MUMBAI, India, Jan. 2 -- Intellectual Property India has published a patent application (202541125585 A) filed by Dr. Bazani Shaik; Dr Anup Negi; Dr. S. Jayanthi; M. Poornima; Hemal Rawal; Dr. Omkar Ghatage; K Jayaprakasam; and Mr. Grandhi Siva Sankar, Eluru, Andhra Pradesh, on Dec. 12, 2025, for 'artificial intelligence based multi-scale feature fusion framework for gastric cancer classification.'
Inventor(s) include Dr. Bazani Shaik; Dr Anup Negi; Dr. S. Jayanthi; M. Poornima; Hemal Rawal; Dr. Omkar Ghatage; K Jayaprakasam; and Mr. Grandhi Siva Sankar.
The application for the patent was published on Jan. 2, under issue no. 01/2026.
According to the abstract released by the Intellectual Property India: "The present invention relates to the development of the technique presents a sophisticated deep learning architecture intended to improve diagnostic precision via thorough feature extraction and integration. The system uses a hybrid convolutional backbone to capture high-level semantic representations and fine-grained textural features across several geographical scales. These diverse variables are constantly combined by a novel feature fusion module, which makes it possible for the model to accurately identify minute morphological differences linked to early and advanced stomach lesions. By reducing irrelevant information, attention-based refinement enhances discriminative regions even more. Large annotated endoscopic image datasets are used for training and validation of the framework, which outperforms traditional single-scale and non-fusion algorithms. The approach helps clinicians discover stomach cancer early, lowers diagnostic subjectivity, and improves patient outcomes by offering reliable, automated categorization."
Disclaimer: Curated by HT Syndication.
