MUMBAI, India, Feb. 27 -- Intellectual Property India has published a patent application (202641018574 A) filed by Dr. S. V. Divya; Dr. P. Venkadesh; Lakshayaa G; Mathumitha R; and Pavithra A, Coimbatore, Tamil Nadu, on Feb. 18, for 'a hybrid cnn-xgboost-based cancer detection framework (cnnxgbf) with genetic algorithm-based feature selection.'
Inventor(s) include Dr. S. V. Divya; Dr. P. Venkadesh; Lakshayaa G; Mathumitha R; and Pavithra A.
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: "A Hybrid Cancer Detection Framework by combining Convolutional Neural Networks (CNN), Genetic Algorithm-based feature selection, and Extreme Gradient Boosting (XGBoost) classification is proposed.The framework aims to increase the precision and effectiveness of cancer detection from medical images. High-level spatial and texture features are extracted from preprocessed medical images using the CNN model, which lessens the need for manual feature extraction. A genetic algorithm that chooses the most important features through evolutionary operations is used to optimize the feature set and remove redundant and unnecessary features.The XGBoost classifier is then given the optimized feature set, and it successfully and reliably classifies cases as either cancerous or non-cancerous. Compared to traditional deep learning or standalone machine learning models, this hybrid framework improves generalization performance, decreases computational complexity, and increases detection accuracy. The suggested system supports early cancer diagnosis and can be used with a variety of medical imaging modalities, which helps clinicians make clinical decisions. For real-time healthcare applications, the system is scalable, effective, and appropriate for integration into computer-aided diagnosis systems."
Disclaimer: Curated by HT Syndication.
