Close menu

SURE

Sunderland Repository records the research produced by the University of Sunderland including practice-based research and theses.

Smart Identification of Psoriasis by Images Using Convolutional Neural Networks: A Case Study in China.

Zhao, Shuang, Xie, Bin, Li, Yi, Zhao, Xin-Yu, Kuang, Yehong, Su, Juan, He, Xiao-Yu, Wu, Xian, Fan, Wei, Huang, Kai, Su, Jie, Peng, Yonghong, Navarini, Alexander A, Huang, Weihong and Chen, Xiang (2019) Smart Identification of Psoriasis by Images Using Convolutional Neural Networks: A Case Study in China. Journal of the European Academy of Dermatology and Venereology : JEADV. ISSN 1468-3083

Item Type: Article

Abstract

Psoriasis is a chronic inflammatory skin disease which holds a high incidence in China. However, professional dermatologists who can diagnose psoriasis early and correctly are insufficient in China, especially in the rural areas. A smart approach to identify psoriasis by pictures would be highly adaptable countrywide, and could play a useful role in early diagnosis and regular treatment of psoriasis. Design and evaluation of a smart psoriasis identification system based on clinical images (without relying on a dermatoscope) that works effectively similar to a dermatologist. A set of deep learning models using convolutional neural networks (CNNs) were explored and compared in the system for automatic identification of psoriasis. The work was carried out on a standardized dermatological dataset with 8021 clinical images of 9 common disorders including psoriasis along with full electronic medical records of patients built over the last 9 years in China. A two-stage deep neural network was designed and developed to identify psoriasis. In the first stage, a multi-label classifier was trained to learn the visual patterns for each individual skin disease. In the second stage, the output of the first stage were utilized to distinguish psoriasis from other skin diseases. The area under the curve (AUC) of the two-stage model reached 0.981±0.015, which outperforms a single-stage model. And the classifier showed superior performance (missed diagnosis rate: 0.04, misdiagnosis rate: 0.03) than 25 Chinese dermatologists (missed diagnosis rate: 0.09, misdiagnosis rate: 0.27) in the diagnosis of psoriasis on 100 clinical images. Using clinical images to identify psoriasis is feasible and effective based on CNNs, which also builds a solid technical base for smart care of skin diseases especially psoriasis using mobile/tablet applications for teledermatology in China. [Abstract copyright: © 2019 European Academy of Dermatology and Venereology.]

Full text not available from this repository.

More Information

Additional Information: ** From PubMed via Jisc Publications Router
Uncontrolled Keywords: classifier, clinical image, convolutional neural network, psoriasis, skin disease dataset
SWORD Depositor: Publication Router
Depositing User: Publication Router

Identifiers

Item ID: 11177
Identification Number: https://doi.org/10.1111/jdv.15965
ISSN: 1468-3083
URI: http://sure.sunderland.ac.uk/id/eprint/11177
Official URL: https://onlinelibrary.wiley.com/doi/full/10.1111/j...

Users with ORCIDS

Catalogue record

Date Deposited: 26 Feb 2020 11:07
Last Modified: 04 Sep 2020 13:34

Contributors

Author: Shuang Zhao
Author: Bin Xie
Author: Yi Li
Author: Xin-Yu Zhao
Author: Yehong Kuang
Author: Juan Su
Author: Xiao-Yu He
Author: Xian Wu
Author: Wei Fan
Author: Kai Huang
Author: Jie Su
Author: Yonghong Peng
Author: Alexander A Navarini
Author: Weihong Huang
Author: Xiang Chen

Actions (login required)

View Item (Repository Staff Only) View Item (Repository Staff Only)