Ibn Al-Haitham Fundus Image Dataset

The Ibn Al-Haitham Glaucoma Fundus Dataset is a curated medical imaging collection developed to support research in glaucoma segmentation and classification. The dataset was compiled in collaboration with the Ibn Al-Haitham Teaching Eye Hospital in Baghdad, Iraq, and includes 3,000 high-resolution retinal fundus images acquired from clinical settings over a three-month data collection period. The dataset represents a diverse patient population, including both male and female subjects across different age groups and ethnic backgrounds, providing a realistic and representative sample of clinical glaucoma cases. Each image has been meticulously annotated by ophthalmology specialists from Ninevah University, who manually segmented the Optic Disc (OD) and Optic Cup (OC) regions to enable accurate cup-to-disc ratio (CDR) measurement. In addition, all images are categorized by glaucoma stage, supporting both segmentation and three-class classification tasks. Data collection and use were conducted under official approval, verified through an authentication letter from the Iraqi Ministry of Health. This dataset serves as a valuable resource for developing and benchmarking deep learning and computer-aided diagnosis systems for glaucoma detection and progression analysis.