MUMBAI, India, Jan. 2 -- Intellectual Property India has published a patent application (202541122930 A) filed by Vellore Institute Of Technology, Vellore, Tamil Nadu, on Dec. 5, 2025, for 'hybrid deep learning system for oral cancer detection.'
Inventor(s) include Dr. Islabudeen M; and Mr. Naveen S.
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 an oral cancer detection system (800) including a data input module (802) configured to receive oral cavity images, a feature extraction module (808) including a DenseNet201 network (810) configured to extract hierarchical visual features from the oral cavity images, a classification module (816) including a CatBoost classifier (818) configured to classify the extracted features as cancerous or non-cancerous tissue using gradient boosting techniques, and an output interface (822) configured to generate diagnostic results (824) distinguishing between cancerous and non-cancerous tissue. The DenseNet201 network (810) implements dense connections where each layer receives feature maps from all preceding layers, enabling feature reuse and improved gradient flow. The system includes a preprocessing unit (806) that resizes images to 224 224 pixels, normalizes pixel values, and applies data augmentation. The CatBoost classifier (818) uses ensemble learning to achieve 99.5% accuracy."
Disclaimer: Curated by HT Syndication.
