Ocular fungal infections, including fungal keratitis and endophthalmitis, pose significant diagnostic and therapeutic challenges, particularly in low-resource settings. These infections are often misdiagnosed due to clinical overlap with bacterial causes and limitations of traditional diagnostics. Artificial intelligence (AI), particularly deep learning, has emerged as a transformative tool in ophthalmology. Deep learning models have demonstrated high accuracy in identifying fungal features and differentiating pathogens, with some outperforming nonspecialist clinicians. Multimodal AI systems combining imaging with clinical or lab data further enhance diagnostic performance. Beyond diagnosis, AI is increasingly used for treatment guidance and prognostication, aiding in drug selection and outcome prediction. Despite promising results, issues related to data generalizability, transparency, ethics, and real-world deployment remain. With proper regulation and inclusive datasets, AI has the potential to democratize expert-level diagnosis and management, significantly reducing global blindness from fungal eye disease. The integration of AI into clinical workflows and remote care holds particular promise for underserved populations. This chapter reviews AI applications in diagnosing fungal infections using various imaging modalities, such as slit-lamp photography, smartphone images, and in vivo confocal microscopy.