Skin Cancer Recognition Using Unified Deep Convolutional Neural Networks

Simple Summary According to the World Fund for Research on Cancer, skin cancer is one of the most common cancers. The early diagnosis of skin cancer lesions plays an essential role in the patient's recovery. Nevertheless, recognizing skin cancer and differentiating it from benign skin lesions is a challenging task for dermatologists due to the visual similarities of benign nevi, seborrheic keratoses, and malignant melanomas. In this context, image-based skin lesion recognition systems have appeared as a solution to recognize these lesions and therefore reduce the number of biopsy procedures. This research investigated the performance of the latest versions of the You Only Look Once (YOLO) deep learning models. Unlike classification-based solutions, the proposed YOLO-based approach locates the skin lesions and categorizes them into the predefined classes. The experiments were conducted using 2750 images from the publicly accessible International Skin Imaging Collaboration (ISIC) dataset.Abstract The incidence of skin cancer is rising globally, posing a significant public health threat. An early and accurate diagnosis is crucial for patient prognoses. However, discriminating between malignant melanoma and benign lesions, such as nevi and keratoses, remains a challenging task due to their visual similarities. Image-based recognition systems offer a promising solution to aid dermatologists and potentially reduce unnecessary biopsies. This research investigated the performance of four unified convolutional neural networks, namely, YOLOv3, YOLOv4, YOLOv5, and YOLOv7, in classifying skin lesions. Each model was trained on a benchmark dataset, and the obtained performances were compared based on lesion localization, classification accuracy, and inference time. In particular, YOLOv7 achieved superior 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 s per image. These findings demonstrated the potential of YOLOv7 as a valuable tool for aiding dermatologists in early skin cancer diagnosis and potentially reducing unnecessary biopsies.