Colorization and automated segmentation of human T2 MR brain images for characterization of soft tissues

Characterization of tissues like brain by using magnetic resonance (MR) images and colorization of the gray scale image has been reported in the literature, along with the advantages and drawbacks. Here, we present two independent methods; (i) a novel colorization method to underscore the variability in brain MR images, indicative of the underlying physical density of bio tissue, (ii) a segmentation method (both hard and soft segmentation) to characterize gray brain MR images. The segmented images are then transformed into color using the above-mentioned colorization method, yielding promising results for manual tracing. Our color transformation incorporates the voxel classification by matching the luminance of voxels of the source MR image and provided color image by measuring the distance between them. The segmentation method is based on single-phase clustering for 2D and 3D image segmentation with a new auto centroid selection method, which divides the image into three distinct regions (gray matter (GM), white matter (WM), and cerebrospinal fluid (CSF) using prior anatomical knowledge). Results have been successfully validated on human T2-weighted (T2) brain MR images. The proposed method can be potentially applied to gray-scale images from other imaging modalities, in bringing out additional diagnostic tissue information contained in the colorized image processing approach as described.     

4D Multi-Modality Tissue Segmentation of Serial Infant Images

Accurate and consistent segmentation of infant brain MR images plays an important role in quantifying patterns of early brain development, especially in longitudinal studies. However, due to rapid maturation and myelination of brain tissues in the first year of life, the intensity contrast of gray and white matter undergoes dramatic changes. In fact, the contrast inverse around 6–8 months of age, when the white and gray matter tissues are isointense and hence exhibit the lowest contrast, posing significant challenges for segmentation algorithms. In this paper, we propose a longitudinally guided level set method to segment serial infant brain MR images acquired from 2 weeks up to 1.5 years of age, including the isointense images. At each single-time-point, the proposed method makes optimal use of T1, T2 and the diffusion-weighted images for complimentary tissue distribution information to address the difficulty caused by the low contrast. Moreover, longitudinally consistent term, which constrains the distance across the serial images within a biologically reasonable range, is employed to obtain temporally consistent segmentation results. Application of our method on 28 longitudinal infant subjects, each with 5 longitudinal scans, shows that the automated segmentations from the proposed method match the manual ground-truth with much higher Dice Ratios than other single-modality, single-time-point based methods and the longitudinal but voxel-wise based methods. The software of the proposed method is publicly available in NITRC (http://www.nitrc.org/projects/ibeat).     

3-Dimensional Diffusion Tensor Imaging (DTI) Atlas of the Rat Brain

Anatomical atlases play an important role in the analysis of neuroimaging data in rodent neuroimaging studies. Having a high resolution, detailed atlas not only can expand understanding of rodent brain anatomy, but also enables automatic segmentation of new images, thus greatly increasing the efficiency of future analysis when applied to new data. These atlases can be used to analyze new scans of individual cases using a variety of automated segmentation methods. This project seeks to develop a set of detailed 3D anatomical atlases of the brain at postnatal day 5 (P5), 14 (P14), and adults (P72) in Sprague-Dawley rats. Our methods consisted of first creating a template image based on fixed scans of control rats, then manually segmenting various individual brain regions on the template. Using itk-SNAP software, subcortical and cortical regions, including both white matter and gray matter structures, were manually segmented in the axial, sagittal, and coronal planes. The P5, P14, and P72 atlases had 39, 45, and 29 regions segmented, respectively. These atlases have been made available to the broader research community.     

Rough-Fuzzy Clustering and Unsupervised Feature Selection for Wavelet Based MR Image Segmentation

Image segmentation is an indispensable process in the visualization of human tissues, particularly during clinical analysis of brain magnetic resonance (MR) images. For many human experts, manual segmentation is a difficult and time consuming task, which makes an automated brain MR image segmentation method desirable. In this regard, this paper presents a new segmentation method for brain MR images, integrating judiciously the merits of rough-fuzzy computing and multiresolution image analysis technique. The proposed method assumes that the major brain tissues, namely, gray matter, white matter, and cerebrospinal fluid from the MR images are considered to have different textural properties. The dyadic wavelet analysis is used to extract the scale-space feature vector for each pixel, while the rough-fuzzy clustering is used to address the uncertainty problem of brain MR image segmentation. An unsupervised feature selection method is introduced, based on maximum relevance-maximum significance criterion, to select relevant and significant textural features for segmentation problem, while the mathematical morphology based skull stripping preprocessing step is proposed to remove the non-cerebral tissues like skull. The performance of the proposed method, along with a comparison with related approaches, is demonstrated on a set of synthetic and real brain MR images using standard validity indices.     

Correction of inhomogeneous magnetic resonance images using multiscale retinex for segmentation accuracy improvement

The purpose of this study was to improve the accuracy of tissue segmentation on brain magnetic resonance (MR) images preprocessed by multiscale retinex (MSR), segmented with a combined boosted decision tree (BDT) and MSR algorithm (hereinafter referred to as the MSRBDT algorithm). Simulated brain MR (SBMR) T1-weighted images of different noise levels and RF inhomogeneities were adopted to evaluate the outcome of the proposed method; the MSRBDT algorithm was used to identify the gray matter (GM), white matter (WM), and cerebral-spinal fluid (CSF) in the brain tissues. The accuracy rates of GM, WM, and CSF segmentation, with spatial features (G, x, y, r, θ), were respectively greater than 0.9805, 0.9817, and 0.9871. In addition, images segmented with the MSRBDT algorithm were better than those obtained with the expectation maximization (EM) algorithm; brain tissue segmentation in MR images was significantly more precise. The proposed MSRBDT algorithm could be beneficial in clinical image segmentation.     

Atlas-free surface reconstruction of the cortical grey-white interface in infants

Background

The segmentation of the cortical interface between grey and white matter in magnetic resonance images (MRI) is highly challenging during the first post-natal year. First, the heterogeneous brain maturation creates important intensity fluctuations across regions. Second, the cortical ribbon is highly folded creating complex shapes. Finally, the low tissue contrast and partial volume effects hamper cortex edge detection in parts of the brain.

Methods and Findings

We present an atlas-free method for segmenting the grey-white matter interface of infant brains in T2-weighted (T2w) images. We used a broad characterization of tissue using features based not only on local contrast but also on geometric properties. Furthermore, inaccuracies in localization were reduced by the convergence of two evolving surfaces located on each side of the inner cortical surface. Our method has been applied to eleven brains of one- to four-month-old infants. Both quantitative validations against manual segmentations and sulcal landmarks demonstrated good performance for infants younger than two months old. Inaccuracies in surface reconstruction increased with age in specific brain regions where the tissue contrast decreased with maturation, such as in the central region.

Conclusions

We presented a new segmentation method which achieved good to very good performance at the grey-white matter interface depending on the infant age. This method should reduce manual intervention and could be applied to pathological brains since it does not require any brain atlas.     

Automatic Structural Parcellation of Mouse Brain MRI Using Multi-Atlas Label Fusion

Multi-atlas segmentation propagation has evolved quickly in recent years, becoming a state-of-the-art methodology for automatic parcellation of structural images. However, few studies have applied these methods to preclinical research. In this study, we present a fully automatic framework for mouse brain MRI structural parcellation using multi-atlas segmentation propagation. The framework adopts the similarity and truth estimation for propagated segmentations (STEPS) algorithm, which utilises a locally normalised cross correlation similarity metric for atlas selection and an extended simultaneous truth and performance level estimation (STAPLE) framework for multi-label fusion. The segmentation accuracy of the multi-atlas framework was evaluated using publicly available mouse brain atlas databases with pre-segmented manually labelled anatomical structures as the gold standard, and optimised parameters were obtained for the STEPS algorithm in the label fusion to achieve the best segmentation accuracy. We showed that our multi-atlas framework resulted in significantly higher segmentation accuracy compared to single-atlas based segmentation, as well as to the original STAPLE framework.     

Increased Gray Matter Diffusion Anisotropy in Patients with Persistent Post-Concussive Symptoms following Mild Traumatic Brain Injury

A significant percentage of individuals diagnosed with mild traumatic brain injury (mTBI) experience persistent post-concussive symptoms (PPCS). Little is known about the pathology of these symptoms and there is often no radiological evidence based on conventional clinical imaging. We aimed to utilize methods to evaluate microstructural tissue changes and to determine whether or not a link with PPCS was present. A novel analysis method was developed to identify abnormalities in high-resolution diffusion tensor imaging (DTI) when the location of brain injury is heterogeneous across subjects. A normative atlas with 145 brain regions of interest (ROI) was built from 47 normal controls. Comparing each subject’s diffusion measures to the atlas generated subject-specific profiles of injury. Abnormal ROIs were defined by absolute z-score values above a given threshold. The method was applied to 11 PPCS patients following mTBI and 11 matched controls. Z-score information for each individual was summarized with two location-independent measures: “load” (number of abnormal regions) and “severity” (largest absolute z-score). Group differences were then computed using Wilcoxon rank sum tests. Results showed statistically significantly higher load (p = 0.018) and severity (p = 0.006) for fractional anisotropy (FA) in patients compared with controls. Subject-specific profiles of injury evinced abnormally high FA regions in gray matter (30 occurrences over 11 patients), and abnormally low FA in white matter (3 occurrences over 11 subjects). Subject-specific profiles provide important information regarding the pathology associated with PPCS. Increased gray matter (GM) anisotropy is a novel in-vivo finding, which is consistent with an animal model of brain trauma that associates increased FA in GM with pathologies such as gliosis. In addition, the individualized analysis shows promise for enhancing the clinical care of PPCS patients as it could play a role in the diagnosis of brain injury not revealed using conventional imaging.     

Methods for acquisition of quantitative from confocal images of gene expression in situ

In this review we summarize original methods for the extraction quantitative information from the confocal images of gene expression patterns. These methods include image segmentation, extraction of quantitative numerical data on gene expression, removal of background signal and spatial registration. Finally it is possible to construct a spatiotemporal atlas of gene expression form individual images obtained at each developmental stage. Initially all methods were developed to extract quantitative numerical information form confocal images of segmentation gene expression in Drosophila melanogaster. Application of these methods to Drosophila images makes it possible to reveal new mechanisms of formation of segmentation gene expression domains, as well as to construct the quantitative atlas of segmentation gene expression. Most image processing procedures can be easily adapted to process a wide range of biological images.     

Methods for acquisition of quantitative data from confocal images of gene expression in situ

In this review, we summarize original methods for the extraction of quantitative information from confocal images of gene-expression patterns. These methods include image segmentation, the extraction of quantitative numerical data on gene expression, and the removal of background signal and spatial registration. Finally, it is possible to construct a spatiotemporal atlas of gene expression from individual images recorded at each developmental stage. Initially all methods were developed to extract quantitative numerical information from confocal images of segmentation gene expression in Drosophila melanogaster. The application of these methods to Drosophila images makes it possible to reveal new mechanisms in the formation of segmentation gene expression domains, as well as to construct a quantitative atlas of segmentation gene expression. Most image processing procedures can be easily adapted to process a wide range of biological images.     

Automatic Segmentation of Eight Tissue Classes in Neonatal Brain MRI

Purpose

Volumetric measurements of neonatal brain tissues may be used as a biomarker for later neurodevelopmental outcome. We propose an automatic method for probabilistic brain segmentation in neonatal MRIs.

Materials and Methods

In an IRB-approved study axial T1- and T2-weighted MR images were acquired at term-equivalent age for a preterm cohort of 108 neonates. A method for automatic probabilistic segmentation of the images into eight cerebral tissue classes was developed: cortical and central grey matter, unmyelinated and myelinated white matter, cerebrospinal fluid in the ventricles and in the extra cerebral space, brainstem and cerebellum. Segmentation is based on supervised pixel classification using intensity values and spatial positions of the image voxels. The method was trained and evaluated using leave-one-out experiments on seven images, for which an expert had set a reference standard manually. Subsequently, the method was applied to the remaining 101 scans, and the resulting segmentations were evaluated visually by three experts. Finally, volumes of the eight segmented tissue classes were determined for each patient.

Results

The Dice similarity coefficients of the segmented tissue classes, except myelinated white matter, ranged from 0.75 to 0.92. Myelinated white matter was difficult to segment and the achieved Dice coefficient was 0.47. Visual analysis of the results demonstrated accurate segmentations of the eight tissue classes. The probabilistic segmentation method produced volumes that compared favorably with the reference standard.

Conclusion

The proposed method provides accurate segmentation of neonatal brain MR images into all given tissue classes, except myelinated white matter. This is the one of the first methods that distinguishes cerebrospinal fluid in the ventricles from cerebrospinal fluid in the extracerebral space. This method might be helpful in predicting neurodevelopmental outcome and useful for evaluating neuroprotective clinical trials in neonates.     

Intravascular Optical Coherence Tomography Image Segmentation Based on Support Vector Machine Algorithm

Intravascular optical coherence tomography (IVOCT) is becoming more and more popular in clinical diagnosis of coronary atherosclerotic. However, reading IVOCT images is of large amount of work. This article describes a method based on image feature extraction and support vector machine (SVM) to achieve semi-automatic segmentation of IVOCT images. The image features utilized in this work including light attenuation coefficients and image textures based on gray level co-occurrence matrix. Different sets of hyper-parameters and image features were tested. This method achieved an accuracy of 83% on the test images. Single class accuracy of 89% for fibrous, 79.3% for calcification and 86.5% lipid tissue. The results show that this method can be a considerable way for semi-automatic segmentation of atherosclerotic plaque components in clinical IVOCT images.     

A Digital Atlas of the Dog Brain

There is a long history and a growing interest in the canine as a subject of study in neuroscience research and in translational neurology. In the last few years, anatomical and functional magnetic resonance imaging (MRI) studies of awake and anesthetized dogs have been reported. Such efforts can be enhanced by a population atlas of canine brain anatomy to implement group analyses. Here we present a canine brain atlas derived as the diffeomorphic average of a population of fifteen mesaticephalic dogs. The atlas includes: 1) A brain template derived from in-vivo, T1-weighted imaging at 1 mm isotropic resolution at 3 Tesla (with and without the soft tissues of the head); 2) A co-registered, high-resolution (0.33 mm isotropic) template created from imaging of ex-vivo brains at 7 Tesla; 3) A surface representation of the gray matter/white matter boundary of the high-resolution atlas (including labeling of gyral and sulcal features). The properties of the atlas are considered in relation to historical nomenclature and the evolutionary taxonomy of the Canini tribe. The atlas is available for download (https://cfn.upenn.edu/aguirre/wiki/public:data_plosone_2012_datta).     

A Logic Programming and Expert Statistical Systems Approach for Tissue Characterization in Magnetic Resonance Imaging

The main research goal has been to evaluate significant factors affecting the in vivo magnetic resonance imaging (MRI) parameters T, T, T₂, and ¹H density. This approach differs significantly from other such projects in that the experimental data analysis is being performed while concurrently developing automated, computer-aided analysis software for such MRI tissue parameters. In the experimental portion of the project, statistical analyses, and a heuristic minimum/maximum discriminant analysis algorithm have been explored. Both methods have been used to classify tissue types from 1.5 Tesla transaxial MR images of the human brain. The developing program, written in the logic programming language Prolog, is similar in a number of ways to many existing expert systems now in use for other medical applications; inclusion of the underlying statistical data base and advanced statistical analyses is the main differentiating feature of the current approach. First results indicate promising classification accuracy of various brain tissues such as gray and white matter, as well as differentiation of different types of gray matter and white matter (e.g.: caudate-nucleus vs. thalamus, both representatives of gray matter; and, cortical white matter vs. internal capsule as representative of white matter). Taking all four tissue types together, the percentage of correct classifications ranges from 73 to 87%.     

A fully-automatic caudate nucleus segmentation of brain MRI: Application in volumetric analysis of pediatric attention-deficit/hyperactivity disorder

Background

Accurate automatic segmentation of the caudate nucleus in magnetic resonance images (MRI) of the brain is of great interest in the analysis of developmental disorders. Segmentation methods based on a single atlas or on multiple atlases have been shown to suitably localize caudate structure. However, the atlas prior information may not represent the structure of interest correctly. It may therefore be useful to introduce a more flexible technique for accurate segmentations.

Method

We present Cau-dateCut: a new fully-automatic method of segmenting the caudate nucleus in MRI. CaudateCut combines an atlas-based segmentation strategy with the Graph Cut energy-minimization framework. We adapt the Graph Cut model to make it suitable for segmenting small, low-contrast structures, such as the caudate nucleus, by defining new energy function data and boundary potentials. In particular, we exploit information concerning the intensity and geometry, and we add supervised energies based on contextual brain structures. Furthermore, we reinforce boundary detection using a new multi-scale edgeness measure.

Results

We apply the novel CaudateCut method to the segmentation of the caudate nucleus to a new set of 39 pediatric attention-deficit/hyperactivity disorder (ADHD) patients and 40 control children, as well as to a public database of 18 subjects. We evaluate the quality of the segmentation using several volumetric and voxel by voxel measures. Our results show improved performance in terms of segmentation compared to state-of-the-art approaches, obtaining a mean overlap of 80.75%. Moreover, we present a quantitative volumetric analysis of caudate abnormalities in pediatric ADHD, the results of which show strong correlation with expert manual analysis.

Conclusion

CaudateCut generates segmentation results that are comparable to gold-standard segmentations and which are reliable in the analysis of differentiating neuroanatomical abnormalities between healthy controls and pediatric ADHD.     

A Probabilistic Atlas of Diffuse WHO Grade II Glioma Locations in the Brain

Diffuse WHO grade II gliomas are diffusively infiltrative brain tumors characterized by an unavoidable anaplastic transformation. Their management is strongly dependent on their location in the brain due to interactions with functional regions and potential differences in molecular biology. In this paper, we present the construction of a probabilistic atlas mapping the preferential locations of diffuse WHO grade II gliomas in the brain. This is carried out through a sparse graph whose nodes correspond to clusters of tumors clustered together based on their spatial proximity. The interest of such an atlas is illustrated via two applications. The first one correlates tumor location with the patient’s age via a statistical analysis, highlighting the interest of the atlas for studying the origins and behavior of the tumors. The second exploits the fact that the tumors have preferential locations for automatic segmentation. Through a coupled decomposed Markov Random Field model, the atlas guides the segmentation process, and characterizes which preferential location the tumor belongs to and consequently which behavior it could be associated to. Leave-one-out cross validation experiments on a large database highlight the robustness of the graph, and yield promising segmentation results.     

Associations between age and gray matter volume in anatomical brain networks in middle‐aged to older adults

Aging is associated with cognitive decline, diminished brain function, regional brain atrophy, and disrupted structural and functional brain connectivity. Understanding brain networks in aging is essential, as brain function depends on large‐scale distributed networks. Little is known of structural covariance networks to study inter‐regional gray matter anatomical associations in aging. Here, we investigate anatomical brain networks based on structural covariance of gray matter volume among 370 middle‐aged to older adults of 45–85 years. For each of 370 subjects, we acquired a T1‐weighted anatomical MRI scan. After segmentation of structural MRI scans, nine anatomical networks were defined based on structural covariance of gray matter volume among subjects. We analyzed associations between age and gray matter volume in anatomical networks using linear regression analyses. Age was negatively associated with gray matter volume in four anatomical networks (P < 0.001, corrected): a subcortical network, sensorimotor network, posterior cingulate network, and an anterior cingulate network. Age was not significantly associated with gray matter volume in five networks: temporal network, auditory network, and three cerebellar networks. These results were independent of gender and white matter hyperintensities. Gray matter volume decreases with age in networks containing subcortical structures, sensorimotor structures, posterior, and anterior cingulate cortices. Gray matter volume in temporal, auditory, and cerebellar networks remains relatively unaffected with advancing age.     

Relationship between body mass index and gray matter volume in 1,428 healthy individuals

Objective: To investigate any correlation between BMI and brain gray matter volume, we analyzed 1,428 healthy Japanese subjects by applying volumetric analysis and voxel‐based morphometry (VBM) using brain magnetic resonance (MR) imaging, which enables a global analysis of brain structure without a priori identification of a region of interest. Methods and Procedures: We collected brain MR images from 690 men and 738 women, and their height, weight, and other clinical information. The collected images were automatically normalized into a common standard space for an objective assessment of neuroanatomical correlations in volumetric analysis and VBM with BMI. Results: Volumetric analysis revealed a significant negative correlation in men (P < 0.001, adjusting for age, lifetime alcohol intake, history of hypertension, and diabetes mellitus), although not in women, between BMI and the gray matter ratio, which represents the percentage of gray matter volume in the intracranial volume. VBM revealed that, in men, the regional gray matter volume of the bilateral medial temporal lobes, anterior lobe of the cerebellum, occipital lobe, frontal lobe, precuneus, and midbrain showed significant negative correlations with BMI, while those of the bilateral inferior frontal gyri, posterior lobe of the cerebellum, frontal lobes, temporal lobes, thalami, and caudate heads showed significant positive correlations with BMI. Discussion: Global loss and regional alterations in gray matter volume occur in obese male subjects, suggesting that male subjects with a high BMI are at greater risk for future declines in cognition or other brain functions.     

Changes in Rat Brain Tissue Microstructure and Stiffness during the Development of Experimental Obstructive Hydrocephalus

Understanding neural injury in hydrocephalus and how the brain changes during the course of the disease in-vivo remain unclear. This study describes brain deformation, microstructural and mechanical properties changes during obstructive hydrocephalus development in a rat model using multimodal magnetic resonance (MR) imaging. Hydrocephalus was induced in eight Sprague-Dawley rats (4 weeks old) by injecting a kaolin suspension into the cisterna magna. Six sham-injected rats were used as controls. MR imaging (9.4T, Bruker) was performed 1 day before, and at 3, 7 and 16 days post injection. T2-weighted MR images were collected to quantify brain deformation. MR elastography was used to measure brain stiffness, and diffusion tensor imaging (DTI) was conducted to observe brain tissue microstructure. Results showed that the enlargement of the ventricular system was associated with a decrease in the cortical gray matter thickness and caudate-putamen cross-sectional area (P < 0.001, for both), an alteration of the corpus callosum and periventricular white matter microstructure (CC+PVWM) and rearrangement of the cortical gray matter microstructure (P < 0.001, for both), while compression without gross microstructural alteration was evident in the caudate-putamen and ventral internal capsule (P < 0.001, for both). During hydrocephalus development, increased space between the white matter tracts was observed in the CC+PVWM (P < 0.001), while a decrease in space was observed for the ventral internal capsule (P < 0.001). For the cortical gray matter, an increase in extracellular tissue water was significantly associated with a decrease in tissue stiffness (P = 0.001). To conclude, this study characterizes the temporal changes in tissue microstructure, water content and stiffness in different brain regions and their association with ventricular enlargement. In summary, whilst diffusion changes were larger and statistically significant for majority of the brain regions studied, the changes in mechanical properties were modest. Moreover, the effect of ventricular enlargement is not limited to the CC+PVWM and ventral internal capsule, the extent of microstructural changes vary between brain regions, and there is regional and temporal variation in brain tissue stiffness during hydrocephalus development.     

Anatomical atlas in the context of head and neck radiotherapy and its use to automatic segmentation

In this paper we present a methodology to form an anatomical atlas based on the analysis of dense deformation fields recovered by the Morphons non-rigid registration algorithm. The methodology is based on measuring the bending energy required to register the whole database to a reference, and the atlas is the one image in the database which yields the smallest bending energy when taken as reference. The suitability of our atlas is demonstrated in the context of head and neck radiotherapy through its application to a database with thirty-one computed tomography (CT) images of the head and neck region. In head and neck radiotherapy, CT is the most frequently used modality for the segmentation of organs at risk and clinical target volumes. One challenge brought by the use of CT images is the presence of important artifacts caused by dental implants. The presence of such artifacts hinders the use of intensity averages, thus severely limiting the application of most atlas building techniques described in the literature in this context. The results presented in the paper show that our bending energy model faithfully represents the shape variability of patients in the head and neck region; they also show its good performance in segmentation of volumes of interest in radiotherapy. Moreover, when compared to other atlases of similar performance in automatic segmentation, our atlas presents the desirable feature of not being blurred after intensity averaging.