Iren Valova, Peter Dinh ,Natacha Gueorguieva

Abstract: Malignant melanoma is the deadliest skin cancer and early detection is important to improve patient prognosis. Recently, deep learning neural networks (DLNNs) have proven to be a powerful tool in classifying medical images for detecting various diseases and it has become viable to address skin cancer detection. In this research we propose a serverless mobile app to assist with skin cancer detection. This mobile app is based on the best performance of five convolutional neural network (CNN) models designed from scratch as well as four state-of-the-art architectures used for transfer learning (Inception v3, ResNet50v2, DenseNet, and Exception v2). Since the skin cancer dataset is imbalanced, we perform data augmentation. We also use the fine-tuning top layers technique for feature extraction on all models to improve the results. The main novelty of the proposed method is deploying the model as part of mobile app where the classification processes are executed locally on the mobile device. This approach reduces the latency and improves the privacy of the end users compared with the cloud-based model where user needs to send images to a third-party cloud service. The achieved accuracy of pre-trained Inception v3 model is 99.99%. Therefore, the proposed mobile solution can serve as a reliable tool that can be used for melanoma detection by dermatologists and individual users.

Keywords: Melanoma, Deep learning, Transfer learning, mobile app, Convolutional neural networks.

Date Published: October 10, 2023
DOI: 10.11159/jmids.2023.003

View Article