MR image-based measurement of rates of change in volumes of brain structures. Part I: method and validation

A detailed analysis procedure is described for evaluating rates of volumetric change in brain structures based on structural magnetic resonance (MR) images. In this procedure, a series of image processing tools have been employed to address the problems encountered in measuring rates of change based on structural MR images. These tools include an algorithm for intensity non-uniformity correction, a robust algorithm for three-dimensional image registration with sub-voxel precision and an algorithm for brain tissue segmentation. However, a unique feature in the procedure is the use of a fractional volume model that has been developed to provide a quantitative measure for the partial volume effect. With this model, the fractional constituent tissue volumes are evaluated for voxels at the tissue boundary that manifest partial volume effect, thus allowing tissue boundaries be defined at a sub-voxel level and in an automated fashion. Validation studies are presented on key algorithms including segmentation and registration. An overall assessment of the method is provided through the evaluation of the rates of brain atrophy in a group of normal elderly subjects for which the rate of brain atrophy due to normal aging is predictably small. An application of the method is given in Part II where the rates of brain atrophy in various brain regions are studied in relation to normal aging and Alzheimer's disease.     

Generalized total variation-based MRI Rician denoising model with spatially adaptive regularization parameters

Magnetic resonance imaging (MRI) is an outstanding medical imaging modality but the quality often suffers from noise pollution during image acquisition and transmission. The purpose of this study is to enhance image quality using feature-preserving denoising method. In current literature, most existing MRI denoising methods did not simultaneously take the global image prior and local image features into account. The denoising method proposed in this paper is implemented based on an assumption of spatially varying Rician noise map. A two-step wavelet-domain estimation method is developed to extract the noise map. Following a Bayesian modeling approach, a generalized total variation-based MRI denoising model is proposed based on global hyper-Laplacian prior and Rician noise assumption. The proposed model has the properties of backward diffusion in local normal directions and forward diffusion in local tangent directions. To further improve the denoising performance, a local variance estimator-based method is introduced to calculate the spatially adaptive regularization parameters related to local image features and spatially varying noise map. The main benefit of the proposed method is that it takes full advantage of the global MR image prior and local image features. Numerous experiments have been conducted on both synthetic and real MR data sets to compare our proposed model with some state-of-the-art denoising methods. The experimental results have demonstrated the superior performance of our proposed model in terms of quantitative and qualitative image quality evaluations.     

Analysis of Light Propagation in a Three-Dimensional Realistic Head Model for Topographic Imaging by Finite Difference Method

Near infrared topographic imaging is a novel non-invasive technique to obtain the activated region in the brain cortex. The light propagation in the head is strongly scattered and this causes results in poor spatial resolution and contrast in the topographic images. Adequate modelling of light propagation in the head in order to deduce the volume of tissue interrogated by a source-detector pair for topographic imaging is very important to improve the quality of image of brain activity. In this study, the light propagation in a three-dimensional realistic head model is calculated by the finite difference method. The geometry of the model is generated from axial slices of an MRI scan. The topographic image is obtained from the change in intensity detected by source-detector pairs caused by the brain activity. The images obtained by two types of source-detector arrangement are compared to evaluate the efficiency of source-detector arrangement. The results show that the double-density arrangement improves the quality of the topographic image of the brain activity.     

A Hybrid Deep Learning Model for Brain Tumour Classification

A brain tumour is one of the major reasons for death in humans, and it is the tenth most common type of tumour that affects people of all ages. However, if detected early, it is one of the most treatable types of tumours. Brain tumours are classified using biopsy, which is not usually performed before definitive brain surgery. An image classification technique for tumour diseases is important for accelerating the treatment process and avoiding surgery and errors from manual diagnosis by radiologists. The advancement of technology and machine learning (ML) can assist radiologists in tumour diagnostics using magnetic resonance imaging (MRI) images without invasive procedures. This work introduced a new hybrid CNN-based architecture to classify three brain tumour types through MRI images. The method suggested in this paper uses hybrid deep learning classification based on CNN with two methods. The first method combines a pre-trained Google-Net model of the CNN algorithm for feature extraction with SVM for pattern classification. The second method integrates a finely tuned Google-Net with a soft-max classifier. The proposed approach was evaluated using MRI brain images that contain a total of 1426 glioma images, 708 meningioma images, 930 pituitary tumour images, and 396 normal brain images. The reported results showed that an accuracy of 93.1% was achieved from the finely tuned Google-Net model. However, the synergy of Google-Net as a feature extractor with an SVM classifier improved recognition accuracy to 98.1%.     

Segmenting and validating brain tissue definitions in the presence of varying tissue contrast

We propose a method for segmenting brain tissue as either gray matter or white matter in the presence of varying tissue contrast, which can derive from either differential changes in tissue water content or increasing myelin content of white matter. Our method models the spatial distribution of intensities as a Markov Random Field (MRF) and estimates the parameters for the MRF model using a maximum likelihood approach. Although previously described methods have used similar models to segment brain tissue, accurate model of the conditional probabilities of tissue intensities and adaptive estimates of tissue properties to local intensities generates tissue definitions that are accurate and robust to variations in tissue contrast with age and across illnesses. Robustness to variations in tissue contrast is important to understand normal brain development and to identify the brain bases of neurological and psychiatric illnesses. We used simulated brains of varying tissue contrast to compare both visually and quantitatively the performance of our method with the performance of prior methods. We assessed validity of the cortical definitions by associating cortical thickness with various demographic features, clinical measures, and medication use in our three large cohorts of participants who were either healthy or who had Bipolar Disorder (BD), Autism Spectrum Disorder (ASD), or familial risk for Major Depressive Disorder (MDD).We assessed validity of the tissue definitions using synthetic brains and data for three large cohort of individuals with various neuropsychiatric disorders. Visual inspection and quantitative analyses showed that our method accurately and robustly defined the cortical mantle in brain images with varying contrast. Furthermore, associating the thickness with various demographic and clinical measures generated findings that were novel and supported by histological analyses or were supported by previous MRI studies, thereby validating the cortical definitions generated by the proposed method: (1) Although cortical thickness decreased with age in adolescents, in adults cortical thickness did not correlate significantly with age. Our synthetic data showed that the previously reported thinning of cortex in adults is likely due to decease in tissue contrast, thereby suggesting that the method generated cortical definitions in adults that were invariant to tissue contrast. In adolescents, cortical thinning with age was preserved likely due to widespread dendritic and synaptic pruning, even though the effects of decreasing tissue contrast were minimized. (3) The method generated novel finding of both localized increases and decreases in thickness of males compared to females after controlling for the differing brain sizes, which are supported by the histological analyses of brain tissue in males and females. (4) The proposed method, unlike prior methods, defined thicker cortex in BD individuals using lithium. The novel finding is supported by the studies that showed lithium treatment increased dendritic arborization and neurogenesis, thereby leading to thickening of cortex. (5) In both BD and ASD participants, associations of more severe symptoms with thinner cortex showed that correcting for the effects of tissue contrast preserved the biological consequences of illnesses. Therefore, consistency of the findings across the three large cohorts of participants, in images acquired on either 1.5T or 3T MRI scanners, and with findings from prior histological analyses provides strong evidence that the proposed method generated valid and accurate definitions of the cortex while controlling for the effects of tissue contrast.     

Atlas-based automatic mouse brain image segmentation revisited: model complexity vs. image registration

Although many atlas-based segmentation methods have been developed and validated for the human brain, limited work has been done for the mouse brain. This paper investigated roles of image registration and segmentation model complexity in the mouse brain segmentation. We employed four segmentation models [single atlas, multiatlas, simultaneous truth and performance level estimation (STAPLE) and Markov random field (MRF) via four different image registration algorithms (affine, B-spline free-form deformation (FFD), Demons and large deformation diffeomorphic metric mapping (LDDMM)] for delineating 19 structures from in vivo magnetic resonance microscopy images. We validated their accuracies against manual segmentation. Our results revealed that LDDMM outperformed Demons, FFD and affine in any of the segmentation models. Under the same registration, increasing segmentation model complexity from single atlas to multiatlas, STAPLE or MRF significantly improved the segmentation accuracy. Interestingly, the multiatlas-based segmentation using nonlinear registrations (FFD, Demons and LDDMM) had similar performance to their STAPLE counterparts, while they both outperformed their MRF counterparts. Furthermore, when the single-atlas affine segmentation was used as reference, the improvement due to nonlinear registrations (FFD, Demons and LDDMM) in the single-atlas segmentation model was greater than that due to increasing model complexity (multiatlas, STAPLE and MRF affine segmentation). Hence, we concluded that image registration plays a more crucial role in the atlas-based automatic mouse brain segmentation as compared to model complexity. Multiple atlases with LDDMM can best improve the segmentation accuracy in the mouse brain among all segmentation models tested in this study.     

Magnetic Resonance Imaging Segmentation via Weighted Level Set Model Based on Local Kernel Metric and Spatial Constraint

Magnetic resonance imaging (MRI) segmentation is a fundamental and significant task since it can guide subsequent clinic diagnosis and treatment. However, images are often corrupted by defects such as low-contrast, noise, intensity inhomogeneity, and so on. Therefore, a weighted level set model (WLSM) is proposed in this study to segment inhomogeneous intensity MRI destroyed by noise and weak boundaries. First, in order to segment the intertwined regions of brain tissue accurately, a weighted neighborhood information measure scheme based on local multi information and kernel function is designed. Then, the membership function of fuzzy c-means clustering is used as the spatial constraint of level set model to overcome the sensitivity of level set to initialization, and the evolution of level set function can be adaptively changed according to different tissue information. Finally, the distance regularization term in level set function is replaced by a double potential function to ensure the stability of the energy function in the evolution process. Both real and synthetic MRI images can show the effectiveness and performance of WLSM. In addition, compared with several state-of-the-art models, segmentation accuracy and Jaccard similarity coefficient obtained by WLSM are increased by 0.0586, 0.0362 and 0.1087, 0.0703, respectively.     

基于光谱与空间特征结合的改进高光谱数据分类算法

针对仅利用光谱信息进行分类未充分利用高光谱数据图谱合一特性的问题,提出了基于马尔可夫随机场的改进分类模型,利用基于最大后验概率的马尔科夫随机场模型进行光谱与空间信息的融合应用,采用基于光谱信息的概率支持向量机方法提高马尔科夫随机场模型中光谱能量函数项的类条件概率估计精度,设计基于信息传播策略、信息更新策略、多尺度传播策略的多重加速策略的高效置信传播优化算法,解决了马尔科夫随机场模型中全局能量最小化优化过程中计算复杂度高、计算耗时等问题。利用航空可见-近红外成像光谱仪AVIRIS对美国印第安纳州西北部的农业示范区数据进行应用分析,并与迭代条件模型、模拟退火、置信传播等方法进行性能比较,试验结果表明：该方法能够达到总体分类精度95.78%、Kappa系数0.933 4,优于现有马尔科夫随机场分类算法,并且计算效率比置信传播优化算法提高了3倍以上。     

A conditioned level-set method with block-division strategy to flame front extraction based on OH-PLIF measurements

A novel approach to extract flame fronts, which is called the conditioned level-set method with block division （CLSB）, has been developed. Based on a two-phase level-set formulation, the conditioned initialization and region-lock optimiza-tion appear to be beneficial to improve the efficiency and accuracy of the flame contour identification. The original block- division strategy enables the approach to be unsupervised by calculating local self-adaptive threshold values autonomously before binarization. The CLSB approach has been applied to deal with a large set of experimental data involving swirl- stabilized premixed combustion in diluted regimes operating at atmospheric pressures. The OH-PLIF measurements have been carried out in this framework. The resulting images are, thus, featured by lower signal-to-noise ratios （SNRs） than the ideal image; relatively complex flame structures lead to significant non-uniformity in the OH signal intensity; and, the mag- nitude of the maximum OH gradient observed along the flame front can also vary depending on flow or local stoichiometry. Compared with other conventional edge detection operators, the CLSB method demonstrates a good ability to deal with the OH-PLIF images at low SNR and with the presence of a multiple scales of both OH intensity and OH gradient. The robustness to noise sensitivity and intensity inhomogeneity has been evaluated throughout a range of experimental images of diluted flames, as well as against a circle test as Ground Truth （GT）.     

Image segmentation using adaptive loopy belief propagation

Loopy belief propagation (LBP) algorithm over pairwise-connected Markov random fields (MRFs) has become widely used for low-level vision problems. However, Pairwise MRF is often insufficient to capture the statistics of natural images well, and LBP is still extremely slow for application on an MRF with large discrete label space. To solve these problems, the present study proposes a new segmentation algorithm based on adaptive LBP. The proposed algorithm utilizes local region information to construct a local region model, as well as a local interaction region MRF model for image segmentation. The adaptive LBP algorithm maximizes the global probability of the proposed MRF model, which employs two very important strategies, namely, “message self-convergence” and “adaptive label pruning”. Message self-convergence can improve the reliability of a pixel in choosing a label in local region, and label pruning can dismiss impossible labels for every pixel. Thus, the most reliable information messages transfer through the LBP algorithm. The experimental results show that the proposed algorithm not only obtains more accurate segmentation results but also greater speed.     

Normalization of brain magnetic resonance images using histogram even-order derivative analysis

The even-ordered (2nd, 4th and 6th) derivatives of a brain MRI histogram were used to calculate a characteristic value for white matter, which was used to normalize the image intensity scale. Simulated image histograms were used to estimate the methodological error as a function of noise level, and the optimum derivative order was determined for each image type studied (T1-, T2- and density-weighted). The algorithm yielded highly reproducible results when used in conjunction with a threshold-sensitive brain segmentation algorithm. It also proved insensitive to the presence of extra-cranial tissues. This method of histogram analysis could find utility in a variety of applications that demand robust intensity normalization including image registration, brain segmentation, tissue classification and spatial inhomogeneity correction.     

Unsupervised MRI segmentation of brain tissues using a local linear model and level set

Real-world magnetic resonance imaging of the brain is affected by intensity nonuniformity (INU) phenomena which makes it difficult to fully automate the segmentation process. This difficult task is accomplished in this work by using a new method with two original features: (1) each brain tissue class is locally modeled using a local linear region representative, which allows us to account for the INU in an implicit way and to more accurately position the region's boundaries; and (2) the region models are embedded in the level set framework, so that the spatial coherence of the segmentation can be controlled in a natural way. Our new method has been tested on the ground-truthed Internet Brain Segmentation Repository (IBSR) database and gave promising results, with Tanimoto indexes ranging from 0.61 to 0.79 for the classification of the white matter and from 0.72 to 0.84 for the gray matter. To our knowledge, this is the first time a region-based level set model has been used to perform the segmentation of real-world MRI brain scans with convincing results.     

Shadow regions detection algorithm by adaptive narrowband two-phase Chan-Vese model

An adaptive narrowband two-phase Chan-Vese(ANBCV) model is proposed for im?proving the shadow regions detection performance of sonar images. In the first noise smoothing step, the anisotropic second-order neighborhood MRF(Markov Random Field, MRF) is used to describe the image texture feature parameters. Then, initial two-class segmentation is processed with the block mode /c-means clustering algorithm, to estimate the approximate position of the shadow regions. On this basis, the zero level set function is adaptively initialized by the approximate position of shadow regions. ANBCV model is provided to complete local op?timization for eliminating the image global interference and obtaining more accurate results.Experimental results show that the new algorithm can efficiently remove partial noise, increase detection speed and accuracy, and with less human intervention.     

基于局部和全局信息的自适应水平集图像分割

针对仅采用局部或全局信息无法快速准确分割灰度不均匀图像的问题,提出了一种基于局部和全局信息的自适应水平集图像分割模型。首先,利用图像局部信息和全局信息建立局部能量项和全局能量项,并且利用演化曲线轮廓内外小邻域的灰度均值差作为自变量,建立了权重函数模型,实现了局部能量项和全局能量项之间权重的自适应调整,提高了模型分割灰度不均匀图像的效率和准确性。其次,提出了一种新的能量惩罚项,避免了水平集函数的重新初始化,增强了数值计算的稳定性。最后,为验证模型的优越性,将模型与CV模型、LBF模型和LGIF模型进行了对比,并通过分割时间、迭代次数以及相似度等指标对分割结果进行了客观、定量分析。最终结果表明:该模型不但对初始轮廓具有较高鲁棒性,而且对灰度不均匀图像具有较高的分割准确性与分割效率。     

Automatic segmentation for brain MR images via a convex optimized segmentation and bias field correction coupled model

Accurate segmentation of magnetic resonance (MR) images remains challenging mainly due to the intensity inhomogeneity, which is also commonly known as bias field. Recently active contour models with geometric information constraint have been applied, however, most of them deal with the bias field by using a necessary pre-processing step before segmentation of MR data. This paper presents a novel automatic variational method, which can segment brain MR images meanwhile correcting the bias field when segmenting images with high intensity inhomogeneities. We first define a function for clustering the image pixels in a smaller neighborhood. The cluster centers in this objective function have a multiplicative factor that estimates the bias within the neighborhood. In order to reduce the effect of the noise, the local intensity variations are described by the Gaussian distributions with different means and variances. Then, the objective functions are integrated over the entire domain. In order to obtain the global optimal and make the results independent of the initialization of the algorithm, we reconstructed the energy function to be convex and calculated it by using the Split Bregman theory. A salient advantage of our method is that its result is independent of initialization, which allows robust and fully automated application. Our method is able to estimate the bias of quite general profiles, even in 7T MR images. Moreover, our model can also distinguish regions with similar intensity distribution with different variances. The proposed method has been rigorously validated with images acquired on variety of imaging modalities with promising results.     

Mixture model and Markov random field-based remote sensing image unsupervised clustering method

In this paper, a novel method for remote sensing image clustering based on mixture model and Markov random field (MRF) is proposed. A remote sensing image can be considered as Gaussian mixture model. The image clustering result corresponding to the image label field is a MRF. So, the image clustering procedure is transformed to a maximum a posterior (MAP) problem by Bayesian theorem. The intensity difference and the spatial distance between the two pixels in the same clique are introduced into the traditional MRF potential function. The iterative conditional model (ICM) is employed to find the solution of MAP. We use the max entropy criterion to choose the optimal clustering number. In the experiments, the method is compared with the traditional MRF clustering method using ICM and simulated annealing (SA). The results show that this method is better than the traditional MRF model both in noise filtering and miss-classification ratio.     

A novel active contour model driven by local and global intensity fitting energies

In this paper, we propose a novel hybrid active contour model for image segmentation. In our model, we define a new region-scalable fitting (RSF) energy functional which combines the local and the global image information. The RSF energy functional can not only attract the contour toward object boundaries, but also improve the robustness to initialization of the contours. In order to segment the image fast and accurately, the length term and regularization term is incorporated into the variational level set formulation. Finally, by adopting gradient descent method, the minimization of the energy equation can be given. Due to the new kernel function we defined, our model can cope with intensity inhomogeneity images and less sensitive to the initialization of the contour when compared with the other models. Experimental results demonstrated that the proposed model can also segment both the real and medical images accurately.     

Signal characteristics of FLAIR related to water content: comparison with conventional spin echo imaging in infarcted rat brain

To examine the correlation between tissue water content and signal intensity on fluid-attenuated inversion recovery (FLAIR) images, we analyzed infarcted rat brain, verified the results by theoretical simulation, and compared them with conventional spin-echo images. We produced brain infarction with cavitation in five rats by middle cerebral artery occlusion. After in vivo MRI, histologic sections of the MRI plane were obtained. We measured the signal intensity of regions on FLAIR and spin-echo images, and measured the area of cavitation on histologic sections. We plotted curves of cavity percentage to signal intensity. Theoretical values were calculated using a two-compartment model. On the curve of cavity area to signal intensity, the signal on FLAIR images peaked in tissues with 20% to 30% area of cavitation. On the theoretical curve, the signal on FLAIR images peaked at 90% tissue water content. These results seem to be characteristic of FLAIR.     

Linear-fitting-based similarity coefficient map for tissue dissimilarity analysis in T_2~*-w magnetic resonance imaging

Similarity coefficient mapping(SCM) aims to improve the morphological evaluation of T*2weighted magnetic resonance imaging(T*2-w MRI). However, how to interpret the generated SCM map is still pending. Moreover, is it probable to extract tissue dissimilarity messages based on the theory behind SCM? The primary purpose of this paper is to address these two questions. First, the theory of SCM was interpreted from the perspective of linear fitting. Then, a term was embedded for tissue dissimilarity information. Finally, our method was validated with sixteen human brain image series from multiecho T*2-w MRI. Generated maps were investigated from signal-to-noise ratio(SNR) and perceived visual quality, and then interpreted from intra- and inter-tissue intensity. Experimental results show that both perceptibility of anatomical structures and tissue contrast are improved. More importantly, tissue similarity or dissimilarity can be quantified and cross-validated from pixel intensity analysis. This method benefits image enhancement, tissue classification, malformation detection and morphological evaluation.     

Multicontext wavelet-based thresholding segmentation of brain tissues in magnetic resonance images

A novel segmentation method based on wavelet transform is presented for gray matter, white matter and cerebrospinal fluid in thin-sliced single-channel brain magnetic resonance (MR) scans. On the basis of the local image model, multicontext wavelet-based thresholding segmentation (MCWT) is proposed to classify 2D MR data into tissues automatically. In MCWT, the wavelet multiscale transform of local image gray histogram is done, and the gray threshold is gradually revealed from large-scale to small-scale coefficients. Image segmentation is independently performed in each local image to calculate the degree of membership of a pixel to each tissue class. Finally, a strategy is adopted to integrate the intersected outcomes from different local images. The result of the experiment indicates that MCWT outperforms other traditional segmentation methods in classifying brain MR images.