Intellectual Property India Publishes Patent Application for 'Hybrid Deep Learning System For Lung Cancer Subtype Classification' Filed by Vellore Institute Of Technology

MUMBAI, India, Jan. 2 -- Intellectual Property India has published a patent application (202541122196 A) filed by Vellore Institute Of Technology, Vellore, Tamil Nadu, on Dec. 4, 2025, for 'hybrid deep learning system for lung cancer subtype classification.'

Inventor(s) include Sathya K; and Jaideep Singh Hada.

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 disclosure provides a hybrid deep learning system for lung cancer subtype classification. The system includes a hybrid ensemble neural network architecture comprising a ResNet-50 component (FIG. 7) configured for hierarchical feature extraction through residual learning blocks, and an Attention U-Net component (FIG. 7) configured for spatial feature localization with attention mechanisms. The system includes a feature fusion module (FIG. 7) configured to combine outputs from the ResNet-50 component and the Attention U-Net component. The system includes a classification output configured to distinguish between adenocarcinoma, neuroendocrine carcinoma, and squamous cell carcinoma subtypes from histopathological images of lung tissue. The system processes medical images through a data preprocessing module that applies Contrast Limited Adaptive Histogram Equalization to enhance image contrast, normalizes pixel values to a range of 0 to 1, resizes images to standardized dimensions, and converts images to grayscale format."

Disclaimer: Curated by HT Syndication.