MUMBAI, India, Jan. 2 -- Intellectual Property India has published a patent application (202541122896 A) filed by Vellore Institute Of Technology, Vellore, Tamil Nadu, on Dec. 5, 2025, for 'explainable ai system for ocular disease detection using deep learning.'
Inventor(s) include Dr. R. Manjula; Bhagyesha Anant Khairnar; and Naman Raj.
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 a computer-implemented system for explainable artificial intelligence-based ocular disease detection. The system includes an input module configured to receive fundus images, a neural network classification module configured to classify the fundus images into multiple ocular disease categories, and an explainability module configured to generate interpretable explanations of classification decisions using multiple explainable artificial intelligence techniques. The techniques generate visual explanations indicating which regions or features of the fundus images influence classification decisions. The neural network classification module incorporates a convolutional neural network architecture with transfer learning from pre-trained weights, having frozen base layers and custom classification layers. The multiple explainable artificial intelligence techniques include Local Interpretable Model-agnostic Explanations for superpixel-based feature attribution, SHapley Additive exPlanations for quantifying feature contributions, and Gradient-weighted Class Activation Mapping for generating spatial attention heatmaps."
Disclaimer: Curated by HT Syndication.
