MUMBAI, India, April 17 -- Intellectual Property India has published a patent application (202641043555 A) filed by Vellore Institute Of Technology, Vellore, Tamil Nadu, on April 6, for 'confidence-aware system for automated diabetic retinopathy detection and clinical decision support.'
Inventor(s) include Dr. Arivoli A; P. S. Vinothini; Y. Parvathi Devi; and D. Nayanasri.
The application for the patent was published on April 17, under issue no. 16/2026.
According to the abstract released by the Intellectual Property India: "Confidence-Aware System for Automated Diabetic Retinopathy Detection and Clinical Decision Support. The present invention relates to a computer-implemented system for automated detection of diabetic retinopathy from retinal fundus images. A retinal image captured using a fundus camera is received by an image acquisition module and processed through an image preprocessing module that performs resizing, pixel intensity normalization and noise reduction to improve image quality. The processed image is analysed by a deep learning based detection module to identify retinal patterns associated with diabetic retinopathy and determine a disease severity stage. A confidence evaluation module generates a confidence score indicating the certainty of the prediction. Based on the predicted severity stage and the confidence score, a clinical decision support module generates structured follow-up recommendations including referral, routine follow-up screening or image re-examination. An explainability module generates heatmap visualizations highlighting retinal regions influencing the prediction. The system outputs the diagnostic result, confidence score, recommendation and heatmap through a user interface to assist clinical decision making."
Disclaimer: Curated by HT Syndication.
