Quantification and Segmentation of Brain Tissues from MR Images: A Probabilistic Neural Network Approach

Application of Clustering-Based Analysis in MRI Brain Tissue Segmentation

The segmentation of brain tissue by MRI not only contributes to the study of the function and anatomical structure of the brain, but it also offers a theoretical foundation for the diagnosis and treatment of brain illnesses. When discussing the anatomy of the brain in a clinical setting, the terms “white matter,” “gray matter,” and “cerebrospinal fluid” are the ones most frequently used (CSF). However, due to the fact that the human brain is highly complicated in its structure and that there are many different types of brain tissues, the human brain structure of each individual has its own set of distinctive qualities. Because of these several circumstances, the process of segmenting brain tissue will be challenging. In this article, several different clustering algorithms will be discussed, and their performance and effects will be compared to one another. The goal of this comparison is to determine which algorithm is most suited for segmenting MRI brain tissue. Based on the clustering method, the primary emphasis of this research is placed on the segmentation approach that is appropriate for medical brain imaging. The qualitative and quantitative findings of the experiment reveal that the FCM algorithm has more steady performance and better universality, but it is necessary to include the additional auxiliary conditions in order to achieve more ideal outcomes.

Resolving-power domination number of probabilistic neural networks

Power utilities must track their power networks to respond to changing demand and availability conditions to ensure effective and efficient operation. As a result, several power companies continuously employ phase measuring units (PMUs) to continuously check their power networks. Supervising an electric power system with the fewest possible measurement equipment is precisely the vertex covering graph-theoretic problems otherwise a variation of the dominating set problem, in which a set D is defined as a power dominating set (PDS) of a graph if it supervises every vertex and edge in the system with a couple of rules. If the distance vector eccentrically characterizes each node in G with respect to the nodes in R, then the subset R of V (G) is a resolving set of G. The problem of finding power dominating set and resolving set problems are proven to be NP-complete in general. The finite subset R of V (G) is said to be resolving-power dominating set (RPDS) if it is both resolving and power dominating set, which is another NP-complete problem. The ηp (G) is the minimal cardinality of an RPDS of a graph G. A neural network is a collection of algorithms that tries to figure out the underlying correlations in a set of data by employing a method that replicates how the human brain functions. Various neural networks have seen rapid progress in multiple fields of study during the last few decades, including neurochemistry, artificial intelligence, automatic control, and informational sciences. Probabilistic neural networks (PNNs) offer a scalable alternative to traditional back-propagation neural networks in classification and pattern recognition applications. They do not necessitate the massive forward and backward calculations that ordinary neural networks entail. This paper investigates the resolving-power domination number of probabilistic neural networks.

Topological Properties of Four-Layered Neural Networks

A topological property or index of a network is a numeric number which characterises the whole structure of the underlying network. It is used to predict the certain changes in the bio, chemical and physical activities of the networks. The 4-layered probabilistic neural networks are more general than the 3-layered probabilistic neural networks. Javaid and Cao [Neural Comput. and Applic., DOI 10.1007/s00521-017-2972-1] and Liu et al. [Journal of Artificial Intelligence and Soft Computing Research, 8(2018), 225-266] studied the certain degree and distance based topological indices (TI’s) of the 3-layered probabilistic neural networks. In this paper, we extend this study to the 4-layered probabilistic neural networks and compute the certain degree-based TI’s. In the end, a comparison between all the computed indices is included and it is also proved that the TI’s of the 4-layered probabilistic neural networks are better being strictly greater than the 3-layered probabilistic neural networks.

Intelligent Computing in Medical Imaging

Biomedical imaging is considered main procedure to acquire valuable physical information about the human body and some other biological species. It produces specialized images of different parts of the biological species for clinical analysis. It assimilates various specialized domains including nuclear medicine, radiological imaging, Positron emission tomography (PET), and microscopy. From the early discovery of X-rays, progress in biomedical imaging continued resulting in highly sophisticated medical imaging modalities, such as magnetic resonance imaging (MRI), ultrasound, Computed Tomography (CT), and lungs monitoring. These biomedical imaging techniques assist physicians for faster and accurate analysis and treatment. The present chapter discussed the impact of intelligent computing methods for biomedical image analysis and healthcare. Different Artificial Intelligence (AI) based automated biomedical image analysis are considered. Different approaches are discussed including the AI ability to resolve various medical imaging problems. It also introduced the popular AI procedures that employed to solve some special problems in medicine. Artificial Neural Network (ANN) and support vector machine (SVM) are active to classify different types of images from various imaging modalities. Different diagnostic analysis, such as mammogram analysis, MRI brain image analysis, CT images, PET images, and bone/retinal analysis using ANN, feed-forward back propagation ANN, probabilistic ANN, and extreme learning machine continuously. Various optimization techniques of ant colony optimization (ACO), genetic algorithm (GA), particle swarm optimization (PSO) and other bio-inspired procedures are also frequently conducted for feature extraction/selection and classification. The advantages and disadvantages of some AI approaches are discussed in the present chapter along with some suggested future research perspectives.

Integration of Network Biology and Imaging to Study Cancer Phenotypes and Responses

Ever growing "omics" data and continuously accumulated biological knowledge provide an unprecedented opportunity to identify molecular biomarkers and their interactions that are responsible for cancer phenotypes that can be accurately defined by clinical measurements such as in vivo imaging. Since signaling or regulatory networks are dynamic and context-specific, systematic efforts to characterize such structural alterations must effectively distinguish significant network rewiring from random background fluctuations. Here we introduced a novel integration of network biology and imaging to study cancer phenotypes and responses to treatments at the molecular systems level. Specifically, Differential Dependence Network (DDN) analysis was used to detect statistically significant topological rewiring in molecular networks between two phenotypic conditions, and in vivo Magnetic Resonance Imaging (MRI) was used to more accurately define phenotypic sample groups for such differential analysis. We applied DDN to analyze two distinct phenotypic groups of breast cancer and study how genomic instability affects the molecular network topologies in high-grade ovarian cancer. Further, FDA-approved arsenic trioxide (ATO) and the ND2-SmoA1 mouse model of Medulloblastoma (MB) were used to extend our analyses of combined MRI and Reverse Phase Protein Microarray (RPMA) data to assess tumor responses to ATO and to uncover the complexity of therapeutic molecular biology.

Unsupervised Neural Techniques Applied to MR Brain Image Segmentation

The primary goal of brain image segmentation is to partition a given brain image into different regions representing anatomical structures. Magnetic resonance image (MRI) segmentation is especially interesting, since accurate segmentation in white matter, grey matter and cerebrospinal fluid provides a way to identify many brain disorders such as dementia, schizophrenia or Alzheimer’s disease (AD). Then, image segmentation results in a very interesting tool for neuroanatomical analyses. In this paper we show three alternatives to MR brain image segmentation algorithms, with the Self-Organizing Map (SOM) as the core of the algorithms. The procedures devised do not use any a priori knowledge about voxel class assignment, and results in fully-unsupervised methods for MRI segmentation, making it possible to automatically discover different tissue classes. Our algorithm has been tested using the images from the Internet Brain Image Repository (IBSR) outperforming existing methods, providing values for the average overlap metric of 0.7 for the white and grey matter and 0.45 for the cerebrospinal fluid. Furthermore, it also provides good results for high-resolution MR images provided by the Nuclear Medicine Service of the “Virgen de las Nieves” Hospital (Granada, Spain).

REGION SIMILARITY RELATIONSHIP BETWEEN WATERSHED AND PENALIZED FUZZY HOPFIELD NEURAL NETWORK ALGORITHMS FOR BRAIN IMAGE SEGMENTATION

A robust image segmentation method that combines the watershed segmentation and penalized fuzzy Hopfield neural network (PFHNN) algorithms to minimize undesirable over-segmentation is described in this paper. This method incorporates spatial graph representation derived from the watershed segmented regions and cluster analysis information obtained from the PFHNN algorithm to achieve efficient image segmentation. The proposed scheme employs the Markov random field (MRF) model on the region adjacency graph (RAG) to improve the quality of watershed segmentation. Here, the fusion criterion is according to the correlation coefficient, which uses inter-region similarities to determine the merging of regions. Analysis of the performance of the proposed technique is presented through quantitative and qualitative validation experiments on benchmark images, and significant and promising segmentation results are presented using brain phantom simulated data.

NEW SELF-ADAPTIVE PROBABILISTIC NEURAL NETWORKS IN BIOINFORMATIC AND MEDICAL TASKS

We propose a self–adaptive probabilistic neural network model, which incorporates optimization algorithms to determine its spread parameters. The performance of the proposed model is investigated on two protein localization problems, as well as on two medical diagnostic tasks. Experimental results are compared with that of feedforward neural networks and support vector machines. Different sampling techniques are used and statistical tests are conducted to calculate the statistical significance of the results.

Automatic segmentation of brain white matter and white matter lesions in normal aging: comparison of five multispectral techniques

White matter loss, ventricular enlargement and white matter lesions are common findings on brain scans of older subjects. Accurate assessment of these different features is therefore essential for normal aging research. Recently, we developed a novel unsupervised classification method, named 'Multispectral Coloring Modulation and Variance Identification' (MCMxxxVI), that fuses two different structural magnetic resonance imaging (MRI) sequences in red/green color space and uses Minimum Variance Quantization (MVQ) as the clustering technique to segment different tissue types. Here we investigate how this method performs compared with several commonly used supervised image classifiers in segmenting normal-appearing white matter, white matter lesions and cerebrospinal fluid in the brains of 20 older subjects with a wide range of white matter lesion load and brain atrophy. The three tissue classes were segmented from T(1)-, T(2)-, T(2)⁎- and fluid attenuation inversion recovery (FLAIR)-weighted structural MRI data using MCMxxxVI and the four supervised multispectral classifiers available in the Analyze package, namely, Back-Propagated Neural Networks, Gaussian classifier, Nearest Neighbor and Parzen Windows. Bland-Altman analysis and Jaccard index values indicated that, in general, MCMxxxVI performed better than the supervised multispectral classifiers in identifying the three tissue classes, although final manual editing was still required to deliver radiologically acceptable results. These analyses show that MVQ, as implemented in MCMxxxVI, has the potential to provide quick and accurate white matter segmentations in the aging brain, although further methodological developments are still required to automate fully this technique.

New multispectral MRI data fusion technique for white matter lesion segmentation: method and comparison with thresholding in FLAIR images

Objective

Brain tissue segmentation by conventional threshold-based techniques may have limited accuracy and repeatability in older subjects. We present a new multispectral magnetic resonance (MR) image analysis approach for segmenting normal and abnormal brain tissue, including white matter lesions (WMLs).

Methods

We modulated two 1.5T MR sequences in the red/green colour space and calculated the tissue volumes using minimum variance quantisation. We tested it on 14 subjects, mean age 73.3 ± 10 years, representing the full range of WMLs and atrophy. We compared the results of WML segmentation with those using FLAIR-derived thresholds, examined the effect of sampling location, WML amount and field inhomogeneities, and tested observer reliability and accuracy.

Results

FLAIR-derived thresholds were significantly affected by the location used to derive the threshold (P = 0.0004) and by WML volume (P = 0.0003), and had higher intra-rater variability than the multispectral technique (mean difference ± SD: 759 ± 733 versus 69 ± 326 voxels respectively). The multispectral technique misclassified 16 times fewer WMLs.

Conclusion

Initial testing suggests that the multispectral technique is highly reproducible and accurate with the potential to be applied to routinely collected clinical MRI data.

Electronic supplementary material

The online version of this article (doi:10.1007/s00330-010-1718-6) contains supplementary material, which is available to authorized users.

Survey on Neural Networks Used for Medical Image Processing

This paper aims to present a review of neural networks used in medical image processing. We classify neural networks by its processing goals and the nature of medical images. Main contributions, advantages, and drawbacks of the methods are mentioned in the paper. Problematic issues of neural network application for medical image processing and an outlook for the future research are also discussed. By this survey, we try to answer the following two important questions: (1) What are the major applications of neural networks in medical image processing now and in the nearby future? (2) What are the major strengths and weakness of applying neural networks for solving medical image processing tasks? We believe that this would be very helpful researchers who are involved in medical image processing with neural network techniques.

Brain MR images segmentation using statistical ratio: mapping between watershed and competitive Hopfield clustering network algorithms

Conventional watershed segmentation methods invariably produce over-segmented images due to the presence of noise or local irregularities in the source images. In this paper, a robust medical image segmentation technique is proposed, which combines watershed segmentation and the competitive Hopfield clustering network (CHCN) algorithm to minimize undesirable over-segmentation. In the proposed method, a region merging method is presented, which is based on employing the region adjacency graph (RAG) to improve the quality of watershed segmentation. The relation of inter-region similarities is then investigated using image mapping in the watershed and CHCN images to determine more appropriate region merging. The performance of the proposed technique is presented through quantitative and qualitative validation experiments on benchmark images. Significant and promising segmentation results were achieved on brain phantom simulated data.

An adaptive markov model-based method to cluster validation in image segmentation

The number of class should be detected as part of the parameter estimation procedure prior to image segmentation for segmentation algorithms. It is very important in theory and application for estimating the class number correctly. In this paper, an adaptive total energy criterion (ATEC) to cluster validation is proposed based on the Markov random field (MRF) in the image segmentation. The criterion is composed of two parts: one part is inner-energy, which describes the difference of data in the same class; another is inter-class energy, which describes the edge information. The correct class number can be obtained by minimizing the ATEC. The parameters are estimated by expectation maximum (EM) algorithm and maximum psedu-likelihood (MPL) algorithm. The complex computation is optimized by the mixture of simulated algorithm (SA) and iterated conditional mode (ICM). The experiments show that the class number can be automatically detected by adjusting the hyper-parameter in MRF. As a by-product, the segmentation can be obtained by the maximum a posteriori (MAP).

Parameter estimation in stochastic mammogram model by heuristic optimization techniques

The appearance of disproportionately large amounts of high-density breast parenchyma in mammograms has been found to be a strong indicator of the risk of developing breast cancer. Hence, the breast density model is popular for risk estimation or for monitoring breast density change in prevention or intervention programs. However, the efficiency of such a stochastic model depends on the accuracy of estimation of the model's parameter set. We propose a new approach-heuristic optimization-to estimate more accurately the model parameter set as compared to the conventional and popular expectation-maximization (EM) algorithm. After initial segmentation of a given mammogram, the finite generalized Gaussian mixture (FGGM) model is constructed by computing the statistics associated with different image regions. The model parameter set thus obtained is estimated by particle swarm optimization (PSO) and evolutionary programming (EP) techniques, where the objective function to be minimized is the relative entropy between the image histogram and the estimated density distributions. When our heuristic approach was applied to different categories of mammograms from the Mini-MIAS database, it yielded lower floor of estimation error in 109 out of 112 cases (97.3 %), and 101 out of 102 cases (99.0%), for the number of image regions being five and eight, respectively, with the added advantage of faster convergence rate, when compared to the EM approach. Besides, the estimated density model preserves the number of regions specified by the information-theoretic criteria in all the test cases, and the assessment of the segmentation results by radiologists is promising.

Data-driven brain MRI segmentation supported on edge confidence and a priori tissue information

Brain magnetic resonance imaging segmentation is accomplished in this work by applying nonparametric density estimation, using the mean shift algorithm in the joint spatial-range domain. The quality of the class boundaries is improved by including an edge confidence map, that represents the confidence of truly being in the presence of a border between adjacent regions; an adjacency graph is then constructed with the labeled regions, and analyzed and pruned to merge adjacent regions. In order to assign image regions to a cerebral tissue type, a spatial normalization between image data and standard probability maps is carried out, so that for each structure a maximum a posteriori probability criterion is applied. The method was applied to synthetic and real images, keeping all parameters constant throughout the process for each type of data. The combination of region segmentation and edge detection proved to be a robust technique, as adequate clusters were automatically identified, regardless of the noise level and bias. In a comparison with reference segmentations, average Tanimoto indexes of 0.90-0.99 were obtained for synthetic data and of 0.59-0.99 for real data, considering gray matter, white matter, and background.

Brain white and gray matter anatomy of MRI segmentation based on tissue evaluation

Different approaches to gray and white matter measurements in magnetic resonance imaging (MRI) have been studied. For clinical use, the estimated values must be reliable and accurate when, unfortunately, many techniques fail on these criteria in an unrestricted clinical environment. A recent method for tissue clusterization in MRI analysis has the advantage of great simplicity, and it takes the account of partial volume effects. In this study, we will evaluate the intensity of MR sequences known as T1-weighted images in an axial sliced section. Intensity group clustering algorithms are proposed to achieve further diagnosis for brain MRI, which has been hardly studied. Subjective study has been suggested to evaluate the clustering group intensity in order to obtain the best diagnosis as well as better detection for the suspected cases. This technique makes use of image tissue biases of intensity value pixels to provide 2 regions of interest as techniques. Moreover, the original mathematic solution could still be used with a specific set of modern sequences. There are many advantages to generalize the solution, which give far more scope for application and greater accuracy.

Whole brain segmentation: automated labeling of neuroanatomical structures in the human brain

We present a technique for automatically assigning a neuroanatomical label to each voxel in an MRI volume based on probabilistic information automatically estimated from a manually labeled training set. In contrast to existing segmentation procedures that only label a small number of tissue classes, the current method assigns one of 37 labels to each voxel, including left and right caudate, putamen, pallidum, thalamus, lateral ventricles, hippocampus, and amygdala. The classification technique employs a registration procedure that is robust to anatomical variability, including the ventricular enlargement typically associated with neurological diseases and aging. The technique is shown to be comparable in accuracy to manual labeling, and of sufficient sensitivity to robustly detect changes in the volume of noncortical structures that presage the onset of probable Alzheimer's disease.

Information-theoretic matching of two point sets

This paper describes the theoretic roadmap of least relative entropy matching of two point sets. The novel feature is to align two point sets without needing to establish explicit point correspondences. The recovery of transformational geometry is achieved using a mixture of principal axes registrations, whose parameters are estimated by minimizing the relative entropy between the two point distributions and using the expectation-maximization algorithm. We give evidence of the optimality of the method and we then evaluate the algorithm's performance in both rigid and nonrigid image registration cases.

Magnetic resonance image analysis by information theoretic criteria and stochastic site models

Quantitative analysis of magnetic resonance (MR) images is a powerful tool for image-guided diagnosis, monitoring, and intervention. The major tasks involve tissue quantification and image segmentation where both the pixel and context images are considered. To extract clinically useful information from images that might be lacking in prior knowledge, we introduce an unsupervised tissue characterization algorithm that is both statistically principled and patient specific. The method uses adaptive standard finite normal mixture and inhomogeneous Markov random field models, whose parameters are estimated using expectation-maximization and relaxation labeling algorithms under information theoretic criteria. We demonstrate the successful applications of the approach with synthetic data sets and then with real MR brain images.

Computerized radiographic mass detection--part I: Lesion site selection by morphological enhancement and contextual segmentation

This paper presents a statistical model supported approach for enhanced segmentation and extraction of suspicious mass areas from mammographic images. With an appropriate statistical description of various discriminate characteristics of both true and false candidates from the localized areas, an improved mass detection may be achieved in computer-assisted diagnosis (CAD). In this study, one type of morphological operation is derived to enhance disease patterns of suspected masses by cleaning up unrelated background clutters, and a model-based image segmentation is performed to localize the suspected mass areas using stochastic relaxation labeling scheme. We discuss the importance of model selection when a finite generalized Gaussian mixture is employed, and use the information theoretic criteria to determine the optimal model structure and parameters. Examples are presented to show the effectiveness of the proposed methods on mass lesion enhancement and segmentation when applied to mammographical images. Experimental results demonstrate that the proposed method achieves a very satisfactory performance as a preprocessing procedure for mass detection in CAD.

Estimating gain fields in multispectral MRI

An unsupervised, completely automatic method for gain field estimation and segmentation of multispectral magnetic resonance (MR) images is presented. This new adaptive algorithm is based on statistical modeling of MR images using finite mixtures. Variability of gain field artifact with imaging parameters (i.e. TE, TR, and TI) is considered in the estimation process. Beside gain field, partial volume artifact is also considered in the labeling phase. Quantitative analysis on experimental results shows an efficient and robust performance of the adaptive algorithm and that it outperforms even advanced nonadaptive intensity-based approaches.