Monkeypox has emerged as a fast-spreading disease around the world and an outbreak has been reported in 42 countries so far. Although the clinical attributes of Monkeypox are similar to that of Smallpox, skin lesions and rashes caused by Monkeypox often resemble that of other pox types, e.g., Chickenpox and Cowpox. This scenario makes an early diagnosis of Monkeypox challenging for the healthcare professional just by observing the visual appearance of lesions and rashes. The rarity of Monkeypox before the current outbreak further created a knowledge gap among healthcare professionals around the world. To tackle this challenging situation, scientists are taking motivation from the success of supervised machine learning in COVID-19 detection. However, the lack of Monkeypox skin image data is making the bottleneck of using machine learning in Monkeypox detection from skin images of patients. Therefore, in this project, we introduce the Monkeypox Skin Image Dataset (MSID), the largest of its kind so far. We used web-scrapping to collect Monkeypox, Chickenpox, Smallpox, Cowpox and Measles infected skin as well as healthy skin images to build a comprehensive image database and made it publicly available. We believe that our database will facilitate the development of baseline machine learning algorithms for early Monkeypox detection in clinical settings. Our dataset is available at the following Kaggle link: https://www.kaggle.com/datasets/arafathussain/monkeypox-skin-image-dataset-2022.
Islam, T.; Hussain, M. A.; Chowdhury, F. U. H.; Islam, B. M. R.