Segmentation Of Brain MR Images Research Articles

Abnormal Region Extraction from MR Brain Images using Hybrid Approach

Automatic brain abnormality segmentation from magnetic resonance images is a key task that is performed by computer aided algorithm or manual extraction by a medical expert. The regions are often partitioned based on the similarities of intensities that persist in a particular region. MR brain image segmentation is a critical step that helps to identify the abnormal region. Accurate identification of this abnormal region helps the radiologist and surgeons in surgical process and research. Through this paper we present a hybrid approach of algorithms based on clustering approach like region and edge based algorithm involved in segmenting abnormal region from MR brain images. The method is an integration of region based (pillar K-means) and edge based (level set) segmentation algorithm that aims to segment the abnormal region precisely. Experimental results show that the proposed approach could attain segmentation efficiency of 89.2%, mitigating the segmentation errors that were prevalent with region or edge based algorithms.

A fast stochastic framework for automatic MR brain images segmentation

This paper introduces a new framework for the segmentation of different brain structures (white matter, gray matter, and cerebrospinal fluid) from 3D MR brain images at different life stages. The proposed segmentation framework is based on a shape prior built using a subset of co-aligned training images that is adapted during the segmentation process based on first- and second-order visual appearance characteristics of MR images. These characteristics are described using voxel-wise image intensities and their spatial interaction features. To more accurately model the empirical grey level distribution of the brain signals, we use a linear combination of discrete Gaussians (LCDG) model having positive and negative components. To accurately account for the large inhomogeneity in infant MRIs, a higher-order Markov-Gibbs Random Field (MGRF) spatial interaction model that integrates third- and fourth- order families with a traditional second-order model is proposed. The proposed approach was tested and evaluated on 102 3D MR brain scans using three metrics: the Dice coefficient, the 95-percentile modified Hausdorff distance, and the absolute brain volume difference. Experimental results show better segmentation of MR brain images compared to current open source segmentation tools.

Variable Variance Adaptive Mean-Shift and possibilistic fuzzy C-means based recursive framework for brain MR image segmentation

Segmentation of brain MR image tissues has been a challenge because of the embedded nonlinear bias field acquired during the image acquisition process. This problem is further compounded due to the presence of noise. In order to deal with such issues, we have proposed a Variable Variance Adaptive Mean-Shift (VVAMS) algorithm which not only removes noise but also reinforces the clustering attribute by its mode seeking ability. We have formulated the problem for jointly estimating the bias field, tissue class labels and noise free pixels. Since, all the parameters are unknown and interdependent it is hard to obtain optimal estimates. In this regard, we have proposed a recursive framework to obtain the estimates of the parameters, which are partial optimal ones. In the first step of the recursion, the possibilistic fuzzy clustering algorithms has been applied to determine different clusters and bias field. These clusters are noisy and hence in the second step of the recursion, VVAMS algorithm has been applied on each cluster to eliminate noise and reinforce the modes of the clusters. These two steps constitute one combined iteration. Theoretically, the recursive framework is supposed to converge after large number of recursions but in practice it converges after a few iterations. This proposed scheme has successfully been tested with 50 biased noisy slices from Brainweb database and some real brain MR image data from IBSR database. The results have been quantitatively evaluated by percentage of misclassification, Rand Index, t-test, fuzzy partition coefficient (Vpc), fuzzy partition entropy (Vpe) and Tanimoto index. The quantitative evaluations of the tissue class labels demonstrate the superiority of proposed scheme over the existing methods.

Brain segmentation in MR images using a texture-based classifier associated with mathematical morphology.

Skull stripping, which refers to the segmentation of brain tissue from non-brain tissue, has been challenging due to the ramification of the human brain structures and volatile parameters in the magnetic resonance imaging (MRI) procedures. It has been one of the most critical preprocessing steps in medical image analysis. We propose a hybrid skull stripping algorithm that is based on texture feature analysis, fuzzy possibilistic c-means (FPCM), and morphological operations. The input MR image is first processed to obtain two texture feature maps, to which the FPCM is applied for acquiring brain and non-brain masks. A number of morphological operations are subsequently performed to extract the brain. Our algorithm has been compared with two famous methods and evaluated on the internet brain segmentation repository (IBSR) datasets. Preliminary experimental results suggested that this new framework achieved high accuracy and outperformed the compared methods. We believe that the proposed scheme is of effectively potential in a wide variety of brain MR image segmentation applications.

Segmentation of brain MR images using a proper combination of DCS based method with MRF

Manual segmentation of Magnetic Resonance Images (MRI) is a time-consuming process, thus automatic segmentation of brain MR images has attracted more attention in recent years. In this paper, we introduce Dynamic Classifier Selection Markov Random Field (DCSMRF) algorithm for supervised segmentation of brain MR images into three main tissues such as White Matter (WM), Gray Matter (GM) and Cerebrospinal Fluid (CSF). DCSMRF combines a novel ensemble method with the Markov Random Field (MRF) algorithm and tries to obtain the advantages of both algorithms. For the ensemble part of DCSMRF, we propose an ensemble method called Dynamic Classifier System-Weighted Local Accuracy (DCS-WLA) which is a type of Combination of Multiple Classifier (CMC) algorithm. Later, the MRF algorithm is utilized for incorporating spatial, contextual and textural information in this paper. For the MRF section, an energy function based on the output of the DCS-WLA algorithm is proposed, then maximum value for Maximum A Posterior (MAP) criterion is searched to obtain optimal segmentation. The MRF algorithm applies similar to a post processing step in which only a subset of pixels is selected for optimization step. Hence, a vast amount of search space is pruned. Consequently, the computational burden of the proposed algorithm is more tolerable than the conventional MRF-based methods. Moreover, by employing ensemble algorithms, the accuracy and reliability of final results are enhanced compared to the individual methods.

Brain MR Image Segmentation for Tumor Detection using Artificial Neural

Brain MR Image Segmentation for Tumor Detection using Artificial Neural

Multilevel Thresholding Method Based on Electromagnetism for Accurate Brain MRI Segmentation to Detect White Matter, Gray Matter, and CSF.

This work explains an advanced and accurate brain MRI segmentation method. MR brain image segmentation is to know the anatomical structure, to identify the abnormalities, and to detect various tissues which help in treatment planning prior to radiation therapy. This proposed technique is a Multilevel Thresholding (MT) method based on the phenomenon of Electromagnetism and it segments the image into three tissues such as White Matter (WM), Gray Matter (GM), and CSF. The approach incorporates skull stripping and filtering using anisotropic diffusion filter in the preprocessing stage. This thresholding method uses the force of attraction-repulsion between the charged particles to increase the population. It is the combination of Electromagnetism-Like optimization algorithm with the Otsu and Kapur objective functions. The results obtained by using the proposed method are compared with the ground-truth images and have given best values for the measures sensitivity, specificity, and segmentation accuracy. The results using 10 MR brain images proved that the proposed method has accurately segmented the three brain tissues compared to the existing segmentation methods such as K-means, fuzzy C-means, OTSU MT, Particle Swarm Optimization (PSO), Bacterial Foraging Algorithm (BFA), Genetic Algorithm (GA), and Fuzzy Local Gaussian Mixture Model (FLGMM).

Automatic segmentation of infant brain MR images: With special reference to myelinated white matter

Automatic segmentation of infant brain images is faced with numerous challenges like poor image contrast, motion artifacts, and changes caused by progressive myelination of the infant brain. Since timely myelination points to normal brain maturity, monitoring the progress and degree of myelination is clinically significant. However, most of the existing segmentation methods do not segment myelinated portions of the infant brain. In this paper, we propose a segmentation approach focused on segmenting the myelinated white matter tissue in T1-weighted magnetic resonance images of the infant brain. The novelty of the algorithm lies in the introduction of a weighted localized Tsallis entropy based thresholding method. The proposed method is also tested on older babies beyond the one-year age mark to verify its utility and robustness. It is seen that the mean Dice coefficients obtained for myelin segmentation by the proposed weighted localized method are higher than that of the other methods, namely, the conventional Tsallis entropy thresholding and modified localized method.

LATEST: Local AdapTivE and Sequential Training for Tissue Segmentation of Isointense Infant Brain MR Images.

Accurate segmentation of isointense infant (~6 months of age) brain MRIs is of great importance, however, a very challenging task, due to extremely low tissue contrast caused by ongoing myelination processes. In this work, we propose a novel learning method based on Local AdapTivE and Sequential Training (LATEST) for segmentation. Specifically, random forest technique is employed to train a local classifier (a single decision tree) for each voxel in the common space based on the neighboring training samples from atlases. Then, for each given voxel, all trained nearby individual classifiers (decision trees) are grouped together to form a forest. Moreover, the estimated probabilities are further used as additional source images to train the next set of local classifiers for refining tissue classification. By iteratively training the subsequent classifiers based on the updated tissue probability maps, a sequence of local classifiers can be built for accurate tissue segmentation.

A joint intensity and edge magnitude-based multilevel thresholding algorithm for the automatic segmentation of pathological MR brain images

Multilevel thresholding is one of the most popular image segmentation techniques due to its simplicity and accuracy. Most of the thresholding approaches use either the histogram of an image or information from the grey-level co-occurrence matrix (GLCM) to compute the threshold. The medical images like MRI usually have vague boundaries and poor contrast. So, segmenting these images using solely histogram or texture attributes of GLCM proves to be insufficient. This paper proposes a novel multilevel thresholding approach for automatic segmentation of tumour lesions from magnetic resonance images. The proposed technique exploits both intensity and edge magnitude information present in image histogram and GLCM to compute the multiple thresholds. Subsequently, using both attributes, a hybrid fitness function has been formulated which can capture the variations in intensity and the edge magnitude present in different tumour groups effectively. Mutation-based particle swarm optimization (MPSO) technique has been used to optimize the fitness function so as to mitigate the problem of high computational complexity existing in the exhaustive search methods. Moreover, MPSO has better exploration capabilities as compared to conventional particle swarm optimization. The performance of the devised technique has been evaluated and compared with two other intensity- and texture-based approaches using three different measures: Jaccard, Dice and misclassification error. To compute these quantitative metrics, experiments were conducted on a series of images, including low-grade glioma tumour volumes taken from brain tumour image segmentation benchmark 2012 and 2015 data sets and real clinical tumour images. Experimental results show that the proposed approach outperforms the other competing algorithms by achieving an average value equal to 0.752, 0.854, 0.0052; 0.648, 0.762, 0.0177; 0.710, 0.813, 0.0148 and 0.886, 0.937, 0.0037 for four different data sets.

Spatial Fuzzy C Means and Expectation Maximization Algorithms with Bias Correction for Segmentation of MR Brain Images.

The Fuzzy C Means (FCM) and Expectation Maximization (EM) algorithms are the most prevalent methods for automatic segmentation of MR brain images into three classes Gray Matter (GM), White Matter (WM) and Cerebrospinal Fluid (CSF). The major difficulties associated with these conventional methods for MR brain image segmentation are the Intensity Non-uniformity (INU) and noise. In this paper, EM and FCM with spatial information and bias correction are proposed to overcome these effects. The spatial information is incorporated by convolving the posterior probability during E-Step of the EM algorithm with mean filter. Also, a method of pixel re-labeling is included to improve the segmentation accuracy. The proposed method is validated by extensive experiments on both simulated and real brain images from standard database. Quantitative and qualitative results depict that the method is superior to the conventional methods by around 25% and over the state-of-the art method by 8%.

Highly Efficient Segmentation and Classification of Premature Infants Brain MR Images at Global and Tissue Level

Objectives: Every year millions of babies born preterm and it is a serious issue in developed countries. Preterm birth is worldwide problem of young children. Methods/Statistical analysis: Advances in Magnetic Resonance Imaging (MRI), comprehensive images of the newborn brain is visualized non-invasively. Here we are focusing on the early assessment of brain development in neonates and premature infants using multi stage segmentation and classification approach with quantitative analysis. To achieve higher segmentation and classification accuracy neural network classifier are used. It is also helpful in detection and classification of more number of brain tissues. Findings: The accurate segmentation and classification of brain tissues is very much useful in evaluating the brain development of newborn and premature infants. Therefore, newborn brain MRI forms a crucial part in analytical neuro-imaging; principally in the neonatal stage.Our method gives higher dice similarity index values and higher computational speed as compared to existing methods. Application: Resulting segmentations are used for volumetric analysis and quantification of cortical descriptions. This analysis plays vital role for neonatologists in early detection and diagnosis of neural impairments.

Automated tissue segmentation of MR brain images in the presence of white matter lesions

Over the last few years, the increasing interest in brain tissue volume measurements on clinical settings has led to the development of a wide number of automated tissue segmentation methods. However, white matter lesions are known to reduce the performance of automated tissue segmentation methods, which requires manual annotation of the lesions and refilling them before segmentation, which is tedious and time-consuming. Here, we propose a new, fully automated T1-w/FLAIR tissue segmentation approach designed to deal with images in the presence of WM lesions. This approach integrates a robust partial volume tissue segmentation with WM outlier rejection and filling, combining intensity and probabilistic and morphological prior maps. We evaluate the performance of this method on the MRBrainS13 tissue segmentation challenge database, which contains images with vascular WM lesions, and also on a set of Multiple Sclerosis (MS) patient images. On both databases, we validate the performance of our method with other state-of-the-art techniques. On the MRBrainS13 data, the presented approach was at the time of submission the best ranked unsupervised intensity model method of the challenge (7th position) and clearly outperformed the other unsupervised pipelines such as FAST and SPM12. On MS data, the differences in tissue segmentation between the images segmented with our method and the same images where manual expert annotations were used to refill lesions on T1-w images before segmentation were lower or similar to the best state-of-the-art pipeline incorporating automated lesion segmentation and filling. Our results show that the proposed pipeline achieved very competitive results on both vascular and MS lesions. A public version of this approach is available to download for the neuro-imaging community.

A novel active contour model for image segmentation using local and global region-based information

In this paper, we propose a novel level set geodesic model for image segmentation. In our model, we define a hybrid signed pressure force (SPF) function integrating local and global region-based information to segment inhomogeneous images. The local region-based SPF utilizes mean values on local circular regions centered in each pixel. By introducing the local image information, the images with intensity inhomogeneity can be effectively segmented. In order to reduce the dependency on complex initialization, we incorporate a global region-based SPF into this model to develop a hybrid SPF. The global SPF and the local SPF are adaptively balanced by an adaptive weight. In addition, we also extend this model to four-phase level set formulation for brain MR image segmentation. Finally, a truncated Gaussian kernel is used to regularize the level set function, which not only regularizes it but also removes the need for computationally expensive re-initialization. Experimental results indicate that the proposed method achieves superior segmentation performance in terms of accuracy and robustness.

Gaussian Mixture Model with the Inclusion of Spatial Factor and Pixel Re-labelling: Application to MR Brain Image Segmentation

A fully automatic and accurate brain image segmentation divided into the three tissue types—Grey Matter, White Matter and Cerebrospinal Fluid (CSF)—is necessary in medical analysis. Gaussian Mixture Model (GMM) is one of the most widely implemented methods for MR Brain Image Segmentation, and Expectation–Maximization algorithm is used to estimate the parameters of the model. The major drawback existing in conventional GMM is that it considers each pixel as independent and does not incorporate the spatial interaction among the neighbouring pixels. This will lead to poor segmentation accuracy in the presence of noise and intensity inhomogeneity. To overcome this drawback, in the proposed method, the posterior probability is weighted with a spatial factor which improves the segmentation accuracy and makes the convergence also faster. Also, in the automatic segmentation of the IBSR MR Brain Image Data, a new approach of re-labelling the voxels for Grey Matter and CSF is proposed. The proposed method is tested on 20 low-resolution T1-weighted IBSR Brain Images and BrainWeb Simulated MR Images. The results show that the proposed method can improve the performance of MR Brain Image Segmentation by around 4 % over the state-of-the-art algorithm.

Soft fuzzy rough set-based MR brain image segmentation

Fuzzy sets, rough sets are efficient tools to handle uncertainty and vagueness in the medical images and are widely used for medical image segmentation. Soft sets are a new mathematical approach to uncertainty and vagueness. In this paper, a hybrid segmentation algorithm based on soft sets namely soft fuzzy rough c-means is proposed to extract the white matter, gray matter and the cerebro spinal fluid from MR brain image with bias field correction. In this algorithm, soft fuzzy rough approximations are applied to obtain the rough regions of image. These approximations are free from defining thresholds, weight parameters and are less complex compared to the existing rough set based algorithms. Soft sets use similarity coefficients to find the similarity of the clusters formed in present and previous step. The proposed algorithm does not involve any negative region, hence all the pixels participate in clustering avoiding clustering mistakes. Also, the histogram based centroids choose the centroids close to the ground truth that in turn effect the definition of approximations, standardizing the clusters. The proposed algorithm evaluated through simulation, compared it with existing k-means, rough k-means, fuzzy c-means and other hybrid algorithms. The soft fuzzy rough c-means algorithm outperforms the considered algorithms in all analyzed scenarios even in extracting the tumor from the brain tissue.

Fast and accurate fuzzy C‐means algorithm for MR brain image segmentation

ABSTRACTFuzzy theory based intelligent techniques are widely preferred for medical applications because of high accuracy. Among the fuzzy based techniques, Fuzzy C‐Means (FCM) algorithm is popular than the other approaches due to the availability of expert knowledge. But, one of the hidden facts is that the computational complexity of the FCM algorithm is significantly high. Since medical applications need to be time effective, suitable modifications must be made in this algorithm for practical feasibility. In this study, necessary changes are included in the FCM approach to make the approach time effective without compromising the segmentation efficiency. An additional data reduction approach is performed in the conventional FCM to minimize the computational complexity and the convergence rate. A comparative analysis with the conventional FCM algorithm and the proposed Fast and Accurate FCM (FAFCM) is also given to show the superior nature of the proposed approach. These techniques are analyzed in terms of segmentation efficiency and convergence rate. Experimental results show promising results for the proposed approach. © 2016 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 26, 188–195, 2016

Multi-scale structured CNN with label consistency for brain MR image segmentation

In this paper, a novel method for brain MR image segmentation has been proposed, with deep learning techniques to obtain preliminary labelling and graphical models to produce the final result. A specific architecture, namely multi-scale structured convolutional neural networks (MS-CNN), is designed to capture discriminative features for each sub-cortical structure and to generate a label probability map for the target image. Due to complex background in brain images and the lack of spatial constraints among testing samples, the initial result obtained with MS-CNN is not smooth. To deal with this problem, dynamic random walker with decayed region of interest is then proposed to enforce label consistency. Comprehensive evaluations have been carried out on two publicly available data-sets and experimental results indicate that the proposed method can obtain better segmentation quality efficiently.

Automatic brain tissue segmentation in MR images using Random Forests and Conditional Random Fields

BackgroundThe segmentation of brain tissue into cerebrospinal fluid, gray matter, and white matter in magnetic resonance imaging scans is an important procedure to extract regions of interest for quantitative analysis and disease assessment. Manual segmentation requires skilled experts, being a laborious and time-consuming task; therefore, reliable and robust automatic segmentation methods are necessary. New methodWe propose a segmentation framework based on a Conditional Random Field for brain tissue segmentation, with a Random Forest encoding the likelihood function. The features include intensities, gradients, probability maps, and locations. Additionally, skull stripping is critical for achieving an accurate segmentation; thus, after extracting the brain we propose to refine its boundary during segmentation. ResultsThe proposed framework was evaluated on the MR Brain Image Segmentation Challenge and the Internet Brain Segmentation Repository databases. The segmentations of brain tissues obtained with the proposed algorithm were competitive both in normal and diseased subjects. The skull stripping refinement significantly improved the results, when comparing against no refinement. Comparison with existing methodsIn the MR Brain Image Segmentation Challenge database, the results were competitive when comparing with top methods. In the Internet Brain Segmentation Repository database, the proposed approach outperformed other well-established algorithms. ConclusionsThe combination of a Random Forest and Conditional Random Field for brain tissue segmentation performed well for normal and diseased subjects. Additionally, refinement of the skull stripping at segmentation time is feasible in learning-based methods and significantly improves the segmentation of cerebrospinal fluid and intracranial volume.

Segmentation and enhancement of brain MR images using fuzzy clustering based on information theory

In recent decades, fuzzy segmentation methods, FCM algorithm in particular, have been widely employed for medical image segmentation, because they can save more information of the original image. But some artifacts like spatial noise and bias in medical images disturb segmentation results. This research presents an improved and robust FCM method based on information theoretic clustering, which estimated and corrected the heterogeneity of the magnetic field image (bias) and minimized the noise effects. To increase accuracy against any noise, the mutual information between data distribution of each cluster and those out of that cluster were maximized. The simulation results of the proposed algorithm are compared with previous fuzzy segmentation methods and its superiority in terms of segmentation of MR images in the database of brain images and synthetic images is illustrated.