Mohd Ezane Aziz

A hybrid harmony search algorithm for MRI brain segmentation

Automatic magnetic resonance imaging (MRI) brain segmentation is a challenging problem that has received significant attention in the field of medical image processing. In this paper, we present a new dynamic clustering algorithm based on the hybridization of harmony search (HS) and fuzzy c-means to automatically segment MRI brain images in an intelligent manner. In our algorithm, the capability of standard HS is modified to automatically evolve the appropriate number of clusters as well as the locations of cluster centers. By incorporating the concept of variable length encoding in each harmony memory vector, this algorithm is able to represent variable numbers of candidate cluster centers at each iteration. A new HS operator, called the “empty operator”, has been introduced to support the selection of empty decision variables in the harmony memory vector. The PBMF cluster validity index is used as an objective function to validate the clustering result obtained from each harmony memory vector. Evaluation of the proposed algorithm has been performed using both real MRI data obtained from the Center for Morphometric Analysis at Massachusetts General Hospital and simulated MRI data generated using the McGill University BrainWeb MRI simulator. Experimental results show the ability of this algorithm to find the appropriate number of naturally occurring regions in brain images. Furthermore, the superiority of the proposed algorithm over various state-of-the-art segmentation algorithms is demonstrated quantitatively.

Dynamic fuzzy clustering using Harmony Search with application to image segmentation

In this paper, a new dynamic clustering approach based on the Harmony Search algorithm (HS) called DCHS is proposed. In this algorithm, the capability of standard HS is modified to automatically evolve the appropriate number of clusters as well as the locations of cluster centers. By incorporating the concept of variable length in each harmony memory vector, DCHS is able to encode variable numbers of candidate cluster centers at each iteration. The PBMF cluster validity index is used as an objective function to validate the clustering result obtained from each harmony memory vector. The proposed approach has been applied onto well known natural images and experimental results show that DCHS is able to find the appropriate number of clusters and locations of cluster centers. This approach has also been compared with other metaheuristic dynamic clustering techniques and has shown to be very promising.

A hybrid Harmony Search algorithm to MRI brain segmentation

Automatic brain MRI image segmentation is a challenging problem and received significant attention in the field of medical image processing. In this paper, we present a new dynamic clustering algorithm based on the Harmony Search (HS) hybridized with Fuzzy C-means called DCHS to automatically segment the brain MRI image in an intelligent manner. In this algorithm, the capability of standard HS is modified to automatically evolve the appropriate number of clusters as well as the locations of cluster centers. By incorporating the concept of variable length in each harmony memory vector, DCHS is able to encode variable numbers of candidate cluster centers at each iteration. Furthermore, a new HS operator, called the ‘empty operator’ is introduced to support the selection of empty decision variables in the harmony memory vector. The PBMF cluster validity index is used as an objective function to validate the clustering result obtained from each harmony memory vector. The proposed algorithm is applied on several simulated T1-weighted normal and MS lesion magnetic resonance brain images. The experimental results show the ability of DCHS to find the appropriate number of naturally occurring regions in brain images. Furthermore, superiority of the proposed algorithm over different clustering-based algorithms is demonstrated quantitatively. All the segmented results obtained by DCHS are also compared with the available ground truth images.

Harmony search-based cluster initialization for fuzzy c-means segmentation of MR images

We propose a new approach to tackle the well known fuzzy c-means (FCM) initialization problem. Our approach uses a metaheuristic search method called Harmony Search (HS) algorithm to produce near-optimal initial cluster centers for the FCM algorithm. We then demonstrate the effectiveness of our approach in a MRI segmentation problem. In order to dramatically reduce the computation time to find near-optimal cluster centers, we use an alternate representation of the search space. Our experiments indicate encouraging results in producing stable clustering for the given problem as compared to using an FCM with randomly initialized cluster centers.

Wavelet energy-guided level set-based active contour: A segmentation method to segment highly similar regions

This paper introduces an approach to perform segmentation of regions in computed tomography (CT) images that exhibit intra-region intensity variations and at the same time have similar intensity distributions with surrounding/adjacent regions. In this work, we adapt a feature computed from wavelet transform called wavelet energy to represent the region information. The wavelet energy is embedded into a level set model to formulate the segmentation model called wavelet energy-guided level set-based active contour (WELSAC). The WELSAC model is evaluated using several synthetic and CT images focusing on tumour cases, which contain regions demonstrating the characteristics of intra-region intensity variations and having high similarity in intensity distributions with the adjacent regions. The obtained results show that the proposed WELSAC model is able to segment regions of interest in close correspondence with the manual delineation provided by the medical experts and to provide a solution for tumour detection.

A Novel Image Segmentation Algorithm Based on Harmony Fuzzy Search Algorithm

Image segmentation is considered as one of the crucial steps in image analysis process and it is the most challenging task. Image segmentation can be modeled as a clustering problem. Therefore, clustering algorithms have been applied successfully in image segmentation problems. Fuzzy c-mean (FCM) algorithm is considered as one of the most popular clustering algorithm. Even that, FCM can generate a local optimal solution. In this paper we propose a novel Harmony Fuzzy Image Segmentation Algorithm (HFISA) which is based on Harmony Search (HS) algorithm. A model of HS which uses fuzzy memberships of image pixels to a predefined number of clusters as decision variables, rather than centroids of clusters, is implemented to achieve better image segmentation results and at the same time, avoid local optima problem. The proposed algorithm is applied onto six different types of images. The experiment results show the efficiency of the proposed algorithm compared to the fuzzy c-means algorithm.

CR images of metacarpel cortical edge detection-bone profile histogram approximation method

The conventional criterion for fracture risk assessment is measured based on bone mineral density (BMD). These are measured using bone densitometry machines. Although there is a strong association between bone strength and BMD, it cannot sufficiently predict fracture risk in osteoperotic patients. In view of this a more accurate measurement of bone strength is required. Bone strength are measured by geometric measurement of the bone cortical area. Cortical thickness can be measured by finding the edges of the endosteal and the periosteal of the cortical bone. Image segmentation methods could be used to find these edges. This paper presents a method of finding these edges from the radiograph of non-dominant hand. Measurements are made from metacarpal two, three and four. The edge detection module developed is based on bone profile histogram approximation algorithm. However better cortical outline can only be obtained after preprocessing the images with smoothing filters. Evaluation is done by comparing the measurements of the inner and outer cortical diameter obtained from the processed images with manual measurements using mirocalipers.

Fusion of fuzzy heuristic and particle swarm optimization as an edge detector

The purpose of this paper is to study the effectiveness of a fusion of fuzzy heuristic edge detection technique into particle swarm optimization. In this paper we experiment on various fuzzy membership threshold values to understand the impact of these threshold on the final optimized edge detected. The testing data used are hand radiograph images. The main aim of the experiment is to detect the left and right outer cortical (OC) and the left and right inner cortical (IC). The success of the edge detection method is determined using a line scan across the longitudinal of the metacarpal. It is consider successful when all four compete edges are detected. Eighty line scan are taken from each metacarpal images. The evaluation of the complete line scan demonstrates a high success rate in detecting the bone edges.

Wavelet Energy Guided Level Set for Segmenting Highly Similar Regions in Medical Images

This paper presents a new segmentation method that integrates a wavelet based feature, which is able to enhance the dissimilarity between regions with low variations in intensity. This feature is integrated to formulate a new level set based active contour model that addresses the segmentation of regions with highly similar intensities in medical images, which do not have clear boundaries between them. In the first phase of this research, the strength of wavelet transform is adapted to formulate a statistical feature, named as wavelet energy. The second phase of this work is dedicated to formulate a new level set based active contour model that is suitable for segmenting regions without clear boundaries and exhibits intensity inhomogeneity within the region. The proposed segmentation method is named wavelet energy guided level set based active contour. Experiments are conducted using medical images focusing on the neck and bladder regions to validate the proposed method. The experimental results show that the proposed method is able to segment the region of interest in close correspondence with the manual delineation by the radiologists.

Gaussian Rule Based Fuzzy (GRBF) Membership Edge Detection on Hand Phantom Radiograph Images

This paper introduces the Gaussian shaped membership function to refine the Rule Based Fuzzy (RBF) image detection. It is expected that the proposed algorithm Gaussian Rule Based Fuzzy (GRBF) method can further refined the detection of periosteal and endosteal edges of hand phantom radiographs. The experimental data consists of four sets of hand phantom radiograph. Only metacarpal 2, 3 and 4 are considered. All of these data are processed with both GRBF and RBF. Mean and median filters are used as preprocessing tools. The results are compared both subjectively and statistically. The periosteal (strong edges) are well detected by both RBF and GRBF. However GRBF performs better than RBF in detecting the endosteal edges (weak edges).