MUMBAI, India, Sept. 22 -- Intellectual Property India has published a patent application (202641110680 A) filed by Vallurupalli Nageswara Rao Vignana Jyothi Institute Of Engineering And Technology on September 15, 2026, for Deep Learning-Based Cardiovascular Disease Detection System Using Retinal Fundus Images And Pso Optimized Resu-Net Architecture.
Inventor includes Dr. Sayanti Chatterjee.
The application for the patent was published on September 18, 2026, under issue no. 38/2026.
Abstract: ABSTRACT [0022] A system and method are provided for predicting cardiovascular disease risk by processing retinal fundus images. Retinal images are acquired and preprocessed through resizing, normalization, and contrast enhancement. A residual U-Net architecture performs precise segmentation of blood vessels. Vascular features including density, tortuosity, thickness, and branching patterns are extracted from the segmented maps. Particle swarm optimization is applied to refine feature selection and classification thresholds, yielding a risk classification of high or low cardiovascular disease likelihood. The system produces visual segmentation overlays, risk scores, and confidence measures, enabling early non-invasive screening that improves upon conventional late-stage detection approaches by capturing microvascular indicators of systemic vascular health.
Disclaimer: Curated by HT Syndication.
