Intellectual Property India Publishes Patent Application for 'Automated Diabetic Retinopathy Detection System Using Hybrid Deep Learning Models' Filed by Vellore Institute Of Technology

MUMBAI, India, Jan. 2 -- Intellectual Property India has published a patent application (202541122160 A) filed by Vellore Institute Of Technology, Vellore, Tamil Nadu, on Dec. 4, 2025, for 'automated diabetic retinopathy detection system using hybrid deep learning models.'

Inventor(s) include Dr. R. Kannadasan; Mr. Dagumati Harsha Vardhan; and Mr. Nagothi V Sarvesh.

The application for the patent was published on Jan. 2, under issue no. 01/2026.

According to the abstract released by the Intellectual Property India: "The present disclosure provides an automated diabetic retinopathy detection system comprising a preprocessing module configured to receive retinal fundus images and perform standardization operations to generate preprocessed images, a model inference engine comprising a model selector configured to route the preprocessed images to at least one deep learning model trained to classify diabetic retinopathy, an explainable artificial intelligence module configured to generate visual explanations identifying feature contributions that influenced a classification decision, and a result handler configured to consolidate classification results and visual explanations to generate diagnostic output. The system incorporates hybrid deep learning architectures including MobileNet, Vision Fusion models combining MobileNetV2 and ResNet50, and Mobile-NASNet architectures, with explainable AI components including LIME and SHAP for generating saliency maps and feature importance values, enabling real-time processing with inference times under one second per image."

Disclaimer: Curated by HT Syndication.