A Novel Approach to Glaucoma Detection: Leveraging Fourier Transform, Structural Similarity Index, and Self-Supervised Learning

Glaucoma is one of the leading causes of irreversible blindness worldwide, affecting millions of people each year. Early diagnosis is crucial to prevent vision loss, but the often asymptomatic nature of the disease and the complexity of clinical signs make timely detection challenging. Advanced ocular imaging technologies, such as optical coherence tomography and fundus photography, offer new diagnostic opportunities but generate complex and voluminous data requiring significant expertise for interpretation. Artificial intelligence (AI) is revolutionizing this field, enabling efficient data analysis and supporting physicians in early risk identification and disease monitoring. In this article, we present a comprehensive approach that combines advanced image preprocessing techniques with artificial intelligence (AI) models to enhance the diagnostic accuracy of glaucoma. Using the REFUGE2 dataset, we implemented the Discrete Fourier Transform (DFT) for image preprocessing, leveraging the Fast Fourier Transform (FFT) algorithm for computational efficiency. This approach effectively preserved visual features, achieving SSIM values of 0.9225 for training, 0.8637 for validation, and 0.8247 for testing. For classification, we employed various models, including Masked Image Modeling (MIM) and Masked Autoencoder (MAE), combined with self-supervised learning techniques such as SimCLR. This multi-model approach allowed us to explore different perspectives in image analysis, achieving an accuracy of 90.06\% with MIM and 90.14\% with MAE on preprocessed images, surpassing the results obtained with non-preprocessed data. Moreover, the MIM model demonstrated a strong discriminative capability, highlighted by an AUC-ROC of 0.9298, a precision of 0.8154, and an F1-score of 0.6998. The results show that combining advanced preprocessing with Transformer neural networks can significantly improve efficiency and diagnostic accuracy in the early detection of glaucoma. This approach offers a scalable and robust method for disease management, contributing to improvements in traditional clinical practices.