MUMBAI, India, Oct. 31 -- Intellectual Property India has published a patent application (202441033279 A) filed by Narayananan Madeshan; Dr. Shaik Meeravali; Ganta Meghana; Pattewar Akshaya; Sirpa Indra; and Alavala Harish, Hyderabad, Telangana, on April 26, 2024, for 'automated diabetic retinopathy classification system with intelligent image quality assessment and expert validation.'
Inventor(s) include Narayananan Madeshan; Dr. Shaik Meeravali; Ganta Meghana; Pattewar Akshaya; Sirpa Indra; and Alavala Harish.
The application for the patent was published on Oct. 31, under issue no. 44/2025.
According to the abstract released by the Intellectual Property India: "This invention presents an innovative method for the automated classification of Diabetic Retinopathy (DR) using Convolutional Neural Networks (CNNs). The process involves collecting a substantial dataset comprising 57,625 DR images sourced from diverse outlets. These images are meticulously annotated by experts to denote whether they exhibit signs of DR or not, and subsequently divided into training and validation subsets. A CNN architecture is then constructed, integrating convolutional and pooling layers for feature extraction. Additionally, Rectified Linear Unit (ReLU) activation functions are utilized to introduce non-linearities and bolster model efficacy. During real-time evaluation, the system utilizes a sophisticated model to assess the quality of DR images from Type II diabetes patients before subjecting them to the trained CNN for classification. To ensure the precision and dependability of the CNN model in early DR detection and management, an expert validation mechanism is integrated. This system holds promise for enhancing patient outcomes within clinical settings."
Disclaimer: Curated by HT Syndication.
