MUMBAI, India, Sept. 7 -- Intellectual Property India has published a patent application (202641064153 A) filed by Srm Institute Of Science And Technology Tiruchirappalli on May 21, 2026, for An Automated Deep Learning Framework For Human Brain Tumor Classification Using Mri.
Inventor includes Dr. B. Devisri.
The application for the patent was published on September 04, 2026, under issue no. 36/2026.
Abstract: Brain tumors present significant diagnostic challenges due to their complex structure and variability in size and location. Manual MRI interpretation is time-consuming and prone to error, particularly in regions with limited medical expertise. The present invention proposes an automated deep learning-based framework for brain tumor detection and classification using MRI images. The system employs optimized DBSCAN clustering integrated with the Firefly Algorithm for accurate tumor segmentation, followed by feature extraction using transfer learning with ResNet-50 and classification using an XGBoost classifier. The proposed approach improves segmentation accuracy, classification performance, and diagnostic efficiency, providing a reliable computer-aided diagnosis solution for early brain tumor detection.
Disclaimer: Curated by HT Syndication.
