Year: 2024
Type: article
Abstract: Monkeypox is a disease that can pose a global epidemic threat, although it is less deadly and contagious compared to the COVID-19 epidemic. Deep learning techniques offer promising results in the diagnosis of diseases in the field of medical imaging. This study develops deep learning models using skin lesion images for early diagnosis of monkeypox. The study comprises two main sections. The first section introduces a deep learning model trained using the Monkeypox Skin Image Dataset, while the second section presents a model trained with a combined dataset derived from the Monkeypox Skin Image, Monkeypox Master, and Monkeypox Original Images datasets. Five distinct deep learning models—DenseNet201, InceptionResNetV2, InceptionV3, NASNetLarge, and Xception—were employed and compared across these two datasets. The DenseNet201 model, trained with augmented datasets, demonstrated significant success in identifying monkeypox, achieving accuracy rates of 99.33% and 98.52% in the MSID and HYBRID datasets, respectively.
Authors: Muhammet Talha Engin, Kemal Adem
Institutions: Aksaray University, Sivas Bilim ve Teknoloji Üniversitesi
Language: English
Subfield: Virology
Field: Immunology and Microbiology
Domain: Life Sciences
Open Access status: diamond
OpenAlex ID: W4401612416