Elshahawy, M.; Elnemr, A.; Oproescu, M.; Schiopu, A.-G.; Elgarayhi, A.; Elmogy, M.M.; Sallah, M. Early Melanoma Detection Based on a Hybrid YOLOv5 and ResNet Technique. Diagnostics2023, 13, 2804.
Elshahawy, M.; Elnemr, A.; Oproescu, M.; Schiopu, A.-G.; Elgarayhi, A.; Elmogy, M.M.; Sallah, M. Early Melanoma Detection Based on a Hybrid YOLOv5 and ResNet Technique. Diagnostics 2023, 13, 2804.
Elshahawy, M.; Elnemr, A.; Oproescu, M.; Schiopu, A.-G.; Elgarayhi, A.; Elmogy, M.M.; Sallah, M. Early Melanoma Detection Based on a Hybrid YOLOv5 and ResNet Technique. Diagnostics2023, 13, 2804.
Elshahawy, M.; Elnemr, A.; Oproescu, M.; Schiopu, A.-G.; Elgarayhi, A.; Elmogy, M.M.; Sallah, M. Early Melanoma Detection Based on a Hybrid YOLOv5 and ResNet Technique. Diagnostics 2023, 13, 2804.
Abstract
Cancer is a condition in which the body's cells proliferate unchecked. Skin cancer is one of the deadliest diseases that impacts the skin on many levels. There are several different types of the disease, including melanoma, basal cell carcinoma (BCC), squamous cell carcinoma (SCC), and melanocytic nevus. Due to its increased prevalence, skin cancer, in particular melanoma, is be-coming a serious health problem. Early identification of skin lesions is crucial for successful treatment. Due to their resemblance, many skin lesions are misclassified, which is a severe issue. Researchers seek computer-aided diagnostic tools for early malignant tumor detection. First, a new model based on the combination of "you only look once" (YOLOv5) and "ResNet50" is proposed for melanoma detection with its degree using humans against a machine with 10,000 training images (HAM10000). Second, feature maps integrate gradient change, which allows rapid inference, boosts precision, and reduces the number of hyperparameters in the model, making it smaller. Finally, to get the desired outcomes, the current YOLOv5 model is changed by adding new classes for dermatoscopic images of typical lesions with pigmented skin. The pro-posed approach improves melanoma detection with a real-time speed of 0.4 ms non-maximum suppression (NMS) per image. The performance metrics average is 99.0%, 98.6%, 98.8%, 99.5, 98.3%, and 98.7% for precision, recall, dice similarity coefficient (DSC), accuracy, mean average precision (MAP) from 0.0 to 0.5, and MAP from 0.5 to 0.95, respectively. Compared to cur-rent melanoma detection approaches, the provided approach is more efficient using deep fea-tures.
Keywords
Skin cancer classification; melanoma detection; you only look once (YOLO); dermatoscopic im-ages analysis; ResNet50 network
Subject
Computer Science and Mathematics, Artificial Intelligence and Machine Learning
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
,
