The public's health is seriously threatened by the viral disease known as monkeypox. Accurate and timely diagnosis is essential for successful control and suppression of outbreaks. Deep learning (DL) approaches have produced encouraging results in the classification of medical images in recent years. The proposed PoxTLNet50 model combines ResNet50V2 DL architecture with a transfer learning technique for the classification of monkeypox diseases using the MSID (Monkeypox Skin Image Dataset). The MSID dataset consists of high-resolution skin images collected from patients diagnosed with monkeypox, encompassing a variety of disease stages and severity levels. The PoxTLNet50 model performance was assessed using a variety of performance metrics, and it attained an accuracy of 98.83%. The PoxTLNet50 model helps for early detection and management of monkeypox, aiding healthcare professionals and public health agencies in timely interventions and preventive measures.

Monkeypox ResNet50V2 Deep learning Transfer Learning ROC