MUMBAI, India, June 30 -- Intellectual Property India has published a patent application (202641075662 A) filed by Sr University on June 18, 2026, for A Computer-Implemented System For Classifying Brain Tumour Stages And Method Thereof.
Inventors include Mruthyunjaya Mendu; and Suresh Kumar Mandala.
The application for the patent was published on June 26, 2026, under issue no. 26/2026.
Abstract: A COMPUTER-IMPLEMENTED SYSTEM FOR CLASSIFYING BRAIN TUMOUR STAGES AND METHOD THEREOF The invention relates to an automated system for high-precision classification of brain tumour stages using convolutional neural networks (CNNs) and transfer learning techniques. The system processes MRI scans through preprocessing steps including skull stripping, normalization, and augmentation, followed by feature extraction using fine-tuned pre-trained CNN architectures such as ResNet50, VGG16, and EfficientNet. By leveraging transfer learning, the invention reduces dependency on large annotated datasets while improving classification accuracy across diverse tumour types and stages. The classification module provides multi-class outputs with enhanced interpretability through visualization tools such as Grad-CAM, thereby supporting radiologists in clinical decision-making. The proposed system achieves robust, consistent, and efficient tumour stage classification, minimizing diagnostic latency and improving patient outcomes in neuro-oncology practice.
Disclaimer: Curated by HT Syndication.
