Diabetic retinopathy (DR) is a major cause of vision loss, particularly in areas with limited resources where access to specialized care is scarce. This study introduces an automated screening system for DR using attention-enhanced deep learning on retinal fundus images, designed specifically for these regions. The system utilizes a convolutional neural network (CNN) with integrated attention mechanisms to focus on critical features indicative of DR, such as microaneurysms and hemorrhages. This attention- enhanced approach improves detection accuracy and reliability. A varied collection of retinal fundus images was employed for both training and validation purposes, with data augmentation to enhance model robustness. The model was optimized for deployment on low-cost hardware, ensuring feasibility in resource- limited settings. Performance evaluation showed high sensitivity and specificity, and attention maps provided interpretability for healthcare providers. This automated system has the potential to improve early DR detection in underserved areas, facilitating timely intervention and reducing the risk of blindness. By making advanced diagnostic tools accessible, this approach promotes equitable healthcare and helps prevent vision loss globally.