Enhancing Skin Lesion Diagnosis using Hybrid BiLSTM-GRU Recurrent Neural Network

Abstract

Skin lesion classification is a significant process in the diagnosis and early detection of melanoma and other conditions. In this study, a combined technique based on LSTM and GRU models was applied to extract spatial and sequential features from skin cancer images and to improve their classification into benign or malignant classes. In order to improve classification performance, various architectures are explored, including BiLSTM, GRU, and GRU combined to BiLSTM. These models process image data as temporal sequences, so that it can learn complex dependencies between pixel patterns. The conducted experiments display that the GRU-based method reached an accuracy of 81.21%, compared to 81% for the BiLSTM model. The blend of both architectures outperformed each of the two individual models, registering a higher accuracy of 85%, thus showcasing the potential of the hybrid approach. These results indicate the strengths of LSTM-GRU combined model in untying temporal structures from sequential features and improving classification accuracy when fused for deep feature extraction. The application of Batch Normalization and Dropout also assists in creating a stable, accurate, and robust classification system.