scholarly journals 463 Automated atopic dermatitis severity assessment based on convolutional neural networks

2021 ◽  
Vol 141 (5) ◽  
pp. S80
Author(s):  
S. Cho ◽  
D. Lee ◽  
B. Han ◽  
J. Lee ◽  
J. Hong ◽  
...  
Keyword(s):  
Neural Networks ◽  
Atopic Dermatitis ◽  
Convolutional Neural Networks ◽  
Severity Assessment ◽  
Atopic Dermatitis Severity

Severity assessment of atopic dermatitis in children

2016 ◽  
Vol 19 (6) ◽  
pp. 334-339
Author(s):  
Elena Yu. Yanchevskaya ◽  
O. A Bashkina ◽  
Ben Mbarek Makrem
Keyword(s):  
Atopic Dermatitis ◽  
Skin Diseases ◽  
Clinical Manifestations ◽  
Laboratory Diagnosis ◽  
Severity Assessment ◽  
Nonspecific Resistance ◽  
Ige Antibodies ◽  
Atopic Dermatitis Severity ◽  
Classification Of Diseases ◽  
Microbiological Parameters

The article is devoted to the analysis of methods to assess the degree of atopic dermatitis (AD) severity, of their clinical manifestations and laboratory diagnosis. Treatment and prognosis of atopic dermatitis depends on the assessment of disease severity. The severity of the disease is the main factor for a doctor in the therapy of a child with AD. There are many scientific studies devoted to the objective classification of diseases and the development of the most effective methods of severity assessment. It is not always possible to quickly determine objectively measurable parameters ofpathologic skin process. Because of that assessment methods of skin diseases are often approximate and subjective. The new pathogenetic data of atopic dermatitis and the main types of defects are described. Dermatology indexes of atopic dermatitis severity were considered. The new biochemical methods to assess the degree of atopic dermatitis severity in children by measuring indicators of spontaneous adhesion of neutrophils were analyzed. Immunological method, in which serum of children with atopic dermatitis is determined by the level of total IgE and IgE antibodies to allergens, with using ImmunoCAP 100 and level IgG- and IgE-antibodies against tissue antigens by ELISA, were analyzed. The indicators of oxidative status were examined. The concentration of circulating biological peroxides (PPI) and nukliozida 8-OHdG (8-hydroxy-2’-deoxyguanosine) differed significantly in mild, moderate and severe AD. Bacteriological methods, based on an integrated assessment of microbiological parameters, characterizing the nonspecific resistance of skin and mucous membranes in the assessment of severity and prognosis of atopic dermatitis in children, were performed.

scholarly journals Automatic Detection and Severity Assessment of Pepper Bacterial Spot Disease via MultiModels Based on Convolutional Neural Networks

2020 ◽  
Vol 11 (2) ◽  
pp. 29-43
Author(s):  
Qiufeng Wu ◽  
Miaomiao Ji ◽  
Zhao Deng
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Xanthomonas Campestris ◽  
Automatic Detection ◽  
Bacterial Disease ◽  
Severity Assessment ◽  
Bacterial Spot ◽  
Deep Convolutional Neural Networks ◽  
Spot Disease ◽  
Bacterial Spot Disease

Pepper bacterial spot disease caused by Xanthomonas campestris is the most common pepper bacterial disease, which ultimately reduces productivity and quality of products. This work uses deep convolutional neural networks (CNNs) to serve fine-grained pepper bacterial spot disease severity classification tasks. The pepper bacterial spot disease leaf images collected from the PlantVillage dataset are further annotated by botanists and split into healthy samples (label1), general samples (label2), and serious samples (label3). To extract more effective and discriminative features, an integrated neural network denoted as MultiModel_VGR is proposed for automatic detection and severity assessment of pepper bacterial spot disease, which is based on three powerful and popular deep learning architectures, namely VGGNet, GoogLeNet and ResNet. Compared with state-of-the-art single CNN architectures and binary-integrated MultiModels, MultiModel_VGR yields the best overall accuracy of 95.34% on the hold-out test dataset, which may have great potential in crop disease control for modern agriculture.

CNN-based Classification of Degraded Images

2020 ◽  
Vol 2020 (10) ◽  
pp. 28-1-28-7 ◽  
Author(s):  
Kazuki Endo ◽  
Masayuki Tanaka ◽  
Masatoshi Okutomi
Keyword(s):  
Neural Networks ◽  
Image Restoration ◽  
Image Classification ◽  
Convolutional Neural Networks ◽  
Deep Convolutional Neural Networks ◽  
Alternative Approach ◽  
Degraded Image ◽  
Degraded Images ◽  
Straightforward Approach

Classification of degraded images is very important in practice because images are usually degraded by compression, noise, blurring, etc. Nevertheless, most of the research in image classification only focuses on clean images without any degradation. Some papers have already proposed deep convolutional neural networks composed of an image restoration network and a classification network to classify degraded images. This paper proposes an alternative approach in which we use a degraded image and an additional degradation parameter for classification. The proposed classification network has two inputs which are the degraded image and the degradation parameter. The estimation network of degradation parameters is also incorporated if degradation parameters of degraded images are unknown. The experimental results showed that the proposed method outperforms a straightforward approach where the classification network is trained with degraded images only.

Sign in / Sign up

Export Citation Format

Share Document