Skin Cancer Detection by Using Deep Learning Approach.

Skin cancer is one of the most widespread and deadly types of cancer. Dermatologists primarily diagnose this disease visually. The classification of skin cancer into multiple categories is challenging due to the precise variation in the appearance of different diagnostic categories. On the other hand, recent studies have shown that convolutional neural networks outperform dermatologists in classifying multi-category skin cancer. In this work, a straight forward methodology was adopted with the aim of attaining high performance at a low cost. The methodology encompassed three stages: image resizing, normalization, and, finally, the classification of the seven types of skin cancer. Through training the convolutional artificial neural network on the HAM10000 dataset and subsequently subjecting it to testing, a performance rate of 78% was achieved by the model.