A deep convolutional neural network-based pigmented skin lesion classification application and experts evaluation

Abstract

Pigmented skin lesions are common spots or growths on the skin that originate from melanocyte cells. Skin cancer occurs as a result of the uncontrolled division of melanocyte cells. Skin cancer is common worldwide and its incidence has been increasing. Timely and accurate diagnosis of skin cancer is important in reducing deaths. Skin cancer cases are diagnosed by expert dermatologists, but the number of experts is insufficient for the population. Dermoscopy is one of the most commonly used methods for imaging skin lesions. Sometimes misdiagnosis can occur in the interpretation of dermoscopic images by human experts. Computer-aided systems help to make accurate and objective decisions in the diagnosis of skin lesions. Convolutional neural network(CNN) is a deep learning technique commonly used in the field of computer vision and is also widely used in medical image analysis In this study, a CNN model was proposed to classify seven different skin lesions in the HAM10000 dataset. The model provided a classification accuracy of 91.51%. The performance of the model was compared with similar studies in the literature and it was found that it showed higher success than most studies. The model was connected to a web application and evaluated in two phases by seven expert dermatologists. In the first phase, it was concluded that the model could diagnose skin lesions with 90.28% accuracy in practice. In the second phase, the model corrected the experts' misdiagnoses by 11.14%.