Autoencoder Performance Analysis of Skin Lesion Detection

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.

Multimodal Biomedical Image Segmentation using Multi-Dimensional U-Convolutional Neural Network

“…Zahraa E. Diame et al [19] evaluated five frameworks (U-Net, Res-U-Net, VGG-16UNET, DenseNet-121, and EfficientNet-B0) to assess the potential application of deep learning techniques for skin lesion segmentation to identify lesion boundaries. The DenseNet-121 framework outperformed other methods in terms of precision rate across all training datasets.…”