MUMBAI, India, Aug. 12 -- Intellectual Property India has published a patent application (202641093840 A) filed by Velammal Institute Of Technology on August 03, 2026, for An Automated Analytics For Diabetic Retinopathy Detection With Deep Learning Models.
Inventors include Dr. Shanmugaraj G; Dr. Sethuram Rao G; Dr. Karthikeyan S; Dilli Babu A; Kishore Chander R; Vishal B; Bhavadharsini B; and Dharshana M S.
The application for the patent was published on August 07, 2026, under issue no. 32/2026.
Abstract: Eye diseases such as diabetic retinopathy, glaucoma, cataract, and age-related macular degeneration (AMD) are among the leading causes of visual impairment and blindness worldwide. Early detection and timely diagnosis are essential to prevent irreversible vision loss; however, conventional diagnostic methods rely heavily on manual examination by experienced ophthalmologists, making the process time-consuming, subjective, and less accessible in resource-limited regions. To address these challenges, the present invention proposes an Artificial Intelligence (AI)-based automated eye disease prediction and classification system using deep learning techniques. The proposed system utilizes retinal fundus images as input and performs a series of image preprocessing operations, including resizing, normalization, grayscale conversion, noise reduction, contrast enhancement, and blood vessel segmentation to enhance the quality of retinal images. Data augmentation techniques such as image rotation, flipping, scaling, and brightness adjustment are employed to improve dataset diversity and reduce class imbalance. The processed images are then analyzed using advanced Convolutional Neural Network (CNN) architectures, including MobileNetV1 and VGG16, for automatic feature extraction. A Softmax- based multi-class classifier accurately categorizes retinal images into diabetic retinopathy, glaucoma, cataract, age-related macular degeneration (AMD), normal retinal conditions, and other retinal abnormalities. The proposed system provides rapid, reliable, and highly accurate disease prediction while minimizing human intervention and diagnostic errors. The automated framework supports ophthalmologists in clinical decision-making and enables large-scale retinal screening in hospitals, diagnostic centers, telemedicine platforms, and rural healthcare facilities. Furthermore, the invention can be integrated with cloud computing, Internet of Medical Things (IoMT), and explainable artificial intelligence (XAI) technologies to improve accessibility, scalability, and real-time ophthalmic diagnosis. By facilitating early detection and timely treatment of retinal diseases, the proposed invention contributes significantly to reducing preventable blindness and improving the quality of healthcare services.
Disclaimer: Curated by HT Syndication.
