This project underscores the significance of [deep learning] and [computer vision] in enhancing ophthalmological diagnostics through fundus image analysis. Accurate detection of patholog ical features within these images is vital for early diagnosis and management of eye diseases such as diabetic retinopathy and glaucoma. Our study conducts a focused literature review on the application of deep learning models for analyzing fundus images, identifying key technological advancements and their diagnostic performance. Following the review, we propose a case study to test select models against a dataset of fundus images. This approach aims to empirically validate the literature findings and assess the real-world applicability of deep learning in improving the accuracy and efficiency of eye disease diagnostics.