Significant public health concerns have been raised by the recent rapid spread of monkeypox (mpox) outside of Africa, primarily because it presents a difficult clinical diagnosis and is frequently mistaken for monkeypox or measles. The computer-assisted detection of monkeypox lesions could be a useful technique for the quick identification of suspected cases when polymerase chain reaction (PCR) testing for confirmation is not easily accessible. Although deep learning has demonstrated success in automated skin lesion diagnosis, its use in this situation is hampered by the dearth of relevant monkeypox datasets. In this study, we present the “Monkeypox Skin Lesion Dataset (MSLD),” which consists of pictures of skin lesions caused by measles, Monkeypox, and monkeypox that have been gathered from a variety of websites, news portals, and publically available case reports. The dataset is expanded using data augmentation techniques, and a threefold cross-validation experiment is run. Furthermore, the classification of diseases such as monkeypox and others is carried out using pre-trained deep learning models, particularly ResNet-50, demonstrating the potential of this method for early diagnosis and surveillance of monkeypox cases.