Intellectual Property India Publishes Patent Application for 'A System And A Method For Staging Oral Cancer From Histopathology Images' Filed by NIT

MUMBAI, India, Jan. 23 -- Intellectual Property India has published a patent application (202531134213 A) filed by NIT, Jamshedpur, Jharkhand, on Dec. 31, 2025, for 'a system and a method for staging oral cancer from histopathology images.'

Inventor(s) include Alka Kumari; Danish Ali Khan; Ashok Kumar Mehta; B Ramachandra Reddy; and Jitesh Pradhan.

The application for the patent was published on Jan. 23, under issue no. 04/2026.

According to the abstract released by the Intellectual Property India: "The present invention relates to a system and method for automated staging of oral cancer from digital histopathology images are disclosed. the system comprises an image acquisition module for receiving histopathology images of oral tissue samples and a preprocessing module configured to perform adaptive bilateral filtering for noise reduction, Sobel-based edge detection for lesion boundary identification, and contrast enhancement. a kernel Gaussian fuzzy clustering module maps pixel or voxel data into a higher-dimensional feature space using a Gaussian kernel and assigns fuzzy membership values to multiple clusters by minimizing an objective function based on cluster center distances, thereby reducing noise while preserving lesion structures. a hybrid deep convolutional squeeze-ResNet (HDCSRNET) feature extraction module extracts spatio-temporal deep features from clustered images using three-dimensional convolutional layers, residual connections, squeeze and excitation channel attention, spatial attention mechanisms, and global average pooling. an ensemble attention transfer autoencoder (EATA) classification module encodes the extracted deep features into a latent representation through encoder-decoder networks with attention fusion. a Gorilla-Grey Wolf hybrid metaheuristic optimization module optimizes trainable parameters of the EATA module by combining Gorilla Troops Optimizer exploration with Grey Wolf Optimizer exploitation based on alpha, beta, and delta leader solutions. finally, a staging output module classifies the latent representation into one of multiple oral cancer stages and generates a stage prediction output. the disclosed system and method improve accuracy, robustness, and reliability of oral cancer staging from histopathology images."

Disclaimer: Curated by HT Syndication.