The device offers a more cost-effective and portable alternative to imported models, making it accessible to a wider range of users, including clinics and healthcare providers in resource-limited settings. Its compact and lightweight design allows for easy transport and use in various environments, from hospitals to remote or temporary medical camps. Additionally, the system is designed for seamless integration with existing medical infrastructure, ensuring compatibility with current diagnostic or monitoring tools and reducing the need for significant upgrades or additional equipment. This enhances both its practicality and potential for widespread adoption in healthcare settings.

Diabetic retinopathy is a leading cause of vision loss among diabetic patients worldwide. Early detection is crucial, but existing screening methods are often invasive, costly, or inaccessible.

DiReScan uses AI-powered image analysis to detect early signs of diabetic retinopathy from retina images. The system captures eye scans using a fundus camera and processes them through a trained AI model that can classify the severity of the condition.

EDR-Net+ is a noise-invariant and computationally efficient deep neural network architecture developed for the early detection of diabetic retinopathy (DR). As diabetic retinopathy remains a leading cause of vision loss globally, timely and accurate screening is essential. EDR-Net+ powers the DiReScan system, which uses AI-based image analysis to assess retina images captured by a fundus camera. The model can detect early signs of DR and classify its severity, offering a non-invasive, affordable, and accessible alternative to conventional screening methods—particularly beneficial for remote or under-resourced healthcare settings.