Content-Based Image Retrieval Using Spatial Layout Information in Brain Tumor T1-Weighted Contrast-Enhanced MR Images

This study aims to develop content-based image retrieval (CBIR) system for the retrieval of T1-weighted contrast-enhanced MR (CE-MR) images of brain tumors. When a tumor region is fed to the CBIR system as a query, the system attempts to retrieve tumors of the same pathological category. The bag-of-visual-words (BoVW) model with partition learning is incorporated into the system to extract informative features for representing the image contents. Furthermore, a distance metric learning algorithm called the Rank Error-based Metric Learning (REML) is proposed to reduce the semantic gap between low-level visual features and high-level semantic concepts. The effectiveness of the proposed method is evaluated on a brain T1-weighted CE-MR dataset with three types of brain tumors (i.e., meningioma, glioma, and pituitary tumor). Using the BoVW model with partition learning, the mean average precision (mAP) of retrieval increases beyond 4.6% with the learned distance metrics compared with the spatial pyramid BoVW method. The distance metric learned by REML significantly outperforms three other existing distance metric learning methods in terms of mAP. The mAP of the CBIR system is as high as 91.8% using the proposed method, and the precision can reach 93.1% when the top 10 images are returned by the system. These preliminary results demonstrate that the proposed method is effective and feasible for the retrieval of brain tumors in T1-weighted CE-MR Images.     

Accuracy and Reliability of Automated Gray Matter Segmentation Pathways on Real and Simulated Structural Magnetic Resonance Images of the Human Brain

Automated gray matter segmentation of magnetic resonance imaging data is essential for morphometric analyses of the brain, particularly when large sample sizes are investigated. However, although detection of small structural brain differences may fundamentally depend on the method used, both accuracy and reliability of different automated segmentation algorithms have rarely been compared. Here, performance of the segmentation algorithms provided by SPM8, VBM8, FSL and FreeSurfer was quantified on simulated and real magnetic resonance imaging data. First, accuracy was assessed by comparing segmentations of twenty simulated and 18 real T1 images with corresponding ground truth images. Second, reliability was determined in ten T1 images from the same subject and in ten T1 images of different subjects scanned twice. Third, the impact of preprocessing steps on segmentation accuracy was investigated. VBM8 showed a very high accuracy and a very high reliability. FSL achieved the highest accuracy but demonstrated poor reliability and FreeSurfer showed the lowest accuracy, but high reliability. An universally valid recommendation on how to implement morphometric analyses is not warranted due to the vast number of scanning and analysis parameters. However, our analysis suggests that researchers can optimize their individual processing procedures with respect to final segmentation quality and exemplifies adequate performance criteria.     

4D Segmentation of Brain MR Images with Constrained Cortical Thickness Variation

Segmentation of brain MR images plays an important role in longitudinal investigation of developmental, aging, disease progression changes in the cerebral cortex. However, most existing brain segmentation methods consider multiple time-point images individually and thus cannot achieve longitudinal consistency. For example, cortical thickness measured from the segmented image will contain unnecessary temporal variations, which will affect the time related change pattern and eventually reduce the statistical power of analysis. In this paper, we propose a 4D segmentation framework for the adult brain MR images with the constraint of cortical thickness variations. Specifically, we utilize local intensity information to address the intensity inhomogeneity, spatial cortical thickness constraint to maintain the cortical thickness being within a reasonable range, and temporal cortical thickness variation constraint in neighboring time-points to suppress the artificial variations. The proposed method has been tested on BLSA dataset and ADNI dataset with promising results. Both qualitative and quantitative experimental results demonstrate the advantage of the proposed method, in comparison to other state-of-the-art 4D segmentation methods.     

A Modified DWT-SVD Algorithm for T1-w Brain MR Images Contrast Enhancement

BackgroundImage contrast enhancement is considered as the most useful technique permitting a better appearance of the low contrast images. This paper presents a modified Discret Wavelet Transform - Singular Value Decomposition (DWT-SVD) approach for the enhancement of low contrast Brain MR Images used for brain tissues exploration.MethodsThe proposed technique is processed as follows: first of all, we consider low contrast T1-weighted MRI slices as input images (A1) on which we apply General Histogram Equalization (GHE) algorithm to have equalized images referred as (A2) having zero as mean and one as variance. Secondly, by using the Discrete Wavelet Transform (DWT) algorithm, both (A1) and (A2) are divided into low and high frequency sub-bands. On the low frequency (LL1) and (LL2) sub-bands, SVD is processed in order to generate three matrix factorization (U, V and Σ) where the maximums of (U) and (V) matrix are used for the estimation of a correction coefficient (ξ). Our contribution in this paper is to estimate the new singular value matrix (New Σ) using a weighted sum of both original and equalized singular value matrix thanks to an adjustable parameter (μ) for the targeted low contrast images. This parameter, ranged between 0.05 and 0.95, is determined empirically according to the input low contrast image. Finally, the enhanced resulting image is easily reconstructed using the Inverse SVD (ISVD) and the Inverse DWT (IDWT) processes.ResultsThe database considered in our research consisted of 120 MR brain images where T1-weighted MR brain modality are selected for the contrast enhancement process. Considering the qualitative results, our proposed contrast enhancement method have shown better distinction between brain tissues and have preserved all White Matter (WM), Gray Matter (GM) and Cerebro-Spinal Fluid (CSF) pixel edges. In fact, histogram plots of images enhanced by proposed method covered all the gray level intensities. For the quantitative results, proposed method gives the highest PSNR, QRCM, SSIM, FSIM and EME values and the lowest AMBE values for (μ) equal to 0.65 as comparing to the rest of methods. These results signifies that proposed contrast enhancement method have provided greater image quality with preservation of image structure, feature and brightness.ConclusionProposed method improved performance of contrast enhancement image without creating unwanted artifact and without destroying image edge information or affecting the specificities of brain tissues. This is due to the use of an empirically (μ) parameter adjustable according to the input MR images. Hence, the proposed approach is appropriate for enhancing contrast of huge type of low contrast images.     

An Objective Method to Optimize the MR Sequence Set for Plaque Classification in Carotid Vessel Wall Images Using Automated Image Segmentation

A typical MR imaging protocol to study the status of atherosclerosis in the carotid artery consists of the application of multiple MR sequences. Since scanner time is limited, a balance has to be reached between the duration of the applied MR protocol and the quantity and quality of the resulting images which are needed to assess the disease. In this study an objective method to optimize the MR sequence set for classification of soft plaque in vessel wall images of the carotid artery using automated image segmentation was developed. The automated method employs statistical pattern recognition techniques and was developed based on an extensive set of MR contrast weightings and corresponding manual segmentations of the vessel wall and soft plaque components, which were validated by histological sections. Evaluation of the results from nine contrast weightings showed the tradeoff between scan duration and automated image segmentation performance. For our dataset the best segmentation performance was achieved by selecting five contrast weightings. Similar performance was achieved with a set of three contrast weightings, which resulted in a reduction of scan time by more than 60%. The presented approach can help others to optimize MR imaging protocols by investigating the tradeoff between scan duration and automated image segmentation performance possibly leading to shorter scanning times and better image interpretation. This approach can potentially also be applied to other research fields focusing on different diseases and anatomical regions.     

Hemodynamic Segmentation of Brain Perfusion Images with Delay and Dispersion Effects Using an Expectation-Maximization Algorithm

Automatic identification of various perfusion compartments from dynamic susceptibility contrast magnetic resonance brain images can assist in clinical diagnosis and treatment of cerebrovascular diseases. The principle of segmentation methods was based on the clustering of bolus transit-time profiles to discern areas of different tissues. However, the cerebrovascular diseases may result in a delayed and dispersed local perfusion and therefore alter the hemodynamic signal profiles. Assessing the accuracy of the segmentation technique under delayed/dispersed circumstance is critical to accurately evaluate the severity of the vascular disease. In this study, we improved the segmentation method of expectation-maximization algorithm by using the results of hierarchical clustering on whitened perfusion data as initial parameters for a mixture of multivariate Gaussians model. In addition, Monte Carlo simulations were conducted to evaluate the performance of proposed method under different levels of delay, dispersion, and noise of signal profiles in tissue segmentation. The proposed method was used to classify brain tissue types using perfusion data from five normal participants, a patient with unilateral stenosis of the internal carotid artery, and a patient with moyamoya disease. Our results showed that the normal, delayed or dispersed hemodynamics can be well differentiated for patients, and therefore the local arterial input function for impaired tissues can be recognized to minimize the error when estimating the cerebral blood flow. Furthermore, the tissue in the risk of infarct and the tissue with or without the complementary blood supply from the communicating arteries can be identified.     

Fully Automatic Localization and Segmentation of 3D Vertebral Bodies from CT/MR Images via a Learning-Based Method

In this paper, we address the problems of fully automatic localization and segmentation of 3D vertebral bodies from CT/MR images. We propose a learning-based, unified random forest regression and classification framework to tackle these two problems. More specifically, in the first stage, the localization of 3D vertebral bodies is solved with random forest regression where we aggregate the votes from a set of randomly sampled image patches to get a probability map of the center of a target vertebral body in a given image. The resultant probability map is then further regularized by Hidden Markov Model (HMM) to eliminate potential ambiguity caused by the neighboring vertebral bodies. The output from the first stage allows us to define a region of interest (ROI) for the segmentation step, where we use random forest classification to estimate the likelihood of a voxel in the ROI being foreground or background. The estimated likelihood is combined with the prior probability, which is learned from a set of training data, to get the posterior probability of the voxel. The segmentation of the target vertebral body is then done by a binary thresholding of the estimated probability. We evaluated the present approach on two openly available datasets: 1) 3D T2-weighted spine MR images from 23 patients and 2) 3D spine CT images from 10 patients. Taking manual segmentation as the ground truth (each MR image contains at least 7 vertebral bodies from T11 to L5 and each CT image contains 5 vertebral bodies from L1 to L5), we evaluated the present approach with leave-one-out experiments. Specifically, for the T2-weighted MR images, we achieved for localization a mean error of 1.6 mm, and for segmentation a mean Dice metric of 88.7% and a mean surface distance of 1.5 mm, respectively. For the CT images we achieved for localization a mean error of 1.9 mm, and for segmentation a mean Dice metric of 91.0% and a mean surface distance of 0.9 mm, respectively.     

Feature-based,Automated Segmentation of Cerebral Infarct Patterns Using T 2- and Diffusion-weighted Imaging

Diffusion-weighted imaging enables the diagnosis of cerebral ischemias very early, thus supporting therapies such as thrombolysis. However, morphology and tissue-characterizing parameters (e.g. relaxation times or water diffusion) may vary strongly in ischemic regions, indicating different underlying pathologic processes. As the determination of the parameters by a supervised segmentation is very time consuming, we evaluated whether different infarct patterns may be segmented by an automated, multidimensional feature-based method using a unified segmentation procedure. Ischemias were classified into 5 characteristic patterns. For each class, a 3D histogram based on T 2 - and diffusion-weighted images as well as calculated apparent diffusion coefficients (ADC) was generated from a representative data set. Healthy and pathologic tissue classes were segmented in the histogram as separate, local density maxima with freely shaped borders. Segmentation control parameters were optimized in a 3-step procedure. The method was evaluated using synthetic images as well as results of a supervised segmentation. For the analysis of cerebral ischemias, the optimal control parameter set led to sensitivities and specificities between 1.0 and 0.9.     

Multi-Atlas Based Adaptive Active Contour Model with Application to Organs at Risk Segmentation in Brain MR Images

BackgroundAccurate delineation of organs at risk (OARs) is critical in radiotherapy. Manual delineation is tedious and suffers from both interobserver and intraobserver variability. Automatic segmentation of brain MR images has a wide range of applications in brain tumor radiotherapy. In this paper, we propose a multi-atlas based adaptive active contour model for OAR automatic segmentation in brain MR images.MethodsThe proposed method consists of two parts: multi-atlas based OAR contour initiation and an adaptive edge and local region based active contour evolution. In the adaptive active contour model, we define an energy functional with an adaptive edge intensity fitting force which is responsible for evaluating contour inwards or outwards, and a local region intensity fitting force which guides the evolution of the contour.ResultsExperimental results show that the proposed method achieved more accurate segmentation results in brainstem, eyes and lens automatic segmentation with the Dice Similar Coefficient (DSC) value of 87.19%, 91.96%, 77.11% respectively. Besides, the dosimetric parameters also demonstrate the high consistency of the manual OAR delineations and the auto segmentation results of the proposed method in brain tumor radiotherapy.ConclusionsThe geometric and dosimetric evaluations show the desirable performance of the proposed method on the application of OARs segmentations in brain tumor radiotherapy.     

Fully Automated Whole-Head Segmentation with Improved Smoothness and Continuity,with Theory Reviewed

Individualized current-flow models are needed for precise targeting of brain structures using transcranial electrical or magnetic stimulation (TES/TMS). The same is true for current-source reconstruction in electroencephalography and magnetoencephalography (EEG/MEG). The first step in generating such models is to obtain an accurate segmentation of individual head anatomy, including not only brain but also cerebrospinal fluid (CSF), skull and soft tissues, with a field of view (FOV) that covers the whole head. Currently available automated segmentation tools only provide results for brain tissues, have a limited FOV, and do not guarantee continuity and smoothness of tissues, which is crucially important for accurate current-flow estimates. Here we present a tool that addresses these needs. It is based on a rigorous Bayesian inference framework that combines image intensity model, anatomical prior (atlas) and morphological constraints using Markov random fields (MRF). The method is evaluated on 20 simulated and 8 real head volumes acquired with magnetic resonance imaging (MRI) at 1 mm3 resolution. We find improved surface smoothness and continuity as compared to the segmentation algorithms currently implemented in Statistical Parametric Mapping (SPM). With this tool, accurate and morphologically correct modeling of the whole-head anatomy for individual subjects may now be feasible on a routine basis. Code and data are fully integrated into SPM software tool and are made publicly available. In addition, a review on the MRI segmentation using atlas and the MRF over the last 20 years is also provided, with the general mathematical framework clearly derived.     

Texture Analysis of T2-Weighted MR Images to Assess Acute Inflammation in Brain MS Lesions

Brain blood barrier breakdown as assessed by contrast-enhanced (CE) T1-weighted MR imaging is currently the standard radiological marker of inflammatory activity in multiple sclerosis (MS) patients. Our objective was to evaluate the performance of an alternative model assessing the inflammatory activity of MS lesions by texture analysis of T2-weighted MR images. Twenty-one patients with definite MS were examined on the same 3.0T MR system by T2-weighted, FLAIR, diffusion-weighted and CE-T1 sequences. Lesions and mirrored contralateral areas within the normal appearing white matter (NAWM) were characterized by texture parameters computed from the gray level co-occurrence and run length matrices, and by the apparent diffusion coefficient (ADC). Statistical differences between MS lesions and NAWM were analyzed. ROC analysis and leave-one-out cross-validation were performed to evaluate the performance of individual parameters, and multi-parametric models using linear discriminant analysis (LDA), partial least squares (PLS) and logistic regression (LR) in the identification of CE lesions. ADC and all but one texture parameter were significantly different within white matter lesions compared to within NAWM (p < 0.0167). Using LDA, an 8-texture parameter model identified CE lesions with a sensitivity Se = 70% and a specificity Sp = 76%. Using LR, a 10-texture parameter model performed better with Se = 86% / Sp = 84%. Using PLS, a 6-texture parameter model achieved the highest accuracy with Se = 88% / Sp = 81%. Texture parameter from T2-weighted images can assess brain inflammatory activity with sufficient accuracy to be considered as a potential alternative to enhancement on CE T1-weighted images.     

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.     

MR 脑图像海马自动分割法在AD 早期诊断中的应用研究

目的:研究磁共振(Magnetic resonance,MR)脑图像中海马的自动分割方法及海马的形态学分析方法,为阿尔茨海默病(Alzheimer’s disease,AD)的早期诊断提供依据。方法:对20例AD患者和60名正常对照者行MRI T1 WI 3D容积扫描,建立海马的三维主动表观模型,并以此模型对每个个体脑部磁共振图像上的海马进行自动识别和三维分割,分别建立正常对照组和AD组的海马统计形状模型,比较AD组与正常对照组间海马形状的差异性。结果:海马三维分割方法与手动分割方法在海马体积测量上无统计学差别(P>0.05);AD患者海马头部发生萎缩(P<0.05)。结论:基于主动表观模型的MR脑图像海马自动识别和三维分割法是准确可靠的;海马头部萎缩可作为AD诊断的依据之一。     

Automated Protein Localization of Blood Brain Barrier Vasculature in Brightfield IHC Images

In this paper, we present an objective method for localization of proteins in blood brain barrier (BBB) vasculature using standard immunohistochemistry (IHC) techniques and bright-field microscopy. Images from the hippocampal region at the BBB are acquired using bright-field microscopy and subjected to our segmentation pipeline which is designed to automatically identify and segment microvessels containing the protein glucose transporter 1 (GLUT1). Gabor filtering and k-means clustering are employed to isolate potential vascular structures within cryosectioned slabs of the hippocampus, which are subsequently subjected to feature extraction followed by classification via decision forest. The false positive rate (FPR) of microvessel classification is characterized using synthetic and non-synthetic IHC image data for image entropies ranging between 3 and 8 bits. The average FPR for synthetic and non-synthetic IHC image data was found to be 5.48% and 5.04%, respectively.     

Detection of Mild Cognitive Impairment Using Kernel Density Estimation Based Texture Analysis of the Corpus Callosum in Brain MR Images

ObjectivesMild Cognitive Impairment (MCI) is the prodromal stage of Alzheimer's disease (AD), which is a progressive and fatal neurodegenerative disorder. Detection of MCI condition can enable early diagnosis resulting in timely intervention to delay the disease progression. Onset of MCI causes tissue alterations in Corpus Callosum (CC) of the brain. Texture analysis of brain Magnetic Resonance (MR) images aids in characterising these imperceptible changes. In this study, Kernel Density Estimation (KDE) technique is used to analyse the textural variations in CC to detect MCI condition.Materials and methodThe pre-processed brain MR images are obtained from a public access database. Reaction Diffusion level set is employed to segment CC from sagittal slices of the images. Kernel density estimation method is applied to study the local intensity variations within the segmented CC. Statistical features quantifying these variations are extracted from the KDE values. These features are used to differentiate MCI condition using linear classifiers based on discriminant analysis and support vector machine. The results are compared with conventional Grey Level Co-occurrence Matrix (GLCM) features for validation.ResultsThe KDE-based texture features extracted from CC show significant variation between normal and MCI classes. Results demonstrate that this approach can differentiate MCI condition with high accuracy and specificity of 81.3% and 82.7%, respectively. The KDE-based features perform better when compared with GLCM features for distinguishing MCI.ConclusionsThe KDE-based texture features are able to capture the subtle changes occurring in CC at the MCI stage. This technique achieves comparable performance to other state-of-the-art methods with reduced number of features. Efficiency of the KDE-based texture analysis confirms that the proposed computer assisted technique can be used for mass screening of MCI, which can aid in handling the disease severity.     

Fast and Accurate Semi-Automated Segmentation Method of Spinal Cord MR Images at 3T Applied to the Construction of a Cervical Spinal Cord Template

Objective

To design a fast and accurate semi-automated segmentation method for spinal cord 3T MR images and to construct a template of the cervical spinal cord.

Materials and Methods

A semi-automated double threshold-based method (DTbM) was proposed enabling both cross-sectional and volumetric measures from 3D T₂-weighted turbo spin echo MR scans of the spinal cord at 3T. Eighty-two healthy subjects, 10 patients with amyotrophic lateral sclerosis, 10 with spinal muscular atrophy and 10 with spinal cord injuries were studied. DTbM was compared with active surface method (ASM), threshold-based method (TbM) and manual outlining (ground truth). Accuracy of segmentations was scored visually by a radiologist in cervical and thoracic cord regions. Accuracy was also quantified at the cervical and thoracic levels as well as at C2 vertebral level. To construct a cervical template from healthy subjects’ images (n=59), a standardization pipeline was designed leading to well-centered straight spinal cord images and accurate probability tissue map.

Results

Visual scoring showed better performance for DTbM than for ASM. Mean Dice similarity coefficient (DSC) was 95.71% for DTbM and 90.78% for ASM at the cervical level and 94.27% for DTbM and 89.93% for ASM at the thoracic level. Finally, at C2 vertebral level, mean DSC was 97.98% for DTbM compared with 98.02% for TbM and 96.76% for ASM. DTbM showed similar accuracy compared with TbM, but with the advantage of limited manual interaction.

Conclusion

A semi-automated segmentation method with limited manual intervention was introduced and validated on 3T images, enabling the construction of a cervical spinal cord template.     

Increasing the Contrast of the Brain MR FLAIR Images Using Fuzzy Membership Functions and Structural Similarity Indices in Order to Segment MS Lesions

Segmentation is an important step for the diagnosis of multiple sclerosis (MS). This paper presents a new approach to the fully automatic segmentation of MS lesions in Fluid Attenuated Inversion Recovery (FLAIR) Magnetic Resonance (MR) images. With the aim of increasing the contrast of the FLAIR MR images with respect to the MS lesions, the proposed method first estimates the fuzzy memberships of brain tissues (i.e., the cerebrospinal fluid (CSF), the normal-appearing brain tissue (NABT), and the lesion). The procedure for determining the fuzzy regions of their member functions is performed by maximizing fuzzy entropy through Genetic Algorithm. Research shows that the intersection points of the obtained membership functions are not accurate enough to segment brain tissues. Then, by extracting the structural similarity (SSIM) indices between the FLAIR MR image and its lesions membership image, a new contrast-enhanced image is created in which MS lesions have high contrast against other tissues. Finally, the new contrast-enhanced image is used to segment MS lesions. To evaluate the result of the proposed method, similarity criteria from all slices from 20 MS patients are calculated and compared with other methods, which include manual segmentation. The volume of segmented lesions is also computed and compared with Gold standard using the Intraclass Correlation Coefficient (ICC) and paired samples t test. Similarity index for the patients with small lesion load, moderate lesion load and large lesion load was 0.7261, 0.7745 and 0.8231, respectively. The average overall similarity index for all patients is 0.7649. The t test result indicates that there is no statistically significant difference between the automatic and manual segmentation. The validated results show that this approach is very promising.     

Semi-Automated Detection of Cerebral Microbleeds on 3.0 T MR Images

Cerebral microbleeds are associated with vascular disease and dementia. They can be detected on MRI and receive increasing attention. Visual rating is the current standard for microbleed detection, but is rater dependent, has limited reproducibility, modest sensitivity, and can be time-consuming. The goal of the current study is to present a tool for semi-automated detection of microbleeds that can assist human raters in the rating procedure. The radial symmetry transform is originally a technique to highlight circular-shaped objects in two-dimensional images. In the current study, the three-dimensional radial symmetry transform was adapted to detect spherical microbleeds in a series of 72 patients from our hospital, for whom a ground truth visual rating was made by four raters. Potential microbleeds were automatically identified on T2*-weighted 3.0 T MRI scans and the results were visually checked to identify microbleeds. Final ratings of the radial symmetry transform were compared to human ratings. After implementing and optimizing the radial symmetry transform, the method achieved a high sensitivity, while maintaining a modest number of false positives. Depending on the settings, sensitivities ranged from 65%–84% compared to the ground truth rating. Rating of the processed images required 1–2 minutes per participant, in which 20–96 false positive locations per participant were censored. Sensitivities of individual raters ranged from 39%–86% compared to the ground truth and required 5–10 minutes per participant per rater. The sensitivities that were achieved by the radial symmetry transform are similar to those of individual experienced human raters, demonstrating its feasibility and usefulness for semi-automated microbleed detection.