Abstract :
Glaucoma is a leading cause of irreversible blindness worldwide, and early detection and timely monitoring are essential to prevent vision loss. Optical coherence tomography (OCT) provides high-resolution, quantitative imaging of the retinal nerve fiber layer (RNFL), ganglion cell complex (GCC), and optic nerve head (ONH), which are central to diagnosis and progression monitoring. Artificial intelligence (AI) has shown strong potential to enhance OCT interpretation by automating segmentation, detecting subtle glaucomatous changes, and predicting progression with performance comparable to expert graders. Challenges include variability across imaging devices, limited dataset diversity, label noise, and lack of prospective real-world validation. Importantly, AI supports but does not replace human expertise in decision-making. Large-scale multicenter datasets, cross-device harmonization, multimodal imaging, and explainable AI frameworks are essential to ensure reliability and trust. With rigorous validation and integration into clinical workflows, AI-enhanced OCT may enable earlier intervention and personalized glaucoma care.
Keyword :
Artificial intelligence, Optical coherence tomography, Glaucoma; Deep learning, Retinal imaging, Glaucoma diagnosis, Disease progression, Explainable AI, Teleophthalmology.