MUMBAI, India, Jan. 9 -- Intellectual Property India has published a patent application (202541132895 A) filed by Karpagam Academy Of Higher Education; Karpagam Institute Of Technology; R Priyadharshini; and B Harish, Coimbatore, Tamil Nadu, on Dec. 29, 2025, for 'ai-based lung cancer detection using x-ray images.'
Inventor(s) include R Priyadharshini; and B Harish.
The application for the patent was published on Jan. 9, under issue no. 02/2026.
According to the abstract released by the Intellectual Property India: "Lung cancer remains one of the most fatal and prevalent diseases worldwide, with early detection being critical for improving patient survival rates. Traditional diagnostic methods such as CT scans and biopsies are accurate but often costly, time-consuming, and dependent on expert interpretation, posing challenges in timely diagnosis. To address these limitations, the proposed invention introduces an AI-based Lung Cancer Detection System leveraging Deep Learning and Convolutional Neural Networks (CNNs) to automatically analyze and classify chest X-ray images as cancerous or non-cancerous with high accuracy. The system integrates a multi-stage pipeline beginning with image preprocessing, which includes noise reduction, normalization, and data augmentation to enhance image clarity and model generalization. A deep learning architecture-such as ResNet50 or EfficientNet-is employed using transfer learning to extract complex patterns indicative of lung cancer. The model is trained and validated on large-scale, publicly available datasets like ChestX-ray14, LUNA16, and RSNA Pneumonia Challenge, ensuring robustness and adaptability across diverse imaging conditions. Performance evaluation is conducted using statistical metrics such as accuracy, precision, recall, F1-score, and ROC-AUC, confirming the system's reliability in clinical diagnostics. Additionally, explainable AI components such as Grad-CAM visualizations are incorporated to provide transparency by highlighting affected regions in X-rays that influence the model's decision. The proposed system can be deployed on cloud or web-based platforms, allowing real-time and remote diagnostic support for healthcare professionals, particularly in resource-limited settings. By combining automation, scalability, and interpretability, this invention offers a cost-effective and efficient solution for early lung cancer screening, significantly reducing human error and assisting radiologists in faster and more accurate decision-making-ultimately contributing to improved patient outcomes and smarter healthcare delivery."
Disclaimer: Curated by HT Syndication.
