MUMBAI, India, July 24 -- Intellectual Property India has published a patent application (202641084915 A) filed by Koneru Lakshmaiah Education Foundation Klef on July 10, 2026, for System And Method For Automated Brain Tumor Segmentation And Detection Using Hybrid Ghostnet And Transformer Networks.
Inventors include Sd. Nehashireen; and Dr. G. Annalakshmi.
The application for the patent was published on July 17, 2026, under issue no. 29/2026.
Abstract: ABSTRACT The present invention relates to a hybrid GhostNet–Transformer-based system (100) and method for automated brain tumor detection and segmentation from magnetic resonance imaging (MRI) images. The system (100) comprises an MRI image acquisition module (101) configured to receive MRI images, an image preprocessing module (102) configured to standardize the acquired images, a GhostNet feature extraction module (103) configured to extract local spatial features, a transformer-based global context learning module (104) configured to determine global contextual relationships, a hybrid feature fusion module (105) configured to integrate local and global feature representations, a tumor detection and segmentation module (106) configured to detect tumor regions and generate segmentation masks, a tumor classification module (107) configured to classify the detected tumor, an output visualization module (108) configured to present diagnostic results, and a processor (109) coupled to a memory (110) to coordinate the operational workflow. The integrated architecture provides automated, computationally efficient, and reliable brain tumor detection, segmentation, classification, and visualization from MRI images. The figure associated with abstract is Fig. 1
Disclaimer: Curated by HT Syndication.
