GLAICOMA uses artificial intelligence to improve the diagnosis of glaucoma by integrating OCT scans with clinical measurements such as RNFL thickness and vertical Cup-to-Disc Ratio (vCDR). Our deep learning model utilizes a bimodal approach, where each input stream is processed separately before combining the outputs in a fully connected layer. This late fusion technique enables the model to capture complex relationships between different types of data, resulting in a multi-class classification that distinguishes between normal, mild/moderate, and severe glaucoma cases.

To further enhance detection, we have developed a specialized deep learning algorithm focused on RNFL thickness maps. This algorithm is designed to differentiate glaucomatous from non-glaucomatous eyes by identifying subtle changes in the retinal nerve fiber layer, which is crucial for early detection and management of glaucoma. By targeting this key area, our approach aims to refine diagnostic precision and contribute to more effective treatment strategies for those at risk of vision loss.