Implementation of detection of skin lesions in monkeypox based on a deep learning model: using an improved bilinear pooling model

Wenshu Liu

doi:10.1117/12.2669408

24 March 2023 Implementation of detection of skin lesions in monkeypox based on a deep learning model: using an improved bilinear pooling model

Wenshu Liu

Author Affiliations +

Proceedings Volume 12611, Second International Conference on Biological Engineering and Medical Science (ICBioMed 2022); 126110U (2023) https://doi.org/10.1117/12.2669408
Event: International Conference on Biological Engineering and Medical Science (ICBioMed2022), 2022, Oxford, United Kingdom

Abstract

Since 2022 May monkeypox virus has emerged one after another in various countries around the world, breaking the number of countries that have not previously recorded monkeypox transmission and becoming a new threat to the global epidemic, with new pathologies from many countries every day, and on July 23, 2022 the World Health Organization decided to classify the emergence of monkeypox outbreaks in several countries as public health emergencies of international concern. The use of lesion image-assisted detection for monkeypox disease could reduce the burden of early diagnosis and help reduce the time and cost required for early mass screening and diagnosis of monkeypox virus, but currently the dataset used for our training is collected from public platforms and is not supported by clinical data and cannot yet be used for monkeypox disease. In this paper, a method based on model fusion with bilinear pooling confluence of EfficientNet and DenseNet is proposed. Images are segmented, feature extraction is carried out by two models given to EfficientNet and DenseNet, respectively, and the outer product and average confluence of various spatial locations are calculated to obtain bilinear features. The classification task was binary classification of monkeypox and non-monkeypox, and the dataset used was the monkeypox skin lesion dataset MSLD, and the highest classification accuracy obtained was 94.57%, the accuracy and recall were 0.94 and 0.94, respectively, and the F1-score obtained was 0.945. The model-assisted detection classification can help us identify monkeypox patients and assist in diagnosis to reduce the large-scale early diagnosis burden and help to limit the rapid spread of monkeypox virus.

Citation Download Citation

Wenshu Liu "Implementation of detection of skin lesions in monkeypox based on a deep learning model: using an improved bilinear pooling model", Proc. SPIE 12611, Second International Conference on Biological Engineering and Medical Science (ICBioMed 2022), 126110U (24 March 2023); https://doi.org/10.1117/12.2669408

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
8 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Data modeling

Deep learning

Education and training

Image segmentation

Diseases and disorders

Image classification

Feature extraction

Show All Keywords

Keywords/Phrases

Search In:

Publication Years