calculated for quantitative evaluation of the results. The influence of each image type on the performance was investigated by alternately leaving out one of the five scan types. This procedure showed that the incorporation of the T1-w, PD or T2-w did not significantly improve the segmentation results. Further investigation indicated that the combination of IR and FLAIR was optimal for segmentation of the five brain tissue types. Evaluation with respect to the gold standard showed that the SI-values for all tissues exceeded 0.8 and all PSI-values exceeded 0.7, implying an excellent agreement.

Automated segmentation of neuroanatomical structures in multispectral MR microscopy of the mouse brain

We present the automated segmentation of magnetic resonance microscopy (MRM) images of the C57BL/6J mouse brain into 21 neuroanatomical structures, including the ventricular system, corpus callosum, hippocampus, caudate putamen, inferior colliculus, internal capsule, globus pallidus, and substantia nigra. The segmentation algorithm operates on multispectral, three-dimensional (3D) MR data acquired at 90-microm isotropic resolution. Probabilistic information used in the segmentation is extracted from training datasets of T2-weighted, proton density-weighted, and diffusion-weighted acquisitions. Spatial information is employed in the form of prior probabilities of occurrence of a structure at a location (location priors) and the pairwise probabilities between structures (contextual priors). Validation using standard morphometry indices shows good consistency between automatically segmented and manually traced data. Results achieved in the mouse brain are comparable with those achieved in human brain studies using similar techniques. The segmentation algorithm shows excellent potential for routine morphological phenotyping of mouse models.