Search

To evaluate the risk factors for crusted scabies in children in France. The retrospective multicenter study, conducted in France, of children (aged < 18 years) with profuse and/or crusted scabies confirmed by dermoscopy and/or microscopy. Data were obtained using a standardized questionnaire. We included 20 children. The mean age was 4.5 years, and 70% of the patients were girls. Their medical history revealed a neurological pathology (agenesis of the corpus callosum; n = 1, 5.0%), prematurity (n = 1, 5.0%), Down syndrome (n = 1, 5.0%), atopic dermatitis (n = 2, 10%), and asthma (n = 2, 10.0%). Fifteen (75.0%) children were treated with steroids before being diagnosed with scabies: 12 (60.0%) with topical steroids, one (5.0%) with a systemic steroid, and two (10.0%) with inhaled steroids. One child (5.0%) lived in a precarious environment. The mean duration of pruritus was 3.4 months, and that of the skin lesions was 3.1 months. The most commonly affected areas for crusted scabies were the palms/hands (66.7%) and the armpits (33.3%). Thirteen children (65.0%) were hospitalized, 14 (70.0%) were treated with ivermectin and all received topical treatments; 85.7% were cured within an average of 38 days, but one child had a relapse 3 months later in the form of common scabies. Conclusion: The main risk factor for developing crusted scabies in France was the misdiagnosis and the use of corticosteroids, especially topical forms typically used in "healthy" children. Management of the children was effective and similar to that used in adults. What is Known: • Crusted scabies is an extremely contagious disease which is rarely reported in infancy, especially in healthy children. • The main risk factors include immunosuppression, physical debilitation, and intellectual disability. What is New: • The main risk factor of severe scabies in this study was delayed diagnosis associated with the use of topical or systemic corticosteroids. • The treatment was successful in 85.7% of cases, and 65% of children needed to be hospitalized. [ABSTRACT FROM AUTHOR]

Glaucoma is a major public health problem that can lead to an optic nerve lesion, requiring systematic screening in the population over 45 years of age. The diagnosis and classification of this disease have had a marked and excellent development in recent years, particularly in the machine learning domain. Multimodal data have been shown to be a significant aid to the machine learning domain, especially by its contribution to improving data driven decision-making. Solving classification problems by combinations of classifiers has made it possible to increase the robustness as well as the classification reliability by using the complementarity that may exist between the classifiers. Complementarity is considered a key property of multimodality. A Convolutional Neural Network (CNN) works very well in pattern recognition and has been shown to exhibit superior performance, especially for image classification which can learn by themselves useful features from raw data. This article proposes a multimodal classification approach based on deep Convolutional Neural Network and Support Vector Machine (SVM) classifiers using multimodal data and multimodal feature for glaucoma diagnosis from retinal fundus images from RIM-ONE dataset. We make use of handcrafted feature descriptors such as the Gray Level Co-Occurrence Matrix, Central Moments and Hu Moments to co-operate with features automatically generated by the CNN in order to properly detect the optic nerve and consequently obtain a better classification rate, allowing a more reliable diagnosis of glaucoma. The experimental results confirm that the combination of classifiers using a new hybrid fusion approach and the BWWV technique is better than learning classifiers separately. The proposed method provides a computerized diagnosis system for glaucoma disease with impressive results comparing them to the main related studies that allow us to continue in this research path. [ABSTRACT FROM AUTHOR]