Ensemble of Pre-Learned Deep Learning Model and an Optimized LSTM for Alopecia Areata Classification

The study proposes an Ensemble Pre-Learned Deep Learning and Optimized Long Short-Term Memory (EPL-OLSTM) model to improve the classification of Alopecia Areata (AA) using medical imaging. By integrating pre-learned CNN structures like AlexNet, ResNet, and InceptionNet with an optimized LSTM using the Battle Royale Optimization algorithm, the model enhances the accuracy of differentiating between healthy and various AA scalp hair classes. The model's performance was validated using the Figaro1k and DermNet datasets, achieving a 93.1% accuracy, surpassing existing deep learning models. This approach aims to address the limitations of current Computer Aided Diagnosis models, which require skilled radiologists and have limited interoperability.