MUMBAI, India, May 29 -- Intellectual Property India has published a patent application (202641047813 A) filed by Agni College Of Technology, Chennai, Tamil Nadu, on April 15, for 'multi agent ai framework for cross verified blood group detection and validation.'
Inventor(s) include Saravanan J; Dharanya S; Immanuel Joshua; Abinaya S; and Dheeraj A.
The application for the patent was published on May 29, under issue no. 22/2026.
According to the abstract released by the Intellectual Property India: "This invention presents a Multi-Agent AI Framework for cross-verified automated blood group detection using deep learning-based medical image analysis and parallel agent-driven validation. The system employs a Convolutional Neural Network (CNN) trained on annotated blood sample images to classify agglutination patterns across Anti-A, Anti-B, and Anti-D reaction zones with high spatial feature extraction accuracy. Contrast Limited Adaptive Histogram Equalization (CLAHE) preprocessing combined with data augmentation strategies including rotation, flipping, and brightness normalization significantly enhance input image quality, enabling robust classification under varying lighting conditions and weak agglutination scenarios. The framework integrates four specialized parallel AI validation agents - Image Quality Validation Agent, Medical Rule Validation Agent, Confidence Scoring Agent, and Ethical Safety Agent - each independently performing domain-specific cross-verification of CNN predictions. A consensus-drive."
Disclaimer: Curated by HT Syndication.
