A vectorial image soft segmentation method based on neighborhood weighted Gaussian mixture model.
TL;DR: A segmentation tool is presented in order to differentiate the anatomical structures within the vectorial volume of the CT uroscan to get a better classification result and is less affected by the noise.
About: This article is published in Computerized Medical Imaging and Graphics.The article was published on 2009-12-01 and is currently open access. It has received 26 citations till now. The article focuses on the topics: Scale-space segmentation & Mixture model.
Summary (1 min read)
Jump to: [1. Introduction] – [2. Gaussian mixture model] and [3. Proposed neighborhood weighted method]
1. Introduction
- The CT uroscan is the classical preoperative examintio for renal surgery.
- It consists of three to four time-spaced 3D acquisitions at several contrast medium diffusion stages, which give complementary information about the kidney anatomy.
- Getting the material probabilities by a soft segmentation method [2] instead of assigning a definite material to the voxels (especially the boundary voxels) will be more conformable to the reality.
- In order to integrate spatial information to the Gaussian mixture model based vectorial data segmentation method, the authors proposed to involve a neighborhood weight within the classification process.
2. Gaussian mixture model
- Each component density follows a Gaussian distribution.
- Based on statistical theory, the parameters are estimated by maximum likelihood (ML) and expectation maximization (EM) algorithm is used as an optimization method.
- Recall that the goal is to estimate the class probabilities on each voxel according to the intensity vectors.
3. Proposed neighborhood weighted method
- The iteration formula described in section 2 didn’t involve any spatial information about current voxel.
- The authors use Eq. (9) to just smooth the class decisions after classification with the classical Gaussian mixture model.
- The results are shown in Fig. 3. Fig. 3(a) illustrates the intensity distribution summation along three axes of the original image.
- Because of the inhomogeneity of the acquisitions and the partial volume effects, the result of the intensity-only method has some misclassification area, especially the renal cortex and the renal medulla because of their close intensity range, which is shown in Fig. 6(a).
- While taking the neighborhood information into the iteration process, the results are improved significantly, as shown in Fig. 7(b).
Did you find this useful? Give us your feedback
Citations
More filters
TL;DR: It is verified that the segmentation results of the improved algorithm have good regional consistency and strong anti-noise robustness, and they meet the needs of noisy image segmentation.
Abstract: This paper addresses the lack of robustness of feature selection algorithms for fuzzy clustering segmentation with the Gaussian mixture model Assuming that the neighbourhood pixels and the centre pixels obey the same distribution, a Markov method is introduced to construct the prior probability distribution and achieve the membership degree regularisation constraint for clustering sample points Then, a noise smoothing factor is introduced to optimise the prior probability constraint Second, a power index is constructed by combining the classification membership degree and prior probability since the Kullback–Leibler (KL) divergence of the noise smoothing factor is used to supervise the prior probability; this probability is embedded into Fuzzy Superpixels Fuzzy C-means (FSFCM) as a regular factor This paper proposes a fuzzy clustering image segmentation algorithm based on an adaptive feature selection Gaussian mixture model with neighbourhood information constraints To verify the segmentation performance and anti-noise robustness of the improved algorithm, the fuzzy C-means clustering algorithm Fuzzy C-means (FCM), FSFCM, Spatially Variant Finite Mixture Model (SVFMM), EGFMM, extended Gaussian mixture model (EGMM), adaptive feature selection robust fuzzy clustering segmentation algorithm (AFSFCM), fast and robust spatially constrained Gaussian mixture model (GMM) for image segmentation (FRSCGMM), and improve method are used to segment grey images containing Gaussian noise, salt-and-pepper noise, multiplicative noise and mixed noise The peak signal-to-noise ratio (PSNR) and the error rate (MCR) are used as the theoretical basis for assessing the segmentation results The improved algorithm indicators proposed in this paper are optimised The improved algorithm yields increases of 01272–129803 dB, 15501–134396 dB, 19113–112613 dB and 10233–102804 dB over the other methods, and the Misclassification rate (MSR) decreases by 032–3732%, 502–4105%, 03–2179% and 09–3095% compared to that with the other algorithms It is verified that the segmentation results of the improved algorithm have good regional consistency and strong anti-noise robustness, and they meet the needs of noisy image segmentation
5 citations
06 Dec 2010
Abstract: NA
5 citations
TL;DR: A method for interventional perfusion estimation in peripherals using C-arms which is based on DSA and two additional 3D images reconstructed from rotational scans is proposed and the use of spatial and temporal regularization proved to be an effective way to limit inaccuracies due to instability in the solution of the inverse problem.
Abstract: The outcome assessment of endovascular revascularization procedures in the lower limbs is currently carried out by x-ray digital subtraction angiography (DSA). Due to the two-dimensional nature of this technique, only visual assessment of arterial blood flow is possible and no tissue blood flow information (i.e. perfusion) is available to assess the effective restoration of blood supply to the tissue. In this work, we propose a method for interventional perfusion estimation in peripherals using C-arms which is based on DSA and two additional 3D images reconstructed from rotational scans. The method assumes spatial homogeneity of contrast within multiple regions identified by segmentation of the reconstructed 3D images. A dedicated segmentation method which relies on local contrast homogeneity and connectivity of anatomical structures is introduced. Region-based perfusion is obtained by mapping the 2D blood flow information from DSA to the 3D segments by solving an inverse problem. Instability of the solution due to the spatial overlap of the regions is addressed by applying spatial and temporal regularizations. The method was evaluated on data simulated from CT perfusion scans of the lower limb. Blood flow values estimated with the optimal number of segmented regions exhibited errors of 1 ± 4 and 2 ± 11 ml/100 ml min−1 for the two analyzed cases, respectively, which showed to be sufficient to differentiate hypoperfused and normally perfused areas. The use of spatial and temporal regularization proved to be an effective way to limit inaccuracies due to instability in the solution of the inverse problem. Results in general proved the feasibility of C-arm interventional perfusion imaging by a combination of temporal information derived from DSA and spatial information derived from 3D reconstructions.
5 citations
TL;DR: The kernel density estimation method is used to estimate the number of components K, and three strategies are proposed to improve the segmentation speed of GMMs, showing that the proposed algorithm has better performance in generating explainable segmentations with faster speed than the common GMMs algorithm.
Abstract: The Gaussian mixture models (GMMs) is a flexible and powerful density clustering tool However, the application of it to medical image segmentation faces some difficulties First, estimation of the number of components is still an open question Second, the speed of it for large medical image is slow Moreover, GMMs has the problem of noise sensitivity In this paper, the kernel density estimation method is used to estimate the number of components K, and three strategies are proposed to improve the segmentation speed of GMMs First, a histogram stratification sampling strategy is proposed to reduce the size of the training data Second, a binning strategy is proposed to search the neighbor points of each center data to compute the approximate density function of the samples Third, a hill-climbing algorithm with the dynamic step size is designed to find the local maxima of the density function The kernel density estimation method and sampling technology reduce the effect of noise Experimental results with the simulated brain images and real CT images show that the proposed algorithm has better performance in generating explainable segmentations with faster speed than the common GMMs algorithm
4 citations
Cites methods from "A vectorial image soft segmentation..."
...In the wide range of segmentation methods, clustering algorithms are termed unsupervised classification methods that organize unlabeled feature vectors into clusters or “natural groups” so that the samples within a cluster are more similar to each other than the samples belonging to different clusters [ 8 ]....
[...]
...Most unsupervised clustering techniques [9], including statistical-based clustering [2,5, 8 ], neural network–based clustering [10] and various fuzzy clustering [1,11–13], have been used to accomplish this task....
[...]
21 Nov 2013
TL;DR: This thesis builds on the existing literature on classification approaches that use MR image textures for early detection of AD and focuses on a type of lesions in the white matter, which are thought to play a role in cognitive decline.
Abstract: Early detection of Alzheimer’s disease (AD) is essential to provide the patients with adequate and timely treatments and to help researchers monitor their effectiveness. Structural Magnetic Resonance Imaging (MRI) is a diagnostic tool that provides high-resolution images and a high brain tissue contrast.
Classification methods have been proposed that use MRI-based biomarkers as features to distinguish between normal controls and AD patients. Most approaches rely substantially on the quality of at least one of the following: 1) the assumptions of which brain regions are affected; 2) the segmentation of these brain structures, which suffers from large variability across studies; 3) a voxelwise inter-subject correspondence, which is difficult to achieve, particularly considering the large anatomical variability of the brain across different subjects. Also, such methods focus on structural (volume, shape, density) changes only. It has recently been considered that also the MR image intensities and textures can provide complementary information that is overlooked by the structural-based features.
In this thesis, we build on the existing literature on classification approaches that use MR image textures for early detection of AD. Firstly, we focus our analysis on a type of lesions in the white matter, which are thought to play a role in cognitive decline. Results show that the lesion textures are more discriminative than the widely used lesion volumes and locations.
Secondly, we propose three approaches that use texture descriptors, determined at local patches over the entire brain. Results show that: 1) texture descriptors are able to achieve high classification rates, comparably to structural-based features; 2) no assumptions need to be made about the expectedly affected brain regions, and consequently no prior segmentations are needed; 3) by only affine-registering the images we are still able to localize discriminative regions using finely sampled patches in the brain.
4 citations
References
More filters
49,597 citations
TL;DR: The authors propose a novel hidden Markov random field (HMRF) model, which is a stochastic process generated by a MRF whose state sequence cannot be observed directly but which can be indirectly estimated through observations.
Abstract: The finite mixture (FM) model is the most commonly used model for statistical segmentation of brain magnetic resonance (MR) images because of its simple mathematical form and the piecewise constant nature of ideal brain MR images. However, being a histogram-based model, the FM has an intrinsic limitation-no spatial information is taken into account. This causes the FM model to work only on well-defined images with low levels of noise; unfortunately, this is often not the the case due to artifacts such as partial volume effect and bias field distortion. Under these conditions, FM model-based methods produce unreliable results. Here, the authors propose a novel hidden Markov random field (HMRF) model, which is a stochastic process generated by a MRF whose state sequence cannot be observed directly but which can be indirectly estimated through observations. Mathematically, it can be shown that the FM model is a degenerate version of the HMRF model. The advantage of the HMRF model derives from the way in which the spatial information is encoded through the mutual influences of neighboring sites. Although MRF modeling has been employed in MR image segmentation by other researchers, most reported methods are limited to using MRF as a general prior in an FM model-based approach. To fit the HMRF model, an EM algorithm is used. The authors show that by incorporating both the HMRF model and the EM algorithm into a HMRF-EM framework, an accurate and robust segmentation can be achieved. More importantly, the HMRF-EM framework can easily be combined with other techniques. As an example, the authors show how the bias field correction algorithm of Guillemaud and Brady (1997) can be incorporated into this framework to achieve a three-dimensional fully automated approach for brain MR image segmentation.
6,335 citations
Journal Article•
TL;DR: In this paper, the authors describe the EM algorithm for finding the parameters of a mixture of Gaussian densities and a hidden Markov model (HMM) for both discrete and Gaussian mixture observation models.
Abstract: We describe the maximum-likelihood parameter estimation problem and how the ExpectationMaximization (EM) algorithm can be used for its solution. We first describe the abstract form of the EM algorithm as it is often given in the literature. We then develop the EM parameter estimation procedure for two applications: 1) finding the parameters of a mixture of Gaussian densities, and 2) finding the parameters of a hidden Markov model (HMM) (i.e., the Baum-Welch algorithm) for both discrete and Gaussian mixture observation models. We derive the update equations in fairly explicit detail but we do not prove any convergence properties. We try to emphasize intuition rather than mathematical rigor.
2,455 citations
TL;DR: A critical appraisal of the current status of semi-automated and automated methods for the segmentation of anatomical medical images is presented, with an emphasis on the advantages and disadvantages of these methods for medical imaging applications.
Abstract: ▪ Abstract Image segmentation plays a crucial role in many medical-imaging applications, by automating or facilitating the delineation of anatomical structures and other regions of interest. We present a critical appraisal of the current status of semiautomated and automated methods for the segmentation of anatomical medical images. Terminology and important issues in image segmentation are first presented. Current segmentation approaches are then reviewed with an emphasis on the advantages and disadvantages of these methods for medical imaging applications. We conclude with a discussion on the future of image segmentation methods in biomedical research.
2,230 citations
"A vectorial image soft segmentation..." refers methods in this paper
...Getting the material probabilities by a soft segmentation method [2] instead of assigning a definite material to the vox els...
[...]
TL;DR: Use of the expectation-maximization (EM) algorithm leads to a method that allows for more accurate segmentation of tissue types as well as better visualization of magnetic resonance imaging data, that has proven to be effective in a study that includes more than 1000 brain scans.
Abstract: Intensity-based classification of MR images has proven problematic, even when advanced techniques are used. Intrascan and interscan intensity inhomogeneities are a common source of difficulty. While reported methods have had some success in correcting intrascan inhomogeneities, such methods require supervision for the individual scan. This paper describes a new method called adaptive segmentation that uses knowledge of tissue intensity properties and intensity inhomogeneities to correct and segment MR images. Use of the expectation-maximization (EM) algorithm leads to a method that allows for more accurate segmentation of tissue types as well as better visualization of magnetic resonance imaging (MRI) data, that has proven to be effective in a study that includes more than 1000 brain scans. Implementation and results are described for segmenting the brain in the following types of images: axial (dual-echo spin-echo), coronal [three dimensional Fourier transform (3-DFT) gradient-echo T1-weighted] all using a conventional head coil, and a sagittal section acquired using a surface coil. The accuracy of adaptive segmentation was found to be comparable with manual segmentation, and closer to manual segmentation than supervised multivariant classification while segmenting gray and white matter.
1,328 citations