MUMBAI, India, Nov. 2 -- Intellectual Property India has published a patent application (202641125869 A) filed by Srm Trp Engineering College on October 22, 2026, for An Artificial Intelligence-Based System And Method For Automated Detection And Severity Grading Of Diabetic Retinopathy Using Retinal Fundus Images.
Inventor includes S. Priyadharshini.
The application for the patent was published on October 30, 2026, under issue no. 44/2026.
Abstract: The present invention discloses an Artificial Intelligence (AI) based system and method for automated detection and severity grading of Diabetic Retinopathy (DR) from retinal fundus images. The system receives retinal fundus images through an image acquisition module and performs image quality assessment, illumination correction, noise reduction, retinal region enhancement, and image normalization. The processed images are analysed using an artificial intelligence model comprising a deep feature extraction module, multi-scale retinal feature learning module, lesion-sensitive feature enhancement module, and classification module. The system identifies retinal abnormalities including Microaneurysms, Haemorrhages, Exudates, Cotton-wool spots, and Abnormal vascular patterns. The extracted features are analysed to classify the retinal image into multiple DR severity categories, including No DR, Mild, Moderate, Severe, and Proliferative DR. The system further provides confidence scores and visual explanation maps indicating image regions contributing to the prediction. The proposed invention supports rapid, automated, and scalable DR screening using computing devices, cloud platforms, or edge-AI devices.
Disclaimer: Curated by HT Syndication.
