Deep Convolutional Neural Network with TensorFlow and Keras to Classify Skin Cancer Images
Houssam Benbrahim, Hanaâ Hachimi, Aouatif Amine
Abstract
Skin cancer is a dangerous disease causing a high proportion of deaths around the world. Any diagnosis of cancer begins with a careful clinical examination, followed by a blood test and medical imaging examinations. Medical imaging is today one of the main tools for diagnosing cancers. It allows us to obtain precise images, internal organs and thus to visualize the possible tumours that they present. These images provide information on the location, size and evolutionary stage of tumour lesions. Automatic classification of skin tumours using images is an important task that can help doctors, laboratory technologists, and researchers to make the best decisions. This work has developed a classification model of skin tumours in images using Deep Learning with a Convolutional Neural Network based on TensorFlow and Keras model. This architecture is tested in the HAM10000 dataset consists of 10,015 dermatoscopic images. The results of the classification of the experiment show that the accuracy was achieved by our model, which is in order of 94.06% in the validation set and 93.93% in the test set.