Magnetic Resonance Imaging of the Newborn Brain: Automatic Segmentation of Brain Images into 50 Anatomical Regions

We studied methods for the automatic segmentation of neonatal and developing brain images into 50 anatomical regions, utilizing a new set of manually segmented magnetic resonance (MR) images from 5 term-born and 15 preterm infants imaged at term corrected age called ALBERTs. Two methods were compared: individual registrations with label propagation and fusion; and template based registration with propagation of a maximum probability neonatal ALBERT (MPNA). In both cases we evaluated the performance of different neonatal atlases and MPNA, and the approaches were compared with the manual segmentations by means of the Dice overlap coefficient. Dice values, averaged across regions, were 0.81±0.02 using label propagation and fusion for the preterm population, and 0.81±0.02 using the single registration of a MPNA for the term population. Segmentations of 36 further unsegmented target images of developing brains yielded visibly high-quality results. This registration approach allows the rapid construction of automatically labeled age-specific brain atlases for neonates and the developing brain.     

Comprehensive brain MRI segmentation in high risk preterm newborns

Most extremely preterm newborns exhibit cerebral atrophy/growth disturbances and white matter signal abnormalities on MRI at term-equivalent age. MRI brain volumes could serve as biomarkers for evaluating the effects of neonatal intensive care and predicting neurodevelopmental outcomes. This requires detailed, accurate, and reliable brain MRI segmentation methods. We describe our efforts to develop such methods in high risk newborns using a combination of manual and automated segmentation tools. After intensive efforts to accurately define structural boundaries, two trained raters independently performed manual segmentation of nine subcortical structures using axial T2-weighted MRI scans from 20 randomly selected extremely preterm infants. All scans were re-segmented by both raters to assess reliability. High intra-rater reliability was achieved, as assessed by repeatability and intra-class correlation coefficients (ICC range: 0.97 to 0.99) for all manually segmented regions. Inter-rater reliability was slightly lower (ICC range: 0.93 to 0.99). A semi-automated segmentation approach was developed that combined the parametric strengths of the Hidden Markov Random Field Expectation Maximization algorithm with non-parametric Parzen window classifier resulting in accurate white matter, gray matter, and CSF segmentation. Final manual correction of misclassification errors improved accuracy (similarity index range: 0.87 to 0.89) and facilitated objective quantification of white matter signal abnormalities. The semi-automated and manual methods were seamlessly integrated to generate full brain segmentation within two hours. This comprehensive approach can facilitate the evaluation of large cohorts to rigorously evaluate the utility of regional brain volumes as biomarkers of neonatal care and surrogate endpoints for neurodevelopmental outcomes.     

A Magnetic Resonance Image Based Atlas of the Rabbit Brain for Automatic Parcellation

Rabbit brain has been used in several works for the analysis of neurodevelopment. However, there are not specific digital rabbit brain atlases that allow an automatic identification of brain regions, which is a crucial step for various neuroimage analyses, and, instead, manual delineation of areas of interest must be performed in order to evaluate a specific structure. For this reason, we propose an atlas of the rabbit brain based on magnetic resonance imaging, including both structural and diffusion weighted, that can be used for the automatic parcellation of the rabbit brain. Ten individual atlases, as well as an average template and probabilistic maps of the anatomical regions were built. In addition, an example of automatic segmentation based on this atlas is described.     

A Multi-Atlas Based Method for Automated Anatomical Rat Brain MRI Segmentation and Extraction of PET Activity

Introduction

Preclinical in vivo imaging requires precise and reproducible delineation of brain structures. Manual segmentation is time consuming and operator dependent. Automated segmentation as usually performed via single atlas registration fails to account for anatomo-physiological variability. We present, evaluate, and make available a multi-atlas approach for automatically segmenting rat brain MRI and extracting PET activies.

Methods

High-resolution 7T 2DT2 MR images of 12 Sprague-Dawley rat brains were manually segmented into 27-VOI label volumes using detailed protocols. Automated methods were developed with 7/12 atlas datasets, i.e. the MRIs and their associated label volumes. MRIs were registered to a common space, where an MRI template and a maximum probability atlas were created. Three automated methods were tested: 1/registering individual MRIs to the template, and using a single atlas (SA), 2/using the maximum probability atlas (MP), and 3/registering the MRIs from the multi-atlas dataset to an individual MRI, propagating the label volumes and fusing them in individual MRI space (propagation & fusion, PF). Evaluation was performed on the five remaining rats which additionally underwent [¹⁸F]FDG PET. Automated and manual segmentations were compared for morphometric performance (assessed by comparing volume bias and Dice overlap index) and functional performance (evaluated by comparing extracted PET measures).

Results

Only the SA method showed volume bias. Dice indices were significantly different between methods (PF>MP>SA). PET regional measures were more accurate with multi-atlas methods than with SA method.

Conclusions

Multi-atlas methods outperform SA for automated anatomical brain segmentation and PET measure’s extraction. They perform comparably to manual segmentation for FDG-PET quantification. Multi-atlas methods are suitable for rapid reproducible VOI analyses.     

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.     

Using Manifold Learning for Atlas Selection in Multi-Atlas Segmentation

Multi-atlas segmentation has been widely used to segment various anatomical structures. The success of this technique partly relies on the selection of atlases that are best mapped to a new target image after registration. Recently, manifold learning has been proposed as a method for atlas selection. Each manifold learning technique seeks to optimize a unique objective function. Therefore, different techniques produce different embeddings even when applied to the same data set. Previous studies used a single technique in their method and gave no reason for the choice of the manifold learning technique employed nor the theoretical grounds for the choice of the manifold parameters. In this study, we compare side-by-side the results given by 3 manifold learning techniques (Isomap, Laplacian Eigenmaps and Locally Linear Embedding) on the same data set. We assess the ability of those 3 different techniques to select the best atlases to combine in the framework of multi-atlas segmentation. First, a leave-one-out experiment is used to optimize our method on a set of 110 manually segmented atlases of hippocampi and find the manifold learning technique and associated manifold parameters that give the best segmentation accuracy. Then, the optimal parameters are used to automatically segment 30 subjects from the Alzheimer’s Disease Neuroimaging Initiative (ADNI). For our dataset, the selection of atlases with Locally Linear Embedding gives the best results. Our findings show that selection of atlases with manifold learning leads to segmentation accuracy close to or significantly higher than the state-of-the-art method and that accuracy can be increased by fine tuning the manifold learning process.     

Surface-based and probabilistic atlases of primate cerebral cortex

Brain atlases play an increasingly important role in neuroimaging, as they are invaluable for analysis, visualization, and comparison of results across studies. For both humans and macaque monkeys, digital brain atlases of many varieties are in widespread use, each having its own strengths and limitations. For studies of cerebral cortex there is particular utility in hybrid atlases that capitalize on the complementary nature of surface and volume representations, are based on a population average rather than an individual brain, and include measures of variation as well as averages. Linking different brain atlases to one another and to online databases containing a growing body of neuroimaging data will enable powerful forms of data mining that accelerate discovery and improve research efficiency.     

Comparison of Segger and other methods for segmentation and rigid-body docking of molecular components in cryo-EM density maps

Segmentation and docking are useful methods for the discovery of molecular components in electron cryo-microscopy (cryo-EM) density maps of macromolecular complexes. In this article, we describe the segmentation and docking methods implemented in Segger. For 11 targets posted in the 2010 cryo-EM challenge, we segmented the regions corresponding to individual molecular components using Segger. We then used the segmented regions to guide rigid-body docking of individual components. Docking results were evaluated by comparing the docked components with published structures, and by calculation of several scores, such as atom inclusion, density occupancy, and geometry clash. The accuracy of the component segmentation using Segger and other methods was assessed by comparing segmented regions with docked components.     

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.     

Spinal Cord Segmentation by One Dimensional Normalized Template Matching: A Novel,Quantitative Technique to Analyze Advanced Magnetic Resonance Imaging Data

Spinal cord segmentation is a developing area of research intended to aid the processing and interpretation of advanced magnetic resonance imaging (MRI). For example, high resolution three-dimensional volumes can be segmented to provide a measurement of spinal cord atrophy. Spinal cord segmentation is difficult due to the variety of MRI contrasts and the variation in human anatomy. In this study we propose a new method of spinal cord segmentation based on one-dimensional template matching and provide several metrics that can be used to compare with other segmentation methods. A set of ground-truth data from 10 subjects was manually-segmented by two different raters. These ground truth data formed the basis of the segmentation algorithm. A user was required to manually initialize the spinal cord center-line on new images, taking less than one minute. Template matching was used to segment the new cord and a refined center line was calculated based on multiple centroids within the segmentation. Arc distances down the spinal cord and cross-sectional areas were calculated. Inter-rater validation was performed by comparing two manual raters (n = 10). Semi-automatic validation was performed by comparing the two manual raters to the semi-automatic method (n = 10). Comparing the semi-automatic method to one of the raters yielded a Dice coefficient of 0.91 +/- 0.02 for ten subjects, a mean distance between spinal cord center lines of 0.32 +/- 0.08 mm, and a Hausdorff distance of 1.82 +/- 0.33 mm. The absolute variation in cross-sectional area was comparable for the semi-automatic method versus manual segmentation when compared to inter-rater manual segmentation. The results demonstrate that this novel segmentation method performs as well as a manual rater for most segmentation metrics. It offers a new approach to study spinal cord disease and to quantitatively track changes within the spinal cord in an individual case and across cohorts of subjects.     

Bayesian estimation of probabilistic atlas for tissue segmentation

Automatic anatomical brain image segmentation is still a challenge. In particular, algorithms have to address the partial volume effect (PVE) as well as the variability of the gray level of internal brain structures which may appear closer to gray matter (GM) than white matter (WM). Atlas based segmentation is one solution as it brings prior information. For such tasks, probabilistic atlases are very useful as they take account of the PVE information. In this paper, we provide a detailed analysis of a generative statistical model based on dense deformable templates that represents several tissue types observed in medical images. The inputs are gray level data whereas our atlas is composed of both an estimation of the deformation metric and probability maps of each tissue (called class). This atlas is used to guide the tissue segmentation of new images. Experiments are shown on brain T1 MRI datasets. This method only requires approximate pre-registration, as the latter is done jointly with the segmentation. Note however that an approximate registration is a reasonable pre-requisite given the application.     

Hierarchical clustering applied to automatic atlas based segmentation of 25 cardiac sub-structures

PurposeSegmentation of cardiac sub-structures for dosimetric analyses is usually performed manually in time-consuming procedure. Automatic segmentation may facilitate large-scale retrospective analysis and adaptive radiotherapy. Various approaches, among them Hierarchical Clustering, were applied to improve performance of atlas-based segmentation (ABS).MethodsTraining dataset of ABS consisted of 36 manually contoured CT-scans. Twenty-five cardiac sub-structures were contoured as regions of interest (ROIs). Five auto-segmentation methods were compared: simultaneous automatic contouring of all 25 ROIs (Method-1); automatic contouring of all 25 ROIs using lungs as anatomical barriers (Method-2); automatic contouring of a single ROI for each contouring cycle (Method-3); hierarchical cluster-based automatic contouring (Method-4); simultaneous truth and performance level estimation (STAPLE). Results were evaluated on 10 patients. Dice similarity coefficient (DSC), average Hausdorff distance (AHD), volume comparison and physician score were used as validation metrics.ResultsAtlas performance improved increasing number of atlases. Among the five ABS methods, Hierarchical Clustering workflow showed a significant improvement maintaining a clinically acceptable time for contouring. Physician scoring was acceptable for 70% of the ROI automatically contoured. Inter-observer evaluation showed that contours obtained by Hierarchical Clustering method are statistically comparable with them obtained by a second, independent, expert contourer considering DSC. Considering AHD, distance from the gold standard is lower for ROIs segmented by ABS.ConclusionsHierarchical clustering resulted in best ABS results for the primarily investigated platforms and compared favorably to a second benchmark system. Auto-contouring of smaller structures, being in range of variation between manual contourers, may be ideal for large-scale retrospective dosimetric analysis.     

3D surface analysis and classification in neuroimaging segmentation

This work emphasizes new algorithms for 3D edge and corner detection used in surface extraction and new concept of image segmentation in neuroimaging based on multidimensional shape analysis and classification. We propose using of NifTI standard for describing input data which enables interoperability and enhancement of existing computing tools used widely in neuroimaging research. In methods section we present our newly developed algorithm for 3D edge and corner detection, together with the algorithm for estimating local 3D shape. Surface of estimated shape is analyzed and segmented according to kernel shapes.     

Identification of Neonatal White Matter on DTI: Influence of More Inclusive Thresholds for Atlas Segmentation

Purpose

Semi-automated diffusion tensor imaging (DTI) analysis of white matter (WM) microstructure offers a clinically feasible technique to assess neonatal brain development and provide early prognosis, but is limited by variable methods and insufficient evidence regarding optimal parameters. The purpose of this research was to investigate the influence of threshold values on semi-automated, atlas-based brain segmentation in very-low-birth-weight (VLBW) preterm infants at near-term age.

Materials and Methods

DTI scans were analyzed from 45 VLBW preterm neonates at near-term-age with no brain abnormalities evident on MRI. Brain regions were selected with a neonatal brain atlas and threshold values: trace <0.006 mm²/s, fractional anisotropy (FA)>0.15, FA>0.20, and FA>0.25. Relative regional volumes, FA, axial diffusivity (AD), and radial diffusivity (RD) were compared for twelve WM regions.

Results

Near-term brain regions demonstrated differential effects from segmentation with the three FA thresholds. Regional DTI values and volumes selected in the PLIC, CereP, and RLC varied the least with the application of different FA thresholds. Overall, application of higher FA thresholds significantly reduced brain region volume selected, increased variability, and resulted in higher FA and lower RD values. The lower threshold FA>0.15 selected 78±21% of original volumes segmented by the atlas, compared to 38±12% using threshold FA>0.25.

Conclusion

Results indicate substantial and differential effects of atlas-based DTI threshold parameters on regional volume and diffusion scalars. A lower, more inclusive FA threshold than typically applied for adults is suggested for consistent analysis of WM regions in neonates.     

Development of a Semi-Automatic Segmentation Method for Retinal OCT Images Tested in Patients with Diabetic Macular Edema

Purpose

To develop EdgeSelect, a semi-automatic method for the segmentation of retinal layers in spectral domain optical coherence tomography images, and to compare the segmentation results with a manual method.

Methods

SD-OCT (Heidelberg Spectralis) scans of 28 eyes (24 patients with diabetic macular edema and 4 normal subjects) were imported into a customized MATLAB application, and were manually segmented by three graders at the layers corresponding to the inner limiting membrane (ILM), the inner segment/ellipsoid interface (ISe), the retinal/retinal pigment epithelium interface (RPE), and the Bruch''s membrane (BM). The scans were then segmented independently by the same graders using EdgeSelect, a semi-automated method allowing the graders to guide/correct the layer segmentation interactively. The inter-grader reproducibility and agreement in locating the layer positions between the manual and EdgeSelect methods were assessed and compared using the Wilcoxon signed rank test.

Results

The inter-grader reproducibility using the EdgeSelect method for retinal layers varied from 0.15 to 1.21 µm, smaller than those using the manual method (3.36–6.43 µm). The Wilcoxon test indicated the EdgeSelect method had significantly better reproducibility than the manual method. The agreement between the manual and EdgeSelect methods in locating retinal layers ranged from 0.08 to 1.32 µm. There were small differences between the two methods in locating the ILM (p = 0.012) and BM layers (p<0.001), but these were statistically indistinguishable in locating the ISe (p = 0.896) and RPE layers (p = 0.771).

Conclusions

The EdgeSelect method resulted in better reproducibility and good agreement with a manual method in a set of eyes of normal subjects and with retinal disease, suggesting that this approach is feasible for OCT image analysis in clinical trials.     

FogBank: a single cell segmentation across multiple cell lines and image modalities

Background

Many cell lines currently used in medical research, such as cancer cells or stem cells, grow in confluent sheets or colonies. The biology of individual cells provide valuable information, thus the separation of touching cells in these microscopy images is critical for counting, identification and measurement of individual cells. Over-segmentation of single cells continues to be a major problem for methods based on morphological watershed due to the high level of noise in microscopy cell images. There is a need for a new segmentation method that is robust over a wide variety of biological images and can accurately separate individual cells even in challenging datasets such as confluent sheets or colonies.

Results

We present a new automated segmentation method called FogBank that accurately separates cells when confluent and touching each other. This technique is successfully applied to phase contrast, bright field, fluorescence microscopy and binary images. The method is based on morphological watershed principles with two new features to improve accuracy and minimize over-segmentation.First, FogBank uses histogram binning to quantize pixel intensities which minimizes the image noise that causes over-segmentation. Second, FogBank uses a geodesic distance mask derived from raw images to detect the shapes of individual cells, in contrast to the more linear cell edges that other watershed-like algorithms produce.We evaluated the segmentation accuracy against manually segmented datasets using two metrics. FogBank achieved segmentation accuracy on the order of 0.75 (1 being a perfect match). We compared our method with other available segmentation techniques in term of achieved performance over the reference data sets. FogBank outperformed all related algorithms. The accuracy has also been visually verified on data sets with 14 cell lines across 3 imaging modalities leading to 876 segmentation evaluation images.

Conclusions

FogBank produces single cell segmentation from confluent cell sheets with high accuracy. It can be applied to microscopy images of multiple cell lines and a variety of imaging modalities. The code for the segmentation method is available as open-source and includes a Graphical User Interface for user friendly execution.

Electronic supplementary material

The online version of this article (doi:10.1186/s12859-014-0431-x) contains supplementary material, which is available to authorized users.     

Bone marrow cell scene segmentation by computer-aided color cytophotometry.

Computer scene segmentation of touching cell images in bone marrow, on the basis of color information, is achieved using digitized scans at three different wavelengths of light. With trivariate histograms and Euler's coordinate transformation, it is possible cytophotometrically to isolate, on the basis of chromatic differences, individual heterogeneous cells located in cell groups. The ability of the described computer methods to isolate correctly the touching cell images is determined by visual comparison of the cells as seen in the microscope and the computer-generated displays of the scanned and segmented scenes.     

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.     

A New Approach to Segment Both Main and Peripheral Retinal Vessels Based on Gray-Voting and Gaussian Mixture Model

Vessel segmentation in retinal fundus images is a preliminary step to clinical diagnosis for some systemic diseases and some eye diseases. The performances of existing methods for segmenting small vessels which are usually of more importance than the main vessels in a clinical diagnosis are not satisfactory in clinical use. In this paper, we present a method for both main and peripheral vessel segmentation. A local gray-level change enhancement algorithm called gray-voting is used to enhance the small vessels, while a two-dimensional Gabor wavelet is used to extract the main vessels. We fuse the gray-voting results with the 2D-Gabor filter results as pre-processing outcome. A Gaussian mixture model is then used to extract vessel clusters from the pre-processing outcome, while small vessels fragments are obtained using another gray-voting process, which complements the vessel cluster extraction already performed. At the last step, we eliminate the fragments that do not belong to the vessels based on the shape of the fragments. We evaluated the approach with two publicly available DRIVE (Staal et al., 2004) and STARE (Hoover et at., 2000) datasets with manually segmented results. For the STARE dataset, when using the second manually segmented results which include much more small vessels than the first manually segmented results as the “gold standard,” this approach achieved an average sensitivity, accuracy and specificity of 65.0%, 92.1% and 97.0%, respectively. The sensitivities of this approach were much higher than those of the other existing methods, with comparable specificities; these results thus demonstrated that this approach was sensitive to detection of small vessels.