MUMBAI, India, July 11 -- Intellectual Property India has published a patent application (202541040704 A) filed by Kcg College Of Technology, Chennai, Tamil Nadu, on April 28, for 'next-gen ai system for automated diabetic retinopathy screening and classification.'
Inventor(s) include Aida Jones; and Mrithula R.
The application for the patent was published on July 11, under issue no. 28/2025.
According to the abstract released by the Intellectual Property India: "Diabetic Retinopathy (DR) is one of the primary contributors to vision loss, making early diagnosis crucial for successful treatment. This study presents an automated DR classification model using DenseNet121, leveraging deep learning for accurate severity grading. The model applies image preprocessing, SMOTE for class balancing, and Gaussian-filtered fundus images to enhance performance. Assessed using accuracy, precision, recall, F1-score, and ROC-AUC, it reaches an accuracy of 90%, surpassing cutting-edge models. Despite some misclassifications between moderate and severe cases, confusion matrix analysis confirms its strong discrimination capability. The results demonstrate DenseNet121's effectiveness in scalable, precise, and automated DR detection."
Disclaimer: Curated by HT Syndication.
