MUMBAI, India, Sept. 14 -- Intellectual Property India has published a patent application (202641094702 A) filed by Dhanalakshmi Srinivasan College Of Engineering And Technology on August 05, 2026, for Deep Learning Based Colon Polyp Detection Using Colonoscopy Images.
Inventors include K. Rajavad; Aswin Williams; Karthikesan B; and Manikandan.
The application for the patent was published on September 11, 2026, under issue no. 37/2026.
Abstract: Deep Learning Based Colon Polyp Detection Using Colonoscopy Images The present invention relates to the fields of Artificial Intelligence, Deep Learning, Medical Image Processing, and Computer-Aided Diagnosis. The invention proposes a deep learningbased system for the automatic detection and localization of colon polyps from colonoscopy images to assist in the early diagnosis and prevention of colorectal cancer. The system acquires colonoscopy images and performs preprocessing operations including image resizing, normalization, contrast enhancement, and noise reduction to improve image quality. A Convolutional Neural Network (CNN) extracts meaningful image features and accurately classifies images as containing polyps or normal tissue while simultaneously localizing detected polyps. The system evaluates its performance using accuracy, precision, recall, F I -score, Intersection over Union (loU), Dice Similarity Coefficient, and confusion matrix metrics. The proposed invention significantly improves detection accuracy, reduces false positives and false negatives, assists gastroenterologists in clinical diagnosis, supports real- time colonoscopy procedures, and contributes to the early detection and prevention of colorectal cancer. It is applicable to hospitals, diagnostic centers, healthcare institutions, telemedicine platforms, and medical research organizations. The invention further supports automated report generation, visualization of detected polyps with confidence scores, and secure storage of examination results for future clinical reference. The system can be integrated with hospital information systems and electronic health records to facilitate seamless clinical workflow and patient management. Additionally, the proposed solution reduces physician workload by providing intelligent decision support and minimizing the possibility of missed polyp detection during colonoscopy procedures. Overall, the invention offers a scalable, reliable, and efficient AIassisted diagnostic tool that enhances colorectal cancer screening, improves patient outcomes, and advances modern computer-aided medical diagnosis.
Disclaimer: Curated by HT Syndication.
