Search

Medical image fusion is the process of combining multiple images from single or multimodal medical image. In this article, we have presented an hybrid image fusion based on non-subsampled contourlet (NSCT) enhancement to highlight the presentation of the original image appearance taking into account the difficulties of classical methods linked to the traditional enhancement methods. This algorithm is performed in CDF 9/7 wavelet transform based on lifting scheme to combine magnetic resonance imaging (MRI) and Positron emission tomography (PET) with applying fusion rules. The coefficients of the low frequency band are combined by a maximal energy rule and coefficients of the high frequency bands are combined by a maximal variance rule. Finally, the results of image fusion are evaluated with mutual information (MI) and spatial frequency (SF) then compared with the existent methods such as (PCA, DWT). [ABSTRACT FROM AUTHOR]

This article describes a fuzzy classifier for the identification of premature ventricular complexes (PVCs) in surface electrocardiograms (ECGs). The classifier uses features extracted from the ECG beat, such as the width of QRS complex and RR interval. The performance of the algorithm is evaluated on the MIT-BIH Arrhythmia Database following the AAMI recommendations. The results of the experiments of the recognition of PVCs have confirmed the reliability and advantage of the proposed approach. [ABSTRACT FROM AUTHOR]

The most widely used signal in clinical practice is the electrocardiogram (ECG). ECG conveys information regarding the electrical function of the heart, by altering the shape of its constituent waves, namely the P, QRS, and T waves. Thus, the required tasks of ECG processing are the reliable recognition of these waves, and the accurate measurement of clinically important parameters measured from the temporal distribution of the ECG constituent waves. The purpose of this paper is the classification of ventricular ectopic beats (VEB's). This research includes noise handling, feature extraction, and neural classification, all integrated in a three-stage procedure. Thirty features extracted from the morphology of the QRS segment, are reduced to seven coefficients using principal component analysis (PCA) and two coefficients using linear predictive coding (LPC) technique in addition to two other temporal parameters were used separately as the input of two neural network classifiers. The neural classifiers were tested on the MIT-BIH database and high scores were obtained for both sensitivity and specificity (84.88% and 91.92% respectively using ACP technique, and 76.17% and 88.95% using LPC method). This study confirms the power of artificial neural networks in the classification of normal and abnormal VEB beats. Clinical use of this method, however, still requires further investigation. [ABSTRACT FROM AUTHOR]

This paper presents a new method for learning the structure of Bayesian Networks. Broadly speaking, we leverage the Branch and Bound (B&B) to derive the best Directed Acyclic Graphs (DAGs) that describes the structure of the network. Our contribution consists in introducing two main heuristics: the first one allows the selection of the graph that has the best score among those that contain less cycles, the second one eliminates the shortest cycle from the selected graph; it aims to reduce the number of explored nodes. Our experimental study asserts that the suggested proposal improves the results for multiple data sets. These facts are confirmed by the reduction of the computation time and the memory overhead. [ABSTRACT FROM AUTHOR]

Introduction La mesure d’impédance électrique permet de différentier différents types de tissus. Elle pourrait optimiser les données de positionnement de l’extrémité de l’aiguille lors d’un bloc nerveux [1] . L’objectif de cette étude était d’observer les variations d’impédance réelle lors de la traversée des tissus jusqu’à la structure nerveuse ciblée avant et pendant l’injection d’AL afin de déterminer son caractère discriminatif (Impédance data loggerÒ + HNS12 BBraun, Allemagne) lors d’un bloc échoguidé (Échographe S7Ò, sonde matricielle, GE healthcare, États-Unis). Matériel et méthodes Avec accord du CPP, l’étude prospective observationnelle a été menée dans notre unité d’anesthésie orthopédique. Des mesures continues d’impédance électriques réelles ont été réalisées lors de blocs nerveux périphériques échoguidés. Cinq mesures d’impédance ont été relevées avant, au moment et après le passage du fascia profond (épimysium musculaire), ainsi qu’avant et après l’injection d’AL. L’Intensité Minimale de Stimulation (IMS) a également été notée avant l’injection de 1 mL d’AL. Résultats Trente-trois blocs nerveux échoguidés ont été réalisés (13 blocs axillaires, 9 fémoraux, 4 sciatiques poplités, 3 supra-claviculaires, 3 infra-claviculaires, 1 obturateur). L’AL était localisé au décours de l’injection à 26 reprises en sous-paraneural, 5 en épineural (involontairement) et 2 en extraneural. L’impédance dans le muscle ou le tissu pariétal avant l’épimysium musculaire était de 2,92 ± 0,81 kΩ ; au contact du fascia l’impédance s’élevait à une valeur de 4,4 ± 0,94 kΩ (variation de variation de 33 % ± 14 % ; p < 0,05). Après le passage du fascia musculaire, la valeur d’impédance chutait à 3,04 ± 0,70 kΩ. Après progression de l’aiguille, l’impédance moyenne avant l’injection était de 2,48 ± 0,85 kΩ (sans tenir compte de sa localisation finale : sous-paraneural, épineural ou extraneural). Après injection, sa valeur était de 0,86 ± 0,25 kΩ (variation de 62 % ± 12 % ; p < 0,001) ( Fig. 1 ). En analyse post-hoc, après relecture des vidéos, l’impédance en extraneural était de 2,85 ± 2,19 kΩ avec une IMS moyenne de 2,85 ± 2,19 mA ; l’impédance pour une injection sous-paraneurale était de 2,4 ± 0,7 kΩ avec une IMS moyenne de 0,54 ± 0,57 mA ; l’impédance en épineural était de 2,62 ± 1,2 kΩ avec une IMS moyenne de 0,32 ± 0,16 mA. Discussion L’impédance réelle lors de la progression de l’aiguille au cours d’un bloc nerveux croît lors du passage du fascia profond (tissu dense peu ionisé) et décroît après le passage de l’épimysium musculaire et après l’injection d’AL (solution ionisée). À intensité constante, ces variations s’accompagnant d’une variation proportionnelle du voltage (V = RxI). Les modifications du champ électrique peuvent expliquer la disparition de la réponse motrice en lâchant l’aiguille ou l’augmentation de l’IMS lors de l’injection. En revanche, cette mesure globale d’impédance ne semble pas différentier les localisations cibles recherchées pour la pointe de l’aiguille avant l’injecti [ABSTRACT FROM AUTHOR]

The present work investigated the ability of antagonistic microorganisms to inhibit the growth of pathogenic strains responsible for the vascular fusarium wilt of date palm or Bayoud's disease. The objective was to evaluate the antagonistic effect of native strains of Trichoderma longibarchiatum, Penicillium sp., Fusarium sp. and one isolate of Bacillus sp. against four isolates of Fusarium oxysporum f.sp. albedinis (Foa) under in vitro conditions. The isolates Bacillus sp. and Fusarium sp. were isolated from soil samples of the rhizosphere of date palm of Tamanrasset region in Algeria, these strains were morphologically identified, and a dual culture confrontation was carried out, placing the Foa in the center of the Petri dish and Bacillus sp. in the two cardinal points. For T. longibarchiatum, Penicillium sp. and Fusarium sp. they were confronted against Foa with a dual confrontation, the inhibition rates were determined, and a percentage of inhibition obtained varied from 64.29 to 65.75%; 57.14 to 64.29% and 36.36 to 52.05% for T. longibarchiatum, Penicillium sp and Fusarium sp. respectively. While Bacillus sp. exhibits the lowest percentage of inhibition in this study, and they were less than 16.67%. Comparison of mean value for each pair between T. longibrachiatum, Penicillium sp., Fusarium sp. on one hand and Bacillus sp. on the other hand concluded that there is a highly significant difference between these three fungal isolates and Bacillus sp. concerning inhibition rates with P-value (P <0.0001). Contrary, no significant difference was observed between T. longibrachiatum and Penicillium sp. with P = 0.1895 and the two antagonists show the same letter A in the letter connection ratio, which means no difference in the level of inhibition. [ABSTRACT FROM AUTHOR]

Purpose Quantification of staining of the ocular surface by fluorescein and lissamine green is important for diagnosis and follow up of dry eye syndromes, especially in clinical trials. Analysis of digital pictures may help improving the reliability of this quantification but require objective data on the basic lesions constitutive of punctuate superficial keratitis (PSK) to develop adequate algorithms. Aim: to evaluate the size spectrum of epithelial lesions of PSK during dry eye to improve the existing diagnosis tools. Methods Fluorescein was instilled to six patients suffering from dry eye graded according to the Oxford scheme. Pictures (3008x1960px) were taken using a Topcon slit-lamp using the Cobalt blue light without barrier filter. Two magnifications (x10 and x16) were used and calibrated using a certified standard reference grating. It allowed determining the size of observed objects with the software ImageJ. The most visible and isolated PSK lesions (green dots) were selected. The size of 180 different PSK lesions (30/patient, 15/magnification) were measured by tracing the light intensity profile and manually measuring the width at half maximum. Results All patients combined, the mean was 21.6 ± 4.8 μm (15.2-30 μm, 10°-90° percentile). Lesion diameters ranged between 11.4 and 30.4 μm. Conclusions Lesions seem to be smaller than epithelial cells (approximatively 25 μm×50 μm for superficial cells) and might correspond to the beginning of cell detachment with fluorescein retained between cells. These new quantitative data will help developing automatic recognition algorithm to obtain reliable objective classification of the corneal staining. [ABSTRACT FROM AUTHOR]