SkinLesNet: Classification of Skin Lesions and Detection of Melanoma Cancer Using a Novel Multi-Layer Deep Convolutional Neural Network

Abstract

Skin cancer is a widespread disease that typically develops on the skin due to frequent exposure to sunlight. Although cancer can appear on any part of the human body, skin cancer accounts for a significant proportion of all new cancer diagnoses worldwide. There are substantial obstacles to the precise diagnosis and classification of skin lesions because of morphological variety and indistinguishable characteristics across skin malignancies. Recently, deep learning models have been used in the field of image-based skin-lesion diagnosis and have demonstrated diagnostic efficiency on par with that of dermatologists. To increase classification efficiency and accuracy for skin lesions, a cutting-edge multi-layer deep convolutional neural network termed SkinLesNet was built in this study. The dataset used in this study was extracted from the PAD-UFES-20 dataset and was augmented. The PAD-UFES-20-Modified dataset includes three common forms of skin lesions: seborrheic keratosis, nevus, and melanoma. To comprehensively assess SkinLesNet's performance, its evaluation was expanded beyond the PAD-UFES-20-Modified dataset. Two additional datasets, HAM10000 and ISIC2017, were included, and SkinLesNet was compared to the widely used ResNet50 and VGG16 models. This broader evaluation confirmed SkinLesNet's effectiveness, as it consistently outperformed both benchmarks across all datasets.

Keywords: computer vision; computer-aided diagnosis; convolutional neural network; deep learning; medical imaging; melanoma; skin cancer; skin lesion.

Figure 1

Illustrative representations from the PAD-UFES-20-Modified dataset employed in this research exhibit diverse visualizations of distinct skin lesions, encompassing the three respective categories of seborrheic keratosis, nevus, and melanoma.

Figure 2

The pie chart highlights the distribution of different skin-lesion classes within the PAD-UFES-20-Modified dataset, and shows that in this dataset there is no significant class imbalance.

Figure 3

Proposed multi-layer deep CNN model architecture to classify different skin lesions categories.

Figure 4

The graph depicts variations in training and validation accuracy and loss of the proposed SkinLesNet model over the first 10 epochs. Accuracy gradually increased and reached 96% after 100 epochs.