MUMBAI, India, Aug. 24 -- Intellectual Property India has published a patent application (202641098647 A) filed by Avs Engineering College on August 14, 2026, for System And Method For Automated Brain Tumor Detection And Multi-Class Classification Using Deep Learning On Mri Images.
Inventors include P. Saranya; C. Ravi; M. R. Sumathi; S. Someshwaran; V. M. C. Venkatraja; S. Saranya; M. Premkumar; M. Sridevi; and S. Sivaranjani.
The application for the patent was published on August 21, 2026, under issue no. 34/2026.
Abstract: ABSTRACT SYSTEM AND METHOD FOR AUTOMATED BRAIN TUMOR DETECTION AND MULTI-CLASS CLASSIFICATION USING DEEP LEARNING ON MRI IMAGES This invention presents a deep learning–based system for automated brain tumor detection, classification, and segmentation using MRI images. The system employs a Convolutional Neural Network (CNN) trained on a multi-class dataset to classify scans into four categories: Glimonia, Pinogononia, Minimona, and No Tumor. Preprocessing steps such as resizing, normalization, and noise reduction enhance model accuracy. For detected tumors, segmentation techniques including Watershed and morphological operations highlight tumor boundaries, enabling precise visualization. A graphical user interface allows clinicians to upload MRI scans and instantly view diagnostic results, reducing interpretation time and minimizing human error. Unlike prior binary classification systems, this invention introduces multi-class diagnosis integrated with segmentation, offering superior diagnostic reliability. The system is applicable in healthcare centers, diagnostic laboratories, and medical imaging platforms, providing a scalable and robust solution for clinical decision support.
Disclaimer: Curated by HT Syndication.
