The Performance improvement using CNN model for melanoma classification

Abstract

Melanoma is a malignant skin cancer with an increasing incidence. To reduce mortalitiy rates due to melanoma, early detection must be taken into consideration. One of the fastest and most useful ways to achieve early detection is to go through Deep learning, and more speci?cically CNN model whose ouput classifies whether the patient is suffereing from melanoma or not. For a better detection, the accuracy of the CNN output has to be high enough so that the patient gets a true result about their state. One of the the hyper-paramters of the CNN model, which leads to more accuracte results, is to add more hidden layers to our model ,at the same time, apply the data augmentation technique for a more perfromant model, and that is what we did in the first part of our project In computer vision, transfer learning is usually expressed through the use of pre-trained models. A pre-trained model is a model that was trained on a large benchmark dataset to solve a problem similar to the one that we want to solve, we want to make a tool capable of detecting melanoma with a higher accuracy than the previous one. In this project, we also focused nusing thepretrained models (VGG, ResNet, Inception and Xception) we then compared the results of our work with the existing works.