Skin cancer is the most prevalent and deadly form of cancer, claiming millions of lives each year. Its early-stage symptoms are often subtle, making initial diagnosis challenging. This study utilizes the Inception v3 model to differentiate between benign and malignant skin lesions with high accuracy using deep learning techniques. The ISIC 2017 dataset, which includes seven different types of skin lesions, was used for screening. The Inception v3 model leverages multiple parallel filters (1 × 1, 3 × 3, 5 × 5) within the same layer, enabling the network to capture features at various scales. This allows for the inclusion of more features without significantly increasing processing complexity. The model was trained, and the desired outcomes were achieved through data preprocessing and transfer learning techniques. The model achieved approximately 80% accuracy on the test set and 84% accuracy on the validation set. In conclusion, the increasing depletion of the ozone layer leads to more UV radiation, which in turn causes a rise in skin cancer cases each year. Early detection of skin cancer could save many lives, potentially allowing for treatment with a cream instead of costly surgery.