Image-guided regularization level set evolution for MR image segmentation and bias field correction

Magnetic resonance (MR) image segmentation is a crucial step in surgical and treatment planning. In this paper, we propose a level-set-based segmentation method for MR images with intensity inhomogeneous problem. To tackle the initialization sensitivity problem, we propose a new image-guided regularization to restrict the level set function. The maximum a posteriori inference is adopted to unify segmentation and bias field correction within a single framework. Under this framework, both the contour prior and the bias field prior are fully used. As a result, the image intensity inhomogeneity can be well solved. Extensive experiments are provided to evaluate the proposed method, showing significant improvements in both segmentation and bias field correction accuracies as compared with other state-of-the-art approaches.     

An energy minimization method for MS lesion segmentation from T1-w and FLAIR images

In this paper, we extend the multiplicative intrinsic component optimization (MICO) algorithm to multichannel MR image segmentation, with focus on segmentation of multiple sclerosis (MS) lesions. The MICO algorithm was originally proposed by Li et al. in Ref. [1] for normal brain tissue segmentation and intensity inhomogeneity correction of a single channel MR image, which exhibits desirable advantages over other methods for MR image segmentation and intensity inhomogeneity correction in terms of segmentation accuracy and robustness. In this paper, we extend the MICO algorithm to multi-channel MR image segmentation and enable the segmentation of MS lesions. We assign different weights for different channels to control the impact of each channel. The weighted channels allow the enhancement of the impact of the FLAIR image on the segmentation of MS lesions by assigning a larger weight to the FLAIR image channel than the other channels. With the inherent mechanism of estimation of the bias field, our method is able to deal with the intensity inhomogeneity in the input multi-channel MR images. In the application of our method, we only use T1-w and FLAIR images as the input two channel MR images. Experimental results show promising result of our method.     

Adaptive segmentation of magnetic resonance images with intensity inhomogeneity using level set method

It is a big challenge to segment magnetic resonance (MR) images with intensity inhomogeneity. The widely used segmentation algorithms are region based, which mostly rely on the intensity homogeneity, and could bring inaccurate results. In this paper, we propose a novel region-based active contour model in a variational level set formulation. Based on the fact that intensities in a relatively small local region are separable, a local intensity clustering criterion function is defined. Then, the local function is integrated around the neighborhood center to formulate a global intensity criterion function, which defines the energy term to drive the evolution of the active contour locally. Simultaneously, an intensity fitting term that drives the motion of the active contour globally is added to the energy. In order to segment the image fast and accurately, we utilize a coefficient to make the segmentation adaptive. Finally, the energy is incorporated into a level set formulation with a level set regularization term, and the energy minimization is conducted by a level set evolution process. Experiments on synthetic and real MR images show the effectiveness of our method.     

An anisotropic images segmentation and bias correction method

Intensity inhomogeneities cause considerable difficulty in the quantitative analysis of magnetic resonance (MR) images. Thus, bias field correction is a necessary step before quantitative analysis of MR data can be undertaken. This paper presents an anisotropic approach to bias correction and segmentation for images with intensity inhomogeneities and noise. Intensity-based methods are usually applied to estimate the bias field; however, most of them only concern the intensity information. When the images have noise or slender topological objects, these methods cannot obtain accurate results or bias fields. We use structure information to construct an anisotropic Gibbs field and combine the anisotropic Gibbs field with the Bayesian framework to segment images while estimating the bias fields. Our method is able to capture bias of quite general profiles. Moreover, it is robust to noise and slender topological objects. The proposed method has been used for images of various modalities with promising results.     

Multiplicative intrinsic component optimization (MICO) for MRI bias field estimation and tissue segmentation

This paper proposes a new energy minimization method called multiplicative intrinsic component optimization (MICO) for joint bias field estimation and segmentation of magnetic resonance (MR) images. The proposed method takes full advantage of the decomposition of MR images into two multiplicative components, namely, the true image that characterizes a physical property of the tissues and the bias field that accounts for the intensity inhomogeneity, and their respective spatial properties. Bias field estimation and tissue segmentation are simultaneously achieved by an energy minimization process aimed to optimize the estimates of the two multiplicative components of an MR image. The bias field is iteratively optimized by using efficient matrix computations, which are verified to be numerically stable by matrix analysis. More importantly, the energy in our formulation is convex in each of its variables, which leads to the robustness of the proposed energy minimization algorithm. The MICO formulation can be naturally extended to 3D/4D tissue segmentation with spatial/sptatiotemporal regularization. Quantitative evaluations and comparisons with some popular softwares have demonstrated superior performance of MICO in terms of robustness and accuracy.     

Non-locally regularized segmentation of multiple sclerosis lesion from multi-channel MRI data

Segmentation of multiple sclerosis (MS) lesion is important for many neuroimaging studies. In this paper, we propose a novel algorithm for automatic segmentation of MS lesions from multi-channel MR images (T1W, T2W and FLAIR images). The proposed method is an extension of Li et al.'s algorithm in [1], which only segments the normal tissues from T1W images. The proposed method is aimed to segment MS lesions, while normal tissues are also segmented and bias field is estimated to handle intensity inhomogeneities in the images. Another contribution of this paper is the introduction of a nonlocal means technique to achieve spatially regularized segmentation, which overcomes the influence of noise. Experimental results have demonstrated the effectiveness and advantages of the proposed algorithm.     

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。     

A fully automated algorithm under modified FCM framework for improved brain MR image segmentation

Automated brain magnetic resonance image (MRI) segmentation is a complex problem especially if accompanied by quality depreciating factors such as intensity inhomogeneity and noise. This article presents a new algorithm for automated segmentation of both normal and diseased brain MRI. An entropy driven homomorphic filtering technique has been employed in this work to remove the bias field. The initial cluster centers are estimated using a proposed algorithm called histogram-based local peak merger using adaptive window. Subsequently, a modified fuzzy c-mean (MFCM) technique using the neighborhood pixel considerations is applied. Finally, a new technique called neighborhood-based membership ambiguity correction (NMAC) has been used for smoothing the boundaries between different tissue classes as well as to remove small pixel level noise, which appear as misclassified pixels even after the MFCM approach. NMAC leads to much sharper boundaries between tissues and, hence, has been found to be highly effective in prominently estimating the tissue and tumor areas in a brain MR scan. The algorithm has been validated against MFCM and FMRIB software library using MRI scans from BrainWeb. Superior results to those achieved with MFCM technique have been observed along with the collateral advantages of fully automatic segmentation, faster computation and faster convergence of the objective function.     

Improvement in robustness of the statistically independent region snake-based segmentation method of target-shape tracking

We propose a technique to increase the robustness of a snake-based segmentation method originally introduced to track the shape of a target with random white Gaussian intensity upon a random white Gaussian background. Because these statistical conditions are not always fulfilled with optronic images, we describe two improvements that increase the field of application of this approach. We first show that regularized whitening preprocessing allows one to apply the original method successfully for a target with a correlated texture upon a correlated background. We then introduce a simple multiscale approach that increases the robustness of the segmentation against the initialization of the snake (i.e., the initial shape used for the segmentation). These results provide a robust and practical method for determination of the reference image for correlation techniques.     

Automatic segmentation of white matter lesions on magnetic resonance images of the brain by using an outlier detection strategy

White matter lesions (WMLs) are commonly observed on the magnetic resonance (MR) images of normal elderly in association with vascular risk factors, such as hypertension or stroke. An accurate WML detection provides significant information for disease tracking, therapy evaluation, and normal aging research. In this article, we present an unsupervised WML segmentation method that uses Gaussian mixture model to describe the intensity distribution of the normal brain tissues and detects the WMLs as outliers to the normal brain tissue model based on extreme value theory. The detection of WMLs is performed by comparing the probability distribution function of a one-sided normal distribution and a Gumbel distribution, which is a specific extreme value distribution. The performance of the automatic segmentation is validated on synthetic and clinical MR images with regard to different imaging sequences and lesion loads. Results indicate that the segmentation method has a favorable accuracy competitive with other state-of-the-art WML segmentation methods.     

A non-iterative multi-scale approach for intensity inhomogeneity correction in MRI

Intensity inhomogeneity is the prime obstacle for MR image processing like automatic segmentation, registration etc. This complication has strong dependence on the associated acquisition hardware and patient anatomy which recommends retrospective correction. In this paper, a new method is developed for correcting the intensity inhomogeneity using a non-iterative multi-scale approach that doesn't necessitate segmentation and any prior knowledge on the scanner or subject. The proposed algorithm extracts bias field at different scales using a Log-Gabor filter bank followed by smoothing operation. Later, they are combined to fit a third degree polynomial to estimate the bias field. Finally, the corrected image is estimated by performing pixel-wise division of original image and bias field. The performance of the same was tested on BrainWeb simulated data, HCP dataset and is found to provide better performance than the state-of-the-art method, N4. A good agreement between the extracted and ground truth bias field is observed through correlation coefficient on different MR modality images that include T1w, T2w and PD. Significant reduction in coefficient variation and coefficient of joint variation ratios in real data indicate an improved inter-class separation and reduced intra-class intensity variations across white and grey matter tissue regions.     

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.     

Hepatic vessel segmentation using variational level set combined with non-local robust statistics

Hepatic vessel segmentation is a challenging step in therapy guided by magnetic resonance imaging (MRI). This paper presents an improved variational level set method, which uses non-local robust statistics to suppress the influence of noise in MR images. The non-local robust statistics, which represent vascular features, are learned adaptively from seeds provided by users. K-means clustering in neighborhoods of seeds is utilized to exclude inappropriate seeds, which are obviously corrupted by noise. The neighborhoods of appropriate seeds are placed in an array to calculate the non-local robust statistics, and the variational level set formulation can be constructed. Bias correction is utilized in the level set formulation to reduce the influence of intensity inhomogeneity of MRI. Experiments were conducted over real MR images, and showed that the proposed method performed better on small hepatic vessel segmentation compared with other segmentation methods.     

Stochastic segmentation of severely degraded images using gibbs random fields

This paper deals with segmentation of noisy images using Gibbs random field (GRF) with an emphasis on modeling of the region process. For noisy image segmentation using the multi-level logistic (MLL) model with the second-order neighborhood system, which is commonly used in image processing, the segmentation performance is degraded significantly in case of low signal to noise ratio. By comparison with the Ising model that explains the magnetic properties of ferromagnetic material, it is evident that the characteristics of the region process modeled using the MLL model with the second-order neighborhood system are different in nature from the expected characteristics of a region. To solve this problem we added the term of the magnetic energy associated with the magnetic field of a spin system (or image) to the energy function of GRF. Using the modified model for the region process, the result of image segmentation was improved and did not depend on the cooling schedule in simulated annealing.     

Narrowband Chan-Vese model of sonar image segmentation: A adaptive ladder initialization approach

A narrowband Chan-Vese model with adaptive ladder initialization approach is proposed in this paper to segment underwater sonar image. Specifically, for the first time, the problem of more iterative times, human intervention necessity and lower segmentation accuracy, which are commonly exist in the SDF and BIF, was solved with the method utilizing the new adaptive ladder initialization of zero level set. Then, to further reduce the impact of the global search on traditional Chan-Vese model, the narrowband Chan-Vese model is introduced. It is shown that by applying the adaptive ladder initialization is ultimately local optimization and accurate segmentation results. On this basis, recurring to analysis of traditional Chan-Vese model law, combined with narrowband Chan-Vese model with adaptive ladder initialization approach, the objective and quantitative analysis method is developed. Finally, segmentation results demonstrate the effectiveness and adaptability of the proposed method.     

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.     

Stable Atlas-based Mapped Prior (STAMP) machine-learning segmentation for multicenter large-scale MRI data

Machine learning (ML)-based segmentation methods are a common technique in the medical image processing field. In spite of numerous research groups that have investigated ML-based segmentation frameworks, there remains unanswered aspects of performance variability for the choice of two key components: ML algorithm and intensity normalization. This investigation reveals that the choice of those elements plays a major part in determining segmentation accuracy and generalizability. The approach we have used in this study aims to evaluate relative benefits of the two elements within a subcortical MRI segmentation framework. Experiments were conducted to contrast eight machine-learning algorithm configurations and 11 normalization strategies for our brain MR segmentation framework. For the intensity normalization, a Stable Atlas-based Mapped Prior (STAMP) was utilized to take better account of contrast along boundaries of structures. Comparing eight machine learning algorithms on down-sampled segmentation MR data, it was obvious that a significant improvement was obtained using ensemble-based ML algorithms (i.e., random forest) or ANN algorithms. Further investigation between these two algorithms also revealed that the random forest results provided exceptionally good agreement with manual delineations by experts. Additional experiments showed that the effect of STAMP-based intensity normalization also improved the robustness of segmentation for multicenter data sets. The constructed framework obtained good multicenter reliability and was successfully applied on a large multicenter MR data set (n > 3000). Less than 10% of automated segmentations were recommended for minimal expert intervention. These results demonstrate the feasibility of using the ML-based segmentation tools for processing large amount of multicenter MR images. We demonstrated dramatically different result profiles in segmentation accuracy according to the choice of ML algorithm and intensity normalization chosen.     

First-order kernel density estimation of abdomen medical image intensity and spatial information and application to segmentation

Kernel density estimators (KDE) used for many medical image applications only consider the intensity information of each pixel or its neighbors without the ability of expressing the structure and shape of tissues and organs, and they suffer from boundary bias problem. In this paper, we propose a new first-order kernel density estimation (FOKDE) method for 1D intensity information and 2D spatial information of medical image in two steps. First, the FOKDE of intensity information is estimated and applied to medical image segmentation with the multi-thresholding algorithm. Second, we estimate the FOKDE of spatial information on the initial segmentation, which can express the structure and shape of organs and tissues. In order to evaluate the FOKDE and KDE of the 2D spatial information, we apply them to medical image segmentation with the hill-climbing strategy. Density estimation experiments and segmentation application results on the simulated dataset and real abdomen CT images show us that the FOKDE has smaller boundary bias than the KDE, and that it can estimate the structure and shape of tissues and organs with spatial information effectively.     

Multistage morphological segmentation of bright-field and fluorescent microscopy images

This paper describes the multistage morphological segmentation method (MSMA) for microscopic cell images. The proposed method enables us to study the cell behaviour by using a sequence of two types of microscopic images: bright field images and/or fluorescent images. The proposed method is based on two types of information: the cell texture coming from the bright field images and intensity of light emission, done by fluorescent markers. The method is dedicated to the image sequences segmentation and it is based on mathematical morphology methods supported by other image processing techniques. The method allows for detecting cells in image independently from a degree of their flattening and from presenting structures which produce the texture. It makes use of some synergic information from the fluorescent light emission image as the support information. The MSMA method has been applied to images acquired during the experiments on neural stem cells as well as to artificial images. In order to validate the method, two types of errors have been considered: the error of cell area detection and the error of cell position using artificial images as the “gold standard”.