Markov random field segmentation of brain MR images

Robust volume assessment of brain tissues for 3-dimensional fourier transformation MRI via a novel multispectral technique

A new TRIO algorithm method integrating three different algorithms is proposed to perform brain MRI segmentation in the native coordinate space, with no need of transformation to a standard coordinate space or the probability maps for segmentation. The method is a simple voxel-based algorithm, derived from multispectral remote sensing techniques, and only requires minimal operator input to depict GM, WM, and CSF tissue clusters to complete classification of a 3D high-resolution multislice-multispectral MRI data. Results showed very high accuracy and reproducibility in classification of GM, WM, and CSF in multislice-multispectral synthetic MRI data. The similarity indexes, expressing overlap between classification results and the ground truth, were 0.951, 0.962, and 0.956 for GM, WM, and CSF classifications in the image data with 3% noise level and 0% non-uniformity intensity. The method particularly allows for classification of CSF with 0.994, 0.961 and 0.996 of accuracy, sensitivity and specificity in images data with 3% noise level and 0% non-uniformity intensity, which had seldom performed well in previous studies. As for clinical MRI data, the quantitative data of brain tissue volumes aligned closely with the brain morphometrics in three different study groups of young adults, elderly volunteers, and dementia patients. The results also showed very low rates of the intra- and extra-operator variability in measurements of the absolute volumes and volume fractions of cerebral GM, WM, and CSF in three different study groups. The mean coefficients of variation of GM, WM, and CSF volume measurements were in the range of 0.03% to 0.30% of intra-operator measurements and 0.06% to 0.45% of inter-operator measurements. In conclusion, the TRIO algorithm exhibits a remarkable ability in robust classification of multislice-multispectral brain MR images, which would be potentially applicable for clinical brain volumetric analysis and explicitly promising in cross-sectional and longitudinal studies of different subject groups.

An extension Gaussian mixture model for brain MRI segmentation

The segmentation of brain magnetic resonance (MR) images into gray matter (GM), white matter (WM) and cerebrospinal fluid (CSF) has been an intensive studied area in the medical image analysis community. The Gaussian mixture model (GMM) is one of the most commonly used model to represent the intensity of different tissue types. However, as a histogram-based model, the spatial relationship between pixels is discarded in the GMM, making it sensitive to noise. Herein we present a new framework which aims to incorporate spatial information into the standard GMM, where each pixel is assigned its individual prior by leveraging its neighborhood information. Expectation maximization (EM) is modified to estimate the parameters of the proposed method. The method is validated on both synthetic and real brain MR images, showing its effectiveness in the segmentation task.

A modified method for MRF segmentation and bias correction of MR image with intensity inhomogeneity

Markov random field (MRF) model is an effective method for brain tissue classification, which has been applied in MR image segmentation for decades. However, it falls short of the expected classification in MR images with intensity inhomogeneity for the bias field is not considered in the formulation. In this paper, we propose an interleaved method joining a modified MRF classification and bias field estimation in an energy minimization framework, whose initial estimation is based on k-means algorithm in view of prior information on MRI. The proposed method has a salient advantage of overcoming the misclassifications from the non-interleaved MRF classification for the MR image with intensity inhomogeneity. In contrast to other baseline methods, experimental results also have demonstrated the effectiveness and advantages of our algorithm via its applications in the real and the synthetic MR images.

Identifying cell types from spatially referenced single-cell expression datasets

Complex tissues, such as the brain, are composed of multiple different cell types, each of which have distinct and important roles, for example in neural function. Moreover, it has recently been appreciated that the cells that make up these sub-cell types themselves harbour significant cell-to-cell heterogeneity, in particular at the level of gene expression. The ability to study this heterogeneity has been revolutionised by advances in experimental technology, such as Wholemount in Situ Hybridizations (WiSH) and single-cell RNA-sequencing. Consequently, it is now possible to study gene expression levels in thousands of cells from the same tissue type. After generating such data one of the key goals is to cluster the cells into groups that correspond to both known and putatively novel cell types. Whilst many clustering algorithms exist, they are typically unable to incorporate information about the spatial dependence between cells within the tissue under study. When such information exists it provides important insights that should be directly included in the clustering scheme. To this end we have developed a clustering method that uses a Hidden Markov Random Field (HMRF) model to exploit both quantitative measures of expression and spatial information. To accurately reflect the underlying biology, we extend current HMRF approaches by allowing the degree of spatial coherency to differ between clusters. We demonstrate the utility of our method using simulated data before applying it to cluster single cell gene expression data generated by applying WiSH to study expression patterns in the brain of the marine annelid Platynereis dumereilii. Our approach allows known cell types to be identified as well as revealing new, previously unexplored cell types within the brain of this important model system.

Skull-stripping with machine learning deformable organisms

BACKGROUND

Segmentation methods for medical images may not generalize well to new data sets or new tasks, hampering their utility. We attempt to remedy these issues using deformable organisms to create an easily customizable segmentation plan. We validate our framework by creating a plan to locate the brain in 3D magnetic resonance images of the head (skull-stripping).

NEW METHOD

Our method borrows ideas from artificial life to govern a set of deformable models. We use control processes such as sensing, proactive planning, reactive behavior, and knowledge representation to segment an image. The image may have landmarks and features specific to that dataset; these may be easily incorporated into the plan. In addition, we use a machine learning method to make our segmentation more accurate.

RESULTS

Our method had the least Hausdorff distance error, but included slightly less brain voxels (false negatives). It also had the lowest false positive error and performed on par to skull-stripping specific method on other metrics.

COMPARISON WITH EXISTING METHOD(S)

We tested our method on 838 T1-weighted images, evaluating results using distance and overlap error metrics based on expert gold standard segmentations. We evaluated the results before and after the learning step to quantify its benefit; we also compare our results to three other widely used methods: BSE, BET, and the Hybrid Watershed algorithm.

CONCLUSIONS

Our framework captures diverse categories of information needed for brain segmentation and will provide a foundation for tackling a wealth of segmentation problems.

Learning from M/EEG data with variable brain activation delays

Magneto- and electroencephalography (M/EEG) measure the electromagnetic signals produced by brain activity. In order to address the issue of limited signal-to-noise ratio (SNR) with raw data, acquisitions consist of multiple repetitions of the same experiment. An important challenge arising from such data is the variability of brain activations over the repetitions. It hinders statistical analysis such as prediction performance in a supervised learning setup. One such confounding variability is the time offset of the peak of the activation, which varies across repetitions. We propose to address this misalignment issue by explicitly modeling time shifts of different brain responses in a classification setup. To this end, we use the latent support vector machine (LSVM) formulation, where the latent shifts are inferred while learning the classifier parameters. The inferred shifts are further used to improve the SNR of the M/EEG data, and to infer the chronometry and the sequence of activations across the brain regions that are involved in the experimental task. Results are validated on a long-term memory retrieval task, showing significant improvement using the proposed latent discriminative method.

Multi-contrast multi-atlas parcellation of diffusion tensor imaging of the human brain

In this paper, we propose a novel method for parcellating the human brain into 193 anatomical structures based on diffusion tensor images (DTIs). This was accomplished in the setting of multi-contrast diffeomorphic likelihood fusion using multiple DTI atlases. DTI images are modeled as high dimensional fields, with each voxel exhibiting a vector valued feature comprising of mean diffusivity (MD), fractional anisotropy (FA), and fiber angle. For each structure, the probability distribution of each element in the feature vector is modeled as a mixture of Gaussians, the parameters of which are estimated from the labeled atlases. The structure-specific feature vector is then used to parcellate the test image. For each atlas, a likelihood is iteratively computed based on the structure-specific vector feature. The likelihoods from multiple atlases are then fused. The updating and fusing of the likelihoods is achieved based on the expectation-maximization (EM) algorithm for maximum a posteriori (MAP) estimation problems. We first demonstrate the performance of the algorithm by examining the parcellation accuracy of 18 structures from 25 subjects with a varying degree of structural abnormality. Dice values ranging 0.8-0.9 were obtained. In addition, strong correlation was found between the volume size of the automated and the manual parcellation. Then, we present scan-rescan reproducibility based on another dataset of 16 DTI images - an average of 3.73%, 1.91%, and 1.79% for volume, mean FA, and mean MD respectively. Finally, the range of anatomical variability in the normal population was quantified for each structure.

Level set method with automatic selective local statistics for brain tumor segmentation in MR images

The level set approach is a powerful tool for segmenting images. This paper proposes a method for segmenting brain tumor images from MR images. A new signed pressure function (SPF) that can efficiently stop the contours at weak or blurred edges is introduced. The local statistics of the different objects present in the MR images were calculated. Using local statistics, the tumor objects were identified among different objects. In this level set method, the calculation of the parameters is a challenging task. The calculations of different parameters for different types of images were automatic. The basic thresholding value was updated and adjusted automatically for different MR images. This thresholding value was used to calculate the different parameters in the proposed algorithm. The proposed algorithm was tested on the magnetic resonance images of the brain for tumor segmentation and its performance was evaluated visually and quantitatively. Numerical experiments on some brain tumor images highlighted the efficiency and robustness of this method.

Robust separation of visceral and subcutaneous adipose tissues in micro-CT of mice

One of the common practices in obesity and diabetes studies is to measure the volumes and weights of various adipose tissues, among which, visceral adipose tissue (VAT) and subcutaneous adipose tissue (SAT) play critical yet different physiological roles in mouse aging. In this paper, a robust two-stage VAT/SAT separation framework for micro-CT mouse data is proposed. The first stage is to distinguish adipose from other tissue types, including background, soft tissue and bone, through a robust mixture of Gaussian model. Spatial recognition relevant to anatomical locations is carried out in the second step to determine whether the adipose is visceral or subcutaneous. We tackle this problem through a novel approach that relies on evolving the abdominal muscular wall to keep VAT/SAT separated. The VAT region of interest (ROI) is also automatically set up through an atlas based skeleton matching procedure. The results of our method are compared with VAT/SAT delineations by human experts, and a high classification accuracy is demonstrated on eight micro-CT mouse volume sets.

Improved inference in Bayesian segmentation using Monte Carlo sampling: application to hippocampal subfield volumetry

Many segmentation algorithms in medical image analysis use Bayesian modeling to augment local image appearance with prior anatomical knowledge. Such methods often contain a large number of free parameters that are first estimated and then kept fixed during the actual segmentation process. However, a faithful Bayesian analysis would marginalize over such parameters, accounting for their uncertainty by considering all possible values they may take. Here we propose to incorporate this uncertainty into Bayesian segmentation methods in order to improve the inference process. In particular, we approximate the required marginalization over model parameters using computationally efficient Markov chain Monte Carlo techniques. We illustrate the proposed approach using a recently developed Bayesian method for the segmentation of hippocampal subfields in brain MRI scans, showing a significant improvement in an Alzheimer's disease classification task. As an additional benefit, the technique also allows one to compute informative "error bars" on the volume estimates of individual structures.

Bayesian Parameter Estimation and Segmentation in the Multi-Atlas Random Orbit Model

This paper examines the multiple atlas random diffeomorphic orbit model in Computational Anatomy (CA) for parameter estimation and segmentation of subcortical and ventricular neuroanatomy in magnetic resonance imagery. We assume that there exist multiple magnetic resonance image (MRI) atlases, each atlas containing a collection of locally-defined charts in the brain generated via manual delineation of the structures of interest. We focus on maximum a posteriori estimation of high dimensional segmentations of MR within the class of generative models representing the observed MRI as a conditionally Gaussian random field, conditioned on the atlas charts and the diffeomorphic change of coordinates of each chart that generates it. The charts and their diffeomorphic correspondences are unknown and viewed as latent or hidden variables. We demonstrate that the expectation-maximization (EM) algorithm arises naturally, yielding the likelihood-fusion equation which the a posteriori estimator of the segmentation labels maximizes. The likelihoods being fused are modeled as conditionally Gaussian random fields with mean fields a function of each atlas chart under its diffeomorphic change of coordinates onto the target. The conditional-mean in the EM algorithm specifies the convex weights with which the chart-specific likelihoods are fused. The multiple atlases with the associated convex weights imply that the posterior distribution is a multi-modal representation of the measured MRI. Segmentation results for subcortical and ventricular structures of subjects, within populations of demented subjects, are demonstrated, including the use of multiple atlases across multiple diseased groups.

Atlas-based neuroinformatics via MRI: harnessing information from past clinical cases and quantitative image analysis for patient care

With the ever-increasing amount of anatomical information radiologists have to evaluate for routine diagnoses, computational support that facilitates more efficient education and clinical decision making is highly desired. Despite the rapid progress of image analysis technologies for magnetic resonance imaging of the human brain, these methods have not been widely adopted for clinical diagnoses. To bring computational support into the clinical arena, we need to understand the decision-making process employed by well-trained clinicians and develop tools to simulate that process. In this review, we discuss the potential of atlas-based clinical neuroinformatics, which consists of annotated databases of anatomical measurements grouped according to their morphometric phenotypes and coupled with the clinical informatics upon which their diagnostic groupings are based. As these are indexed via parametric representations, we can use image retrieval tools to search for phenotypes along with their clinical metadata. The review covers the current technology, preliminary data, and future directions of this field.

Parameterization of the distribution of white and grey matter in MRI using the α-stable distribution

This work presents a study of the distribution of the grey matter (GM) and white matter (WM) in brain magnetic resonance imaging (MRI). The distribution of GM and WM is characterized using a mixture of α-stable distributions. A Bayesian α-stable mixture model for histogram data is presented and unknown parameters are sampled using the Metropolis-Hastings algorithm. The proposed methodology is tested in 18 real images from the MRI brain segmentation repository. The GM and WM distributions are accurately estimated. The α-stable distribution mixture model presented in this paper can be used as previous step in more complex MRI segmentation procedures using spatial information. Furthermore, due to the fact that the α-stable distribution is a generalization of the Gaussian distribution, the proposed methodology can be applied instead of the Gaussian mixture model, which is widely used in segmentation of brain MRI in the literature.

Adaptive Markov random fields for joint unmixing and segmentation of hyperspectral images

Linear spectral unmixing is a challenging problem in hyperspectral imaging that consists of decomposing an observed pixel into a linear combination of pure spectra (or endmembers) with their corresponding proportions (or abundances). Endmember extraction algorithms can be employed for recovering the spectral signatures while abundances are estimated using an inversion step. Recent works have shown that exploiting spatial dependencies between image pixels can improve spectral unmixing. Markov random fields (MRF) are classically used to model these spatial correlations and partition the image into multiple classes with homogeneous abundances. This paper proposes to define the MRF sites using similarity regions. These regions are built using a self-complementary area filter that stems from the morphological theory. This kind of filter divides the original image into flat zones where the underlying pixels have the same spectral values. Once the MRF has been clearly established, a hierarchical Bayesian algorithm is proposed to estimate the abundances, the class labels, the noise variance, and the corresponding hyperparameters. A hybrid Gibbs sampler is constructed to generate samples according to the corresponding posterior distribution of the unknown parameters and hyperparameters. Simulations conducted on synthetic and real AVIRIS data demonstrate the good performance of the algorithm.

Joint probabilistic model of shape and intensity for multiple abdominal organ segmentation from volumetric CT images

We propose a novel joint probabilistic model that correlates a new probabilistic shape model with the corresponding global intensity distribution to segment multiple abdominal organs simultaneously. Our probabilistic shape model estimates the probability of an individual voxel belonging to the estimated shape of the object. The probability density of the estimated shape is derived from a combination of the shape variations of target class and the observed shape information. To better capture the shape variations, we used probabilistic principle component analysis optimized by expectation maximization to capture the shape variations and reduce computational complexity. The maximum a posteriori estimation was optimized by the iterated conditional mode-expectation maximization. We used 72 training datasets including low- and high-contrast CT images to construct the shape models for the liver, spleen and both kidneys. We evaluated our algorithm on 40 test datasets that were grouped into normal (34 normal cases) and pathologic (6 datasets) classes. The testing datasets were from different databases and manual segmentation was performed by different clinicians. We measured the volumetric overlap percentage error, relative volume difference, average square symmetric surface distance, false positive rate and false negative rate and our method achieved accurate and robust segmentation for multiple abdominal organs simultaneously.

Automatic segmentation of ground-glass opacities in lung CT images by using Markov random field-based algorithms

Chest radiologists rely on the segmentation and quantificational analysis of ground-glass opacities (GGO) to perform imaging diagnoses that evaluate the disease severity or recovery stages of diffuse parenchymal lung diseases. However, it is computationally difficult to segment and analyze patterns of GGO while compared with other lung diseases, since GGO usually do not have clear boundaries. In this paper, we present a new approach which automatically segments GGO in lung computed tomography (CT) images using algorithms derived from Markov random field theory. Further, we systematically evaluate the performance of the algorithms in segmenting GGO in lung CT images under different situations. CT image studies from 41 patients with diffuse lung diseases were enrolled in this research. The local distributions were modeled with both simple and adaptive (AMAP) models of maximum a posteriori (MAP). For best segmentation, we used the simulated annealing algorithm with a Gibbs sampler to solve the combinatorial optimization problem of MAP estimators, and we applied a knowledge-guided strategy to reduce false positive regions. We achieved AMAP-based GGO segmentation results of 86.94%, 94.33%, and 94.06% in average sensitivity, specificity, and accuracy, respectively, and we evaluated the performance using radiologists' subjective evaluation and quantificational analysis and diagnosis. We also compared the results of AMAP-based GGO segmentation with those of support vector machine-based methods, and we discuss the reliability and other issues of AMAP-based GGO segmentation. Our research results demonstrate the acceptability and usefulness of AMAP-based GGO segmentation for assisting radiologists in detecting GGO in high-resolution CT diagnostic procedures.

A survey of GPU-based medical image computing techniques

Medical imaging currently plays a crucial role throughout the entire clinical applications from medical scientific research to diagnostics and treatment planning. However, medical imaging procedures are often computationally demanding due to the large three-dimensional (3D) medical datasets to process in practical clinical applications. With the rapidly enhancing performances of graphics processors, improved programming support, and excellent price-to-performance ratio, the graphics processing unit (GPU) has emerged as a competitive parallel computing platform for computationally expensive and demanding tasks in a wide range of medical image applications. The major purpose of this survey is to provide a comprehensive reference source for the starters or researchers involved in GPU-based medical image processing. Within this survey, the continuous advancement of GPU computing is reviewed and the existing traditional applications in three areas of medical image processing, namely, segmentation, registration and visualization, are surveyed. The potential advantages and associated challenges of current GPU-based medical imaging are also discussed to inspire future applications in medicine.

An open source multivariate framework for n-tissue segmentation with evaluation on public data

We introduce Atropos, an ITK-based multivariate n-class open source segmentation algorithm distributed with ANTs ( http://www.picsl.upenn.edu/ANTs). The Bayesian formulation of the segmentation problem is solved using the Expectation Maximization (EM) algorithm with the modeling of the class intensities based on either parametric or non-parametric finite mixtures. Atropos is capable of incorporating spatial prior probability maps (sparse), prior label maps and/or Markov Random Field (MRF) modeling. Atropos has also been efficiently implemented to handle large quantities of possible labelings (in the experimental section, we use up to 69 classes) with a minimal memory footprint. This work describes the technical and implementation aspects of Atropos and evaluates its performance on two different ground-truth datasets. First, we use the BrainWeb dataset from Montreal Neurological Institute to evaluate three-tissue segmentation performance via (1) K-means segmentation without use of template data; (2) MRF segmentation with initialization by prior probability maps derived from a group template; (3) Prior-based segmentation with use of spatial prior probability maps derived from a group template. We also evaluate Atropos performance by using spatial priors to drive a 69-class EM segmentation problem derived from the Hammers atlas from University College London. These evaluation studies, combined with illustrative examples that exercise Atropos options, demonstrate both performance and wide applicability of this new platform-independent open source segmentation tool.

Quantitative mouse brain phenotyping based on single and multispectral MR protocols

Sophisticated image analysis methods have been developed for the human brain, but such tools still need to be adapted and optimized for quantitative small animal imaging. We propose a framework for quantitative anatomical phenotyping in mouse models of neurological and psychiatric conditions. The framework encompasses an atlas space, image acquisition protocols, and software tools to register images into this space. We show that a suite of segmentation tools (Avants, Epstein et al., 2008) designed for human neuroimaging can be incorporated into a pipeline for segmenting mouse brain images acquired with multispectral magnetic resonance imaging (MR) protocols. We present a flexible approach for segmenting such hyperimages, optimizing registration, and identifying optimal combinations of image channels for particular structures. Brain imaging with T1, T2* and T2 contrasts yielded accuracy in the range of 83% for hippocampus and caudate putamen (Hc and CPu), but only 54% in white matter tracts, and 44% for the ventricles. The addition of diffusion tensor parameter images improved accuracy for large gray matter structures (by >5%), white matter (10%), and ventricles (15%). The use of Markov random field segmentation further improved overall accuracy in the C57BL/6 strain by 6%; so Dice coefficients for Hc and CPu reached 93%, for white matter 79%, for ventricles 68%, and for substantia nigra 80%. We demonstrate the segmentation pipeline for the widely used C57BL/6 strain, and two test strains (BXD29, APP/TTA). This approach appears promising for characterizing temporal changes in mouse models of human neurological and psychiatric conditions, and may provide anatomical constraints for other preclinical imaging, e.g. fMRI and molecular imaging. This is the first demonstration that multiple MR imaging modalities combined with multivariate segmentation methods lead to significant improvements in anatomical segmentation in the mouse brain.

Machine learning and radiology

In this paper, we give a short introduction to machine learning and survey its applications in radiology. We focused on six categories of applications in radiology: medical image segmentation, registration, computer aided detection and diagnosis, brain function or activity analysis and neurological disease diagnosis from fMR images, content-based image retrieval systems for CT or MRI images, and text analysis of radiology reports using natural language processing (NLP) and natural language understanding (NLU). This survey shows that machine learning plays a key role in many radiology applications. Machine learning identifies complex patterns automatically and helps radiologists make intelligent decisions on radiology data such as conventional radiographs, CT, MRI, and PET images and radiology reports. In many applications, the performance of machine learning-based automatic detection and diagnosis systems has shown to be comparable to that of a well-trained and experienced radiologist. Technology development in machine learning and radiology will benefit from each other in the long run. Key contributions and common characteristics of machine learning techniques in radiology are discussed. We also discuss the problem of translating machine learning applications to the radiology clinical setting, including advantages and potential barriers.

Semi-Huber potential function for image segmentation

In this work, a novel model of Markov Random Field (MRF) is introduced. Such a model is based on a proposed Semi-Huber potential function and it is applied successfully to image segmentation in presence of noise. The main difference with respect to other half-quadratic models that have been taken as a reference is, that the number of parameters to be tuned in the proposed model is smaller and simpler. The idea is then, to choose adequate parameter values heuristically for a good segmentation of the image. In that sense, some experimental results show that the proposed model allows an easier parameter adjustment with reasonable computation times.

Very large fMRI study using the IMAGEN database: sensitivity-specificity and population effect modeling in relation to the underlying anatomy

In this paper we investigate the use of classical fMRI Random Effect (RFX) group statistics when analyzing a very large cohort and the possible improvement brought from anatomical information. Using 1326 subjects from the IMAGEN study, we first give a global picture of the evolution of the group effect t-value from a simple face-watching contrast with increasing cohort size. We obtain a wide activated pattern, far from being limited to the reasonably expected brain areas, illustrating the difference between statistical significance and practical significance. This motivates us to inject tissue-probability information into the group estimation, we model the BOLD contrast using a matter-weighted mixture of Gaussians and compare it to the common, single-Gaussian model. In both cases, the model parameters are estimated per-voxel for one subgroup, and the likelihood of both models is computed on a second, separate subgroup to reflect model generalization capacity. Various group sizes are tested, and significance is asserted using a 10-fold cross-validation scheme. We conclude that adding matter information consistently improves the quantitative analysis of BOLD responses in some areas of the brain, particularly those where accurate inter-subject registration remains challenging.

Consistent segmentation using a Rician classifier

Several popular classification algorithms used to segment magnetic resonance brain images assume that the image intensities, or log-transformed intensities, satisfy a finite Gaussian mixture model. In these methods, the parameters of the mixture model are estimated and the posterior probabilities for each tissue class are used directly as soft segmentations or combined to form a hard segmentation. It is suggested and shown in this paper that a Rician mixture model fits the observed data better than a Gaussian model. Accordingly, a Rician mixture model is formulated and used within an expectation maximization (EM) framework to yield a new tissue classification algorithm called Rician Classifier using EM (RiCE). It is shown using both simulated and real data that RiCE yields comparable or better performance to that of algorithms based on the finite Gaussian mixture model. As well, we show that RiCE yields more consistent segmentation results when used on images of the same individual acquired with different T1-weighted pulse sequences. Therefore, RiCE has the potential to stabilize segmentation results in brain studies involving heterogeneous acquisition sources as is typically found in both multi-center and longitudinal studies.

A prior feature SVM-MRF based method for mouse brain segmentation

We introduce an automated method, called prior feature Support Vector Machine-Markov Random Field (pSVMRF), to segment three-dimensional mouse brain Magnetic Resonance Microscopy (MRM) images. Our earlier work, extended MRF (eMRF) integrated Support Vector Machine (SVM) and Markov Random Field (MRF) approaches, leading to improved segmentation accuracy; however, the computation of eMRF is very expensive, which may limit its performance on segmentation and robustness. In this study pSVMRF reduces training and testing time for SVM, while boosting segmentation performance. Unlike the eMRF approach, where MR intensity information and location priors are linearly combined, pSVMRF combines this information in a nonlinear fashion, and enhances the discriminative ability of the algorithm. We validate the proposed method using MR imaging of unstained and actively stained mouse brain specimens, and compare segmentation accuracy with two existing methods: eMRF and MRF. C57BL/6 mice are used for training and testing, using cross validation. For formalin fixed C57BL/6 specimens, pSVMRF outperforms both eMRF and MRF. The segmentation accuracy for C57BL/6 brains, stained or not, was similar for larger structures like hippocampus and caudate putamen, (~87%), but increased substantially for smaller regions like susbtantia nigra (from 78.36% to 91.55%), and anterior commissure (from ~50% to ~80%). To test segmentation robustness against increased anatomical variability we add two strains, BXD29 and a transgenic mouse model of Alzheimer's disease. Segmentation accuracy for new strains is 80% for hippocampus, and caudate putamen, indicating that pSVMRF is a promising approach for phenotyping mouse models of human brain disorders.

A joint shape evolution approach to medical image segmentation using expectation-maximization algorithm

This study proposes an expectation-maximization (EM)-based curve evolution algorithm for segmentation of magnetic resonance brain images. In the proposed algorithm, the evolution curve is constrained not only by a shape-based statistical model but also by a hidden variable model from image observation. The hidden variable model herein is defined by the local voxel labeling, which is unknown and estimated by the expected likelihood function derived from the image data and prior anatomical knowledge. In the M-step, the shapes of the structures are estimated jointly by encoding the hidden variable model and the statistical prior model obtained from the training stage. In the E-step, the expected observation likelihood and the prior distribution of the hidden variables are estimated. In experiments, the proposed automatic segmentation algorithm is applied to multiple gray nuclei structures such as caudate, putamens and thalamus of three-dimensional magnetic resonance imaging in volunteers and patients. As for the robustness and accuracy of the segmentation algorithm, the results of the proposed EM-joint shape-based algorithm outperformed those obtained using the statistical shape model-based techniques in the same framework and a current state-of-the-art region competition level set method.

A multiscale and multiblock fuzzy C-means classification method for brain MR images

PURPOSE

Classification of magnetic resonance (MR) images has many clinical and research applications. Because of multiple factors such as noise, intensity inhomogeneity, and partial volume effects, MR image classification can be challenging. Noise in MRI can cause the classified regions to become disconnected. Partial volume effects make the assignment of a single class to one region difficult. Because of intensity inhomogeneity, the intensity of the same tissue can vary with respect to the location of the tissue within the same image. The conventional "hard" classification method restricts each pixel exclusively to one class and often results in crisp results. Fuzzy C-mean (FCM) classification or "soft" segmentation has been extensively applied to MR images, in which pixels are partially classified into multiple classes using varying memberships to the classes. Standard FCM, however, is sensitive to noise and cannot effectively compensate for intensity inhomogeneities. This paper presents a method to obtain accurate MR brain classification using a modified multiscale and multiblock FCM.

METHODS

An automatic, multiscale and multiblock fuzzy C-means (MsbFCM) classification method with MR intensity correction is presented in this paper. We use a bilateral filter to process MR images and to build a multiscale image series by increasing the standard deviation of spatial function and by reducing the standard deviation of range function. At each scale, we separate the image into multiple blocks and for every block a multiscale fuzzy C-means classification method is applied along the scales from the coarse to fine levels in order to overcome the effect of intensity inhomogeneity. The result from a coarse scale supervises the classification in the next fine scale. The classification method is tested with noisy MR images with intensity inhomogeneity.

RESULTS

Our method was compared with the conventional FCM, a modified FCM (MFCM) and multiscale FCM (MsFCM) method. Validation studies were performed on synthesized images with various contrasts, on the simulated brain MR database, and on real MR images. Our MsbFCM method consistently performed better than the conventional FCM, MFCM, and MsFCM methods. The MsbFCM method achieved an overlap ratio of 91% or higher. Experimental results using real MR images demonstrate the effectiveness of the proposed method. Our MsbFCM classification method is accurate and robust for various MR images.

CONCLUSIONS

As our classification method did not assume a Gaussian distribution of tissue intensity, it could be used on other image data for tissue classification and quantification. The automatic classification method can provide a useful quantification tool in neuroimaging and other applications.

Voxel-based adaptive spatio-temporal modelling of perfusion cardiovascular MRI

Contrast enhanced myocardial perfusion magnetic resonance imaging (MRI) is a promising technique, providing insight into how reduced coronary flow affects the myocardial tissue. Stenosis in a coronary vessel leads to reduced myocardial blood flow, but collaterals may secure the blood supply of the myocardium, with altered tracer kinetics. Due to a low signal-to-noise ratio, quantitative analysis of the signal is typically difficult to achieve at the voxel level. Hence, analysis is often performed on measurements that are aggregated in predefined myocardial segments, that ignore the variability in blood flow in each segment. The approach presented in this paper uses local spatial information that enables one to perform a robust analysis at the voxel level. The spatial dependencies between local response curves are modelled via a hierarchical Bayesian model. In the proposed framework, all local systems are analyzed simultaneously along with their dependencies, producing a more robust context-driven estimation of local kinetics. Detailed validation on both simulated and patient data is provided.

A general system for automatic biomedical image segmentation using intensity neighborhoods

Image segmentation is important with applications to several problems in biology and medicine. While extensively researched, generally, current segmentation methods perform adequately in the applications for which they were designed, but often require extensive modifications or calibrations before being used in a different application. We describe an approach that, with few modifications, can be used in a variety of image segmentation problems. The approach is based on a supervised learning strategy that utilizes intensity neighborhoods to assign each pixel in a test image its correct class based on training data. We describe methods for modeling rotations and variations in scales as well as a subset selection for training the classifiers. We show that the performance of our approach in tissue segmentation tasks in magnetic resonance and histopathology microscopy images, as well as nuclei segmentation from fluorescence microscopy images, is similar to or better than several algorithms specifically designed for each of these applications.

A discriminative model-constrained EM approach to 3D MRI brain tissue classification and intensity non-uniformity correction

We describe a fully automated method for tissue classification, which is the segmentation into cerebral gray matter (GM), cerebral white matter (WM), and cerebral spinal fluid (CSF), and intensity non-uniformity (INU) correction in brain magnetic resonance imaging (MRI) volumes. It combines supervised MRI modality-specific discriminative modeling and unsupervised statistical expectation maximization (EM) segmentation into an integrated Bayesian framework. While both the parametric observation models and the non-parametrically modeled INUs are estimated via EM during segmentation itself, a Markov random field (MRF) prior model regularizes segmentation and parameter estimation. Firstly, the regularization takes into account knowledge about spatial and appearance-related homogeneity of segments in terms of pairwise clique potentials of adjacent voxels. Secondly and more importantly, patient-specific knowledge about the global spatial distribution of brain tissue is incorporated into the segmentation process via unary clique potentials. They are based on a strong discriminative model provided by a probabilistic boosting tree (PBT) for classifying image voxels. It relies on the surrounding context and alignment-based features derived from a probabilistic anatomical atlas. The context considered is encoded by 3D Haar-like features of reduced INU sensitivity. Alignment is carried out fully automatically by means of an affine registration algorithm minimizing cross-correlation. Both types of features do not immediately use the observed intensities provided by the MRI modality but instead rely on specifically transformed features, which are less sensitive to MRI artifacts. Detailed quantitative evaluations on standard phantom scans and standard real-world data show the accuracy and robustness of the proposed method. They also demonstrate relative superiority in comparison to other state-of-the-art approaches to this kind of computational task: our method achieves average Dice coefficients of 0.93 ± 0.03 (WM) and 0.90 ± 0.05 (GM) on simulated mono-spectral and 0.94 ± 0.02 (WM) and 0.92 ± 0.04 (GM) on simulated multi-spectral data from the BrainWeb repository. The scores are 0.81 ± 0.09 (WM) and 0.82 ± 0.06 (GM) and 0.87 ± 0.05 (WM) and 0.83 ± 0.12 (GM) for the two collections of real-world data sets-consisting of 20 and 18 volumes, respectively-provided by the Internet Brain Segmentation Repository.

Hybrid genetic and variational expectation-maximization algorithm for gaussian-mixture-model-based brain MR image segmentation

The expectation-maximization (EM) algorithm has been widely applied to the estimation of gaussian mixture model (GMM) in brain MR image segmentation. However, the EM algorithm is deterministic and intrinsically prone to overfitting the training data and being trapped in local optima. In this paper, we propose a hybrid genetic and variational EM (GA-VEM) algorithm for brain MR image segmentation. In this approach, the VEM algorithm is performed to estimate the GMM, and the GA is employed to initialize the hyperparameters of the conjugate prior distributions of GMM parameters involved in the VEM algorithm. Since GA has the potential to achieve global optimization and VEM can steadily avoid overfitting, the hybrid GA-VEM algorithm is capable of overcoming the drawbacks of traditional EM-based methods. We compared our approach to the EM-based, VEM-based, and GA-EM based segmentation algorithms, and the segmentation routines used in the statistical parametric mapping package and FMRIB Software Library in 20 low-resolution and 17 high-resolution brain MR studies. Our results show that the proposed approach can improve substantially the performance of brain MR image segmentation.

Real-time segmentation by Active Geometric Functions

Recent advances in 4D imaging and real-time imaging provide image data with clinically important cardiac dynamic information at high spatial or temporal resolution. However, the enormous amount of information contained in these data has also raised a challenge for traditional image analysis algorithms in terms of efficiency. In this paper, a novel deformable model framework, Active Geometric Functions (AGF), is introduced to tackle the real-time segmentation problem. As an implicit framework paralleling to level-set, AGF has mathematical advantages in efficiency and computational complexity as well as several flexible feature similar to level-set framework. AGF is demonstrated in two cardiac applications: endocardial segmentation in 4D ultrasound and myocardial segmentation in MRI with super high temporal resolution. In both applications, AGF can perform real-time segmentation in several milliseconds per frame, which was less than the acquisition time per frame. Segmentation results are compared to manual tracing with comparable performance with inter-observer variability. The ability of such real-time segmentation will not only facilitate the diagnoses and workflow, but also enables novel applications such as interventional guidance and interactive image acquisition with online segmentation.

Automated brain tissue segmentation based on fractional signal mapping from inversion recovery Look-Locker acquisition

Most current automated segmentation methods are performed on T(1)- or T(2)-weighted MR images, relying on relative image intensity that is dependent on other MR parameters and sensitive to B(1) magnetic field inhomogeneity. Here, we propose an image segmentation method based on quantitative longitudinal magnetization relaxation time (T(1)) of brain tissues. Considering the partial volume effect, fractional volume maps of brain tissues (white matter, gray matter, and cerebrospinal fluid) were obtained by fitting the observed signal in an inversion recovery procedure to a linear combination of three exponential functions, which represents the relaxations of each of the tissue types. A Look-Locker acquisition was employed to accelerate the acquisition process. The feasibility and efficacy of this proposed method were evaluated using simulations and experiments. The potential applications of this method in the study of neurological disease as well as normal brain development and aging are discussed.

The brain MR Image segmentation techniques and use of diagnostic packages

RATIONALE AND OBJECTIVES

This article provides a survey of segmentation methods for medical images. Usually, classification of segmentation methods is done based on the approaches adopted and the domain of application.

MATERIALS AND METHODS

This survey is conducted on the recent segmentation methods used in biomedical image processing and explores the methods useful for better segmentation. A critical appraisal of the current status of semiautomated and automated methods is made for the segmentation of anatomical medical images emphasizing the advantages and disadvantages. Computer-aided diagnosis (CAD) used by radiologists as a second opinion has become one of the major research areas in medical imaging and diagnostic radiology. A picture archiving communication system (PACS) is an integrated workflow system for managing images and related data that is designed to streamline operations throughout the whole patient care delivery process.

RESULTS

By using PACS, the medical image interpretation may be changed from conventional hard-copy images to soft-copy studies viewed on the systems workstations.

CONCLUSION

The automatic segmentations assist the doctors in making quick diagnosis. The CAD need not be comparable to that of physicians, but is surely complementary.

A multidimensional segmentation evaluation for medical image data

Evaluation of segmentation methods is a crucial aspect in image processing, especially in the medical imaging field, where small differences between segmented regions in the anatomy can be of paramount importance. Usually, segmentation evaluation is based on a measure that depends on the number of segmented voxels inside and outside of some reference regions that are called gold standards. Although some other measures have been also used, in this work we propose a set of new similarity measures, based on different features, such as the location and intensity values of the misclassified voxels, and the connectivity and the boundaries of the segmented data. Using the multidimensional information provided by these measures, we propose a new evaluation method whose results are visualized applying a Principal Component Analysis of the data, obtaining a simplified graphical method to compare different segmentation results. We have carried out an intensive study using several classic segmentation methods applied to a set of MRI simulated data of the brain with several noise and RF inhomogeneity levels, and also to real data, showing that the new measures proposed here and the results that we have obtained from the multidimensional evaluation, improve the robustness of the evaluation and provides better understanding about the difference between segmentation methods.

Joint brain parametric T1-map segmentation and RF inhomogeneity calibration

We propose a constrained version of Mumford and Shah's (1989) segmentation model with an information-theoretic point of view in order to devise a systematic procedure to segment brain magnetic resonance imaging (MRI) data for parametric T(1)-Map and T(1)-weighted images, in both 2-D and 3D settings. Incorporation of a tuning weight in particular adds a probabilistic flavor to our segmentation method, and makes the 3-tissue segmentation possible. Moreover, we proposed a novel method to jointly segment the T(1)-Map and calibrate RF Inhomogeneity (JSRIC). This method assumes the average T(1) value of white matter is the same across transverse slices in the central brain region, and JSRIC is able to rectify the flip angles to generate calibrated T(1)-Maps. In order to generate an accurate T(1)-Map, the determination of optimal flip-angles and the registration of flip-angle images are examined. Our JSRIC method is validated on two human subjects in the 2D T(1)-Map modality and our segmentation method is validated by two public databases, BrainWeb and IBSR, of T(1)-weighted modality in the 3D setting.

Distributed local MRF models for tissue and structure brain segmentation

Accurate tissue and structure segmentation of magnetic resonance (MR) brain scans is critical in several applications. In most approaches this task is handled through two sequential steps. We propose to carry out cooperatively both tissue and subcortical structure segmentation by distributing a set of local and cooperative Markov random field (MRF) models Tissue segmentation is performed by partitioning the volume into subvolumes where local MRFs are estimated in cooperation with their neighbors to ensure consistency. Local estimation fits precisely to the local intensity distribution and thus handles nonuniformity of intensity without any bias field modelization. Similarly, subcortical structure segmentation is performed via local MRF models that integrate localization constraints provided by a priori fuzzy description of brain anatomy. Subcortical structure segmentation is not reduced to a subsequent processing step but joined with tissue segmentation: the two procedures cooperate to gradually and conjointly improve model accuracy. We propose a framework to implement this distributed modeling integrating cooperation, coordination, and local model checking in an efficient way. Its evaluation was performed using both phantoms and real 3 T brain scans, showing good results and in particular robustness to nonuniformity and noise with a low computational cost. This original combination of local MRF models, including anatomical knowledge, appears as a powerful and promising approach for MR brain scan segmentation.

A RICIAN MIXTURE MODEL CLASSIFICATION ALGORITHM FOR MAGNETIC RESONANCE IMAGES

Tissue classification algorithms developed for magnetic resonance images commonly assume a Gaussian model on the statistics of noise in the image. While this is approximately true for voxels having large intensities, it is less true as the underlying intensity becomes smaller. In this paper, the Gaussian model is replaced with a Rician model, which is a better approximation to the observed signal. A new classification algorithm based on a finite mixture model of Rician signals is presented wherein the expectation maximization algorithm is used to find the joint maximum likelihood estimates of the unknown mixture parameters. Improved accuracy of tissue classification is demonstrated on several sample data sets. It is also shown that classification repeatability for the same subject under different MR acquisitions is improved using the new method.

Automatic segmentation of the human brain ventricles from MR images by knowledge-based region growing and trimming

Automatic segmentation of the human brain ventricular system from MR images is useful in studies of brain anatomy and its diseases. Existing intensity-based segmentation methods are adaptive to large shape and size variations of the ventricular system, but may leak to the non-ventricular regions due to the non-homogeneity, noise and partial volume effect in the images. Deformable model-based methods are more robust to noise and alleviate the leakage problem, but may generate wrong results when the shape or size of the ventricle to be segmented in the images has a large difference in comparison to its model. In this paper, we propose a knowledge-based region growing and trimming approach where: (1) a model of a ventricular system is used to define regions of interest (ROI) for the four ventricles (i.e., left, right, third and fourth); (2) to segment a ventricle in its ROI, a region growing procedure is first applied to obtain a connected region that contains the ventricle, and (3) a region trimming procedure is then employed to trim the non-ventricle regions. A hysteretic thresholding is developed for the region growing procedure to cope with the partial volume effect and minimize non-ventricular regions. The domain knowledge on the shape and intensity features of the ventricular system is used for the region trimming procedure. Due to the joint use of the model-based and intensity-based approaches, our method is robust to noise and large shape and size variations. Experiments on 18 simulated and 58 clinical MR images show that the proposed approach is able to segment the ventricular system accurately with the dice similarity coefficient ranging from 91% to 99%.