A New Glaucoma Detection Method Using a Swin Transformer and Image Segmentation

This study develops and evaluates an advanced automated system for glaucoma detection using deep learning techniques, addressing the limitations of traditional diagnostic methods that rely heavily on ophthalmologists’ expertise, often leading to inconsistencies and delays. By merging five publicly available datasets—ODIR-5K, ACRIMA, RIM-ONE, ORIGA, and REFUGE—into a comprehensive dataset, the research ensures robust model training and evaluation. The SegFormer model is employed for effective image segmentation, overcoming the feature discrimination challenges of traditional convolutional neural networks. The segmented images are then classified using the Swin Transformer, which efficiently handles high-resolution images with reduced computational complexity. The combined SegFormer and Swin Transformer model demonstrates superior performance, achieving 97.8% accuracy, 97.5% precision, 98.29% recall, and a 98.33% F1-score. This approach not only outperforms standalone models but also surpasses other state-of-the-art CNNs, highlighting the significant potential of deep learning in enhancing glaucoma detection and improving diagnostic accuracy.