Mpox (formerly known as monkeypox) is a skin disease associated with substantial morbidity. As per current World Health Organization (WHO) guidelines, the severity of mpox disease is determined by the number of skin lesions present on the body. Lesion count is also a key parameter in mpox therapeutic trials, making accurate counts vital. However, counting skin lesions manually is time consuming and logistically challenging, particularly in remote areas prone to mpox outbreaks. This study reported the development of an artificial intelligence (AI) algorithm able to count mpox skin lesions in patient photographs with close correlation to manual counts.

What is exciting about this article?

In 2022, WHO declared a public health emergency due to an outbreak of mpox in Europe and North America. The number of skin lesions on the body is a key factor in determining the extent of mpox disease. This study developed and tested an AI algorithm using photographs from an observational study of 18 people in a remote area of the Democratic Republic of the Congo (DRC) who had all been confirmed to have mpox virus infection by PCR testing. In the future, this could aid diagnosing, staging, and monitoring the disease worldwide.

How does this fit into the larger NIAMS portfolio?

Dr. Cowen leads the NIH Dermatology Consultation Service, conducts independent and collaborative research, and participates in the NIH Undiagnosed Diseases program. This effort was part of a joint intramural/extramural collaboration between investigators at Vanderbilt University, the National Institute of Allergy and Infectious Diseases (NIAID), and the Institut National de Recherche Biomédicale in the DRC. Dr. Cowen is also providing dermatologic support for the NIAID randomized clinical trial studying the benefit of tecovirimat for the treatment of mpox in the DRC (NCT05559099).

Grant support


Research Areas:

Clinical Research Immunology Skin Biology


Counting Monkeypox Lesions in Patient Photographs: Limits of Agreement of Manual Counts and Artificial Intelligence.

McNeil AJ, House DW, Mbala-Kingebeni P, Mbaya OT, Dodd LE, Cowen EW, Nussenblatt V, Bonnett T, Chen Z, Saknite I, Dawant BM, Tkaczyk ER
J Invest Dermatol.
2023 Feb;
doi: 10.1016/j.jid.2022.08.044
PMID: 36116509

Research reported in this publication was supported by the Intramural Research Program of the NIHʼs National Institute of Arthritis and Musculoskeletal and Skin Diseases.