MUMBAI, India, May 29 -- Intellectual Property India has published a patent application (202631043274 A) filed by Narula Institute Of Technology, Kolkata, West Bengal, on April 4, for 'integrating wiener filters with u-net++ and inception v4 for advanced mri brain tumor classification.'
Inventor(s) include Dr. Chandrima Chakrabarti; Dr. Nabanita Das; Ms. Jayita Pal; Mr. Rajarshi Nath; Mr. Saket Srivastava; Mr. Subhraneel Saha; and Mr. Sayak Bhunia.
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 provides an integrated diagnostic framework for automated brain tumor classification from MRI scans, addressing challenges posed by imaging noise and complex tumor morphologies. The pipeline employs adaptive Wiener filtering for noise mitigation while preserving anatomical structures, followed by normalization. A U-Net++ architecture with dense skip connections is used to achieve high-precision segmentation of tumor boundaries. Segmented regions are then evaluated by an Inception V4 network to extract multi-scale features, enabling the accurate categorization of tumors into subtypes such as glioma, meningioma, and pituitary tumors. This modular approach significantly enhances automated diagnostic reliability, achieving a classification accuracy of 95.1% to assist radiologists in real-time medical environments."
Disclaimer: Curated by HT Syndication.
