MUMBAI, India, April 17 -- Intellectual Property India has published a patent application (202531104579 A) filed by Asansol Engineering College; Jis University; and Abacus Institute Of Engineering & Management, Asansol, West Bengal, on Oct. 30, 2025, for 'analyzing vgg19 and resnet50 architectures for improved diabetic retinopathy screening through image enhancement.'
Inventor(s) include Sumanta Karmakar; Dr. Jyotirmoy Chatterjee; Dr. Sambit S Mondal; Dr. Goutam Kumar Das; Dr. Khushi Banerjee; Dr. Ashmi Chakraborty; Rupam Garai; and Rupnath Chatterjee.
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: "Diabetic Retinopathy (DR), a leading cause of preventable vision loss worldwide, requires timely detection for effective clinical management. Manual screening of retinal fundus images is often labor-intensive and subject to inter-observer variability, creating a strong need for reliable automated solutions. This research presents a comparative analysis of two convolutional neural network (CNN) architectures, VGG19 and ResNet50, for DR classification, with a focus on the impact of retinal image enhancement on model performance. Image preprocessing techniques were applied to improve the visibility of pathological features such as microaneurysms, hemorrhages, and exudates prior to classification. Experimental results demonstrate that image enhancement significantly improves model accuracy, with ResNet50 achieving superior performance and generalization compared to VGG19. The findings highlight the effectiveness of combining image enhancement with deep learning models for early DR detection, offering a promising tool to support ophthalmologists in rapid and accurate screening, thereby reducing the risk of irreversible vision loss."
Disclaimer: Curated by HT Syndication.
