Skin Cancer Detection using Convolutional Neural Network

The advancement of artificial intelligence is reshaping various sectors of our lives including disease identification. Today, dermatologists depend greatly on digitalized output of patients' results to be absolutely confirm about skin cancer. In recent times, many researches based on machine learning pave the way to classify the stages of skin cancer in clinicopathological practice. In this paper, we have tried to evaluate the chance of deep learning algorithm namely Convolutional Neural Network (CNN) to detect skin cancer classifying benign and malignant mole. We have discussed recent studies that use different models of deep learning on practical datasets to develop the classification process. The dataset we use for this research is ISIC containing a total of 2460 colored images. We use 1800 images as training set and the rest 660 for testing set. A detailed workflow to build and run the system is presented too. We have used Keras and TensorFlow to structure our model. Our proposed VGG-16 model shows a promising development upon some modification to the parameters and classification functions. The model achieves an accuracy of 87.6%. As a result, the study shows a significant outcome of using CNN model in detecting skin cancer.