MUMBAI, India, July 30 -- Intellectual Property India has published a patent application (202641087324 A) filed by Anitha Raju; and Koneru Lakshmaiah Education Foundation on July 16, 2026, for Artificial Intelligence-Based Brain Tumor Detection System Using Quantum Attention Transformer Networks.
Inventors include Dr. Raju Anitha; Mrs. Amrutavalli Akula; and Dr. Ramadevi Chappala.
The application for the patent was published on July 24, 2026, under issue no. 30/2026.
Abstract: The present invention discloses an Artificial Intelligence-Based Brain Tumor Detection System using Quantum Attention Transformer Networks for the automated detection and classification of brain tumors from Magnetic Resonance Imaging (MRI) scans. The proposed system integrates advanced image preprocessing, quantum- inspired attention mechanisms, transformer-based deep learning, and intelligent decision support into a unified diagnostic framework. Initially, brain MRI images are acquired and subjected to preprocessing operations including noise reduction, intensity normalization, image resizing, contrast enhancement, and data augmentation to improve image quality and ensure consistency for subsequent analysis. The processed images are then supplied to a Quantum Attention module that adaptively emphasizes diagnostically significant regions while suppressing redundant or irrelevant information, thereby improving feature representation. The extracted features are provided to a Transformer Network that utilizes multi-head self-attention and encoder layers to learn both local structural characteristics and long-range spatial dependencies within MRI images. Based on the learned feature representations, the classification module automatically identifies and categorizes brain tumors with improved precision and reliability. The system further generates diagnostic predictions and confidence scores that support clinicians in medical decision-making and treatment planning. The proposed invention enhances classification accuracy, minimizes false-positive and false-negative predictions, and improves computational efficiency compared with conventional deep learning approaches. Its scalable architecture enables deployment in hospitals, diagnostic imaging centers, cloud-based healthcare platforms, and telemedicine environments for real-time computer-aided diagnosis. The invention provides a reliable, adaptable, and intelligent medical imaging solution capable of supporting early brain tumor detection, reducing diagnostic workload, and improving overall healthcare outcomes through accurate and automated analysis of brain MRI images.
Disclaimer: Curated by HT Syndication.
