 This paper proposes two methods for diagnosing skin cancer using hybrid CNN models. The first method involves analyzing the area of skin lesions and classifying them as either benign or malignant using a combination of CNN models and artificial neural networks. The second method uses a combination of CNN models and random forest algorithms to analyze the area of skin lesions and classify them as either benign or malignant. Both methods achieve promising results, with the first achieving an AUC of 94.41 percent and the second achieving an AUC of 97.31 percent. This article was authored by Fekri Olia, Ebrahim Mohamed Senan, Ibrahim Abdel Rabbaq Med, and others.