Melanoma is a dangerous and metastatic cancer that may be fatal and it has a high ability to invade other tissues and organs. Early diagnosis is an important reason to recover from melanoma and reduce mortality. So, automatic skin segmentation is considered an enthusiastic study at present. In this paper, we investigate the applicability of deep learning approaches to the segmentation of skin lesions by evaluating five architectures: Deeplabv3plus, mobilenetv2_unet, Resnet50_unet, vgg19_unet by providing a comparative study of those methods. All methods were trained on the ISIC2017 dataset. The methods were trained on the original dataset, and then the dataset was pre-processed for use in training the five methods. We used quantitative evaluation metrics to evaluate the performance of the methods. The Deeplabv3+ architecture showed significant results compared to the rest of the architecture in F1 as high as 89%, Jaccard as high as 83% and Recall as high as 91%.

No abstract

Melanoma is a rapidly pervasive and deathly type of skin cancer that is responsible for most deaths from this kind of disease. It can quickly prevail in other organs if not handled early. Fortunately, the symptoms of skin cancer become visible to the sick, which creates a chance to detect it at an early stage. Because people know so little about their specific symptoms and because of a shortage of expert doctors, automated skin cancer detection has become an important public health issue. Many computer-aided diagnostic methods have been suggested so far. Besides traditional techniques based on image processing, researchers have recently used deep learning successfully for many different purposes. Deep neural networks are widely used in segmentation, classification, detection, etc. In this paper, we check the applicability of deep learning approaches to the segmentation of skin lesions to detect lesion boundaries by evaluating five architectures: U-NET, RESU-NET, VGG16UNET, DENSENET121, and EfficientNet-B0 by presenting a comparative view of those approaches. The five architectures were trained on three different data sets: ISIC 2016, ISIC 2018, and PH2, each set consisting of skin lesion images and the ground truth for their segmentation, and then used pre-processed on three datasets. Quantitative evaluation metrics were used for evaluating the performance of the studied architectures. Among these five architectures, the DENSENET121 architecture showed the best precision rate in all training datasets. We obtained an above 95% precision score in the PH2 dataset. In addition, the pre-processing steps were beneficial for the results.