Intellectual Property India Publishes Patent Application for Adaptive Tumor Variation Intelligence (atvi): A Knowledge-Driven System And Method For Brain Tumor Classification

MUMBAI, India, Sept. 7 -- Intellectual Property India has published a patent application (202641104436 A) filed by Dr Rvr Nri Institute Of Technology Deemed To Be University; Ms. B. Yamini; Ms. K. Lakshmi Apurupa; Mr. R. Nanda Kumar; Mr. T. Mani Sekhar; Mrs. J. Naga Surekha; and Dr. P. Rajendra Kumar on August 31, 2026, for Adaptive Tumor Variation Intelligence (atvi): A Knowledge-Driven System And Method For Brain Tumor Classification.

Inventors include Ms. B. Yamini; Ms. K. Lakshmi Apurupa; Mr. R. Nanda Kumar; Mr. T. Mani Sekhar; Mrs. J. Naga Surekha; and Dr. P. Rajendra Kumar.

The application for the patent was published on September 04, 2026, under issue no. 36/2026.

Abstract: Abstract Brain tumor classification using magnetic resonance imaging (MRI) has become an important application of artificial intelligence for computer-aided diagnosis. Conventional deep learning approaches primarily rely on direct feature-based classification, where extracted image features are directly mapped to tumor categories. However, these methods generally lack an adaptive mechanism for learning, organizing, and utilizing representative tumor variation knowledge during the diagnostic process. The present invention proposes an Adaptive Tumor Variation Intelligence (ATVI) Framework that introduces an Adaptive Tumor Variation Knowledge Space (ATVKS) for knowledge-driven brain tumor classification. The framework comprises a Feature Representation Module, the Adaptive Tumor Variation Knowledge Space, and a Decision Intelligence Module operating within a unified architecture. Representative image features are utilized to construct Adaptive Tumor Variation Profiles (ATVPs), which are continuously refined through a knowledge evolution mechanism and subsequently retrieved to guide the final classification process. By integrating adaptive knowledge construction, knowledge refinement, and knowledge-guided decision-making, the proposed framework provides a systematic and adaptive approach for classifying brain MRI images into tumor categories. The invention offers improved diagnostic consistency, adaptability, and reliability while overcoming the limitations associated with conventional feature-based brain tumor classification methods.

Disclaimer: Curated by HT Syndication.