Search

This paper suggests a new system for the automated detection of road signs. This driver assistance system detects traffic signs that have a red border with different shapes (circular, triangular, hexagonal). So, our approach relies on Support Vector Machines (SVM) implementation for road signs detection supported by feature extraction technique supported employment of a range of filters from Gabor that simplifies the recognition of interest's points in our database. On the other hand, our approach has been improved on the Edited Shuffled Frogs Leaping Algorithm (ESFLA) optimisation technique that helps in road signs detection and this technique is termed Gabor-ESFLA-SVM. This strategy ensures an intelligent recognition system. The obtained results show that this optimised classification provides higher results compared to the previous dual classification Gabor-SVM and other research works published in a few articles.

This manuscript introduces a novel 3D face authentication system inspired from the advantageous capacities of Gabor-Edge filters. The approach studies 3D face difficulties such as expression variety, different rotations and exposure to illuminations. The proposed systems starts by preprocessing the 3D face images to resolve acquisition problems. Then, a filtering process is performed by implanting our 3D Gabor-Edge technique extended based on the classic 3D Gabor masks. The next step is to achieve the classification of facial features from the edge saliency by the artificial Neural Network Classifier (NNC). The evaluation of the adopted system is achieved by exporting common datasets from GavabDB database. Experimental results are reported to prove the high accuracy rates of our method compared to the recent researches in the same biometric field.

The steganography is the art of hidden; its main aim is to pass unnoticed data in another data. There are many types of data that used in steganography, such as message, image, and video. In this work, we are interested in hiding a message inside an image. Our work focuses on the study of three approaches based on least significant bit (LSB) techniques that mean put the bits of the message in the least significant bits in each pixel of the image. Moreover, we propose an improved approach for LSB-based image steganography. In this approach, we reduce the length of hidden message by Deflate algorithm which is a lossless data compression algorithm that combines the LZ77 algorithm and the Huffman algorithm. Another important characteristic of our approach is to protect the reduced hidden data by AES (Advanced Encryption Standard) algorithm. Our experiment results show that our improved approach is most effective compared to existing approaches.

We present a comparative analysis of cell-mediated immunity between circulating lymphocytes and tumor-infiltrating lymphocytes (TIL) from patients with nasopharyngeal carcinoma (NPC). Phenotypic analysis using a panel of monoclonal antibodies (MAbs) to define lymphocytic subsets has revealed a selective homing of phenotypically lytic cells such as CD8- and CD16-positive cells, but a low percentage of macrophages when compared to PBL of NPC patients. Also, PBL and TIL contain an equivalent percentage of activated T-lymphocytes expressing HLA-DR molecules and IL-2 receptors. Functionally, TIL exhibit an abolished NK-cell activity and concomitant decrease of proliferative response to phytohemagglutinin (PHA) and concanavalin A (ConA) stimulation when compared with PBL.

El cancer de la nasofaringe, en el que predomina el carcinoma epidermoide, sobre todo de tipo indiferenciado (CNFTI), tiene una incidencia variable, que es intermedia en el Magreb y la cuenca mediterranea, muy elevada en el sudeste asiatico y baja (

I tumori del rinofaringe, in cui spiccano in particolare i carcinomi epidermoidi indifferenziati di tipo undifferentiated carcinoma of nasopharyngeal type (UCNT), hanno un’incidenza variabile, intermedia per il Maghreb e il bacino del Mediterraneo, molto alta per il Sud-Est asiatico e bassa ( early antigen » (EA) e «viral capsid antigen» (VCA). Per il cancro del rinofaringe sono state messe in evidenza alterazioni genetiche a livello dei geni oncosoppressori nelle regioni dei cromosomi 3p, 9p, 11q, 13q, 14q e 16q. I marcatori sierici piu attendibili sono il Cyfra 21 e i livelli dell’acido desossiribonucleico (DNA) sierico. I segni evocatori piu frequenti sono la presenza di adenopatie cervicali, di sintomi otologici oppure rinologici. La valutazione della lesione si basa sulla rinoscopia con biopsia della neoplasia, sulla diagnostica per immagini con tomografia e risonanza magnetica cerebrocervicale e sulla valutazione della ricerca di metastasi. I tumori del rinofaringe sono stadiati secondo la classificazione tumor-nodes-metastases (TNM)-Unione internazionale contro il cancro (UICC) 2002, che ha un valore prognostico e di orientamento terapeutico. La radioterapia resta il trattamento di riferimento locoregionale, con un beneficio in termini di sopravvivenza globale e senza malattia dell’aggiunta della chemioterapia prima o contemporaneamente nelle forme ad alto rischio di metastasi (N3, T3-4). La prognosi dipende soprattutto dal volume della massa locoregionale (T e N) come anche dalla risposta alla chemio- e radioterapia.

Objectifs Caracteristiques cliniques, radiologiques et histologiques des tumeurs malignes survenant sur une thyroide linguale ainsi que leur traitement. Materiel et methodes Nous rapportons le cas d’un carcinome papillo-vesiculaire survenu sur une thyroide linguale surnumeraire. Resultats La tumeur linguale a provoque une dysphagie et une douleur cervicale, par obstruction de l’oropharynx. Une pharyngotomie par voie trans-hyoidienne a permis une bonne resection des lesions. Par ailleurs, la glande thyroide eutopique etait en place, en position pre-tracheale, indemne de toute proliferation tumorale. Conclusions La survenue d’un carcinome sur une thyroide linguale est une situation tres rare. Son diagnostic est avant tout histologique. Son traitement est chirurgical associe a une iratherapie.

Annales Francaises d'Oto-Rhino-Laryngologie et de pathologie cervico-faciale - Vol. 123 - N° 3 - p. 115-119

Nasopharyngeal carcinoma (NPC) represents an interesting model in the field of head and neck cancers. This cancer is rare in occidental countries (

Objectif Repertorier les seconds cancers observes au niveau de la tete et du cou apres traitement par chimiotherapie et/ou radiotherapie pour un carcinome indifferencie du cavum en Tunisie. Patients et methodes C’est une etude retrospective des dossiers des patients ayant developpe une tumeur secondaire (TS) apres traitement d’un carcinome indifferencie du cavum. Pour etre retenue dans cette etude, la tumeur secondaire doit etre d’histologie differente de l’UCNT initial, localisee dans le champ d’irradiation et survenant apres un delai minimum de 3 ans. Resultats Sur une serie de 2 346 patients traites de 1984 a 2001 a Tunis, Sousse et Sfax, nous avons observe 11 tumeurs secondaires, soit une frequence de 0,46 %. Les patients avaient ete traites pour des UCNT du cavum en majorite etendus T3-T4 (72 %) ou N2-N3 (63 %). L’âge median etait de 20 ans (11 a 48). Le sex-ratio etait de 0,3 (3 H/8 F). Le protocole therapeutique avait comporte une association de chimiotherapie et de radiotherapie dans 8 cas et une radiotherapie seule dans 3 cas. La chimiotherapie etait premiere dans 4 cas combinant adriamycine (40-90 mg/m2)-cisplatine (100 mg/m2) et adjuvante a la radiotherapie dans 4 cas. La dose moyenne de radiotherapie etait de 72 Gy (70 a 75). Le delai median de survenue des TS etait de 9 ans (3 a 17). Il s’agissait de carcinomes epidermoides bien differencies des VADS dans 4 cas, de fibrosarcomes cervico-mandibulaires (2 cas), osteosarcomes du massif facial (2 cas), d’un glioblastome temporal et de deux carcinomes basocellulaires du nez et de la tempe. Le traitement de la tumeur secondaire a comporte une chirurgie seule dans 4 cas et une chimiotherapie seule dans 7 cas. Aucun des patients n’a ete reirradie. La survie mediane etait de 17 mois, 4 patients sont decedes, et 7 sont vivants dont 4 en remission (24+, 36, 36 et 48+ mois) et 3 en evolution tumorale (8, 16 et 18 mois). Conclusion Les tumeurs secondaires apres traitement du cancer du cavum sont rares mais de mauvais pronosticn, justifiant leur detection et leur depistage.

This paper presents a novel optimal algorithm for MRI brain tumor recognition. To do this, we use the newly developed meta-heuristic MSFLA (Modified Shuffled Frog Leaping Algorithm). Otherwise, a suitable choice of the fitness function ensures faster time of research with greater chance of convergence to the optimal value. The calculation of the used fitness function is linked to the image. The image must be scanned to calculate this function. For this, this function assists to quickly discover the adequate area modeling the tumor. Computer simulation results illustrate the effectiveness of the developed algorithm.

Secondary tumours to radio- and/or chemotherapy have rarely been reported after treatment for head and neck cancers. We report a case of mandibular fibrosarcoma observed 7 years after chemoradiotherapy for undifferentiated nasopharyngeal carcinoma in a patient treated when 20 years old.

Resume Objectif de l’etude. – Rapporter les aspects cliniques et les resultats therapeutiques dans une serie tunisienne de lymphomes primitifs nasosinusiens. Patients et methodes. – Notre etude retrospective a porte sur les cas de lymphomes primitifs nasosinusiens histologiquement confirmes, diagnostiques et traites a l’nstitut Salah Azaiz de 1975 a 1997. Le bilan initial a comporte : examen clinique general et ORL, des examens biologiques (numeration et formule sanguine, vitesse de sedimentation, dosage de la LDH), une echographie abdominale, une biopsie medullaire et une tomodensitometrie du massif facial depuis 1985. Nous avons procede a une relecture des lames histologiques. Le protocole etait base sur la radiotherapie avec ou sans chimiotherapie. Resultats. – Nous avons collige les dossiers de 22 hommes et trois femmes (sex-ratio = 7). L’âge moyen etait de 48 ans (extremes : 18–78 ans) et le delai moyen entre le premier symptome et la premiere consultation de quatre mois. Le symptome le plus frequent etait represente par l’obstruction nasale (65 %), plus rarement une epistaxis (40 %) ou une rhinorrhee (20 %). L’examen ORL a retrouve dans 20 % des cas une tumeur des fosses nasales, bourgeonnante et unilaterale dans 80 % des cas et associee a une adenopathie cervicale dans 25 %. Les lymphomes etaient de haut grade dans 60 % des cas et localises (stade IE) chez 60 % des patients. Tous les lymphomes de stade IE de bas grade ont ete traites par irradiation exclusive alors que l’association de radiotherapie et de chimiotherapie a ete utilisee pour les lymphomes de stade plus avance (huit patients). Le taux de survie actuarielle a cinq ans etait de 69 % pour toute la population avec un pronostic favorable pour les lymphomes de stade IE et ceux de bas grade de malignite. Conclusion. – La radiotherapie reste le traitement standard des lymphomes primitifs nasosinusiens localises de stade IE. Dans les stades plus avances ou avec les tumeurs volumineuses, l’association therapeutique represente la meilleure option therapeutique a l’instar des autres lymphomes de la sphere ORL.

Support vector machine (SVM) is a popular method of learning classification with lots of applications. In this work, we extend SVM to recognize the appearance of tumors in MR brain image. Parameterization of the kernel in SVM learning procedure, along selecting features, influences the accuracy of the recognition and increases the computational effect. For this, a Shuffled Frog Leaping Algorithm (SFLA) based approach for feature selection of the SVM, termed SFLA-SVM, is developed. To demonstrate the quality of our technique, we give some experiments on MR brain images.

In this work, we bring to light a novel face recognition (FR) system based on modified shuffled frog leaping algorithm (MSFLA) blended to Gabor wavelets. This new approach operates straightly on feature extraction and selection stages by providing the most propitious Gabor representations of a face image. While many researchers are seeking to find better parameterisation for Gabor filters, we introduce our evolutionary MSFLA-Gabor prototype combined to support vector machine (SVM) classifier as a robust contribution in the face biometric field. Primarily, we start by highlighting the impressive quality insured by Gabor filters in salient point extraction. Next, we present the potential dynamism of metaheuristic MSFLA in enhancing feature selection as well as up grading SVM classifier performance. Then, our optimised MSFLA-Gabor-SVM algorithm is tested on three databases under varied facial expressions, illuminations and poses. The experimental results have shown higher recognition rates and lower computational complexity scores than previous techniques.

This paper outlines efficient hardware architecture of detection of bacteria and alga in microscopic images, using Xilinx System Generator (XSG). XSG is a high-level design tool based on blocks. It gives bit and cycle accurate simulation. The approach of detection used is the Hough transform. The latter is a very efficient approach of location of parametric curves in an image, especially lines. System was implemented on Virtex-V FPGA. To demonstrate the quality of the system, some experiments on microscopic images are given.

Nasopharyngeal carcinomas (NPC) are predominantly of undifferentiated type (UCNT or undifferentiated carcinoma of nasopharyngeal type), rare (1/100,000) and sporadic in occidental countries, but endemic in the Mediterranean area of intermediate incidence (2 to 10/100,000) and highly frequent (10/100,000) in South East Asia. NPC staging is based on TNM UICC 2002 that has a prognostic and therapeutic orientation impact. Irradiation of the primitive tumor and its extensions remains the standard loco-regional treatment. The recent introduction of primary and concomitant chemotherapy leads to an improvement in terms of overall and disease-free survival, specially for for high-risk-patients (T3-4 and N2-3 disease). Prognosis remain linked to T, N, histologic type and quality of response to chemotherapy and radiotherapy.