An Efficient Skin Cancer Recognition Using Hybrid GAN Model And Deep GRU-CNN Neural Network
Mohammed Saeb Nahi
Abstract
Accurate detection of skin melanoma plays a vital role in clinical diagnosis and treatment planning. In this study, we propose an advanced deep learning approach—a hybrid GAN-CNN-GRU model—for skin cancer classification. Leveraging deep learning techniques allows healthcare providers to efficiently analyze large volumes of images, leading to faster and more accurate diagnoses. However, the requirement for large centralized datasets to train these models poses challenges, particularly due to privacy regulations surrounding medical data. To address this issue, we develop a model that uses a Generative Adversarial Network (GAN) to generate synthetic melanoma images. These images are then classified using a combined CNN-GRU architecture. The hybrid model achieves impressive results, reaching a classification accuracy of 96.07%.
References
Back