A Deep Learning-based Methodology for Predicting Monkey Pox from Skin Sores

ABSTRACT

Monkeypox is a zoonosis that is becoming more prevalent and is the most significant orthopoxvirus epidemic in humans in the models that show the elimination of smallpox. The clinical signs of smallpox and monkeypox are identical. Approximately 1 to 11% of cases lead to death, although among survival, disfigurement and other side effects are common. A rapid clinical identification and diagnosis of monkeypox may be challenging due to its resemblance to measles and chickenpox. In situations whereby confirmatory Polymerase Chain reactions methods aren't always readily available, computer-assisted monkeypox histopathologic identification may be extremely helpful for monitoring and rapid identification of cases reported. Deep learning techniques devise revealed to be effective in the automatic identification of skin infections when there are sufficient training samples available. The paper provides a brief investigation into the growth and spread of monkeypox throughout the world while also deploying a pre-trained deep learning model for illness prediction based on symptoms. Monkeypox might cause an epidemic breakout and a worse crisis than COVID-19, which would have a bigger negative economic impact on Asian nations. The paper concludes by emphasizing that, in trying to make the environment more secure for people, society needs an automated monkeypox prediction and diagnosis system. © 2022 IEEE.