MUMBAI, India, Feb. 27 -- Intellectual Property India has published a patent application (202631018104 A) filed by National Institute Of Technology, Patna, Bihar, on Feb. 18, for 'classification of medical images with parallel feature extraction and weighted fusion.'
Inventor(s) include Tiwari, Abhishek Kumar; and Bhandari, Ashish Kumar.
The application for the patent was published on Feb. 27, under issue no. 09/2026.
According to the abstract released by the Intellectual Property India: "The present disclosure provides a system (100) and a method (300) for classification of medical images. The system (100) includes a preprocessing unit (102) that receives medical image data (104) from one or more imaging sources (208) and normalizes spatial dimensions (112), intensity values, and stain characteristics (114) to generate a standardized image representation (116). A first feature extraction branch (118) and a second feature extraction branch (120) operate in parallel to extract pixel-level spatial feature representations and region-level contextual feature representations respectively. A classification unit (124) generates a classification output (128) corresponding to a disease class and a visual map (130) identifying contributing image regions. Unlike conventional approaches that process features through a single extraction pathway, the present disclosure enables complementary parallel feature extraction with significance-based weighted fusion for robust classification across heterogeneous imaging sources."
Disclaimer: Curated by HT Syndication.
