Artificial Intelligence Mobile Dermoscopy: A Method for Class Imbalance Management

Artificial Intelligence (AI) can help analyze medical images to diagnose skin-related diseases such as melanoma. This thesis presents an end-to-end framework for detecting melanoma in real-time on mole images acquired through mobile devices equipped with magnification lenses. The models utilized were trained with public domain ISIC-2019 and ISIC-2020 datasets using EfficientNet convolutional neural networks. The aim of this work is to reduce the problem of class imbalance. As a result, the standard training model with data balance schemes that use oversampling, under sampling, and RCL loss function was integrated. A blurring technique that emulates aberrations caused by magnifying lenses to apply the under sampling method is also introduced. Lastly, a novel loss function that incorporates the cost difference between false positive (melanoma misses) and false negative (benign misses) predictions is used. Results show significant progress in the AUC scale with 98.64% and an accuracy of 96.91%.