Automatic Brain Tissue Segmentation Research Articles

Dealing With Noise and Partial Volume Effects in Alzheimer Disease Brain Tissue Classification by a Fuzzy-Possibilistic Modeling Based on Fuzzy-Genetic Initialization

Segmentation is a key step in brain imaging where clustering techniques are widely used, particularly the fuzzy approach which offers active and robust methods against noise and partial volume effect (PVE). To address those imperfections, this article suggests an automatic segmentation of brain tissues for magnetic resonance and functional images of Alzheimer's patients, based on an efficient and robust genetic-fuzzy-possibilistic clustering scheme for the assessment of white matter, gray matter and cerebrospinal fluid volumes. The proposed hybrid clustering process based on: 1) A fuzzy possibilistic c-means algorithm that models the degree of relationship between each voxel and a given tissue. 2) A fuzzy c-means algorithm to initialize the clusters centers, with subsequent optimization by a genetic algorithm. Each stage of the proposed clustering process is validated on real brain data and synthetic images of an Alzheimer's Disease Neuroimaging Initiative (ADNI) phantom. A performance comparison is made with the usual fuzzy techniques. The visual and quantitative results obtained with the proposed approach using various signal-to-noise ratios prove its effectiveness to quantify the tissue volume of images of different modalities types in the presence of noise and PVE. The effectiveness in terms of computational rate is also demonstrated.

Automatic extraction of the intracranial volume in fetal and neonatal MR scans using convolutional neural networks.

MR images of infants and fetuses allow non-invasive analysis of the brain. Quantitative analysis of brain development requires automatic brain tissue segmentation that is typically preceded by segmentation of the intracranial volume (ICV). Fast changes in the size and morphology of the developing brain, motion artifacts, and large variation in the field of view make ICV segmentation a challenging task. We propose an automatic method for segmentation of the ICV in fetal and neonatal MRI scans. The method was developed and tested with a diverse set of scans regarding image acquisition parameters (i.e. field strength, image acquisition plane, image resolution), infant age (23-45 weeks post menstrual age), and pathology (posthaemorrhagic ventricular dilatation, stroke, asphyxia, and Down syndrome). The results demonstrate that the method achieves accurate segmentation with a Dice coefficient (DC) ranging from 0.98 to 0.99 in neonatal and fetal scans regardless of image acquisition parameters or patient characteristics. Hence, the algorithm provides a generic tool for segmentation of the ICV that may be used as a preprocessing step for brain tissue segmentation in fetal and neonatal brain MR scans.

Automatic brain tissue segmentation in MR images using hybrid atlas forest based on confidence‐weighted probability matrix

AbstractThe segmentation of specific tissues in an MR brain image for quantitative analysis can assist the disease diagnosis and medical research. Therefore, a robust and accurate method for automatic segmentation is necessary. Atlas‐based‐method is a common and effective method of automatic segmentation where an atlas refers to a pair of image consist of an intensity image and its corresponding label image. Apart from the general multi‐atlas‐based methods, which propagate labels through the single atlas then fuse them, we proposed a hybrid atlas forest based on confidence‐weighted probability matrix to consider the atlases set as a whole and treat each voxel differently. In the framework, we first register the atlas to the image space of target and calculate the confidence of voxels in the registered atlas. Then, a confidence‐weighted probability matrix is generated and it augments to the intensity image of the atlas or target for providing spatial information of the target tissue. Third, a hybrid atlas forest is trained to gather the features and correlation information among the atlases in the dataset. Finally, the segmentation of the target tissues is predicted by the trained hybrid atlas forest. The segment performance and the components efficiency of the proposed method are evaluated on the two public datasets. Based on the experiment results and quantitative comparisons, our method can gather spatial information and correlation among the atlases to obtain an accurate segmentation.

Automatic brain tissue segmentation based on graph filter

BackgroundAccurate segmentation of brain tissues from magnetic resonance imaging (MRI) is of significant importance in clinical applications and neuroscience research. Accurate segmentation is challenging due to the tissue heterogeneity, which is caused by noise, bias filed and partial volume effects.MethodsTo overcome this limitation, this paper presents a novel algorithm for brain tissue segmentation based on supervoxel and graph filter. Firstly, an effective supervoxel method is employed to generate effective supervoxels for the 3D MRI image. Secondly, the supervoxels are classified into different types of tissues based on filtering of graph signals.ResultsThe performance is evaluated on the BrainWeb 18 dataset and the Internet Brain Segmentation Repository (IBSR) 18 dataset. The proposed method achieves mean dice similarity coefficient (DSC) of 0.94, 0.92 and 0.90 for the segmentation of white matter (WM), grey matter (GM) and cerebrospinal fluid (CSF) for BrainWeb 18 dataset, and mean DSC of 0.85, 0.87 and 0.57 for the segmentation of WM, GM and CSF for IBSR18 dataset.ConclusionsThe proposed approach can well discriminate different types of brain tissues from the brain MRI image, which has high potential to be applied for clinical applications.

Automated pixel-wise brain tissue segmentation of diffusion-weighted images via machine learning.

The diffusion-weighted (DW) MR signal sampled over a wide range of b-values potentially allows for tissue differentiation in terms of cellularity, microstructure, perfusion, and T2 relaxivity. This study aimed to implement a machine learning algorithm for automatic brain tissue segmentation from DW-MRI datasets, and to determine the optimal sub-set of features for accurate segmentation. DWI was performed at 3T in eight healthy volunteers using 15 b-values and 20 diffusion-encoding directions. The pixel-wise signal attenuation, as well as the trace and fractional anisotropy (FA) of the diffusion tensor, were used as features to train a support vector machine classifier for gray matter, white matter, and cerebrospinal fluid classes. The datasets of two volunteers were used for validation. For each subject, tissue classification was also performed on 3D T1 -weighted data sets with a probabilistic framework. Confusion matrices were generated for quantitative assessment of image classification accuracy in comparison with the reference method. DWI-based tissue segmentation resulted in an accuracy of 82.1% on the validation dataset and of 82.2% on the training dataset, excluding relevant model over-fitting. A mean Dice coefficient (DSC) of 0.79±0.08 was found. About 50% of the classification performance was attributable to five features (i.e. signal measured at b-values of 5/10/500/1200s/mm2 and the FA). This reduced set of features led to almost identical performances for the validation (82.2%) and the training (81.4%) datasets (DSC=0.79±0.08). Machine learning techniques applied to DWI data allow for accurate brain tissue segmentation based on both morphological and functional information.

SyMRI of the Brain: Rapid Quantification of Relaxation Rates and Proton Density, With Synthetic MRI, Automatic Brain Segmentation, and Myelin Measurement.

Conventional magnetic resonance images are usually evaluated using the image signal contrast between tissues and not based on their absolute signal intensities. Quantification of tissue parameters, such as relaxation rates and proton density, would provide an absolute scale; however, these methods have mainly been performed in a research setting. The development of rapid quantification, with scan times in the order of 6 minutes for full head coverage, has provided the prerequisites for clinical use. The aim of this review article was to introduce a specific quantification method and synthesis of contrast-weighted images based on the acquired absolute values, and to present automatic segmentation of brain tissues and measurement of myelin based on the quantitative values, along with application of these techniques to various brain diseases. The entire technique is referred to as “SyMRI” in this review. SyMRI has shown promising results in previous studies when used for multiple sclerosis, brain metastases, Sturge-Weber syndrome, idiopathic normal pressure hydrocephalus, meningitis, and postmortem imaging.

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.

3D cerebral MR image segmentation using multiple-classifier system.

The three soft brain tissues white matter (WM), gray matter (GM), and cerebral spinal fluid (CSF) identified in a magnetic resonance (MR) image via image segmentation techniques can aid in structural and functional brain analysis, brain's anatomical structures measurement and visualization, neurodegenerative disorders diagnosis, and surgical planning and image-guided interventions, but only if obtained segmentation results are correct. This paper presents a multiple-classifier-based system for automatic brain tissue segmentation from cerebral MR images. The developed system categorizes each voxel of a given MR image as GM, WM, and CSF. The algorithm consists of preprocessing, feature extraction, and supervised classification steps. In the first step, intensity non-uniformity in a given MR image is corrected and then non-brain tissues such as skull, eyeballs, and skin are removed from the image. For each voxel, statistical features and non-statistical features were computed and used a feature vector representing the voxel. Three multilayer perceptron (MLP) neural networks trained using three different datasets were used as the base classifiers of the multiple-classifier system. The output of the base classifiers was fused using majority voting scheme. Evaluation of the proposed system was performed using Brainweb simulated MR images with different noise and intensity non-uniformity and internet brain segmentation repository (IBSR) real MR images. The quantitative assessment of the proposed method using Dice, Jaccard, and conformity coefficient metrics demonstrates improvement (around 5% for CSF) in terms of accuracy as compared to single MLP classifier and the existing methods and tools such FSL-FAST and SPM. As accurately segmenting a MR image is of paramount importance for successfully promoting the clinical application of MR image segmentation techniques, the improvement obtained by using multiple-classifier-based system is encouraging.

Comparison of accelerated T1-weighted whole-brain structural-imaging protocols

Imaging in neuroscience, clinical research and pharmaceutical trials often employs the 3D magnetisation-prepared rapid gradient-echo (MPRAGE) sequence to obtain structural T1-weighted images with high spatial resolution of the human brain. Typical research and clinical routine MPRAGE protocols with ~1mm isotropic resolution require data acquisition time in the range of 5–10min and often use only moderate two-fold acceleration factor for parallel imaging.Recent advances in MRI hardware and acquisition methodology promise improved leverage of the MR signal and more benign artefact properties in particular when employing increased acceleration factors in clinical routine and research. In this study, we examined four variants of a four-fold-accelerated MPRAGE protocol (2D-GRAPPA, CAIPIRINHA, CAIPIRINHA elliptical, and segmented MPRAGE) and compared clinical readings, basic image quality metrics (SNR, CNR), and automated brain tissue segmentation for morphological assessments of brain structures. The results were benchmarked against a widely-used two-fold-accelerated 3T ADNI MPRAGE protocol that served as reference in this study.22 healthy subjects (age=20–44yrs.) were imaged with all MPRAGE variants in a single session. An experienced reader rated all images of clinically useful image quality. CAIPIRINHA MPRAGE scans were perceived on average to be of identical value for reading as the reference ADNI-2 protocol. SNR and CNR measurements exhibited the theoretically expected performance at the four-fold acceleration.The results of this study demonstrate that the four-fold accelerated protocols introduce systematic biases in the segmentation results of some brain structures compared to the reference ADNI-2 protocol. Furthermore, results suggest that the increased noise levels in the accelerated protocols play an important role in introducing these biases, at least under the present study conditions.

Discriminative Clustering and Feature Selection for Brain MRI Segmentation

Automatic segmentation of brain tissues from MRI is of great importance for clinical application and scientific research. Recent advancements in supervoxel-level analysis enable robust segmentation of brain tissues by exploring the inherent information among multiple features extracted on the supervoxels. Within this prevalent framework, the difficulties still remain in clustering uncertainties imposed by the heterogeneity of tissues and the redundancy of the MRI features. To cope with the aforementioned two challenges, we propose a robust discriminative segmentation method from the view of information theoretic learning. The prominent goal of the method is to simultaneously select the informative feature and to reduce the uncertainties of supervoxel assignment for discriminative brain tissue segmentation. Experiments on two brain MRI datasets verified the effectiveness and efficiency of the proposed approach.

Quantifying brain tissue volume in multiple sclerosis with automated lesion segmentation and filling.

Lesion filling has been successfully applied to reduce the effect of hypo-intense T1-w Multiple Sclerosis (MS) lesions on automatic brain tissue segmentation. However, a study of fully automated pipelines incorporating lesion segmentation and lesion filling on tissue volume analysis has not yet been performed. Here, we analyzed the % of error introduced by automating the lesion segmentation and filling processes in the tissue segmentation of 70 clinically isolated syndrome patient images. First of all, images were processed using the LST and SLS toolkits with different pipeline combinations that differed in either automated or manual lesion segmentation, and lesion filling or masking out lesions. Then, images processed following each of the pipelines were segmented into gray matter (GM) and white matter (WM) using SPM8, and compared with the same images where expert lesion annotations were filled before segmentation. Our results showed that fully automated lesion segmentation and filling pipelines reduced significantly the % of error in GM and WM volume on images of MS patients, and performed similarly to the images where expert lesion annotations were masked before segmentation. In all the pipelines, the amount of misclassified lesion voxels was the main cause in the observed error in GM and WM volume. However, the % of error was significantly lower when automatically estimated lesions were filled and not masked before segmentation. These results are relevant and suggest that LST and SLS toolboxes allow the performance of accurate brain tissue volume measurements without any kind of manual intervention, which can be convenient not only in terms of time and economic costs, but also to avoid the inherent intra/inter variability between manual annotations.

Early diagnosis of Alzheimer׳s disease based on partial least squares, principal component analysis and support vector machine using segmented MRI images

Computer aided diagnosis (CAD) systems using functional and structural imaging techniques enable physicians to detect early stages of the Alzheimer׳s disease (AD). For this purpose, magnetic resonance imaging (MRI) have been proved to be very useful in the assessment of pathological tissues in AD. This paper presents a new CAD system that allows the early AD diagnosis using tissue-segmented brain images. The proposed methodology aims to discriminate between AD, mild cognitive impairment (MCI) and elderly normal control (NC) subjects and is based on several multivariate approaches, such as partial least squares (PLS) and principal component analysis (PCA). In this study, 188 AD patients, 401 MCI patients and 229 control subjects from the Alzheimer׳s Disease Neuroimaging Initiative (ADNI) database were studied. Automated brain tissue segmentation was performed for each image obtaining gray matter (GM) and white matter (WM) tissue distributions. The validity of the analyzed methods was tested on the ADNI database by implementing support vector machine classifiers with linear or radial basis function (RBF) kernels to distinguish between normal subjects and AD patients. The performance of our methodology is validated using k-fold cross technique where the system based on PLS feature extraction and linear SVM classifier outperformed the PCA method. In addition, PLS feature extraction is found to be more effective for extracting discriminative information from the data. In this regard, the developed latter CAD system yielded maximum sensitivity, specificity and accuracy values of 85.11%, 91.27% and 88.49%, respectively.

PO-0453 Maturational Changes In Cortical Folding In Extremely Preterm Infants

Background and aim Our aim was to analyse the development of cortical morphology in preterm infants, as alterations in cortical folding affect functional development. Methods MRI was performed at 30 and 40 weeks corrected age in 19 preterm born infants (gestational age (GA) 24.71–27.86 wks, 11 males). After automatic brain tissue segmentation, 1 a 3D reconstruction of the inner cortical surface was computed and cortical sulci were labelled with Brainvisa software. 2 We measured global sulcal index (SI=folded/unfolded surface areas), and per sulcus surface area (SA, mm 2 ) and mean geodesic depth (MGD, mm), all corrected for scan-age. Results In 10 weeks, SI increased from 0.18 to 1.08 (6 times, 40 wks: right > left). Central sulcus, lateral fissure, and insula increased more in SA (resp. 2.3, 2.6, 1.7-times) than in MGD (resp.1.2, 1.1, 1.3-times). The superior temporal sulcus (STS) expanded in SA with factor 16.3 left and 12.6 right (30 wks: right > left), and factor 1.6 in MGD (30 and 40 wks: right > left). White matter injury in these infants (9 IVH,1 PVHI, 4 treated for PHVD) or GA did not significantly influence cortical morphology changes. Conclusion Over this short period, cortical folding is immense in preterm newborns, and shows inter-hemispherical asymmetries. Sulci increased more in surface area than in depth, STS showed the largest increase. The influence of brain injury on cortical morphology needs to be elucidated in a larger cohort. References Chita S, et al. Medical Imaging (2013) Perrot M, et al. Medical Image Analysis (2011)

Automatic Brain Tissue Segmentation of Multi-sequence MR Images Using Random Decision Forests

This work is integrated in the MICCAI Grand Challenge: MR Brain Image Segmentation 2013. It aims for the automatic segmentation of brain into Cerebrospinal fluid (CSF), Gray matter (GM) and White matter (WM). The provided dataset contains patients with white matter lesions, which makes the segmentation task more challenging. The proposed algorithm uses multi-sequence MR images to extract meaningful features and learn a Random Decision Forest that classifies each voxel of the image. The results show that it is robust to the presence of the white matter lesions, and the metrics show that the overall results are competitive.

Auto-kNN: Brain Tissue Segmentation using Automatically Trained k-Nearest-Neighbor Classification

In this paper we applied one of our regularly used processing pipelines for fully automated brain tissue segmentation. Brain tissue was segmented in cerebrospinal fluid (CSF), gray matter (GM) and white matter (WM). Our algorithms for skull stripping, tissue segmentation and white matter lesion (WML) detection were slightly adapted and applied to twelve data sets within the MRBrainS13 brain tissue segmentation challenge. Skull stripping is performed using non-rigid registration of 5 atlas masks. Our tissue segmentation is based on an automatically trained kNN-classifier. Training samples were obtained by non-rigid registration of 5 manually labeled scans followed by a pruning step in feature space to remove any residual erroneously sampled tissue voxels. The kNN-classification incorporates voxel intensities from a T1-weighted scan and a FLAIR scan. The white matter lesion detection is based on an automatically determined threshold on the FLAIR scan. The application of the algorithms on the data from the MRBrainS13 Challenge showed that our pipeline produces acceptable segmentations. Average resulting Dice scores were 77.86 (CSF), 81.22 (GM), 87.27 (WM), 93.78 (total parenchyma), and 96.26 (all intracranial structures). Total processing time was about 2 hours per subject.

Contour-Based Brain Segmentation Method for Magnetic Resonance Imaging Human Head Scans

The high-resolution magnetic resonance brain images often contain some nonbrain tissues (ie, skin, fat, muscle, neck, eye balls, etc) compared with the functional images such as positron emission tomography, single-photon emission computed tomography, and functional magnetic resonance imaging (MRI) scans, which usually contain few nonbrain tissues. Automatic segmentation of brain tissues from MRI scans remains a challenging task due to the variation in shape and size, use of different pulse sequences, overlapping signal intensities and imaging artifacts. This article presents a contour-based automatic brain segmentation method to segment the brain regions from T1-, T2-, and proton density-weighted MRI of human head scans. The proposed method consists of 2 stages. In stage 1, the brain regions in the middle slice is extracted. Many of the existing methods failed to extract brain regions in the lower and upper slices of the brain volume, where the brain appears in more than 1 connected region. To overcome this problem, in the proposed method, a landmark circle is drawn at the center of the extracted brain region of a middle slice and is likely to pass through all the brain regions in the remaining lower and upper slices irrespective of whether the brain is composed of 1 or more connected components. In stage 2, the brain regions in the remaining slices are extracted with reference to the landmark circle obtained in stage 1. The proposed method is robust to the variability of brain anatomy, image orientation, and image type, and it extracts the brain regions accurately in T1-, T2-, and proton density-weighted normal and abnormal brain images. Experimental results by applying the proposed method on 100 volumes of brain images show that the proposed method exhibits best and consistent performance than by the popular existing methods brain extraction tool, brain surface extraction, watershed algorithm, hybrid watershed algorithm, and skull stripping using graph cuts.

BRAIN TUMOR TISSUE CATEGORIZATION IN 3D MAGNETIC RESONANCE IMAGES USING IMPROVED PSO FOR EXTREME LEARNING MACHINE

Magnetic Resonance Imaging (MRI) technique is one of the most useful diagnostic tools for human soft tissue analysis. Moreover, the brain anatomy features and internal tissue architecture of brain tumor are a complex task in case of 3-D anatomy. The additional spatial relationship in transverse, longitudinal planes and the coronal plane information has been proved to be helpful for clinical applications. This study extends the computation of gray level co- occurrence matrix (GLCM) and Run length matrix (RLM) to a three- dimensional form for feature extraction. The sub-selection of rich optimal bank of features to model a classifler is achieved with custom Genetic Algorithm design. An improved Extreme Learning Machine (ELM) classifler algorithm is explored, for training single hidden layer artiflcial neural network, integrating an enhanced swarm-based method in optimization of the best parameters (input-weights, bias, norm and hidden neurons), enhancing generalization and conditioning of the algorithm. The method is modeled for automatic brain tissue and pathological tumor classiflcation and segmentation of 3D MRI tumor images. The method proposed demonstrates good generalization capability from the best individuals obtained in the learning phase to handle sparse image data on publically available benchmark dataset and real time data sets.

Brain tissue segmentation based on spatial information fusion by Dempster-Shafer theory

As a result of noise and intensity non-uniformity, automatic segmentation of brain tissue in magnetic resonance imaging (MRI) is a challenging task. In this study a novel brain MRI segmentation approach is presented which employs Dempster-Shafer theory (DST) to perform information fusion. In the proposed method, fuzzy c-mean (FCM) is applied to separate features and then the outputs of FCM are interpreted as basic belief structures. The salient aspect of this paper is the interpretation of each FCM output as a belief structure with particular focal elements. The results of the proposed method are evaluated using Dice similarity and Accuracy indices. Qualitative and quantitative comparisons show that our method performs better and is more robust than the existing method.

Automatic segmentation of brain tissue based on improvedfuzzy c means clustering algorithm

In medical images, exist often a lot of noise, the noise will seriously affect the accuracy of the segmentation results. The traditional standard fuzzy c-means(FCM) algorithm in image segmentation do not taken into account the relationship the adjacent pixels, which leads to the standard fuzzy c-means(FCM) algorithm is very sensitive to noise in the image. Proposed improvedfuzzy c-means(FCM) algorithm, taking both the local and non-local information into the standard fuzzy c-means(FCM) clustering algorithm. The ex-periment results can show that the improved algorithm can achieve better effect than other methods of brain tissue segmentation.

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

Most current automated segmentation methods are performed on T1- or T2-weighted MR images, relying on relative image intensity that is dependent on other MR parameters and sensitive to B1 magnetic field inhomogeneity. Here, we propose an image segmentation method based on quantitative longitudinal magnetization relaxation time (T1) 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.