Skin cancer presents a formidable challenge in healthcare, consisting of various forms such as melanoma and benign lesions, which demand early detection and precise treatment. In this study, the application of an advanced deep learning model, EfficientNetV2-Small, for the automated classification of skin lesions using the HAM10000 dataset was proposed. This dataset is renowned for its diversity and comprehensive representation of dermoscopy images. This research addresses the critical need for accurate and timely diagnosis in dermatology. The proposed EfficientNetV2-Small model achieved a remarkable accuracy of 88.62% in distinguishing between different types of pigmented skin lesions, including melanoma, nevi, and other benign and malignant lesions. This performance emphasizes the importance of deep learning techniques in image analysis and diagnostic decision support. By using state-of-the-art computational tools, the aim of this study is to contribute to the advancement of clinical practices in dermatology, offering a reliable and objective tool for dermatologists to improve diagnostic accuracy and optimize patient care pathways.