Dry and Wet Age-Related Macular Degeneration Classification Using Oct Images and Deep Learning

AMD represents a substantial reason behind vision loss because it exists as two different types known as Dry and Wet AMD thus requiring swift proper diagnosis methods to deliver successful treatment possibilities. The research examines the application of Vision Transformers (ViTs) in Global OCT Image Analysis through their ability to detect local and global retinal abnormalities using the self-attention mechanism. The proposed model operates through Hugging Face Transformers and PyTorch to analyze high-resolution OCT images for precise identification of Dry and Wet AMD. The classification accuracy together with robustness is superior in ViTs compared to standard CNN-based approaches when analyzing constrained datasets. The produced results show substantial improvement of diagnostic accuracy together with better feature capturing abilities and more transparent assessment capabilities making automated AMD diagnosis more efficient. The research proves that ViTs represent an advanced deep learning technique which can deliver optimized retinal disease classification from OCT images while offering an effective AI-assisted diagnostic system. The subsequent research will focus on combining multiple data sources to boost practical medical system use.