MUMBAI, India, July 11 -- Intellectual Property India has published a patent application (202521054496 A) filed by Ms. Prachi Navinchandra Shah; and Dr. Rais Abdul Hamid Khan, Nashik, India, on June 5, for 'system and method for cervical cancer detection using machine learning and deep learning technique.'
Inventor(s) include Ms. Prachi Navinchandra Shah.
The application for the patent was published on July 11, under issue no. 28/2025.
According to the abstract released by the Intellectual Property India: "The present invention discloses an intelligent, automated system and method for the early detection and classification of cervical cancer using machine learning (ML) and deep learning (DL) techniques. The system operates on medical image data (e.g., Pap smear, colposcopy images) and structured clinical records to provide accurate, efficient, and scalable diagnostics. It comprises sequential modules for data acquisition, preprocessing, data augmentation, feature extraction, model training, ensemble classification, and performance evaluation. Augmentation techniques such as image rotation, noise injection, and brightness adjustment enhance data diversity and generalization. Features are extracted using conventional methods (e.g., HOG, GLCM) and CNNs for robust pattern recognition. Classifiers include SVM, k-NN, Random Forest, and CNNs, whose outputs are combined via ensemble models for improved accuracy. Performance is assessed using metrics like F1-score, ROC-AUC, and MCC. The invention is deployable in both high-end hospital systems and low-resource settings, aiding clinicians with reliable, interpretable diagnostic support."
Disclaimer: Curated by HT Syndication.
