AI-Driven Biomarker Discovery & Progression Modeling for Precision Diagnosis of Glaucoma

This dissertation presents a comprehensive study on the integration of artificial intelligence (AI) for glaucoma diagnosis and retinal image analysis. Leveraging multimodal imaging data including fundus photography, Optical Coherence Tomography Optical Coherence Tomography (OCT) and Optical Coherence Tomography Angiography (OCTA), the research develops a suite of deep learning frameworks designed to detect early glaucomatous changes with high precision, robustness, and interpretability. A series of novel architectures are introduced, spanning vessel segmentation networks, biomarker discovery pipelines, and multimodal fusion models, all designed to enhance diagnostic accuracy and generalizability across diverse populations. To facilitate reproducible and scalable ophthalmic AI research, this work also contributes several curated datasets, including GSS-RetVein, which provide standardized benchmarks for cross-domain validation. Extensive evaluation demonstrates that the proposed models outperform existing state-of-the-art approaches across multiple public and clinical datasets, achieving marked improvements in diagnostic sensitivity and specificity. Collectively, these findings underscore the potential of AI-assisted imaging systems to support clinicians in early detection, disease progression modeling, and personalized risk assessment. Beyond methodological innovation, this dissertation envisions a broader paradigm for precision ophthalmology, where the convergence of computing, medicine, and responsible data governance fosters equitable, transparent, and data-driven healthcare for global populations.