This article presents a study on the use of unified deep convolutional neural networks, specifically YOLOv3, YOLOv4, YOLOv5, and YOLOv7, for skin cancer recognition. Skin cancer is a growing public health issue, and early diagnosis is crucial for effective treatment. However, differentiating between malignant melanoma and benign skin lesions is challenging for dermatologists due to their visual similarities. The study evaluates the performance of these YOLO models in classifying skin lesions using the International Skin Imaging Collaboration (ISIC) dataset, which contains 2750 images of skin lesions. The models were trained and tested on this dataset to assess their ability to detect and classify skin lesions accurately. YOLOv7 showed the best performance with an Intersection over Union (IoU) of 86.3%, a mean Average Precision (mAP) of 75.4%, an F1-measure of 80%, and an inference time of 0.32 seconds per image. The study also explored the use of data augmentation to improve the generalization of the models. The results indicate that YOLOv7 is a promising tool for aiding dermatologists in early skin cancer diagnosis and potentially reducing unnecessary biopsies. The study highlights the potential of deep learning in improving the accuracy and efficiency of skin cancer detection.This article presents a study on the use of unified deep convolutional neural networks, specifically YOLOv3, YOLOv4, YOLOv5, and YOLOv7, for skin cancer recognition. Skin cancer is a growing public health issue, and early diagnosis is crucial for effective treatment. However, differentiating between malignant melanoma and benign skin lesions is challenging for dermatologists due to their visual similarities. The study evaluates the performance of these YOLO models in classifying skin lesions using the International Skin Imaging Collaboration (ISIC) dataset, which contains 2750 images of skin lesions. The models were trained and tested on this dataset to assess their ability to detect and classify skin lesions accurately. YOLOv7 showed the best performance with an Intersection over Union (IoU) of 86.3%, a mean Average Precision (mAP) of 75.4%, an F1-measure of 80%, and an inference time of 0.32 seconds per image. The study also explored the use of data augmentation to improve the generalization of the models. The results indicate that YOLOv7 is a promising tool for aiding dermatologists in early skin cancer diagnosis and potentially reducing unnecessary biopsies. The study highlights the potential of deep learning in improving the accuracy and efficiency of skin cancer detection.