Nacéra Benamrane

Verified

Nacéra verified their affiliation via an institutional email.

Learn more

Verified

Nacéra verified their affiliation via an institutional email.

Learn more

• Full Professor and a head of SIMPA Laboratoty at Université des Sciences et de la Technologie d'Oran Mohamed Boudiaf

Brain structure segmentation in 3D Magnetic Resonance Images is crucial for understanding neurodegenerative disorders. Manual segmentation is error-prone, necessitating robust automated techniques. In this paper, we introduce a novel and robust approach for the simultaneous segmentation of multiple brain structures in MRI images. Our method involve...

Image interpretation corresponds to the analysis of an image or a scene making it possible to describe the objects making up the scene and their relationships, i.e. to extract the semantics of the image, in order to better to understand. The problem of image interpretation is a problem of perception of the environment and decision�making. It i...

Hospitals generate a significant amount of medical data every day, which constitute a very rich database for research. Today, this database is still not exploitable because to make its valorization possible, the images require an annotation which remains a costly and difficult task. Thus, the use of an unsupervised segmentation method could facilit...

This paper presents a segmentation method to detect multiple sclerosis (MS) lesions in brain MRI based on the artificial immune systems (AIS) and a support vector machines (SVM). In the first step, AIS is used to segment the three main brain tissues white matter, gray matter, and cerebrospinal fluid. Then the features were extracted and SVM is appl...

In biomedicine, cells nuclei detection is a leading topic research and one of the most challenging. Histopathological analysis represents the cells of the tissue sample that provide a set of essential information for detection and characterization of the cancer. Deep learning (DL) has recently demonstrated promising performance in breast cancer dia...

Breast cancer is a common disease of women. The number of new cases diagnosed in Algeria is increasingly high and it is the first cause of cancer related deaths for women. The microcalcifications are considered the primary sign of breast cancer. The early detection of these allows doctors to take the necessary measures for the treatment of this pat...

The important thing about mobile robotics is that its use satisfies rapid movement without collisions. Several methods have been designed for this purpose, but not all of them give the results expected by the user. Our contribution in this article is to allow the mobile robot to take advantage of two methods by the hybridization effect. These metho...

Breast cancer is the most typical form of cancer among the female population and the most common form of cancer-related death. However, if the cancer is detected at an early stage, treatment may be more effective. Mammography is one of the most used imaging modalities for the early breast cancer diagnosis. The present paper proposes an intelligent...

Clustering methods are generally used to study the homogeneity in a set of observations. The results obtained from the clustering process differ from one method to another, to the extent that the same method or validity index gives different outcomes depending on the initial parameters. Analytical evaluation appears to be insufficient for studying...

This paper presents a segmentation method to detect multiple sclerosis (MS) lesions in brain MRI based on the artificial immune systems (AIS) and a support vector machines (SVM). In the first step, AIS is used to segment the three main brain tissues white matter, gray matter, and cerebrospinal fluid. Then the features were extracted and SVM is appl...

Fuzzy Clustering Means (FCM) algorithm is a widely used clustering method in image segmentation, but it often falls into local minimum and is quite sensitive to initial values which are random in most cases. In this work, we consider the extension to FCM to multimodal data improved by a Dynamic Particle Swarm Optimization (DPSO) algorithm which by...

The performance of medical image segmentation is generally affected by the parameters of the adopted method and noise. To overcome these issues we introduce in this paper a novel segmentation approach of brain MRI using a region based-active contour model and evolutionary algorithm and without performing any pre-processing step. Our main objective...

The ad hoc nature of the clustering methods makes simulated data paramount in assessing the performance of clustering methods. Real datasets could be used in the evaluation of clustering methods with the major drawback of missing the assessment of many test scenarios. In this paper, we propose a formal quantification of component overlap. This quan...

Breast cancer is a common disease of women. The number of new cases diagnosed in Algeria is increasingly high and it is the first cause of cancer related deaths for women. The microcalcifications are considered the primary sign of breast cancer. The early detection of these allows doctors to take the necessary measures for the treatment of this pat...

In this article we propose an intelligent system for mobile robot navigation in different environments, using ANFIS and ACOr. This system is capable of ensuring to mobile robot to navigate by reacting to the various situations encountered in different environments. In a first step, we use the ANFIS controller (Adaptive network-based fuzzy inference...

For a secure data image transmission purpose, digital watermarking techniques are used by embedding and extracting the same watermark into digital content. One of the widely used transform domains for watermarking of most digital images is the Discrete Wavelet Transform domain (DWT)and the hybridization in the digital domain of the image watermarki...

This article presents a modified Fuzzy C Means segmentation approach based on multi-resolution image analysis. Fuzzy C-Means standard methods are improved through fuzzy clustering at different image resolution levels by propagating fuzzy membership values pyramidally from a lower to a higher level. Processing at a lower resolution image level provi...

Image Segmentation is one of the most important fields in artificial vision due to its complexity and the diversity of its application to different image cases. In this paper, a new ROI segmentation in medical images approach is proposed, based on modified level sets controlled by fuzzy rules and incorporating local statistical constraints (mean, v...

This paper proposes a new K-means segmentation approach applied on multiresolution images and based on spatial constraints. K-means clustering is performed first on various image resolution levels where the limit of resolution level can reach 1/8th of image. Then, clustering result of each pixel p of the original image can be updated depending on c...

Le codeur SPIHT, même s’il est connu pour son efficacité, reste limité dans l’allocation de la mémoire pour le stockage des images compressées. Afin de remédier à cela, notre travail rejoint cette philosophie et propose, dans cet article, une amélioration de la compression par une réduction du débit binaire à la sortie de l’encodeur SPIHT. Cette te...

Breast cancer is one of the leading causes of death among women. Mammography remains today the best technology to detect breast cancer, early and efficiently, to distinguish between benign and malignant diseases. Several techniques in image processing and analysis have been developed to address this problem. In this paper, we propose a new solution...

The aim of this work is to develop a new model for segmentation of brain structures in medical brain MR images. Brain segmentation is a challenging task due to the complex anatomical structure of brain structures as well as intensity nonuniformity, partial volume effects and noise. Generally the structures of interest are of relatively complicated...

Since the progress of digital medical imaging techniques, it has been needed to compress the variety of medical images. In medical imaging, reversible compression of image's region of interest (ROI) which is diagnostically relevant is considered essential. Then, improving the global compression rate of the image can also be obtained by separately c...

We propose in this article an approach to optimize the processing time and to improve the quality of brain magnetic resonance images segmentation. Level set method (LSM) was adopted with a periodic reinitialization process to prevent the LS function from being too steep or too flat near the interface. Although it is used to maintain the stability o...

In this paper, we propose an approach for segmentation of Brain Magnetic Resonance Images (MRI) using an active contour model. We adopted a Greedy Algorithm which is a simple and an effective method. However it requires an adjustment of functional energy parameters. To overcome this disadvantage we propose a hybridization with optimization method....

This paper proposes a new multi agent system for boundary detection and object tracking in image sequence. It exploits advantages of three elements: multi agent solution, active contour model and multi resolution treatment. The proposed system is organized as multi level structure where each level is composed of many cooperative agents. In edge det...

De plus en plus, les images médicales sont acquises et stockées digitalement. Ces images peuvent être très grandes en nombre et en dimension. La compression offre à un moyen de réduire le coût de stockage et augmenter la vitesse de transmission sans une altération flagrante de la qualité de l'image. Une compression avec perte permet d'obtenir une h...

In this paper, we propose a method for evaluating the displacement and deformation fields for pair of multi temporal images, one before and one after deformation; based on a matchning technique of cross correlation. First, according to the noise present in the images and the long computation time, a denoising based on the Kalman filter and a multi-...

Breast cancer is one of the leading causes of cancer death among women. As such, the role of digital mammographic screening is to detect cancerous lesions, at an early stage, and to provide high accuracy in the analysis of the size, shape, and location of abnormalities. Segmentation is arguably one of the most important aspects of a computer aided...

This paper proposes a segmentation method of 2D image sequence based on active contour or snake. We define energy functional of active contour for detecting object in first frame of sequence. Then, the final snake is used as initial snake in the next frame. Our idea of tracking object is achieved by change of energy functional. Therefore, we substi...

This paper proposes an approach to automatically segment MS lesions in MR images using fuzzy c-means (FCM) and a support vector machines (SVM) based on the sequential minimal optimization (SMO) in learning step. A postprocessing based on morphological operations was applied to refine the obtained results. The proposed approach was tested on 3D MR i...

A new approach for automated diagnosis and classification of Magnetic Resonance (MR) human brain images is proposed. The proposed method uses Wavelets Transform (WT) as input module to Genetic Algorithm (GA) and Support Vector Machine (SVM). It segregates MR brain images into normal and abnormal. This contribution employs genetic algorithm for feat...

In this paper, we propose a hybrid approach for mammographic images interpretation in order to detect the benign and malignant anomalies. Using a neural evolutionary approach based on the Radial Basis Function neural network (RBF) and the evolutionary strategy (ES). After applying the growing region algorithm in segmentation stage, the RBF neural n...

With nearly 100.000 cases in Algeria, Alzheimer's disease (AD) represents a major public health problem. Therefore, several different automated methods have been developed to assist clinicians in their diagnosis. We propose here a method based on binary support vector machines (SVM) to distinguish between patients with Alzheimer disease (AD), patie...

Be en na am mr ra an ne e Laboratoire Imagerie et Vision Artificielle, Département d'Informatique, Université des Sciences et de la technologie Mohamed Boudiaf, Oran Résumé: L'interprétation des images médicales est un des domaines de recherche les plus encourageants, étant donné qu'il offre des facilités pour le diagnostic et les décisions thérape...

The selection of features has a considerable impact on the success or failure of classification process. Feature selection refers to the procedure of selecting a subset of informative attributes to build models describing data. The main purpose of feature selection is to reduce the number of features used in classification while maintaining high cl...

Medical imaging techniques produce very large amounts of data, that have to be transmitted or stored, and therefore, there is a need for image compression. Fractal image compression still suffers from a high encoding time. We propose a new optimization approach to reduce the time of fractal image encoding. This approach is a hybridization of the SP...

A new approach for automated diagnosis and classification of Magnetic Resonance (MR) human brain images is proposed. The proposed method uses Wavelets Transform (WT) as input module to Genetic Algorithm (GA) and Support Vector Machine (SVM). It segregates MR brain images into normal and abnormal. Our contribution employs genetic algorithm for featu...

Although the wavelet transform is effective for compressing digital images it does not preserve edges because it is often used separably in horizontal and vertical image. We propose in this paper image compression technique based on bandlets to capture the singularities along edges. We applied particle swarm optimization technique (PSO) on a dictio...

This paper presents an original approach for detecting and tracking of objects in medical image sequence. We propose a multi-agent system (MAS) based on NetLogo platform for implementing parametric contour active model or snake. In NetLogo, mobile agents (turtles) move over a grid of stationary agents (patches). In our proposed MAS, each mobile age...

The parameter selection is very important for successful modelling of input–output relationship in a function classification model. In this study, support vector machine (SVM) has been used as a function classification tool for accurate segregation and genetic algorithm (GA) has been utilised for optimisation of the parameters of the SVM model....

Dans cet article, nous avons étudié la segmentation des images médicales à laquelle nous avons appliqué les algorithmes génétiques. Nous allons réunir les deux modes pour pallier à ce problème. Dans un premier temps, nous avons utilisé l'algorithme de quadtree qui permet de découper l'image en quatre régions selon l'étendue, le gradient et la varia...

Dans cet article, nous avons étudié la segmentation des images médicales à laquelle nous avons appliqué les algorithmes génétiques. Nous allons réunir les deux modes pour pallier à ce problème. Dans un premier temps, nous avons utilisé l'algorithme de quadtree qui permet de découper l'image en quatre régions selon l'étendue, le gradient et la varia...

We purpose a hybrid approach for classification of brain tissues in magnetic resonance images (MRI) based on genetic algorithm (GA) and support vector machine (SVM). A wavelet based texture feature set is derived. The optimal texture features are extracted from normal and tumor regions by using spatial gray level dependence method (SGLDM). These fe...

In this paper a modular approach of segmentation which combines the Bayesian model with the deformable model is proposed. It is based on the level set method, and breaks up into two great parts. Initially, a preliminary stage allows constructing the information map. Then, a deformable model, implemented with the Generalized Fast Marching Method (GF...

—In this paper we propose a new approach for automated diagnosis and classification of Magnetic Resonance (MR) human brain images, using Wavelets Transform (WT) as input to Genetic Algorithm (GA) and Support Vector Machine (SVM). The proposed method segregates MR brain images into normal and abnormal. Our contribution employs genetic algorith...

Le recalage d’images trouve de nombreuses applications médicales aussi bien dans le suivi thérapeutique que dans le diagnostic d’un patient. En s’inspirant des méthodes proposées dans la littérature nous proposons dans ce papier, une méthode de recalage d images médicales basée sur une hybridation entre deux techniques géométrique et iconique afin...

The selection of features has a considerable impact on the success or failure of classification process. Feature selection refers to the procedure of selecting a subset of informative attributes to build models describing data. The main purpose of feature selection is to reduce the number of features used in classification while maintaining high c...

In this paper a modular approach of segmentation which combines the Bayesian model with the deformable model is proposed. It is based on the level set method, and breaks up into two great parts. Initially, a preliminary stage allows constructing the information map. Then, a deformable model, implemented with the Generalized Fast Marching Method (GF...

This paper introduces an efficient detection of brain tumor from cerebral MRI images. The methodology consists of three steps: enhancement, segmentation and classification. To improve the quality of images and limit the risk of distinct regions fusion in the segmentation phase an enhancement process is applied. We adopt mathematical morphology to i...

Dans cet article, nous proposons une méthode de détection et de sui-vi d’un objet dans une séquence d’images basée sur le contour actif. Une fonc-tionnelle d’énergies est attachée au contour actif. Après une initialisation du contour actif dans la première image de la séquence, la minimisation des éner-gies attachées est utilisé afin de détecter le...

This paper introduces an efficient detection of brain tumor from cerebral MRI images. The methodology consists of three steps: enhancement, segmentation and classification. To improve the quality of images and limit the risk of distinct regions fusion in the segmentation phase an enhancement process is applied. We adopt mathematical morpholog...

In this paper we present a Block Matching approach to registration of medical 2D images IRM/IRM. The registered images are assumed to be rigidly aligned before starting this procedure. The sum of absolute differences (SAD), sum of squared differences (SSD), mutual information (MI) and correlation coefficient (CC) are used as measures of similar...

This research present a method of 2D and 3D segmentation based on the Enhanced Hoshen-Kopelman algorithm and its extension to non-lattice structure. The main feature of this method is to combine a merging strategy of a region growing algorithm with the multiple labeling technique of the EHK algorithm for regular and non-regular lattice. An efficien...

The Bioinformatics is a multidisciplinary research domain aiming the automatic treatment of the biologic information including the sequences (Multiple Sequence Alignment), the structures (protein’s secondary or tertiary structures), and the functions (protein structural motifs). One of the Bioinformatics challenges is the Protein Secondary Structur...

This article presents a new system for training Radial Basis Function Networks (RBF networks) using heuristic training techniques and more precisely the DDA Algorithm (short for “Dynamic Decay Adjustments”) combined with a Genetic Algorithm. This system is called GA‐DDA. The GA is used in the pre‐training stage to find the initial centroids of the...

In this paper, we propose an approach for medical Image segmentation based on a FIPA compliant multi-agent system. The idea consists in merging the regions following several criteria and with a massive population of situated agents which cooperate, negotiate with the help of interaction protocols and communicate by passing asynchronous messages. Th...

En compression Fractale l'étape de codage nécessite un coût calculatoire important. Dans ce papier, un schéma de codage rapide pour la compression d'image par fractale, est proposé. La technique est basée sur l'hybridation des fractales et la quantification vectorielle par un réseau de Kohonen à plusieurs dictionnaires. Cette technique a été testée...

This paper proposes a technique for lane boundaries detection and following, which can be used in a driver assistance system. This technique is destined only to painted road with slow curvature. Then, a linear model is used to obtain robust information about vehicle position and orientation compared to the road boundaries. Based on the gray level i...

In this paper, we propose an approach for detection and specification of anomalies present in medical images. The idea is to combine three metaphors: neural networks, fuzzy logic and genetic algorithms in a hybrid system. The neural networks and fuzzy logic metaphors are coupled in one system called fuzzy neural networks. The genetic algorithm adds...

In this paper, we propose an approach based on the RBF neural networks and the genetic algorithms for magnetic resonance (MR) brain images segmentation. In the feature extraction stage, nine features are calculated and used as RBF network inputs. The genetic algorithm build automatically a RBF NN (It determines the number of hidden neurons, and the...

In this study, we propose an approach to detect suspect zones or tumors in medical images. The idea is to define with precision the existence of different kinds of lesions using a hybrid system, which combines Fuzzy Neural Networks and Expert System. After applying a method of image segmentation to extract regions (by region growing algorithm or by...