MUMBAI, India, Sept. 22 -- Intellectual Property India has published a patent application (202641106022 A) filed by Saveetha Institute Of Medical And Technical Sciences on September 03, 2026, for Utility Of Enhanced U-Net Architecture For Semantic Segmentation And 3d Reconstruction Of Brain Tumor Regions.
Inventors include Dr. V. Sheeja Kumari; and Dr Ramya Mohan.
The application for the patent was published on September 18, 2026, under issue no. 38/2026.
Abstract: The present invention relates to a system and method utilizing an enhanced U-Net architecture for semantic segmentation and three-dimensional reconstruction of brain tumor regions from medical imaging data. The proposed system processes magnetic resonance imaging (MRI) scans using advanced preprocessing techniques to improve image quality and remove noise. An enhanced UNet deep learning architecture is employed to accurately segment tumor regions and surrounding abnormal tissues. The segmented outputs are further processed to generate a three-dimensional reconstruction of the tumor structure, enabling improved visualization of tumor shape, volume, and spatial distribution. The system integrates feature extraction, deep learning segmentation, and 3D reconstruction modules to assist clinicians in accurate diagnosis, surgical planning, and treatment monitoring. The invention improves segmentation accuracy, reduces computational complexity, and provides reliable tumor visualization for clinical decision-making.
Disclaimer: Curated by HT Syndication.
