MUMBAI, India, May 29 -- Intellectual Property India has published a patent application (202641062203 A) filed by Dr. Balaji N; Dr. Vani S V; D. Vidhya; Dr. Rajan Singh; Dr. Nidhi Tiwari; and Mrs. R. Jaya, Chennai, Tamil Nadu, on May 15, for 'algebraic topology-based pattern recognition system for medical imaging using artificial intelligence.'
Inventor(s) include Dr. Balaji N; Dr. Vani S V; D. Vidhya; Dr. Rajan Singh; Dr. Nidhi Tiwari; and Mrs. R. Jaya.
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: "The present invention relates to a system and method for pattern recognition in medical imaging using algebraic topology integrated with artificial intelligence. The invention employs topological data analysis techniques, particularly persistent homology, to extract structural and geometric features from medical images that are not captured by conventional pixel-based methods. The extracted topological features, including connected components, loops, and higher-dimensional structures, are represented using persistence diagrams and transformed into numerical feature vectors. These topology-based features are combined with machine learning and deep learning models, such as convolutional neural networks, to perform classification, segmentation, and anomaly detection in medical images. The proposed system enhances robustness against noise, deformation, and variations in imaging conditions while improving diagnostic accuracy and interpretability. The invention is applicable to multiple imaging modalities, including Magnetic Resonance Imaging (MRI), Computed Tomography (CT), ultrasound, and X-ray, and can be deployed in clinical decision support systems, diagnostic platforms, and intelligent healthcare applications. The proposed approach provides a scalable and efficient solution for advanced medical image analysis."
Disclaimer: Curated by HT Syndication.
