MUMBAI, India, July 30 -- Intellectual Property India has published a patent application (202621066943 A) filed by Pimpri Chinchwad College Of Engineering, Pune; Mr. Kshitij Jadhav; Dr. Santwana Gudadhe; Mr. Parth Bendre; Mr. Aditya Pingle; and Mr. Vedant Patil on May 28, 2026, for System For Classification Of Brain Tumors From Multi-Modal Magnetic Resonance Imaging Data.
Inventors include Mr. Kshitij Jadhav; Dr. Santwana Gudadhe; Mr. Parth Bendre; Mr. Aditya Pingle; and Mr. Vedant Patil.
The application for the patent was published on July 24, 2026, under issue no. 30/2026.
Abstract: ABSTRACT SYSTEM FOR CLASSIFICATION OF BRAIN TUMORS FROM MULTI-MODAL MAGNETIC RESONANCE IMAGING DATA A system (100) for classification of brain tumors from multi-modal magnetic resonance imaging (MRI) data is disclosed. The system (100) includes an input interface (102) configured to receive multi-modal MRI data, and a processing unit (104) configured to pre-process the MRI data by performing normalization and artifact correction. The processing unit (104) is further configured to generate local image features using a convolutional neural network (106), global contextual features using a transformer-based model (108), structural features using topological data analysis (110), and radiomic features (112). The structural features are transformed into numerical representations (114), and adaptive weights are determined using a learnable attention mechanism (116). The weighted features are fused to obtain a unified feature representation (118), which is classified into one or more tumor classes (120). An output module (122) generates a diagnostic output including classification probabilities and explanatory indicators. FIG. 1 will be the reference figure.
Disclaimer: Curated by HT Syndication.
