Background/Purpose: Skin cancer is the commenest cancer in Australia and around the world with increasing incidence and mortality rates. Automated systems utilizing deep learning algorithms have emerged as promising tools for the detection and classification of skin cancers, aiding in early diagnosis and management (1) Methods: This study evaluates the application of deep learning models in the automated detection and classification of skin cancers, melanoma and non melanoma skin cancers. A dataset of dermoscopic images from publicly available repositories was used to train and test Convolutional neural networks (CNN) models. Preprocessing techniques included image augmentation and normalization. Model performance was assessed for accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve (AUC-ROC). (1) Results: A total of over 15 studies met the inclusion and exclusion criteria. CNNs in particular, showed remarkable accuracy in identifying malignant lesions, often outperforming plastic surgeons and dermatologists. The reviewed studies highlighted the potential of AI-assisted diagnostic systems to improve sensitivity and specificity in detecting skin cancers. Conclusion: The integration of deep learning and artificial intelligence has the potential to revolutionize skin cancer screening, offering reliable, image-based diagnostic support. With further validation and clinical integration, these systems can enhance diagnostic precision and improve patient care, particularly in Australia, where skin cancer rates are exceptionally high. (1) (1)Naqvi M, Gilani SQ, Syed T, Marques O, Kim HC. Skin cancer detection using deep learning—a review. Diagnostics. 2023 May 30;13(11):1911.