Utilizing Swin Transformer for the Classification of Ophthalmic Diseases in Optical Coherence Tomography (OCT) Images: A Novel Approach

This paper presents the use of Swin Transformers (ST) for the detection of common eye diseases like Age-related Macular Degeneration (AMD) and Diabetic Retinopathy (DR) using a Kaggle dataset of Optical Coherence Tomography (OCT) images. The performance of the ST-based model was evaluated against established deep learning-based image classification methods such as Convolutional Neural Networks (CNNs) and Autoencoders, using metrics like Accuracy, Precision, F1-score, and Recall. The study found that Swin Transformers have the potential to significantly improve the diagnosis of eye diseases, highlighting a promising direction for future advancements in medical image analysis. This work contributes valuable insights into the application of state-of-the-art deep learning techniques for medical diagnosis in this area, emphasizing the importance of efficient and accurate detection of eye conditions for timely intervention and patient care.