MUMBAI, India, May 29 -- Intellectual Property India has published a patent application (202641063974 A) filed by Mohamed Noordeen A; and Dhaanish Ahmed Institute Of Technology, Coimbatore, Tamil Nadu, on May 20, for 'deep learning and ai for rapid annotation of medical image to lung cancer.'
Inventor(s) include Mrs J R Justilin; Sharmila R; Mariselvam M; Vishwa Kumar V; Manjula P; and Mamatha K R.
The application for the patent was published on May 29, under issue no. 22/2026.
According to the abstract released by the Intellectual Property India: "The present invention relates to a deep learning and artificial intelligence-based system for rapid annotation and automated classification of lung CT scan images for early lung cancer detection. Lung cancer remains one of the leading causes of cancer-related mortality worldwide, with delayed diagnosis significantly reducing patient survival rates. Conventional manual analysis of Computed Tomography (CT) scans is time-consuming, highly dependent on radiologist expertise, and susceptible to diagnostic variability. The proposed invention introduces a Computer-Aided Diagnosis (CAD) system utilizing the EfficientNet-B0 deep learning architecture integrated with transfer learning for automatic classification of lung CT images into three categories: Normal, Benign, and Malignant. The system incorporates an advanced preprocessing pipeline including image resizing, normalization, grayscale-to-RGB conversion, and targeted data augmentation techniques such as rotation, scaling, brightness adjustment, and contrast enhancement to improve prediction robustness and address dataset imbalance. The invention employs a two-phase transfer learning strategy comprising feature extraction and fine-tuning to optimize classification performance on the IQ-OTH/NCCD lung cancer dataset. The deep learning model achieves high prediction accuracy with strong malignant case detection capability while maintaining reduced computational complexity suitable for real-time deployment. A Flask-based web application framework is integrated for practical deployment, enabling users to upload CT scan images and receive rapid prediction results with associated confidence scores through an accessible graphical interface. The system provides automated and consistent medical image annotation within seconds, thereby reducing diagnostic delays and assisting healthcare professionals in clinical decision-making. The invention offers significant advantages including improved early-stage lung cancer screening, reduced radiologist workload, enhanced diagnostic consistency, real-time prediction capability, and suitability for deployment in hospitals, diagnostic laboratories, telemedicine systems, and resource-limited healthcare environments."
Disclaimer: Curated by HT Syndication.
