Detection and Removal of Assymmetrical Skin Lesions Using DU-Net for Patch Extraction

Abstract

The incidence of melanoma, a highly fatal kind of malignant tumor, is exhibiting an upward trend in its progression. Timely intervention and management of skin cancer significantly enhance the likelihood of survival. Analyzing dermoscopic images poses challenges for dermatologists due to various distracting factors, including fluctuations in lighting and reflections on the skin's surface. Accurately delineating the area of skin pathology is crucial for diagnosing the specific skin condition. This study introduces DU-net, a method for identifying and removing pigmented skin lesions. The DU-net framework incorporates deep convolutional neural networks, notably YOLOv5, to perform patch detection. It also employs asymmetrical patch contouring methods to preserve edge information. Additionally, clustering algorithms are utilized to identify pixel groups and extract patches from the image. The De Trop Noise Exclusion technique, in conjunction with the process of in-painting, is employed to successfully eliminate hair from the images within the ISIC-2018 and 2019 datasets. Rigorous annotation of skin images with lesions of various sizes and shapes using rectangle bounding is carried out, and YOLOv5 hyper-parameters are fine-tuned to achieve high-confidence multiple lesion detection in dermoscopic images. Despite complex textures and unclear boundaries, our approach consistently detects and labels patches, accurately segmenting the areas of skin pathology. The model's performance is assessed on these datasets using various parameter metrics, the results of the study indicate that the segmentation strategies described in this research exhibit an average accuracy ranging from about 92% to 94%.