A new method for detection and classification of melanoma skin cancer using deep learning based transfer learning architecture models

Abstract

Melanoma is a kind of skin cancer that develops in melanocyte cells. It is one of the most serious kind of skin cancer, yet it is not as frequent as other types of skin cancer.It is very hard to detect, even under expert supervision. A Deep Convolutional Neural Network (D-CNN) Visual Geometry Group (VGG16) model, is proposed to improve the classification performance of skin lesions.The main disadvantage of using the deep learning methods is that more time is needed for training. Thus, with the help of transfer learning technique, the training time is reduced. The datasets utilized in the proposed strategy to train the model were obtained from International Skin Imaging Collaboration (ISIC).Metrics like Accuracy (ACC), Positive Predictive Value (PPV), Negative Predictive Value (NPV), Specificity (SPC), and Sensitivity (SE) were measured for the evaluation of the classification.The performance of the classification process done by the classifier model on a test data is represented using a confusion matrix. The proposed method of using transfer learning technique in Deep Convolutional Neural Network improved the accuracy of classification to 85% compared to 81% obtained from Convolutional Neural Network.