HFMD Skin Rash Detection Using Convolutional Neural Networks
Conference proceedings article
Authors/Editors
Strategic Research Themes
Publication Details
Author list: Vakili, Naqibullah; Phattarakijtham, Nipat; Chan, Jonathan H.; Krathu, Worarat;
Publisher: Springer Science and Business Media Deutschland GmbH
Publication year: 2021
Title of series: Lecture Notes in Network and Systems (LNNS)
Volume number: 251
Start page: 159
End page: 168
Number of pages: 10
ISBN: 9783030797560
ISSN: 23673370
Languages: English-Great Britain (EN-GB)
Abstract
Skin rash problems are common and often temporary if they can be treated in time. Hand-Foot-Mouth disease (HFMD) is an extremely contagious viral infection common in infants, and can quickly develop into a severe problem. The infection can spread quickly through close contact with an infected person. HFMD usually involves the hands, feet and mouth, but sometimes can be detected elsewhere. To assist in diagnosing HFMD, we built a dataset of various skin conditions from readily available web sources. We propose the use of a deep convolutional neural networks (CNN) to distinguish HFMD rash from other skin conditions and normal skin. This study presents a promising application of CNN with a precision rate of 0.92%, 0.96%, and 0.88 for HFMD, non-HFMD, and normal skin, respectively. Our proposed model can facilitate a proper and early detection of HFMD rash to assist in containing HFMD outbreaks regionally. © 2021, The Author(s), under exclusive license to Springer Nature Switzerland AG.
Keywords
Convolutional neural networks (CNN), Deep Learning, Hand, Foot and Mouth Disease, HFMD, Multiclass classification
Contact Information