Gaussian mixture model-based segmentation of MR images taken from premature infant brains

Methods of Brain Extraction from Magnetic Resonance Images of Human Head: A Review

Medical images are providing vital information to aid physicians in diagnosing a disease afflicting the organ of a human body. Magnetic resonance imaging is an important imaging modality in capturing the soft tissues of the brain. Segmenting and extracting the brain is essential in studying the structure and pathological condition of brain. There are several methods that are developed for this purpose. Researchers in brain extraction or segmentation need to know the current status of the work that have been done. Such an information is also important for improving the existing method to get more accurate results or to reduce the complexity of the algorithm. In this paper we review the classical methods and convolutional neural network-based deep learning brain extraction methods.

State-of-the-Art Traditional to the Machine- and Deep-Learning-Based Skull Stripping Techniques, Models, and Algorithms

Several neuroimaging processing applications consider skull stripping as a crucial pre-processing step. Due to complex anatomical brain structure and intensity variations in brain magnetic resonance imaging (MRI), an appropriate skull stripping is an important part. The process of skull stripping basically deals with the removal of the skull region for clinical analysis in brain segmentation tasks, and its accuracy and efficiency are quite crucial for diagnostic purposes. It requires more accurate and detailed methods for differentiating brain regions and the skull regions and is considered as a challenging task. This paper is focused on the transition of the conventional to the machine- and deep-learning-based automated skull stripping methods for brain MRI images. It is observed in this study that deep learning approaches have outperformed conventional and machine learning techniques in many ways, but they have their limitations. It also includes the comparative analysis of the current state-of-the-art skull stripping methods, a critical discussion of some challenges, model of quantifying parameters, and future work directions.

Adaptive and Efficient Mixture-Based Representation for Range Data

Modern range sensors generate millions of data points per second, making it difficult to utilize all incoming data effectively in real time for devices with limited computational resources. The Gaussian mixture model (GMM) is a convenient and essential tool commonly used in many research domains. In this paper, an environment representation approach based on the hierarchical GMM structure is proposed, which can be utilized to model environments with weighted Gaussians. The hierarchical structure accelerates training by recursively segmenting local environments into smaller clusters. By adopting the information-theoretic distance and shape of probabilistic distributions, weighted Gaussians can be dynamically allocated to local environments in an arbitrary scale, leading to a full adaptivity in the number of Gaussians. Evaluations are carried out in terms of time efficiency, reconstruction, and fidelity using datasets collected from different sensors. The results demonstrate that the proposed approach is superior with respect to time efficiency while maintaining the high fidelity as compared to other state-of-the-art approaches.

3D U-Net for Skull Stripping in Brain MRI

Skull stripping in brain magnetic resonance imaging (MRI) is an essential step to analyze images of the brain. Although manual segmentation has the highest accuracy, it is a time-consuming task. Therefore, various automatic segmentation algorithms of the brain in MRI have been devised and proposed previously. However, there is still no method that solves the entire brain extraction problem satisfactorily for diverse datasets in a generic and robust way. To address these shortcomings of existing methods, we propose the use of a 3D-UNet for skull stripping in brain MRI. The 3D-UNet was recently proposed and has been widely used for volumetric segmentation in medical images due to its outstanding performance. It is an extended version of the previously proposed 2D-UNet, which is based on a deep learning network, specifically, the convolutional neural network. We evaluated 3D-UNet skull-stripping using a publicly available brain MRI dataset and compared the results with three existing methods (BSE, ROBEX, and Kleesiek’s method; BSE and ROBEX are two conventional methods, and Kleesiek’s method is based on deep learning). The 3D-UNet outperforms two typical methods and shows comparable results with the specific deep learning-based algorithm, exhibiting a mean Dice coefficient of 0.9903, a sensitivity of 0.9853, and a specificity of 0.9953.

Anatomy-guided joint tissue segmentation and topological correction for 6-month infant brain MRI with risk of autism

Tissue segmentation of infant brain MRIs with risk of autism is critically important for characterizing early brain development and identifying biomarkers. However, it is challenging due to low tissue contrast caused by inherent ongoing myelination and maturation. In particular, at around 6 months of age, the voxel intensities in both gray matter and white matter are within similar ranges, thus leading to the lowest image contrast in the first postnatal year. Previous studies typically employed intensity images and tentatively estimated tissue probabilities to train a sequence of classifiers for tissue segmentation. However, the important prior knowledge of brain anatomy is largely ignored during the segmentation. Consequently, the segmentation accuracy is still limited and topological errors frequently exist, which will significantly degrade the performance of subsequent analyses. Although topological errors could be partially handled by retrospective topological correction methods, their results may still be anatomically incorrect. To address these challenges, in this article, we propose an anatomy-guided joint tissue segmentation and topological correction framework for isointense infant MRI. Particularly, we adopt a signed distance map with respect to the outer cortical surface as anatomical prior knowledge, and incorporate such prior information into the proposed framework to guide segmentation in ambiguous regions. Experimental results on the subjects acquired from National Database for Autism Research demonstrate the effectiveness to topological errors and also some levels of robustness to motion. Comparisons with the state-of-the-art methods further demonstrate the advantages of the proposed method in terms of both segmentation accuracy and topological correctness.

A Heavy Tailed Expectation Maximization Hidden Markov Random Field Model with Applications to Segmentation of MRI

A wide range of segmentation approaches assumes that intensity histograms extracted from magnetic resonance images (MRI) have a distribution for each brain tissue that can be modeled by a Gaussian distribution or a mixture of them. Nevertheless, intensity histograms of White Matter and Gray Matter are not symmetric and they exhibit heavy tails. In this work, we present a hidden Markov random field model with expectation maximization (EM-HMRF) modeling the components using the α-stable distribution. The proposed model is a generalization of the widely used EM-HMRF algorithm with Gaussian distributions. We test the α-stable EM-HMRF model in synthetic data and brain MRI data. The proposed methodology presents two main advantages: Firstly, it is more robust to outliers. Secondly, we obtain similar results than using Gaussian when the Gaussian assumption holds. This approach is able to model the spatial dependence between neighboring voxels in tomographic brain MRI.

Methods on Skull Stripping of MRI Head Scan Images-a Review

The high resolution magnetic resonance (MR) brain images contain some non-brain tissues such as skin, fat, muscle, neck, and eye balls compared to the functional images namely positron emission tomography (PET), single photon emission computed tomography (SPECT), and functional magnetic resonance imaging (fMRI) which usually contain relatively less non-brain tissues. The presence of these non-brain tissues is considered as a major obstacle for automatic brain image segmentation and analysis techniques. Therefore, quantitative morphometric studies of MR brain images often require a preliminary processing to isolate the brain from extra-cranial or non-brain tissues, commonly referred to as skull stripping. This paper describes the available methods on skull stripping and an exploratory review of recent literature on the existing skull stripping methods.

Automatic Tissue Segmentation of Neonate Brain MR Images with Subject-specific Atlases

Automatic tissue segmentation of the neonate brain using Magnetic Resonance Images (MRI) is extremely important to study brain development and perform early diagnostics but is challenging due to high variability and inhomogeneity in contrast throughout the image due to incomplete myelination of the white matter tracts. For these reasons, current methods often totally fail or give unsatisfying results. Furthermore, most of the subcortical midbrain structures are misclassified due to a lack of contrast in these regions. We have developed a novel method that creates a probabilistic subject-specific atlas based on a population atlas currently containing a number of manually segmented cases. The generated subject-specific atlas is sharp and adapted to the subject that is being processed. We then segment brain tissue classes using the newly created atlas with a single-atlas expectation maximization based method. Our proposed method leads to a much lower failure rate in our experiments. The overall segmentation results are considerably improved when compared to using a non-subject-specific, population average atlas. Additionally, we have incorporated diffusion information obtained from Diffusion Tensor Images (DTI) to improve the detection of white matter that is not visible at this early age in structural MRI (sMRI) due to a lack of myelination. Although this necessitates the acquisition of an additional sequence, the diffusion information improves the white matter segmentation throughout the brain, especially for the mid-brain structures such as the corpus callosum and the internal capsule.

LINKS: learning-based multi-source IntegratioN frameworK for Segmentation of infant brain images

Segmentation of infant brain MR images is challenging due to insufficient image quality, severe partial volume effect, and ongoing maturation and myelination processes. In the first year of life, the image contrast between white and gray matters of the infant brain undergoes dramatic changes. In particular, the image contrast is inverted around 6-8months of age, and the white and gray matter tissues are isointense in both T1- and T2-weighted MR images and thus exhibit the extremely low tissue contrast, which poses significant challenges for automated segmentation. Most previous studies used multi-atlas label fusion strategy, which has the limitation of equally treating the different available image modalities and is often computationally expensive. To cope with these limitations, in this paper, we propose a novel learning-based multi-source integration framework for segmentation of infant brain images. Specifically, we employ the random forest technique to effectively integrate features from multi-source images together for tissue segmentation. Here, the multi-source images include initially only the multi-modality (T1, T2 and FA) images and later also the iteratively estimated and refined tissue probability maps of gray matter, white matter, and cerebrospinal fluid. Experimental results on 119 infants show that the proposed method achieves better performance than other state-of-the-art automated segmentation methods. Further validation was performed on the MICCAI grand challenge and the proposed method was ranked top among all competing methods. Moreover, to alleviate the possible anatomical errors, our method can also be combined with an anatomically-constrained multi-atlas labeling approach for further improving the segmentation accuracy.

Automatic segmentation of corpus callosum using Gaussian mixture modeling and Fuzzy C means methods

This paper presents a comparative study of the success and performance of the Gaussian mixture modeling and Fuzzy C means methods to determine the volume and cross-sectionals areas of the corpus callosum (CC) using simulated and real MR brain images. The Gaussian mixture model (GMM) utilizes weighted sum of Gaussian distributions by applying statistical decision procedures to define image classes. In the Fuzzy C means (FCM), the image classes are represented by certain membership function according to fuzziness information expressing the distance from the cluster centers. In this study, automatic segmentation for midsagittal section of the CC was achieved from simulated and real brain images. The volume of CC was obtained using sagittal sections areas. To compare the success of the methods, segmentation accuracy, Jaccard similarity and time consuming for segmentation were calculated. The results show that the GMM method resulted by a small margin in more accurate segmentation (midsagittal section segmentation accuracy 98.3% and 97.01% for GMM and FCM); however the FCM method resulted in faster segmentation than GMM. With this study, an accurate and automatic segmentation system that allows opportunity for quantitative comparison to doctors in the planning of treatment and the diagnosis of diseases affecting the size of the CC was developed. This study can be adapted to perform segmentation on other regions of the brain, thus, it can be operated as practical use in the clinic.

Segmentation of neonatal brain MR images using patch-driven level sets

The segmentation of neonatal brain MR image into white matter (WM), gray matter (GM), and cerebrospinal fluid (CSF), is challenging due to the low spatial resolution, severe partial volume effect, high image noise, and dynamic myelination and maturation processes. Atlas-based methods have been widely used for guiding neonatal brain segmentation. Existing brain atlases were generally constructed by equally averaging all the aligned template images from a population. However, such population-based atlases might not be representative of a testing subject in the regions with high inter-subject variability and thus often lead to a low capability in guiding segmentation in those regions. Recently, patch-based sparse representation techniques have been proposed to effectively select the most relevant elements from a large group of candidates, which can be used to generate a subject-specific representation with rich local anatomical details for guiding the segmentation. Accordingly, in this paper, we propose a novel patch-driven level set method for the segmentation of neonatal brain MR images by taking advantage of sparse representation techniques. Specifically, we first build a subject-specific atlas from a library of aligned, manually segmented images by using sparse representation in a patch-based fashion. Then, the spatial consistency in the probability maps from the subject-specific atlas is further enforced by considering the similarities of a patch with its neighboring patches. Finally, the probability maps are integrated into a coupled level set framework for more accurate segmentation. The proposed method has been extensively evaluated on 20 training subjects using leave-one-out cross validation, and also on 132 additional testing subjects. Our method achieved a high accuracy of 0.919±0.008 for white matter and 0.901±0.005 for gray matter, respectively, measured by Dice ratio for the overlap between the automated and manual segmentations in the cortical region.

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 prior probability and spatial temporal intensity change estimation for segmentation of the one-year-old human brain

The degree of white matter (WM) myelination is rather inhomogeneous across the brain. White matter appears differently across the cortical lobes in MR images acquired during early postnatal development. Specifically at 1-year of age, the gray/white matter contrast of MR T1 and T2 weighted images in prefrontal and temporal lobes is reduced as compared to the rest of the brain, and thus, tissue segmentation results commonly show lower accuracy in these lobes. In this novel work, we propose the use of spatial intensity growth maps (IGM) for T1 and T2 weighted images to compensate for local appearance inhomogeneity. The IGM captures expected intensity changes from 1 to 2 years of age, as appearance homogeneity is greatly improved by the age of 24 months. The IGM was computed as the coefficient of a voxel-wise linear regression model between corresponding intensities at 1 and 2 years. The proposed IGM method revealed low regression values of 1-10% in GM and CSF regions, as well as in WM regions at maturation stage of myelination at 1 year. However, in the prefrontal and temporal lobes we observed regression values of 20-25%, indicating that the IGM appropriately captures the expected large intensity change in these lobes mainly due to myelination. The IGM is applied to cross-sectional MRI datasets of 1-year-old subjects via registration, correction and tissue segmentation of the IGM-corrected dataset. We validated our approach in a small leave-one-out study of images with known, manual 'ground truth' segmentations.

An accurate skull stripping method based on simplex meshes and histogram analysis for magnetic resonance images

Skull stripping methods are designed to eliminate the non-brain tissue in magnetic resonance (MR) brain images. Removal of non-brain tissues is a fundamental step in enabling the processing of brain MR images. The aim of this study is to develop an automatic accurate skull stripping method based on deformable models and histogram analysis. A rough-segmentation step is used to find the optimal starting point for the deformation and is based on thresholds and morphological operators. Thresholds are computed using comparisons with an atlas, and modeling by Gaussians. The deformable model is based on a simplex mesh and its deformation is controlled by the image local gray levels and the information obtained on the gray level modeling of the rough-segmentation. Our Simplex Mesh and Histogram Analysis Skull Stripping (SMHASS) method was tested on the following international databases commonly used in scientific articles: BrainWeb, Internet Brain Segmentation Repository (IBSR), and Segmentation Validation Engine (SVE). A comparison was performed against three of the best skull stripping methods previously published: Brain Extraction Tool (BET), Brain Surface Extractor (BSE), and Hybrid Watershed Algorithm (HWA). Performance was measured using the Jaccard index (J) and Dice coefficient (κ). Our method showed the best performance and differences were statistically significant (p<0.05): J=0.904 and κ=0.950 on BrainWeb; J=0.905 and κ=0.950 on IBSR; J=0.946 and κ=0.972 on SVE.

Optimized T1- and T2-weighted volumetric brain imaging as a diagnostic tool in very preterm neonates

BACKGROUND

T1- and T2-W MR sequences used for obtaining diagnostic information and morphometric measurements in the neonatal brain are frequently acquired using different imaging protocols. Optimizing one protocol for obtaining both kinds of information is valuable.

OBJECTIVE

To determine whether high-resolution T1- and T2-W volumetric sequences optimized for preterm brain imaging could provide both diagnostic and morphometric value.

MATERIALS AND METHODS

Thirty preterm neonates born between 24 and 32 weeks' gestational age were scanned during the first 2 weeks after birth. T1- and T2-W high-resolution sequences were optimized in terms of signal-to-noise ratio, contrast-to-noise ratio and scan time and compared to conventional spin-echo-based sequences.

RESULTS

No differences were found between conventional and high-resolution T1-W sequences for diagnostic confidence, image quality and motion artifacts. A preference for conventional over high-resolution T2-W sequences for image quality was observed. High-resolution T1 images provided better delineation of thalamic myelination and the superior temporal sulcus. No differences were found for detection of myelination and sulcation using conventional and high-resolution T2-W images.

CONCLUSION

High-resolution T1- and T2-W volumetric sequences can be used in clinical MRI in the very preterm brain to provide both diagnostic and morphometric information.