MUMBAI, India, July 7 -- Intellectual Property India has published a patent application (202641079985 A) filed by Sona College Of Technology on June 29, 2026, for Brain Tumor Detection And Classification Using Deep Learning.
Inventors include Sasirekha N; Shanmathi S; Ragasuruthi A; Ravi G; Harirajkumar J; Vivek Karthick P; Saranya K; and Vijayashaarathi S.
The application for the patent was published on July 03, 2026, under issue no. 27/2026.
Abstract: ABSTRACT The present invention relates to a deep learning-based system and method for automated brain tumor detection and classification using Magnetic Resonance Imaging (MRI) brain images. The system comprises an image acquisition module, preprocessing module, segmentation module, feature extraction module comprising a deep learning neural network, tumor detection module, classification module, and output visualization module. The preprocessing module performs noise reduction, normalization, and image enhancement to improve diagnostic quality. The feature extraction module automatically extracts hierarchical image features for identifying abnormal tumor regions. The classification module classifies detected tumors into predefined categories including glioma, meningioma, pituitary tumor, metastatic tumor, and non-tumorous conditions. The invention further includes a model training engine and feature optimization unit for improving classification accuracy and reducing overfitting. The proposed invention provides improved diagnostic accuracy, reduced manual intervention, enhanced processing efficiency, and reliable computer-aided diagnosis suitable for clinical and telemedicine applications.
Disclaimer: Curated by HT Syndication.
