Skull stripping using graph cuts

Comparative performance evaluation of automated segmentation methods of hippocampus from magnetic resonance images of temporal lobe epilepsy patients

PURPOSE

Segmentation of the hippocampus from magnetic resonance (MR) images is a key task in the evaluation of mesial temporal lobe epilepsy (mTLE) patients. Several automated algorithms have been proposed although manual segmentation remains the benchmark. Choosing a reliable algorithm is problematic since structural definition pertaining to multiple edges, missing and fuzzy boundaries, and shape changes varies among mTLE subjects. Lack of statistical references and guidance for quantifying the reliability and reproducibility of automated techniques has further detracted from automated approaches. The purpose of this study was to develop a systematic and statistical approach using a large dataset for the evaluation of automated methods and establish a method that would achieve results better approximating those attained by manual tracing in the epileptogenic hippocampus.

METHODS

A template database of 195 (81 males, 114 females; age range 32-67 yr, mean 49.16 yr) MR images of mTLE patients was used in this study. Hippocampal segmentation was accomplished manually and by two well-known tools (FreeSurfer and hammer) and two previously published methods developed at their institution [Automatic brain structure segmentation (ABSS) and LocalInfo]. To establish which method was better performing for mTLE cases, several voxel-based, distance-based, and volume-based performance metrics were considered. Statistical validations of the results using automated techniques were compared with the results of benchmark manual segmentation. Extracted metrics were analyzed to find the method that provided a more similar result relative to the benchmark.

RESULTS

Among the four automated methods, ABSS generated the most accurate results. For this method, the Dice coefficient was 5.13%, 14.10%, and 16.67% higher, Hausdorff was 22.65%, 86.73%, and 69.58% lower, precision was 4.94%, -4.94%, and 12.35% higher, and the root mean square (RMS) was 19.05%, 61.90%, and 65.08% lower than LocalInfo, FreeSurfer, and hammer, respectively. The Bland-Altman similarity analysis revealed a low bias for the ABSS and LocalInfo techniques compared to the others.

CONCLUSIONS

The ABSS method for automated hippocampal segmentation outperformed other methods, best approximating what could be achieved by manual tracing. This study also shows that four categories of input data can cause automated segmentation methods to fail. They include incomplete studies, artifact, low signal-to-noise ratio, and inhomogeneity. Different scanner platforms and pulse sequences were considered as means by which to improve reliability of the automated methods. Other modifications were specially devised to enhance a particular method assessed in this study.

Multigrid Nonlocal Gaussian Mixture Model for Segmentation of Brain Tissues in Magnetic Resonance Images

We propose a novel segmentation method based on regional and nonlocal information to overcome the impact of image intensity inhomogeneities and noise in human brain magnetic resonance images. With the consideration of the spatial distribution of different tissues in brain images, our method does not need preestimation or precorrection procedures for intensity inhomogeneities and noise. A nonlocal information based Gaussian mixture model (NGMM) is proposed to reduce the effect of noise. To reduce the effect of intensity inhomogeneity, the multigrid nonlocal Gaussian mixture model (MNGMM) is proposed to segment brain MR images in each nonoverlapping multigrid generated by using a new multigrid generation method. Therefore the proposed model can simultaneously overcome the impact of noise and intensity inhomogeneity and automatically classify 2D and 3D MR data into tissues of white matter, gray matter, and cerebral spinal fluid. To maintain the statistical reliability and spatial continuity of the segmentation, a fusion strategy is adopted to integrate the clustering results from different grid. The experiments on synthetic and clinical brain MR images demonstrate the superior performance of the proposed model comparing with several state-of-the-art algorithms.

Robust Skull-Stripping Segmentation Based on Irrational Mask for Magnetic Resonance Brain Images

This paper proposes a new method for simple, efficient, and robust removal of the non-brain tissues in MR images based on an irrational mask for filtration within a binary morphological operation framework. The proposed skull-stripping segmentation is based on two irrational 3 × 3 and 5 × 5 masks, having the sum of its weights equal to the transcendental number π value provided by the Gregory-Leibniz infinite series. It allows maintaining a lower rate of useful pixel loss. The proposed method has been tested in two ways. First, it has been validated as a binary method by comparing and contrasting with Otsu's, Sauvola's, Niblack's, and Bernsen's binary methods. Secondly, its accuracy has been verified against three state-of-the-art skull-stripping methods: the graph cuts method, the method based on Chan-Vese active contour model, and the simplex mesh and histogram analysis skull stripping. The performance of the proposed method has been assessed using the Dice scores, overlap and extra fractions, and sensitivity and specificity as statistical methods. The gold standard has been provided by two neurologist experts. The proposed method has been tested and validated on 26 image series which contain 216 images from two publicly available databases: the Whole Brain Atlas and the Internet Brain Segmentation Repository that include a highly variable sample population (with reference to age, sex, healthy/diseased). The approach performs accurately on both standardized databases. The main advantage of the proposed method is its robustness and speed.

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.

Brain extraction in pediatric ADC maps, toward characterizing neuro-development in multi-platform and multi-institution clinical images

Apparent Diffusion Coefficient (ADC) maps can be used to characterize myelination and to detect abnormalities in the developing brain. However, given the normal variation in regional ADC with myelination, detection of abnormalities is difficult when based on visual assessment. Quantitative and automated analysis of pediatric ADC maps is thus desired but requires accurate brain extraction as the first step. Currently, most existing brain extraction methods are optimized for structural T1-weighted MR images of fully myelinated brains. Due to differences in age and image contrast, these approaches do not translate well to pediatric ADC maps. To address this problem, we present a multi-atlas brain extraction framework that has 1) specificity: designed and optimized specifically for pediatric ADC maps; 2) generality: applicable to multi-platform and multi-institution data, and to subjects at various neuro-developmental stages across the first 6 years of life; 3) accuracy: highly accurate compared to expert annotations; and 4) consistency: consistently accurate regardless of sources of data and ages of subjects. We show how we achieve these goals, via optimizing major components in a multi-atlas brain extraction framework, and via developing and evaluating new criteria for its atlas ranking component. Moreover, we demonstrate that these goals can be achieved with a fixed set of atlases and a fixed set of parameters, which opens doors for our optimized framework to be used in large-scale and multi-institution neuro-developmental and clinical studies. In a pilot study, we use this framework in a dataset containing scanner-generated ADC maps from 308 pediatric patients collected during the course of routine clinical care. Our framework leads to successful quantifications of the changes in whole-brain volumes and mean ADC values across the first 6 years of life.

Investigation of Fat Metabolism during Antiobesity Interventions by Magnetic Resonance Imaging and Spectroscopy

The focus of current treatments for obesity is to reduce the body weight or visceral fat, which requires longer duration to show effect. In this study, we investigated the short-term changes in fat metabolism in liver, abdomen, and skeletal muscle during antiobesity interventions including Sibutra mine treatment and diet restriction in obese rats using magnetic resonance imaging, magnetic resonance spectroscopy, and blood chemistry. Sibutramine is an antiobesity drug that results in weight loss by increasing satiety and energy expenditure. The Sibutramine-treated rats showed reduction of liver fat and intramyocellular lipids on day 3. The triglycerides (TG) decreased on day 1 and 3 compared to baseline (day 0). The early response/nonresponse in different fat depots will permit optimization of treatment for better clinical outcome rather than staying with a drug for longer periods.

Nonlocal intracranial cavity extraction

Automatic and accurate methods to estimate normalized regional brain volumes from MRI data are valuable tools which may help to obtain an objective diagnosis and followup of many neurological diseases. To estimate such regional brain volumes, the intracranial cavity volume (ICV) is often used for normalization. However, the high variability of brain shape and size due to normal intersubject variability, normal changes occurring over the lifespan, and abnormal changes due to disease makes the ICV estimation problem challenging. In this paper, we present a new approach to perform ICV extraction based on the use of a library of prelabeled brain images to capture the large variability of brain shapes. To this end, an improved nonlocal label fusion scheme based on BEaST technique is proposed to increase the accuracy of the ICV estimation. The proposed method is compared with recent state-of-the-art methods and the results demonstrate an improved performance both in terms of accuracy and reproducibility while maintaining a reduced computational burden.

Body fat partitioning does not explain the interethnic variation in insulin sensitivity among Asian ethnicity: the Singapore adults metabolism study

We previously showed that ethnicity modifies the association between adiposity and insulin resistance. We sought to determine whether differential body fat partitioning or abnormalities in muscle insulin signaling associated with higher levels of adiposity might underlie this observation. We measured the insulin sensitivity index (ISI), percentage of body fat (%body fat), visceral (VAT) and subcutaneous (SAT) adipose tissue, liver fat, and intramyocellular lipids (IMCL) in 101 Chinese, 82 Malays, and 81 South Asians, as well as phosphorylated (p)-Akt levels in cultured myoblasts from Chinese and South Asians. Lean Chinese and Malays had higher ISI than South Asians. Although the ISI was lower in all ethnic groups when %body fat was higher, this association was stronger in Chinese and Malays, such that no ethnic differences were observed in overweight individuals. These ethnic differences were observed even when %body fat was replaced with fat in other depots. Myoblasts obtained from lean South Asians had lower p-Akt levels than those from lean Chinese. Higher adiposity was associated with lower p-Akt levels in Chinese but not in South Asians, and no ethnic differences were observed in overweight individuals. With higher %body fat, Chinese exhibited smaller increases in deep SAT and IMCL compared with Malays and South Asians, which did not explain the ethnic differences observed. Our study suggests that body fat partitioning does not explain interethnic differences in insulin sensitivity among Asian ethnic groups. Although higher adiposity had greater effect on skeletal muscle insulin sensitivity among Chinese, obesity-independent pathways may be more relevant in South Asians.

Brain extraction based on locally linear representation-based classification

Brain extraction is an important procedure in brain image analysis. Although numerous brain extraction methods have been presented, enhancing brain extraction methods remains challenging because brain MRI images exhibit complex characteristics, such as anatomical variability and intensity differences across different sequences and scanners. To address this problem, we present a Locally Linear Representation-based Classification (LLRC) method for brain extraction. A novel classification framework is derived by introducing the locally linear representation to the classical classification model. Under this classification framework, a common label fusion approach can be considered as a special case and thoroughly interpreted. Locality is important to calculate fusion weights for LLRC; this factor is also considered to determine that Local Anchor Embedding is more applicable in solving locally linear coefficients compared with other linear representation approaches. Moreover, LLRC supplies a way to learn the optimal classification scores of the training samples in the dictionary to obtain accurate classification. The International Consortium for Brain Mapping and the Alzheimer's Disease Neuroimaging Initiative databases were used to build a training dataset containing 70 scans. To evaluate the proposed method, we used four publicly available datasets (IBSR1, IBSR2, LPBA40, and ADNI3T, with a total of 241 scans). Experimental results demonstrate that the proposed method outperforms the four common brain extraction methods (BET, BSE, GCUT, and ROBEX), and is comparable to the performance of BEaST, while being more accurate on some datasets compared with BEaST.

Knowledge-guided robust MRI brain extraction for diverse large-scale neuroimaging studies on humans and non-human primates

Accurate and robust brain extraction is a critical step in most neuroimaging analysis pipelines. In particular, for the large-scale multi-site neuroimaging studies involving a significant number of subjects with diverse age and diagnostic groups, accurate and robust extraction of the brain automatically and consistently is highly desirable. In this paper, we introduce population-specific probability maps to guide the brain extraction of diverse subject groups, including both healthy and diseased adult human populations, both developing and aging human populations, as well as non-human primates. Specifically, the proposed method combines an atlas-based approach, for coarse skull-stripping, with a deformable-surface-based approach that is guided by local intensity information and population-specific prior information learned from a set of real brain images for more localized refinement. Comprehensive quantitative evaluations were performed on the diverse large-scale populations of ADNI dataset with over 800 subjects (55∼90 years of age, multi-site, various diagnosis groups), OASIS dataset with over 400 subjects (18∼96 years of age, wide age range, various diagnosis groups), and NIH pediatrics dataset with 150 subjects (5∼18 years of age, multi-site, wide age range as a complementary age group to the adult dataset). The results demonstrate that our method consistently yields the best overall results across almost the entire human life span, with only a single set of parameters. To demonstrate its capability to work on non-human primates, the proposed method is further evaluated using a rhesus macaque dataset with 20 subjects. Quantitative comparisons with popularly used state-of-the-art methods, including BET, Two-pass BET, BET-B, BSE, HWA, ROBEX and AFNI, demonstrate that the proposed method performs favorably with superior performance on all testing datasets, indicating its robustness and effectiveness.

Brain extraction using the watershed transform from markers

Isolation of the brain from other tissue types in magnetic resonance (MR) images is an important step in many types of neuro-imaging research using both humans and animal subjects. The importance of brain extraction is well appreciated-numerous approaches have been published and the benefits of good extraction methods to subsequent processing are well known. We describe a tool-the marker based watershed scalper (MBWSS)-for isolating the brain in T1-weighted MR images built using filtering and segmentation components from the Insight Toolkit (ITK) framework. The key elements of MBWSS-the watershed transform from markers and aggressive filtering with large kernels-are techniques that have rarely been used in neuroimaging segmentation applications. MBWSS is able to reliably isolate the brain without expensive preprocessing steps, such as registration to an atlas, and is therefore useful as the first stage of processing pipelines. It is an informative example of the level of accuracy achievable without using priors in the form of atlases, shape models or libraries of examples. We validate the MBWSS using a publicly available dataset, a paediatric cohort, an adolescent cohort, intra-surgical scans and demonstrate flexibility of the approach by modifying the method to extract macaque brains.

Multi-atlas skull-stripping

RATIONALE AND OBJECTIVES

We present a new method for automatic brain extraction on structural magnetic resonance images, based on a multi-atlas registration framework.

MATERIALS AND METHODS

Our method addresses fundamental challenges of multi-atlas approaches. To overcome the difficulties arising from the variability of imaging characteristics between studies, we propose a study-specific template selection strategy, by which we select a set of templates that best represent the anatomical variations within the data set. Against the difficulties of registering brain images with skull, we use a particularly adapted registration algorithm that is more robust to large variations between images, as it adaptively aligns different regions of the two images based not only on their similarity but also on the reliability of the matching between images. Finally, a spatially adaptive weighted voting strategy, which uses the ranking of Jacobian determinant values to measure the local similarity between the template and the target images, is applied for combining coregistered template masks.

RESULTS

The method is validated on three different public data sets and obtained a higher accuracy than recent state-of-the-art brain extraction methods. Also, the proposed method is successfully applied on several recent imaging studies, each containing thousands of magnetic resonance images, thus reducing the manual correction time significantly.

CONCLUSIONS

The new method, available as a stand-alone software package for public use, provides a robust and accurate brain extraction tool applicable for both clinical use and large population studies.

iBEAT: A toolbox for infant brain magnetic resonance image processing

It's a great challenge to analyze infant brain MR images due to the small brain size and low contrast of the developing brain tissues. We have developed an Infant Brain Extraction and Analysis Toolbox (iBEAT) for various processing of magnetic resonance (MR) images of infant brains. Several major functions generally used in infant brain analysis are integrated in iBEAT, including image preprocessing, brain extraction, tissue segmentation, and brain labeling. The functions of brain extraction, tissue segmentation, and brain labeling are provided respectively by three state-of-the-art algorithms. First, a learning-based meta-algorithm which integrates a group of brain extraction results generated by the two existing brain extraction algorithms (BET and BSE) was implemented in iBEAT for extraction of infant brains from MR images. Second, a level-sets-based tissue segmentation algorithm that utilizes multimodality information, cortical thickness constraint, and longitudinal consistency constraint was also included in iBEAT for segmentation of infant brain tissues. Third, HAMMER (standing for Hierarchical Attribute Matching Mechanism for Elastic Registration) registration algorithm was further included in iBEAT to label regions of interest (ROIs) of infant brain images by warping the pre-labeled ROIs of a template to the infant brain image space. By integration of these state-of-the-art methods, iBEAT is able to segment and label infant brain MR images accurately. Moreover, it can process not only single-time-point images for cross-sectional studies, but also multiple-time-point images of the same infant for longitudinal studies. The performance of iBEAT has been comprehensively evaluated with hundreds of infant brain images. A Linux-based standalone package of iBEAT is freely available at http://www.nitrc.org/projects/ibeat .

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.

Skull stripping of neonatal brain MRI: using prior shape information with graph cuts

In this paper, we propose a novel technique for skull stripping of infant (neonatal) brain magnetic resonance images using prior shape information within a graph cut framework. Skull stripping plays an important role in brain image analysis and is a major challenge for neonatal brain images. Popular methods like the brain surface extractor (BSE) and brain extraction tool (BET) do not produce satisfactory results for neonatal images due to poor tissue contrast, weak boundaries between brain and non-brain regions, and low spatial resolution. Inclusion of prior shape information helps in accurate identification of brain and non-brain tissues. Prior shape information is obtained from a set of labeled training images. The probability of a pixel belonging to the brain is obtained from the prior shape mask and included in the penalty term of the cost function. An extra smoothness term is based on gradient information that helps identify the weak boundaries between the brain and non-brain region. Experimental results on real neonatal brain images show that compared to BET, BSE, and other methods, our method achieves superior segmentation performance for neonatal brain images and comparable performance for adult brain images.

Brain extraction from cerebral MRI volume using a hybrid level set based active contour neighborhood model

Background

The extraction of brain tissue from cerebral MRI volume is an important pre-procedure for neuroimage analyses. The authors have developed an accurate and robust brain extraction method using a hybrid level set based active contour neighborhood model.

Methods

The method uses a nonlinear speed function in the hybrid level set model to eliminate boundary leakage. When using the new hybrid level set model an active contour neighborhood model is applied iteratively in the neighborhood of brain boundary. A slice by slice contour initial method is proposed to obtain the neighborhood of the brain boundary. The method was applied to the internet brain MRI data provided by the Internet Brain Segmentation Repository (IBSR).

Results

In testing, a mean Dice similarity coefficient of 0.95±0.02 and a mean Hausdorff distance of 12.4±4.5 were obtained when performing our method across the IBSR data set (18 × 1.5 mm scans). The results obtained using our method were very similar to those produced using manual segmentation and achieved the smallest mean Hausdorff distance on the IBSR data.

Conclusions

An automatic method of brain extraction from cerebral MRI volume was achieved and produced competitively accurate results.

aBEAT: a toolbox for consistent analysis of longitudinal adult brain MRI

Longitudinal brain image analysis is critical for revealing subtle but complex structural and functional changes of brain during aging or in neurodevelopmental disease. However, even with the rapid increase of clinical research and trials, a software toolbox dedicated for longitudinal image analysis is still lacking publicly. To cater for this increasing need, we have developed a dedicated 4D Adult Brain Extraction and Analysis Toolbox (aBEAT) to provide robust and accurate analysis of the longitudinal adult brain MR images. Specially, a group of image processing tools were integrated into aBEAT, including 4D brain extraction, 4D tissue segmentation, and 4D brain labeling. First, a 4D deformable-surface-based brain extraction algorithm, which can deform serial brain surfaces simultaneously under temporal smoothness constraint, was developed for consistent brain extraction. Second, a level-sets-based 4D tissue segmentation algorithm that incorporates local intensity distribution, spatial cortical-thickness constraint, and temporal cortical-thickness consistency was also included in aBEAT for consistent brain tissue segmentation. Third, a longitudinal groupwise image registration framework was further integrated into aBEAT for consistent ROI labeling by simultaneously warping a pre-labeled brain atlas to the longitudinal brain images. The performance of aBEAT has been extensively evaluated on a large number of longitudinal MR T1 images which include normal and dementia subjects, achieving very promising results. A Linux-based standalone package of aBEAT is now freely available at http://www.nitrc.org/projects/abeat.

A two-stage rule-constrained seedless region growing approach for mandibular body segmentation in MRI

PURPOSE

Extraction of the mandible from 3D volumetric images is frequently required for surgical planning and evaluation. Image segmentation from MRI is more complex than CT due to lower bony signal-to-noise. An automated method to extract the human mandible body shape from magnetic resonance (MR) images of the head was developed and tested.

METHODS

Anonymous MR images data sets of the head from 12 subjects were subjected to a two-stage rule-constrained region growing approach to derive the shape of the body of the human mandible. An initial thresholding technique was applied followed by a 3D seedless region growing algorithm to detect a large portion of the trabecular bone (TB) regions of the mandible. This stage is followed with a rule-constrained 2D segmentation of each MR axial slice to merge the remaining portions of the TB regions with lower intensity levels. The two-stage approach was replicated to detect the cortical bone (CB) regions of the mandibular body. The TB and CB regions detected from the preceding steps were merged and subjected to a series of morphological processes for completion of the mandibular body region definition. Comparisons of the accuracy of segmentation between the two-stage approach, conventional region growing method, 3D level set method, and manual segmentation were made with Jaccard index, Dice index, and mean surface distance (MSD).

RESULTS

The mean accuracy of the proposed method is [Formula: see text] for Jaccard index, [Formula: see text] for Dice index, and [Formula: see text] mm for MSD. The mean accuracy of CRG is [Formula: see text] for Jaccard index, [Formula: see text] for Dice index, and [Formula: see text] mm for MSD. The mean accuracy of the 3D level set method is [Formula: see text] for Jaccard index, [Formula: see text] for Dice index, and [Formula: see text] mm for MSD. The proposed method shows improvement in accuracy over CRG and 3D level set.

CONCLUSION

Accurate segmentation of the body of the human mandible from MR images is achieved with the proposed two-stage rule-constrained seedless region growing approach. The accuracy achieved with the two-stage approach is higher than CRG and 3D level set.

LABEL: pediatric brain extraction using learning-based meta-algorithm

Magnetic resonance imaging of pediatric brain provides valuable information for early brain development studies. Automated brain extraction is challenging due to the small brain size and dynamic change of tissue contrast in the developing brains. In this paper, we propose a novel Learning Algorithm for Brain Extraction and Labeling (LABEL) specially for the pediatric MR brain images. The idea is to perform multiple complementary brain extractions on a given testing image by using a meta-algorithm, including BET and BSE, where the parameters of each run of the meta-algorithm are effectively learned from the training data. Also, the representative subjects are selected as exemplars and used to guide brain extraction of new subjects in different age groups. We further develop a level-set based fusion method to combine multiple brain extractions together with a closed smooth surface for obtaining the final extraction. The proposed method has been extensively evaluated in subjects of three representative age groups, such as neonate (less than 2 months), infant (1-2 years), and child (5-18 years). Experimental results show that, with 45 subjects for training (15 neonates, 15 infant, and 15 children), the proposed method can produce more accurate brain extraction results on 246 testing subjects (75 neonates, 126 infants, and 45 children), i.e., at average Jaccard Index of 0.953, compared to those by BET (0.918), BSE (0.902), ROBEX (0.901), GCUT (0.856), and other fusion methods such as Majority Voting (0.919) and STAPLE (0.941). Along with the largely-improved computational efficiency, the proposed method demonstrates its ability of automated brain extraction for pediatric MR images in a large age range.

Statistical 4D graphs for multi-organ abdominal segmentation from multiphase CT

The interpretation of medical images benefits from anatomical and physiological priors to optimize computer-aided diagnosis applications. Diagnosis also relies on the comprehensive analysis of multiple organs and quantitative measures of soft tissue. An automated method optimized for medical image data is presented for the simultaneous segmentation of four abdominal organs from 4D CT data using graph cuts. Contrast-enhanced CT scans were obtained at two phases: non-contrast and portal venous. Intra-patient data were spatially normalized by non-linear registration. Then 4D convolution using population training information of contrast-enhanced liver, spleen and kidneys was applied to multiphase data to initialize the 4D graph and adapt to patient-specific data. CT enhancement information and constraints on shape, from Parzen windows, and location, from a probabilistic atlas, were input into a new formulation of a 4D graph. Comparative results demonstrate the effects of appearance, enhancement, shape and location on organ segmentation. All four abdominal organs were segmented robustly and accurately with volume overlaps over 93.6% and average surface distances below 1.1mm.

A Simple and Fast Method of 3D Registration and Statistical Landmark Localization for Sparse Multi-Modal/Time-Series Neuroimages Based on Cortex Ellipse Fitting

Existing methods of neuroimage registration typically require high quality scans and are time-consuming. We propose a simple and fast method which allows intra-patient multi-modal and time-series neuroimage registration as well as landmark identification (including commissures and superior/inferior brain landmarks) for sparse data. The method is based on elliptical approximation of the brain cortical surface in the vicinity of the midsagittal plane (MSP). Scan registration is performed by a 3D affine transformation based on parameters of the cortex elliptical fit and by aligning the MSPs. The landmarks are computed using a statistical localization method based on analysis of 53 structural scans without detectable pathology. The method is illustrated for multi-modal registration, analysis of hemorrhagic stroke time series, and ischemic stroke follow ups, as well as for localization of hardly visible or not discernible landmarks in sparse neuroimages. The method also enables a statistical localization of landmarks in sparse morphological/non-morphological images, where landmark points may be invisible.

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.

Robust brain extraction across datasets and comparison with publicly available methods

Automatic whole-brain extraction from magnetic resonance images (MRI), also known as skull stripping, is a key component in most neuroimage pipelines. As the first element in the chain, its robustness is critical for the overall performance of the system. Many skull stripping methods have been proposed, but the problem is not considered to be completely solved yet. Many systems in the literature have good performance on certain datasets (mostly the datasets they were trained/tuned on), but fail to produce satisfactory results when the acquisition conditions or study populations are different. In this paper we introduce a robust, learning-based brain extraction system (ROBEX). The method combines a discriminative and a generative model to achieve the final result. The discriminative model is a Random Forest classifier trained to detect the brain boundary; the generative model is a point distribution model that ensures that the result is plausible. When a new image is presented to the system, the generative model is explored to find the contour with highest likelihood according to the discriminative model. Because the target shape is in general not perfectly represented by the generative model, the contour is refined using graph cuts to obtain the final segmentation. Both models were trained using 92 scans from a proprietary dataset but they achieve a high degree of robustness on a variety of other datasets. ROBEX was compared with six other popular, publicly available methods (BET, BSE, FreeSurfer, AFNI, BridgeBurner, and GCUT) on three publicly available datasets (IBSR, LPBA40, and OASIS, 137 scans in total) that include a wide range of acquisition hardware and a highly variable population (different age groups, healthy/diseased). The results show that ROBEX provides significantly improved performance measures for almost every method/dataset combination.

Simple paradigm for extra-cerebral tissue removal: algorithm and analysis

Extraction of the brain-i.e. cerebrum, cerebellum, and brain stem-from T1-weighted structural magnetic resonance images is an important initial step in neuroimage analysis. Although automatic algorithms are available, their inconsistent handling of the cortical mantle often requires manual interaction, thereby reducing their effectiveness. This paper presents a fully automated brain extraction algorithm that incorporates elastic registration, tissue segmentation, and morphological techniques which are combined by a watershed principle, while paying special attention to the preservation of the boundary between the gray matter and the cerebrospinal fluid. The approach was evaluated by comparison to a manual rater, and compared to several other leading algorithms on a publically available data set of brain images using the Dice coefficient and containment index as performance metrics. The qualitative and quantitative impact of this initial step on subsequent cortical surface generation is also presented. Our experiments demonstrate that our approach is quantitatively better than six other leading algorithms (with statistical significance on modern T1-weighted MR data). We also validated the robustness of the algorithm on a very large data set of over one thousand subjects, and showed that it can replace an experienced manual rater as preprocessing for a cortical surface extraction algorithm with statistically insignificant differences in cortical surface position.

Skull-stripping method for brain MRI using a 3D level set with a speedup operator

PURPOSE

To extract the brain region from brain magnetic resonance (MR) images using a fast 3D level set method and a refinement process.

MATERIALS AND METHODS

The proposed method introduces a speedup operator to the conventional 3D level set method in order to accelerate the level set evolution. While the processing time for brain extraction is reduced by the speedup operator, the accuracy of brain extraction is also improved by adopting a refinement process.

RESULTS

The speedup operator yielded a 75% reduction in the total iteration numbers for the synthesized volume. The proposed method was applied to several datasets and compared with previous methods, ie, BrainVisa, BET, and FreeSurfer. The proposed method provided a Jaccard index of 0.971 ± 0.0114 for the BrainWeb dataset, 0.864 ± 0.035 for the IBSR dataset, and 0.9414 ± 0.0517 for a self-produced dataset acquired with a 3T MRI system.

CONCLUSION

Utilizing a speedup operator, the proposed method reduced the evolution time. Robust and accurate results for various datasets were obtained in experiments.

Atlas-based automated positioning of outer volume suppression slices in short-echo time 3D MR spectroscopic imaging of the human brain

Spatial suppression of peripheral lipid-containing regions in volumetric MR spectroscopic imaging of the human brain requires placing large numbers of outer volume suppression (OVS) slices, which is time-consuming, prone to operator error and may introduce subject-dependent variability in volume coverage. We developed a novel, computationally efficient atlas-based approach for automated positioning of up to 16 OVS slices and the MR spectroscopic imaging slab. Standardized positions in Montreal Neurological Institute atlas space were established offline using a recently developed iterative optimization procedure. During the scanning session, positions in subject space were computed using affine transformation of standardized positions in Montreal Neurological Institute space. Offline analysis using magnetization prepared rapid gradient echo scans from 11 subjects demonstrated reliable OVS placement, comparable with but faster than iterative placement in subject space. This atlas-based method was further validated in 14 subjects using 3D short-echo time proton-echo-planar-spectroscopic-imaging at 3 T. Comparison of manual and automatic placement using 8 OVS slices demonstrated consistent MR spectroscopic imaging volume selection and comparable spectral quality with similar degree of lipid suppression and number of usable voxels. Automated positioning of 16 OVS slices enabled larger volume coverage, while maintaining similar spectral quality and lipid suppression. Atlas-based automatic prescription of short echo time MR spectroscopic imaging is expected to be advantageous for longitudinal and cross-sectional studies.

Automated brain extraction from T2-weighted magnetic resonance images

PURPOSE

To develop and implement an automated and robust technique to extract brain from T2-weighted images.

MATERIALS AND METHODS

Magnetic resonance imaging (MRI) was performed on 75 adult volunteers to acquire dual fast spin echo (FSE) images with fat-saturation technique on a 3T Philips scanner. Histogram-derived thresholds were derived directly from the original images followed by the application of regional labeling, regional connectivity, and mathematical morphological operations to extract brain from axial late-echo FSE (T2-weighted) images. The proposed technique was evaluated subjectively by an expert and quantitatively using Bland-Altman plot and Jaccard and Dice similarity measures.

RESULTS

Excellent agreement between the extracted brain volumes with the proposed technique and manual stripping by an expert was observed based on Bland-Altman plot and also as assessed by high similarity indices (Jaccard: 0.9825 ± 0.0045; Dice: 0.9912 ± 0.0023).

CONCLUSION

Brain extraction using the proposed automated methodology is robust and the results are reproducible.

Component analysis approach to estimation of tissue intensity distributions of 3D images

Many segmentation algorithms in medical imaging rely on accurate modeling and estimation of tissue intensity probability density functions. Gaussian mixture modeling, currently the most common approach, has several drawbacks, such as reliance on a Gaussian model and iterative local optimization used to estimate the model parameters. It also does not take advantage of substantially larger amount of data provided by 3D acquisitions, which are becoming standard in clinical environment. We propose a novel and completely non-parametric algorithm to estimate the tissue intensity probabilities in 3D images. Instead of relying on traditional framework of iterating between classification and estimation, we pose the problem as an instance of a blind source separation problem, where the unknown distributions are treated as sources and histograms of image subvolumes as mixtures. The new approach performed well on synthetic data and real magnetic resonance imaging (MRI) scans of the brain, robustly capturing intensity distributions of even small image structures and partial volume voxels.

A reproducible evaluation of ANTs similarity metric performance in brain image registration

The United States National Institutes of Health (NIH) commit significant support to open-source data and software resources in order to foment reproducibility in the biomedical imaging sciences. Here, we report and evaluate a recent product of this commitment: Advanced Neuroimaging Tools (ANTs), which is approaching its 2.0 release. The ANTs open source software library consists of a suite of state-of-the-art image registration, segmentation and template building tools for quantitative morphometric analysis. In this work, we use ANTs to quantify, for the first time, the impact of similarity metrics on the affine and deformable components of a template-based normalization study. We detail the ANTs implementation of three similarity metrics: squared intensity difference, a new and faster cross-correlation, and voxel-wise mutual information. We then use two-fold cross-validation to compare their performance on openly available, manually labeled, T1-weighted MRI brain image data of 40 subjects (UCLA's LPBA40 dataset). We report evaluation results on cortical and whole brain labels for both the affine and deformable components of the registration. Results indicate that the best ANTs methods are competitive with existing brain extraction results (Jaccard=0.958) and cortical labeling approaches. Mutual information affine mapping combined with cross-correlation diffeomorphic mapping gave the best cortical labeling results (Jaccard=0.669±0.022). Furthermore, our two-fold cross-validation allows us to quantify the similarity of templates derived from different subgroups. Our open code, data and evaluation scripts set performance benchmark parameters for this state-of-the-art toolkit. This is the first study to use a consistent transformation framework to provide a reproducible evaluation of the isolated effect of the similarity metric on optimal template construction and brain labeling.

Robust deformable-surface-based skull-stripping for large-scale studies

Skull-stripping refers to the separation of brain tissue from non-brain tissue, such as the scalp, skull, and dura. In large-scale studies involving a significant number of subjects, a fully automatic method is highly desirable, since manual skull-stripping requires tremendous human effort and can be inconsistent even after sufficient training. We propose in this paper a robust and effective method that is capable of skull-stripping a large number of images accurately with minimal dependence on the parameter setting. The key of our method involves an initial skull-stripping by co-registration of an atlas, followed by a refinement phase with a surface deformation scheme that is guided by prior information obtained from a set of real brain images. Evaluation based on a total of 831 images, consisting of normal controls (NC) and patients with mild cognitive impairment (MCI) or Alzheimer's Disease (AD), from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database indicates that our method performs favorably at a consistent overall overlap rate of approximately 98% when compared with expert results. The software package will be made available to the public to facilitate neuroimaging studies.

Robust skull stripping of clinical glioblastoma multiforme data

Skull stripping is the first step in many neuroimaging analyses and its success is critical to all subsequent processing. Methods exist to skull strip brain images without gross deformities, such as those affected by Alzheimer's and Huntington's disease. However, there are no techniques for extracting brains affected by diseases that significantly disturb normal anatomy. Glioblastoma multiforme (GBM) is such a disease, as afflicted individuals develop large tumors that often require surgical resection. In this paper, we extend the ROBEX skull stripping method to extract brains from GBM images. The proposed method uses a shape model trained on healthy brains to be relatively insensitive to lesions inside the brain. The brain boundary is then searched for potential resection cavities using adaptive thresholding and the Random Walker algorithm corrects for leakage into the ventricles. The results show significant improvement over three popular skull stripping algorithms (BET, BSE and HWA) in a dataset of 48 GBM cases.

Brain MAPS: an automated, accurate and robust brain extraction technique using a template library

Whole brain extraction is an important pre-processing step in neuroimage analysis. Manual or semi-automated brain delineations are labour-intensive and thus not desirable in large studies, meaning that automated techniques are preferable. The accuracy and robustness of automated methods are crucial because human expertise may be required to correct any suboptimal results, which can be very time consuming. We compared the accuracy of four automated brain extraction methods: Brain Extraction Tool (BET), Brain Surface Extractor (BSE), Hybrid Watershed Algorithm (HWA) and a Multi-Atlas Propagation and Segmentation (MAPS) technique we have previously developed for hippocampal segmentation. The four methods were applied to extract whole brains from 682 1.5T and 157 3T T(1)-weighted MR baseline images from the Alzheimer's Disease Neuroimaging Initiative database. Semi-automated brain segmentations with manual editing and checking were used as the gold-standard to compare with the results. The median Jaccard index of MAPS was higher than HWA, BET and BSE in 1.5T and 3T scans (p<0.05, all tests), and the 1st to 99th centile range of the Jaccard index of MAPS was smaller than HWA, BET and BSE in 1.5T and 3T scans ( p<0.05, all tests). HWA and MAPS were found to be best at including all brain tissues (median false negative rate ≤0.010% for 1.5T scans and ≤0.019% for 3T scans, both methods). The median Jaccard index of MAPS were similar in both 1.5T and 3T scans, whereas those of BET, BSE and HWA were higher in 1.5T scans than 3T scans (p<0.05, all tests). We found that the diagnostic group had a small effect on the median Jaccard index of all four methods. In conclusion, MAPS had relatively high accuracy and low variability compared to HWA, BET and BSE in MR scans with and without atrophy.

A head phantom prototype to verify subdural electrode localization tools in epilepsy surgery

When planning epilepsy surgery, the position of subdural electrodes in relation to the cortex is crucial. Electrodes may dislocate after implantation. Neurosurgeons are highly interested in the accuracy of methods that visualize these electrodes. In order to determine the accuracy of an electrode visualization method, we have developed a physical head phantom and evaluated our new method of subdural electrode localization. This method projects automatically segmented electrodes of a preimplantation computed tomography (CT) data set onto the segmented brain surface of a postimplantation magnetic resonance imaging (MRI) data set within 2 to 5 min. The phantom consists of a skull, an adipose layer for skin replication, and a deformable brain. It further contains gyri and sulci structures, composed of gelatin and different additives used as phantom material for white matter, gray matter, and cerebrospinal fluid. The phantom allows a well-defined displacement of an "implanted" electrode grid perpendicular to the brain surface. By using the phantom data, we demonstrated that our electrode visualization tool did in fact function accurately. The image contrasts between different phantom materials in MRI and CT phantom data sets were similar to patient data sets. The phantom appears suitable for obtaining a more complex patient data replication, as well as for simulating different deformation scenarios.