Improved Fuzzy C-Means Segmentation Algorithm for Images with Intensity Inhomogeneity

Segmentation of brain magnetic resonance imaging (MRI) data plays an important role in the computer-aided diagnosis and neuroscience research. Fuzzy c-means (FCM) clustering algorithm is one of the most usually used techniques for brain MRI image segmentation because of its fuzzy nature. However, the conventional FCM method fails to carry out segmentation well enough due to intensity inhomogeneity in MRI data. To overcome this issue, we propose an improved algorithm based on FCM clustering for segmentation of brain MRI data. Specifically, we modify the conventional FCM algorithm to allow for intensity inhomogeneity by introducing the regularization of the neighborhood influence and bias field. Results show that our proposed algorithm obtains reasonable segmentation of white matter (WM), gray matter (GM), and cerebrospinal fluid (CSF) from MRI data, which is superior to the expectation-maximization (EM) and conventional FCM methods.

Most fuzzy rule-based image segmentation techniques to date have been primarily developed for gray level images. In this paper, a new algorithm called fuzzy rule-based colour image segmentation (FRCIS) is proposed by extending the generic fuzzy rule-based image segmentation (GFFUS) algorithm G.C. Karmakar, L.S. Dooley [2002] and integrating a novel algorithm for averaging hue angles. Qualitative and quantitative analysis of the performance of FRCIS is examined and contrasted with the popular fuzzy c-means (FCM) and possibilistic c-means (PCM) algorithms for both the hue-saturation-value (HSV) and RGB colour models. Overall, FRCIS provides considerable improvement for many different image types.

Since the phenomena of intensity inhomogeneity in MR images are prominent and adversely affect quantitative image analysis .In this paper ,we propose a novel magnetic resonance (MR) image segmentation approach based on the kernel graph cuts technique .Because of automatic multiregion segmentation and global energy minimization ,the kernel graph cuts method can be applied to many kinds of images segmentation ,such as MR images and so on . To reduce or eliminate intensity inhomogeneity in MR images ,we add the intensity inhomogeneity correction step which is based on fuzzy c-means (FCM) algorithm before the segment procedure .Firstly , the real MR image data obtained after bias corrected by FCM algorithm .Secondly ,we segment the real MR image data by kernel graph cuts method .Experiments show that the kernel graph cuts method with intensity inhomogeneity correction have a better segment result in accuracy and over-segmentation .

In this paper, a suitable novel algorithm has been proposed for segmenting the brain magnetic resonance imaging (MRI) data using an efficient kernelized fuzzy c-means (EKFCM) with spatial constraints. In this proposed algorithm, the Euclidean distance in the standard fuzzy c-means (FCM) is replaced by a Gaussian radial basis function with additive bias. The proposed method will segment the given MRI data automatically, by considering the effects of intensity inhomogeneity, partial volume and noise. The neighbourhood effect acts as a regularizer, and the regularization term is useful in segmenting the MR Imaging corrupted by noise and intensity inhomogeneity. Experimental results on both real and simulated images, prove that the proposed algorithm has higher segmenting accuracy than other segmenting techniques.

Cloud extraction and classification from satellite imagery is important for many applications in remote sensing. Satellite images are segmented based on distance, intensity and texture of the images. The popular segmentation algorithms, k‐means (KM) and fuzzy c‐means (FCM) clustering algorithms, face some problems such as unknown number of groups, unknown initialization and dead centers. In this paper, an unsupervised pixel classification by the KM and FCM algorithms is improved and the selection of centroids is made automatic. The proposed improved k‐means (IKM) and improved fuzzy c‐means (IFCM) clustering algorithms segment the INSAT‐3D satellite's thermal infrared image into low‐level, middle‐level, high‐level clouds and non‐cloudy region. As human beings can easily find the clouds in the satellite images, visible image is used to differentiate the clouds from the background. A threshold is found from the histogram of the visible image to separate the cloudy and non‐cloudy pixels. The other three thresholds to divide the clouds into three types are found from the thermal infrared image's histogram. The segmentation results of IKM and IFCM algorithms are compared with the existing segmentation algorithms. The comparison shows that IFCM algorithm matches well with original image followed by IKM algorithm as compared with existing algorithms.

An algorithm is proposed for the fuzzy segmentation of two and three-dimensional multispectral magnetic resonance (MR) images that have been corrupted by intensity inhomogeneities, also known as shading artifacts. The algorithm is an extension of the two-dimensional adaptive fuzzy C-means algorithm (2-D AFCM) presented in previous work by the authors. This algorithm models the intensity inhomogeneities as a gain field that causes image intensities to smoothly and slowly vary through the image space. It iteratively adapts to the intensity inhomogeneities and is completely automated. In this paper, we fully generalize 2-D AFCM to three-dimensional (3-D) multispectral images. Because of the potential size of 3-D image data, we also describe a new, faster multigrid-based algorithm for its implementation. We show using simulated MR data that 3-D AFCM yields significantly lower error rates than both the standard fuzzy C-means algorithm and several other competing methods when segmenting corrupted images. Its efficacy is further demonstrated using real 3-D scalar and multispectral MR brain images.

Brain Magnetic Resonance Imaging (MRI) image segmentation is one of the critical technologies of clinical medicine, and is the basis of three-dimensional reconstruction and downstream analysis between normal tissues and diseased tissues. However, there are various limitations in brain MRI images, such as gray irregularities, noise, and low contrast, reducing the accuracy of the brain MRI images segmentation. In this paper, we propose two optimization solutions for the fuzzy clustering algorithm based on local Gaussian probability fuzzy C-means (LGP-FCM) model and anisotropic weight fuzzy C-means (AW-FCM) model and apply it in brain MRI image segmentation. An FCM clustering algorithm is proposed based on AW-FCM. By introducing the new neighborhood weight calculation method, each point has the weight of anisotropy, effectively overcomes the influence of noise on the image segmentation. In addition, the LGP model is introduced in the objective function of fuzzy clustering, and a fuzzy clustering segmentation algorithm based on LGP-FCM is proposed. A clustering segmentation algorithm of adaptive scale fuzzy LGP model is proposed. The neighborhood scale corresponding to each pixel in the image is automatically estimated, which improves the robustness of the model and achieves the purpose of precise segmentation. Extensive experimental results demonstrate that the proposed LGP-FCM algorithm outperforms comparison algorithms in terms of sensitivity, specificity and accuracy. LGP-FCM can effectively segment the target regions from brain MRI images.

Brain magnetic resonance (MR) image segmentation is pivotal for quantitative brain analyses, in which statistical models are most commonly used. However, in spite of its computational effectiveness, these models are less capable of handling the intensity non-uniformity (INU) and partial volume effect (PVE), and hence may produce less accurate results. In this paper, a novel brain MR image segmentation algorithm is proposed. To address the INU and PVE, voxel values in each small volume are characterized by a local variational Bayes (LVB) model, which is inferred by the niche differential evolution (NDE) technique to avoid local optima. A probabilistic brain atlas is constructed for each image to incorporate the anatomical prior into the segmentation process. The proposed NDE-LVB algorithm has been compared to the variational expectation-maximization based and genetic algorithm based segmentation algorithms and the segmentation routine in the widely used statistical parametric mapping package on both synthetic and clinical brain MR images. Our results suggest that the NDE-LVB algorithm can differentiate major brain tissue types more effectively and produce more accurate segmentation results.KeywordsImage segmentationMagnetic resonance imaging (MRI)Gaussian mixture modelVariational Bayes inferenceNiche differential evolution

This study proposed automatic detection and segmentation of brain lesion in diffusion-weighted magnetic resonance images (DWI) based on Fuzzy C-Means (FCM). Due to noises and intensity inhomogeneity, FCM technique fails in producing accurate results. Active contour and correlation template are integrated to overcome this problem. The brain lesions are acute stroke and solid tumor foe hyperintense lesions, and necrosis and chronic stroke for hypointense lesions. The proposed analysis framework has been validated by using Jaccard (AO), Dice, false negative rate (FNR) and false positive rate (FPR). FCM with correlation template provides more accurate results compared with FCM with active contour. The results are 0.547, 0.258, 0.192 and 0.687 for Jaccard, FPR, FNR and Dice indices. This method also can segment the lesions precisely.

Multicontext fuzzy clustering for separation of brain tissues in magnetic resonance images

Magnetic resonance (MR) imaging is increasingly being used to assess brain growth and development in infants. Such studies are often based on quantitative analysis of anatomical segmentations of brain MR images. However, the large changes in brain shape and appearance associated with development, the lower signal to noise ratio and partial volume effects in the neonatal brain present challenges for automatic segmentation of neonatal MR imaging data. In this study, we propose a framework for accurate intensity-based segmentation of the developing neonatal brain, from the early preterm period to term-equivalent age, into 50 brain regions. We present a novel segmentation algorithm that models the intensities across the whole brain by introducing a structural hierarchy and anatomical constraints. The proposed method is compared to standard atlas-based techniques and improves label overlaps with respect to manual reference segmentations. We demonstrate that the proposed technique achieves highly accurate results and is very robust across a wide range of gestational ages, from 24 weeks gestational age to term-equivalent age.

Fuzzy algorithms: Application to adipose tissue quantification on MR images

Magnetic resonance images are often corrupted by intensity inhomogeneity (i.e., bias field effects), which manifests itself as slow intensity variations over the image domain. Such shading artifacts must be corrected before performing computerized analyses such as intensity-based segmentation and quantitative analysis. In this paper, we present a novel strategy in the fuzzy c-means (FCM) framework that simultaneously estimates the bias field while segmenting the image. An additive field term that models the bias field is incorporated into the FCM objective function. We propose a new term based on the spectral parameterization (i.e., wavelet coefficients) of the bias field that serves as a regularizer to enforce the smoothness of the estimated bias field. We also introduce a second regularization term that causes the labeling of each pixel to be influenced by its immediate neighborhood pixels. The latter regularization term renders the algorithm less sensitive to noise. We show that the novel objective functional could be optimized efficiently using an iterative process. The efficacy of the algorithm is demonstrated on synthesized images as well as on clinical breast MR images. With the synthesize images, segmentation accuracy using standard FCM is 89.07% while segmentation accuracy with the proposed algorithm is 99.95%.

Fuzzy c-means (FCM) algorithm has been widely used in image segmentation. However, the traditional FCM algorithm does not take into account any image spatial information, which makes it very sensitive to noise. In order to make improvements on the basis of FCM, we proposed a fuzzy entropy clustering image segmentation algorithm based on potential two-dimensional histogram. Firstly, the two-dimensional gray histogram is constructed by using the gray value of image pixels and its local spatial uniform gray value, and the potential function is used to map-the mutual influence between image pixels into the data field, so as to describe the interaction between pixels more accurately. Secondly, the kernel function will be used to map the data to a high dimensional space to complete the linear transformation, this makes the data in the original space linearly indivisible become linearly separable or approximately linearly separable, which overcomes the defect that FCM is not suitable for multiple data distributions in some extent. Finally, the iterative formula of image segmentation is obtained by Lagrange multiplier method. Experimental results show that the proposed algorithm has higher correct segmentation rate and stronger robustness.

Fast and globally convex multiphase active contours for brain MRI segmentation