MUMBAI, India, July 24 -- Intellectual Property India has published a patent application (202611067441 A) filed by Manipal University Jaipur on May 29, 2026, for A System And Method For Breast Tumor Detection Using Multi-Modal Image Fusion And Multi-Feature Block Neural Architecture.
Inventors include Bersha Kumari; and Dr Amita Nandal.
The application for the patent was published on July 17, 2026, under issue no. 29/2026.
Abstract: The present invention relates to a method for breast tumor detection using multi-modal image fusion and a multi-feature block neural architecture. The method comprises acquiring CT and MRI images of a breast region and performing pre-processing involving normalization, denoising, intensity correction, and spatial registration. A fused image is generated using a log-ratio-based fusion mechanism that integrates structural and soft tissue information from both modalities. The fused image is subjected to feature extraction to obtain edge, texture, intensity, and spatial gradient features, which are organized into a feature change matrix representing tumor-specific characteristics. The collected features are processed using a multi-feature block neural network with minimal information loss. The method further performs pixel-level segmentation and classification of tumor regions to produce diagnostic outputs, including tumor boundaries, visualization maps, and probability-based clinical decision support information for improved diagnosis accuracy.
Disclaimer: Curated by HT Syndication.
